• Vita
  • Positionsbeschreibung
  • Publikationen
  • Vorlesungen
  • Projekte
  • Gremien
  • Forschungsthemen
Show publication details

Getto, Roman; Merz, Johannes; Kuijper, Arjan; Fellner, Dieter W.

3D Meta Model Generation with Application in 3D Object Retrieval

2017

Mao, Xiaoyang (Ed.) et al.: CGI 2017. Proceedings of the Computer Graphics International Conference. New York: ACM, 2017. (ACM International Conference Proceedings Series (ICPS) 1368), 6 p.

Computer Graphics International (CGI) <34, 2017, Yokohama, Japan>

In the application of 3D object retrieval we search for 3D objects similar to a given query object. When a user searches for a certain class of objects like 'planes' the results can be unsatisfying: Many object variations are possible for a single class and not all of them are covered with one or a few example objects. We propose a meta model representation which corresponds to a procedural model with meta-parameters. Changing the meta-parameters leads to different variations of a 3D object. For the meta model generation a single object is constructed with a modeling tool. We automatically extract a procedural representation of the object. By inserting metaparameters we generate our meta model. The meta model defines a whole object class. The user can choose a meta model and search for all objects similar to any instance of the meta model to retrieve all objects of a certain class from a 3D object database. We show that the retrieval precision is signifcantly improved using the meta model as retrieval query.

Show publication details

Majewski, Martin; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

3D-printed Electrodes for Electric Field Sensing Technologies

2017

Darmstadt, TU, Master Thesis, 2017

Electrical field sensing and capacitive sensing have been an intensively explored research topic for over a century. Combined with the rising popularity of rapid prototyping technologies, like affordable all- in-one micro-controller boards and especially fused filament fabrication 3D-printing, new possibilities occur. 3D-printing drives the ambitions of custom designed objects with fully integrated and unobtrusive electronics. Conductive 3D-printing materials (filaments) can be used to create electrodes for electrical field sensing. These electrodes can be 3D-printed as an integral part into the overall object. However, none of the previous work examines the properties of these conductive materials, the chosen 3D-printing configurations, and patters regarding their sensing performance and costs. This thesis provides a first insight into the interdependency between the chosen 3D- printing parameters and the overall sensing performance. For this, 30 3D-printed electrodes were created from graphene filament and evaluated against one copper electrode, and a placebo electrode. The evaluation was performed by a custom made measuring toolkit, the CapLiper, which was also evaluated for proper sensing behavior. The results show, that 3D-printed electrodes can compete with the sensing performance of copper electrodes, with some exceeding its performance. Using these results, as well as lessons learned in creating two different prototypes, the thesis establishes best practice and gives an outlook on potential future work in this domain.

Show publication details

Bidarahalli, Suman; Kuijper, Arjan (Betreuer); Brunton, Alan (Betreuer)

A Distributed 3D Print Driver

2017

Darmstadt, TU, Master Thesis, 2017

Determining material arrangements to control high-resolution multi-material 3D printers for reproducing shape and visual attributes of a 3D model (e.g. spatially-varying color, translucency and gloss) requires large computational effort. Today's resolution and print tray sizes allow prints with more than 1012 voxels each filled with one of the available printing materials (today up to 7 materials can be combined in a single print). Cuttlefish, a 3D printing pipeline, processes the input in a serial fashion leading to increased computation time for higher number of models. Distributed computing is one way of achieving better performance for large computations. Through this master thesis, we have developed a distributed version of the cuttlefish printer driver in which the computational task is distributed amongst multiple nodes in the cluster and the resulting partial output is merged to generate the full slices. The architecture supports streaming, which is required to rapidly start the print before the full computation is finished, as cuttlefish processes the input in small parts and generates chunk-wise output. Finally, the comparison of the performance achieved by the distributed vs the non-distributed cuttlefish version is established to get a better understanding of the advantages and the challenges of distributed computing.

Show publication details

Wilmsdorff, Julian von; Kirchbuchner, Florian; Fu, Biying; Braun, Andreas; Kuijper, Arjan

An Exploratory Study on Electric Field Sensing

2017

Braun, Andreas (Ed.) et al.: Ambient Intelligence : 13th European Conference, AmI 2017. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10217), pp. 247-262

European Conference on Ambient Intelligence (AmI) <13, 2017, Malaga, Spain>

Electric fields are influenced by the human body and other conducting materials. Capacitive measurement techniques are used in touch-screens, in the automobile industry, and for presence and activity recognition in Ubiquitous Computing. However, a drawback of the capacitive technology is the energy consumption, which is an important aspect for mobile devices. In this paper we explore possible applications of electric field sensing, a purely passive capacitive measurement technique, which can be implemented with an extremely low power consumption. To cover a wide range of applications, we examine five possible use cases in more detail. The results show that the application is feasible both in interior spaces and outdoors. Moreover, due to the low energy consumption, mobile usage is also possible.

Show publication details

Frank, Sebastian; Kuijper, Arjan

AuthentiCap - A Touchless Vehicle Authentication and Personalization System

2017

Braun, Andreas (Ed.) et al.: Ambient Intelligence : 13th European Conference, AmI 2017. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10217), pp. 46-63

European Conference on Ambient Intelligence (AmI) <13, 2017, Malaga, Spain>

Current authentication systems in vehicles use portable keys or biometric and/or touch based inputs. They can be outwitted by stealing the keys or by copying the biometric information and analyzing the touch marks. This has to be inhibited, since vehicles are not only an expensive property, that would be lost in non-authenticated hands, but wrong permitted access also can unleash heavy machine power to inexperienced drivers or even people without a driver's license. We present a system that authenticates drivers and unlocks personalization features without any portable keys or touching. Moreover, it is invisibly integrated into a vehicle structure, the steering wheel. In contrast to biometric authentication, the password pattern is adjustable and changeable. With the presented system, vehicle manufactures are able to install driver authentication systems without any visible design changes. The manufacturer thus provides more freedom and responsibility to the driver by giving him the option to choose his own unlock pattern. Still, the security is increased by avoiding common vulnerabilities like smudge attacks, the stealing of keys, or copying of biometric data. Our experiments show excellent recognition rates for multiple string patterns. A small user study shows that our system achieves 86% accuracy for inexperienced users, up to 96% for experienced ones. The users appreciated the easy of use.

Show publication details

Fina, Kenten; Kuijper, Arjan (Betreuer); Getto, Roman (Betreuer)

Automated Detection of Significant Parameters in Procedural 3D Models

2017

Darmstadt, TU, Bachelor Thesis, 2017

This bachelor thesis present an approach to automatically detect significant parameters in a procedural model. For the distinction of significant and insignificant parameters we present both a static version and a method using machine learning. In the process parameters are grouped, which represent symmetries or other relations in the model. Additionally we allow the user to adapt the selection of significant parameters to his needs. For this purpose we support the user by visualizing the changes of a parameter. Furthermore a hierarchical arrangement of the parameters is done to give the user an overview of all design possibilities. Subsequently, we show how ranges for the selected parameters can be calculated, which retain the object.

Show publication details

Sagare, Anagha; Kuijper, Arjan (Betreuer); Fu, Biying (Betreuer)

Best Practices to Visualize Activity Data in Mobile Apps

2017

Darmstadt, TU, Master Thesis, 2017

Physical activity and exercise are essential factors to live a healthy life. Fitness trackers have great potential to assist individuals in making healthy changes to their lifestyle. A variety of fitness trackers are available in the market such as fitness apps based on mobile platform, wearable sensors (e.g. smartwatch, armband, wristband), balancing boards (e.g. Wii fit) etc. In this thesis, the focus is on fitness apps based on mobile platform. These apps provide different information and features to the user such as a summary of the physical activity performed, feedback of the activity (e.g. through virtual trainer), exercise plans according to the user's workout routine, user's achievements and many more. Also, fitness apps aim to present a lot of statistical data to the users regarding their current or previous physical activity which may range from days to years. To visualize this data, visual designs such as maps, graphs, images are used. However, very little is known about such visualization schemes and design strategies for fitness data w.r.t engaging users. Furthermore, it is important to know if the provided features in the app are useful. The main objective of this study is to evaluate different visualization schemes used in visualizing fitness data and to explore usability requirements, motivating factors for using mobile fitness apps. For this purpose, a profound research is done in three phases. The first phase focuses on finding expectations of a user from fitness app through a short primary survey in University Gym, the second phase includes designing an extensive user survey and fitness app mock-ups based on the survey findings in the first phase. In the third phase, the designed mock-ups are evaluated by means of the user survey designed in second phase and the survey results are analyzed using statistical test. The study reveals that users find some visualization schemes very useful whereas they do not prefer some visualization schemes at all. Same is the case observed for motivational features e.g. ranking, rewards and other functionalities of the app e.g. workout summary, nutrition information. This thesis concludes with best practices for designing visualization schemes and analysis of user requirements for mobile fitness applications such as integrated feedback, home screen design of the app and some features like data sharing, data export etc. These findings show the way to develop highly usable fitness applications with user-centric design.

Show publication details

Gao, Shan; Ye, Qixiang; Xing, Junliang; Kuijper, Arjan; Han, Zhenjun; Jiao, Jianbin; Ji, Xiangyang

Beyond Group: Multiple Person Tracking via Minimal Topology-Energy-Variation

2017

IEEE Transactions on Image Processing, Vol.26 (2017), 12, pp. 5575-5589

Tracking multiple persons is a challenging task when persons move in groups and occlude each other. Existing group-based methods have extensively investigated how to make group division more accurately in a tracking-by-detection framework; however, few of them quantify the group dynamics from the perspective of targets' spatial topology or consider the group in a dynamic view. Inspired by the sociological properties of pedestrians, we propose a novel socio-topology model with a topology-energy function to factor the group dynamics of moving persons and groups. In this model, minimizing the topologyenergy- variance in a two-level energy form is expected to produce smooth topology transitions, stable group tracking, and accurate target association. To search for the strong minimum in energy variation, we design the discrete group-tracklet jump moves embedded in the gradient descent method, which ensures that the moves reduce the energy variation of group and trajectory alternately in the varying topology dimension. Experimental results on both RGB and RGB-D data sets show the superiority of our proposed model for multiple person tracking in crowd scenes.

Show publication details

Matthies, Denys J.C.; Roumen, Thijs; Kuijper, Arjan; Urban, Bodo

CapSoles: Who Is Walking on What Kind of Floor?

2017

Association for Computing Machinery (ACM): MobileHCI 2017 : Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services. New York: ACM, 2017, 14 p.

International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI) <19, 2017, Vienna, Austria>

Foot interfaces, such as pressure-sensitive insoles, still yield unused potential such as for implicit interaction. In this paper, we introduce CapSoles, enabling smart insoles to implicitly identify who is walking on what kind of floor. Our insole prototype relies on capacitive sensing and is able to sense plantar pressure distribution underneath the foot, plus a capacitive ground coupling effect. By using machine-learning algorithms, we evaluated the identification of 13 users, while walking, with a confidence of ~95% after a recognition delay of ~1s. Once the user's gait is known, again we can discover irregularities in gait plus a varying ground coupling. While both effects in combination are usually unique for several ground surfaces, we demonstrate to distinguish six kinds of floors, which are sand, lawn, paving stone, carpet, linoleum, and tartan with an average accuracy of ~82%. Moreover, we demonstrate the unique effects of wet and electrostatically charged surfaces.

Show publication details

Braun, Andreas; Zander-Walz, Sebastian; Majewski, Martin; Kuijper, Arjan

Curved - Free-Form Interaction Using Capacitive Proximity Sensors

2017

Procedia Computer Science [online], Vol.109 (2017), pp. 59-66

International Conference on Ambient Systems, Networks and Technologies (ANT) <8, 2017, Madeira, Portugal>

Large interactive surfaces have found increased popularity in recent years. However, with increased surface size ergonomics become more important, as interacting for extended periods may cause fatigue. Curved is a large-surface interaction device, designed to follow the natural movement of a stretched arm when performing gestures. It tracks one or two hands above the surface, using an array of capacitive proximity sensors and supports both touch and mid-air gestures. It requires specific object tracking methods and the synchronized measurement from 32 sensors. We have created an example application for users wearing a virtual reality headset while seated that may benefit from haptic feedback and ergonomically shaped surfaces. A prototype with adaptive curvature has been created that allows us to evaluate gesture recognition performance and different surface inclinations.

Show publication details

Knuth, Martin; Bender, Jan; Goesele, Michael; Kuijper, Arjan

Deferred Warping

2017

IEEE Computer Graphics and Applications, Vol.37 (2017), 6, pp. 76 - 87. Published Online: 18 March 2016

We introduce deferred warping, a novel approach for real-time deformation of 3D objects attached to an animated or manipulated surface. Our target application is virtual prototyping of garments where 2D pattern modeling is combined with 3D garment simulation which allows an immediate validation of the design. The technique works in two steps: First, the surface deformation of the target object is determined and the resulting transformation field is stored as a matrix texture. Then the matrix texture is used as look-up table to transform a given geometry onto a deformed surface. Splitting the process in two steps yields a large flexibility since different attachment types can be realized by simply defining specific mapping functions. Our technique can directly handle complex topology changes within the surface. We demonstrate a fast implementation in the vertex shading stage allowing the use of highly decorated surfaces with millions of triangles in real-time.

Show publication details

Schufrin, Marija; Kuijper, Arjan (Betreuer); Burkhardt, Dirk (Betreuer)

Designstudie und Entwicklung von Konzepten zur visuellen Trendanalyse für mobile Umgebungen

2017

Darmstadt, TU, Master Thesis, 2017

Die immer schneller wachsenden Datenmengen in nahezu allen Bereichen des Lebens führen zu dem verstärkten Bestreben, die darin enthaltenen Informationen zu gewinnen und nützlich einzusetzen. Die menschlichen Kapazitäten im Hinblick auf die kognitive Verarbeitung von Informationen sind jedoch begrenzt. Daher werden Techniken und Methoden entwickelt, um den Menschen bei dieser Aufgabe zu unterstützen. Eine Ausprägung der Informationssuche in Datenmengen ist die analytische Untersuchung der Daten. Dazu gehört unter anderem das Erkennen von Trends und Mustern. Visual Analytics hat das Ziel, den Menschen durch eine Kombination aus Informationsvisualisierungen und automatisierten Analyseverfahren bei diesem Prozess zu unterstützen. Die meiste Forschung auf diesem Gebiet bezieht sich bislang überwiegend auf Computer und Laptops. Durch die rasante Verbreitung von mobilen Geräten in den letzten Jahren entstand die Notwendigkeit, die Methoden und Techniken auch im Hinblick auf den Einsatz auf mobilen Geräten zu untersuchen. Die mobile Umgebung bringt neue Herausforderungen, aber auch Möglichkeiten, mit sich. Am Fraunhofer IGD in Darmstadt wurde eine Software zur visuellen Trendanalyse auf Basis von digitalen Publikationsdatenbanken entwickelt. Ziel ist es, durch die Visualisierung der darin zur Verfügung stehenden Informationen, aufkommende und verschwindende Trends zu erkennen. Diese Software ist allerdings für die Benutzung auf einem Desktop-Computer ausgelegt. Im Rahmen dieser Arbeit wurde daher eine Designstudie durchgeführt, um die Designmöglichkeiten zur Umsetzung der Software auf mobilen Geräten zu untersuchen. Dazu wurde ein Modell der Zielgruppe (Entscheidungsträger) erstellt, welches aus drei Eigenschaften besteht. Eine dieser Eigenschaften besteht aus zwei Merkmalen - Bauchgefühl und Verstand - welche als gegensätzliche Aspekte identifiziert wurden, deren Vorteile jedoch jeweils stark vom Kontext abhängen. Gerade bei mobilen Umgebungen hat der sich stets verändernde Kontext einen starken Einfluss auf die Benutzererfahrung. Adaptive Mechanismen mit Bezug auf die mentale Verfassung des Benutzers (z.B. geteilte Aufmerksamkeit) können große Vorteile im Hinblick auf die positive Nutzererfahrung mit sich bringen. Im Rahmen dieser Designstudie wurden drei Designs entwickelt und untersucht, die jeweils das Bauchgefühl, den Verstand oder eine Kombination aus beiden in den Fokus stellen. Die Konzepte wurden prototypisch implementiert und im Rahmen eines kleinen kontrollierten Experiments evaluiert.

Show publication details

Reinhard, Johann; Kuijper, Arjan (Betreuer); Brunton, Alan (Betreuer)

Discrete Medial Axis Transform and Applications for 3D Printing

2017

Darmstadt, TU, Bachelor Thesis, 2017

3D printing is becoming a more commonly used manufacturing process, both for industrial and consumer use, with ever increasing capabilities and areas of application. These opportunities also introduce higher expectations on the quality of the resulting prints, generally in terms of the resulting shape and appearance of the object, but also rigidness and structural integrity. Detecting characteristics in a model that are a source of errors opens up possible approaches to mitigate or eliminate these errors before printing it. One such characteristic are thin structures that can lead to missing or deformed shapes, changes in the appearance of full color prints or fragile structures that break during post-processing steps. The aim of this work is to detect thin structures using the discrete medial axis, representing the centers of a shape. In order to compute the discrete medial axis a discrete medial axis transform based on image processing techniques is implemented in the Cuttlefish 3D printer driver. The result for different models are assessed and possible correlations of the medial axis and thin structures evaluated. Possible applications of the medial axis or filtered medial axis are proposed and discussed.

Show publication details

Rus, Silvia; Braun, Andreas; Kuijper, Arjan

E-Textile Couch: Towards Smart Garments Integrated Furniture

2017

Braun, Andreas (Ed.) et al.: Ambient Intelligence : 13th European Conference, AmI 2017. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10217), pp. 214-224

European Conference on Ambient Intelligence (AmI) <13, 2017, Malaga, Spain>

Application areas like health-care and smart environments have greatly benefited from embedding sensors into every-day-objects, enabling for example sleep apnea detection. We propose to further integrate parts of sensors into the very own materials of the objects. Thus, in this work we explore integrating smart garments into furniture using a couch as our use-case. Equipped with textile capacitive sensing electrodes, we show that our prototype outperforms existing systems achieving an F-measure of 94.1%. Furthermore, we discuss implications and limitation of the integration process.

Show publication details

Räsch, Sascha; Herz, Maximilian; Behr, Johannes; Kuijper, Arjan

Efficient Compression for Server-Side G-Buffer Streaming in Web Applications

2017

ACM SIGGRAPH: Proceedings Web3D 2017 : 22nd International Conference on 3D Web Technology. New York: ACM, 2017, 7 p.

International Conference on 3D Web Technology (WEB3D) <22, 2017, Brisbane, Australia>

Remote rendering methods enable devices with low computing power like smart phones or tablets to visualize massive data. By transmitting G-Buffers, Depth-Image-Based Rendering (DIBR) methods can be used to compensate the artefacts caused by the latency. However, the drawback is that a G-Buffer has at least twice as much data as an image. We present a method for compressing G-Buffers which provides an efficient decoding suitable for web applications. Depending on the computing power of the device, software methods, which run on the CPU, may not be fast enough for an interactive experience. Therefore, we developed a decoding which runs entirely on the GPU. As we use only standard WebGL for our implementation, our compression is suitable for every modern browser.

Show publication details

Damer, Naser; Terhörst, Philipp; Braun, Andreas; Kuijper, Arjan

Efficient, Accurate, and Rotation-Invariant Iris Code

2017

IEEE Signal Processing Letters, Vol.24 (2017), 8, pp. 1233-1237

The large scale of the recently demanded biometric systems has put a pressure on creating a more efficient, accurate, and private biometric solutions. Iris biometrics is one of the most distinctive and widely used biometric characteristics. High-performing iris representations suffer from the curse of rotation inconsistency. This is usually solved by assuming a range of rotational errors and performing a number of comparisons over this range, which results in a high computational effort and limits indexing and template protection. This work presents a generic and parameter-free transformation of binary iris representation into a rotation-invariant space. The goal is to perform accurate and efficient comparison and enable further indexing and template protection deployment. The proposed approach was tested on a database of 10 000 subjects of the ISYN1 iris database generated by CASIA. Besides providing a compact and rotational-invariant representation, the proposed approach reduced the equal error rate by more than 55% and the computational time by a factor of up to 44 compared to the original representation.

Show publication details

Hartl, Tabea; Kuijper, Arjan (Betreuer); Jung, Florian (Betreuer)

Ein interaktives Segmentierungsverfahren für Strukturen in medizinischen Bilddaten unter Verwendung eines Random Walk Ansatzes

2017

Darmstadt, TU, Bachelor Thesis, 2017

Tumore im Kopf-Hals-Bereich stellen eine gefährliche invasive Krankheit dar, daher ist eine ausführliche Diagnose und Therapieplanung für den Patienten von großer Bedeutung. Ein wichtiger Teil dieser Diagnose und Therapieplanung ist die Segmentierung des Tumors. Häufig werden hierzu Bilddaten verwendet, die mit Hilfe der Magnetresonanztomographie aufgenommen wurden. Für diesen speziellen Anwendungsfall gibt es aktuell kein Verfahren, dass gute Ergebnisse liefert. Diese Arbeit stellt einen interaktiven Segmentierungsalgorithmus für Tumore im Kopf-Hals-Bereich vor, der einen Random Walk Ansatz nutzt. Der Algorithmus verwendet initiale Markierungen um eine Segmentierung von Tumoren zu erstellen, auch wenn Strukturen mit ähnlichen Intensitätswerten angrenzen. Aus Effizienzgründen wird die Ähnlichkeit zu einem Problem aus der Schaltungstheorie ausgenutzt. Dafür werden die Bilddaten in eine Graphendarstellung überführt, die aus Knoten und gewichteten Kanten besteht. Ausgehend von dieser Darstellung wird ein lineares Gleichungssystem aufgestellt, welches die Lösung des Random Walk Ansatzes berechnet. Der Algorithmus liefert in MR-Daten für Tumore im Kopf-Hals-Bereich gute Ergebnisse. Wir haben den Algorithmus für 18 verschiedene Tumore und jeweils zwei unterschiedliche initiale Markierungen getestet. Der Median der Hausdorff-Distanz aller Segmentierungen liegt bei einem Wert von 8,83 und der Dice-Koeffizient bei einem Wert von 0,71. Zusätzlich wurde der Ansatz auch auf CT-Daten für vier verschiedenen Strukturen und für Lymphknoten auf MR-Bildern evaluiert. Ein großer Vorteil des Verfahrens ist, die Möglichkeit Expertenwissen durch initiale Markierungen einfließen zu lassen und damit die Ergebnisse des Algorithmus zu verbessern. Dies erlauben die meisten andere Verfahren nicht. Der Algorithmus liefert nutzbare Segmentierungen für Tumore und Lymphknoten in MR-Bilddaten. Er ist generisch verwendbar und kann auch für andere Strukturen und Modalitäten genutzt werden.

Show publication details

Joshi, Dhanashree Jayant; Kuijper, Arjan (Betreuer); Rus, Silvia (Betreuer)

Emotion Detection By Evaluating Activities For Smart Home Appliances

2017

Darmstadt, TU, Master Thesis, 2017

Human computer interactions can be made easier if we make computers understand person's emotions. Over the years, research in emotion recognition has mainly focused on facial expressions, voice analysis and hand-writing. Apart from these conventional methods, body movements, body postures and gestures or quality of movements can also be used to differentiate basic or fundamental emotions like happiness, anger, fear, sadness, surprise etc. For instance in case of fear, body of a person contracts, muscles tighten while as in case of happiness, muscles are more relaxed and body tends to occupy more area. Recognizing emotions of a person solely on his movements will enable efficient communication between human and machine. This master thesis is based on this idea of the machine being able to recognize the emotions from postures and movements of a human. A couch as a smart furniture has been used for the prediction of postures which are further used to predict the fundamental emotions including anxiety, happiness, sadness, relaxation, being focused/interested by using capacitive proximity sensors integrated into the couch. Android application was developed to predict the real-time postures of a person using machine learning classification algorithms. A relation between postures and movements with emotions has been established. This relation was considered as a baseline for the prediction of emotions. For the recognition of mentioned emotions, the detected movements and postures were analyzed and evaluated using various classification algorithms in machine learning. Furthermore the comparison of these classification algorithms with respect to performance was done and the better accuracy classification algorithm was chosen. This thesis also discusses in depth various methods that have been used to evoke the emotions of a human being during evaluation experiments. After successful evoking and prediction of the emotions, the results can then be used in various smart home applications.

Show publication details

Rimal, Mristi; Kuijper, Arjan (Betreuer); Ben Hmida, Helmi (Betreuer)

Enhancing Visual Interface Aspects of Internet of Things Smart Objects

2017

Darmstadt, TU, Master Thesis, 2017

The Internet of Things, commonly known as "IoT", is the current ongoing evolution of the Internet. IoT encompasses all the services of a real-world object and therefore impacts everyday human life. IoT development runs around finding ways to cooperate humans and objects. Humans are the producers and consumers of the IoT ecosystem. One key to the successful use of the IoT systems is more human involvement. Human users interact with the smart objects in the IoT ecosystem through the use of an interface. The interface of an IoT allows users to trigger actions in the smart objects, control the smart objects, and query the state of the smart objects. Technically naive users usually view the whole IoT system in terms of user interface. Any IoT development that does not address the user interface aspects is bound to fail. Recognizing the value of user interface, this thesis focuses on the enhancement of the visual interface aspects of IoT. This thesis provides an overview of the existing IoT platforms, their capabilities, characteristics, limitations and their comparison in terms of design requirements for a successful user interface. The limitations are then addressed and a user interface is proposed, combining all success factors which is evaluated with a user requirements survey and an implementation feedback questionnaire. The evaluation also follows possible future work.

Show publication details

Rus, Silvia; Große-Puppendahl, Tobias; Kuijper, Arjan

Evaluating the Recognition of Bed Postures Using Mutual Capacitance Sensing

2017

Journal of Ambient Intelligence and Smart Environments, Vol.9 (2017), 1, pp. 113-127

Capacitive sensing is increasingly used to gather contextual information about humans. They can be used to create stationary or mobile systems for non-contact activity recognition. They are able to sense any conductive objects at distances up to 50 cm. This paper investigates an approach to classify bed postures using mutual capacitance sensing. The goal is to develop a system that prevents decubitus ulcers, which is a condition caused by prolonged pressure on the skin that can result in injuries to the skin and underlying tissues. The posture recognition is used to detect prolonged lying in a single pose and can notify care personnel. A low-cost grid of crossed wires is proposed that is placed between the mattress and the bed sheet that creates 48 measurement points. The experiments analyze a set of five bedding positions with 14 users. Using self-defined features, we achieved an accuracy of 80.8% for all users and an accuracy of 93.8% for individuals of similar body size. Refining the classification approach by directly classifying the raw data an overall accuracy of 90.5% was reached. By introducing an uncertainty threshold the classification is correct in 97.6% of cases.

Show publication details

Dimitrov, Kristiyan; Kuijper, Arjan (Betreuer); Damer, Naser (Betreuer)

Exploring Deep Multi-biometric Fusion

2017

Darmstadt, TU, Master Thesis, 2017

The field of biometrics aims at performing automatic recognition of individuals based on their biological traits and is, hence, increasingly applied in places with high security requirements. To make biometric systems truly robust and reliable, multiple biometric sources could be combined with a particular fusion scheme. Mainly due to its ease of access, score-level fusion is the most practical method of multi-biometric fusion and has, thus, received the most attention from the research community. Higher-level fusion schemes (e.g. data or feature), in contrast, are difficult to achieve in practice. Yet, they are expected to yield superior results, owing to the higher amount of information available at the point of fusion. A central problem with this type of fusion is the extraction of a discriminative joint feature set. Feature extractors have to be manually designed and typically require a great deal of technical knowledge; for many tasks it is also infeasible to find an appropriate solution. Deep learning offers the ability to automatically learn useful features from raw data for any particular task with minimal human intervention. As a result, it is considered a reasonable option for realizing fusion in a multi-biometric scenario. Within the scope of this work, several architectures, based on a convolutional neural network model, are considered. Their performance have been tested in a multi-modal and a multiinstance setup, respectively. The results have been compared against baseline score-level fusion solutions. It has been shown, that with comparable network structures and computational costs, the less sophisticated, score-level fusion approach performs better than utilizing deep learning for the multi-biometric fusion process. As a future outlook, this thesis proposes possible modifications to the deep fusion approach that might improve the overall performance.

Show publication details

Damer, Naser; Terhörst, Philipp; Braun, Andreas; Kuijper, Arjan

General Borda Count for Multi-biometric Retrieval

2017

IEEE Computer Society: 2017 International Joint Conference on Biometrics : IJCB 2017. IEEE Computer Society Conference Publishing Services (CPS), 2017, pp. 420-428

IEEE International Joint Conference on Biometrics (IJCB) <2017, Denver, CO, USA>

Indexing of multi-biometric data is required to facilitate fast search in large-scale biometric systems. Previous works addressing this issue were challenged by including biometric sources of different nature, utilizing the knowledge about the biometric sources, and optimizing and tuning the retrieval performance. This work presents a generalized multi-biometric retrieval approach that adapts the Borda count algorithm within an optimizable structure. The approach was tested on a database of 10k reference and probe instances of the left and the right irises. The experiments and comparisons to five baseline solutions proved to achieve advances in terms of general indexing performance, tunability to certain operating points, and response to missing data. A clear advantage of the proposed solution was noticed when faced by candidate lists of low quality.

Show publication details

Frank, Sebastian; Kuijper, Arjan

HUDConCap - Automotive Head-Up Display Controlled with Capacitive Proximity Sensing

2017

Braun, Andreas (Ed.) et al.: Ambient Intelligence : 13th European Conference, AmI 2017. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10217), pp. 197-213

European Conference on Ambient Intelligence (AmI) <13, 2017, Malaga, Spain>

Most of the current Head-Up Display solutions in the automotive domains can not handle user input. Nevertheless, many automotive manufacturers develop and/or implement gesture interaction systems, controlled by the user's hand, into their head-down infotainment displays. The gesture recognition, precisely the hand tracking, is mostly facilitated with camera systems that monitor the driver or with infrared sensors. These systems require a line of sight between the driver's hands and the measurement transducer. Therefore, they require interior design integration and are visible to the user. Moreover, the permanent camera monitoring of the driver, in combination with an internet connected vehicle, can cause privacy issues and increase the driver's feeling of observation. We therefore present a system that integrates user control into a Head-Up Display, similar to a computer mouse. Moreover, the presented system's capacitive proximity sensors can sense through non-conductive materials. Thus, the system can be invisibly integrated into existing vehicle structures. In our case, it is part of the steering wheel. With our presented system, vehicle manufactures are able to install a Head-Up display control system without any visible design changes. Furthermore, the manufacturer provides more interaction space in driving situations. Additionally, he can rely on the lower level of driver distraction provided by Head-Up displays. Therefore, the presented system can increase driving safety. The systems usability is shown by a small user-study that consists of performance tests on a proof-of-concept prototype and a questionnaire.

Show publication details

Scherf, Lisa Katharina; Kuijper, Arjan (Betreuer); Kirchbuchner, Florian (Betreuer)

Human Behavior Analysis and Prediction Based on a Smart Floor

2017

Darmstadt, TU, Bachelor Thesis, 2017

Older adults have the desire to live independently in their own homes for as long as possible. The development of sensor technologies in Smart Homes support this aim by providing sufficient security standards in case of emergencies. For example, a call of emergency can be triggered if a fall of a person is detected by sensors hidden in the floor. However, it is often not only about urgent situations, but also about gradual changes in behavior. Especially when a user is not able to follow his or her daily routine, long-term activity recognition based on location tracking allows for early detection of diseases such as Alzheimer's and dementia and can generally reveal a decrease in the ability to live independently. The focus of this work was the investigation of health related activities and their most accurate measurement only using an intelligent floor based system. Based on these considerations, a method to extrapolate from the collected sensor data to the chosen values is proposed. In addition, a model to detect gradual changes in these health indicators is developed and tested on the smart floor in the Living Lab of Fraunhofer IGD as well as in two apartments in everyday life. The findings of these thesis show a way of using smart floors for health monitoring. The applicability in everyday life could not be shown due to independent problems with the location tracking of the floor during the evaluation period and the lack of additional data for the validation. However, the evaluation under testing conditions showed promising results and an untapped potential of smart floors in health monitoring.

Show publication details

Damer, Naser; Terhörst, Philipp; Braun, Andreas; Kuijper, Arjan

Indexing of Single and Multi-instance Iris Data Based on LSH-Forest and Rotation Invariant Representation

2017

Felsberg, Michael (Ed.) et al.: Computer Analysis of Images and Patterns : CAIP 2017 Proceedings, Part II. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10425), p. 190-201

International Conference on Computer Analysis of Images and Patterns (CAIP) <17, 2017, Ystad, Sweden>

Indexing of iris data is required to facilitate fast search in large-scale biometric systems. Previous works addressing this issue were challenged by the tradeoffs between accuracy, computational efficacy, storage costs, and maintainability. This work presents an iris indexing approach based on rotation invariant iris representation and LSH-Forest to produce an accurate and easily maintainable indexing structure. The complexity of insertion or deletion in the proposed method is limited to the same logarithmic complexity of a query and the required storage grows linearly with the database size. The proposed approach was extended into a multi-instance iris indexing scheme resulting in a clear performance improvement. Single iris indexing scored a hit rate of 99.7% at a 0.1% penetration rate while multi-instance indexing scored a 99.98% hit rate at the same penetration rate. The evaluation of the proposed approach was conducted on a large database of 50k references and 50k probes of the left and the right irises. The advantage of the proposed solution was put into prospective by comparing the achieved performance to the reported results in previous works.

Show publication details

Fu, Biying; Kirchbuchner, Florian; Wilmsdorff, Julian von; Große-Puppendahl, Tobias; Braun, Andreas; Kuijper, Arjan

Indoor Localization Based on Passive Electric Field Sensing

2017

Braun, Andreas (Ed.) et al.: Ambient Intelligence : 13th European Conference, AmI 2017. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10217), pp. 64-79

European Conference on Ambient Intelligence (AmI) <13, 2017, Malaga, Spain>

The ability to perform accurate indoor positioning opens a wide range of opportunities, including smart home applications and location-based services. Smart floors are a well-established technology to enable marker-free indoor localization within an instrumented environment. Typically, they are based on pressure sensors or varieties of capacitive sensing. These systems, however, are often hard to deploy as mechanical or electrical features are required below the surface. They might also have a limited range or not be compatible with different floor materials. In this paper, we present a novel indoor positioning system using an uncommon form of passive electric field sensing, which detects the change in body electric potential during movement. It is easy to install by deploying a grid of passive wires underneath any non-conductive floor surface. The proposed architecture achieves a high position accuracy and an excellent spatial resolution. In our evaluation, we measure a mean positioning error of only 12.7 cm. The proposed system also combines the advantages of very low power consumption, easy installation, easy maintenance, and the preservation of privacy.

Show publication details

Patzwahl, Alex; Kuijper, Arjan (Betreuer); Brodkorb, Felix (Betreuer)

Interaktives Erzeugen von dynamischen geographischen Netzwerken

2017

Darmstadt, TU, Bachelor Thesis, 2017

Graphen finden in den unterschiedlichsten Gebieten Anwendung. Neben vielen anderen Eigenschaften besitzen diese auch oft einen geographischen Kontext. Beispielsweise Computernetzwerke, bei denen die einzelnen Computer über geographische Standorte verfügen. Diese Besonderheit ist keinesfalls unwichtig, da sie zusätzliche Informationen bergen kann. Ebenfalls ist es sehr wahrscheinlich, dass sich diese Netzwerke auch über die Zeit entwickeln. Zur genaueren Analyse der Netzwerke werden folglich einige Daten benötigt, welche aber nur in geringen Mengen frei zur Verfügung stehen. Genauso werden auch größere, vielfältigere Datenmengen zu Test- oder Simulationszwecken gebraucht, die kaum zu finden sind. Deswegen bedarf es an dieser Stelle an Wegen zur künstlichen Generierung dieser Daten. In dieser Arbeit wird ein interaktiv, visuelles Generatormodel zur Erzeugung von dynamisch geographischen Netzwerken präsentiert. Dabei wird der Benutzer beim Steuern des Generierungsprozesses durch einen Wizard geführt, um die Bedienung zu erleichtern. Der eigentliche Algorithmus hinter dem Generator arbeitet zum Teil auf Power-Law Basis sowie auf weiteren, in dieser Arbeit präsentierten analytischen Ergebnissen.

Show publication details

Wen, Zhuoman; Kuijper, Arjan; Fraissinet-Tachet, Matthieu; Wang, Yanjie; Luo, Jun

Mutual Information-Based Tracking for Multiple Cameras and Multiple Planes

2017

Arabian Journal for Science and Engineering, Vol.42 (2017), 8, pp. 3451-3463

Based onmutual information (MI), this paper proposes a systematic analysis of tracking a multi-plane object with multiple cameras. Firstly, a geometric model consisting of a piecewise planar object and multiple cameras is setup. Given an initial pose guess, the method seeks a pose update that maximizes the global MI of all the pairs of reference image and camera image. An object pose-dependent warp is proposed to ensure computation precision. Six variations of the proposed method are designed and tested. Mode 1, i.e., computing the 2nd-order Hessian of MI at each step as the object pose changes, leads to the highest convergence rates; Mode 2, i.e., computing the 1st-order Hessian of MI once at the beginning, occupies the least time (0.5-1.0 s). For objects with simple-textured planes, applying Gaussian blur first and then useMode 1 shall generate the highest convergence rate.

Show publication details

Damer, Naser; Alkhatib, Wael; Braun, Andreas; Kuijper, Arjan

Neighbor Distance Ratios and Dynamic Weighting in Multi-biometric Fusion

2017

Alexandre, Luís A. (Ed.) et al.: Pattern Recognition and Image Analysis : IbPRIA 2017. Springer International Publishing, 2017. (Lecture Notes in Computer Science (LNCS) 10255), pp. 491-500

Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) <8, 2017, Faro, Portugal>

Multi-biometrics aims at building more accurate unified biometric decisions based on the information provided by multiple biometric sources. Information fusion is used to optimize the process of creating this unified decision. In previous works dealing with score-level multibiometric fusion, the scores of different biometric sources belonging to the comparison of interest are used to create the fused score. This is usually achieved by assigning static weights for the different biometric sources. In contrast, we focus on integrating the information imbedded in the relative relation between the comparison scores (within a 1:N comparison) in the biometric fusion process using a dynamic weighting scheme. This is performed by considering the neighbors distance ratio in the ranked comparisons to influence the dynamic weights of the fused scores. The evaluation was performed on the Biometric Scores Set BSSR1 database. The enhanced performance induced by including the neighbors distance ratio information within a dynamic weighting scheme in comparison to the baseline solution was shown by an average reduction of the equal error rate by more than 40% over the different test scenarios.

Show publication details

Mammadova, Chinara; Ben Hmida, Helmi; Braun, Andreas; Kuijper, Arjan

New Approach for Optimizing the Usage of Situation Recognition Algorithms Within IoT Domains

2017

Braun, Andreas (Ed.) et al.: Ambient Intelligence : 13th European Conference, AmI 2017. Springer, 2017. (Lecture Notes in Computer Science (LNCS) 10217), pp. 183-196

European Conference on Ambient Intelligence (AmI) <13, 2017, Malaga, Spain>

The growth of the Internet of Things (IoT) over the past few years enabled a lot of application domains. Due to the increasing number of IoT connected devices, the amount of generated data is increasing too. Processing huge amounts of data is complex due to the continuously running situation recognition algorithms. To overcome these problems, this paper proposes an approach for optimizing the usage of situation recognition algorithms in Internet of Things domains. The key idea of our approach is to select important data, based on situation recognition purposes, and to execute the situation recognition algorithms after all relevant data have been collected. The main advantage of our approach is that situation recognition algorithms will not be executed each time new data is received, thus allowing the reduction of the situation recognition algorithms execution frequency and saving computational resources.

Show publication details

Dimitrov, Dimitar Tomov; Kuijper, Arjan (Betreuer)

Non-Local Bayes Denoising of Digital Images on GPU using OpenCL

2017

Darmstadt, TU, Master Thesis, 2017

Image sensors or lens inevitably produce a wide range of degradations in digital images. Among these degradations are various types of noise. Image noise is undesirable, random information added to the image that can cause significant quality degradation. Therefore, image denoising methods are very often the first step of an image processing chain. Non-Local Bayes (NL-Bayes) is a state of the art image denoising algorithm that provides effective noise reduction with good preservation of image details. Although efficient CPU implementations of this method exist, they still have performance issues. Nowadays, GPUs become a general-purpose computational devices and provide their power for more generalized tasks. Their massively parallel capabilities can significantly improve the performance of computationally expensive programs. However, due to the specific execution and memory model, algorithms for GPUs require special design that divides the computational task into as many independent pieces as possible. This thesis proposes solutions to perform NL-Bayes image denoising on the GPU using the OpenCL standard. Our study evaluates quantitatively and qualitatively the proposed implementations by making comparisons with an existing CPU implementation. We show that a GPU-based solution is six times faster compared to the CPU-based solution when maximal denoising quality is demanded. Additionally, we describe general problems in the parallelization of such a complex image denoising algorithm.

Show publication details

Ritter, Christian; Kuijper, Arjan (Betreuer); Bernard, Jürgen (Betreuer)

Personalized Music Classification and Feature Creation based on Visual-Interactive Learning

2017

Darmstadt, TU, Bachelor Thesis, 2017

I present an approach for personalized music classification and feature generation. Currently existing approaches cover general models that match the common taste of music and use (small) sets of pre-defined features. Allowing a user to interactively build a music classification model is a complex task. In this work, I introduce a two-level approach that utilizes Visual Analytics to solve that task. At high-level granularity, a user can interactively classify music in a visual interface. The system supports the user with multiple views that grant model insights and information about the feature space. Furthermore, the user can freely define classes and assign them to songs of his collection. At low-level granularity, a user is able to create features matching his task by defining important audio patterns. A similarity over the song is calculated from each pattern and then used to create features that depend on the preferences of the user. The approach I contribute allows classification of music (or, in general, multivariate time series) for various tasks with features created at run-time. Thus, it makes classification interactive and applicable to multiple tasks. Several evaluation techniques showed the usefulness of the approach in different scenarios and the effectiveness of personalized features.

Show publication details

Hafner, Morris; Kuijper, Arjan (Betreuer); Limper, Max (Betreuer)

Robust and Efficient Bijective Parameterization

2017

Darmstadt, TU, Bachelor Thesis, 2017

The goal of this thesis was to create a novel algorithm for bijective parameterizations of 3D triangle meshes with disk topology. Existing methods are either fast, but create non-bijective parameterizations, or are too slow to be applied to bigger meshes like high-resolution 3D scans or video game levels. We show an approach to transform an arbitrary, potentially non-bijective parameterization into a bijective mapping. The results show that the new algorithm produces results that are at least competitive with existing bijective parameterizers and still has room for future improvements.

Show publication details

Wen, Zhuoman; Wang, Yanjie; Luo, Jun; Kuijper, Arjan; Di, Nan; Jin, Minghe

Robust, Fast and Accurate Vision-Based Localization of a Cooperative Target Used for Space Robotic Arm

2017

Acta Astronautica, Vol.136 (2017), pp. 101-114

When a space robotic arm deploys a payload, usually the pose between the cooperative target fixed on the payload and the hand-eye camera installed on the arm is calculated in real-time. A high-precision robust visual cooperative target localization method is proposed. Combing a circle, a line and dots as markers, a target that guarantees high detection rates is designed. Given an image, single-pixel-width smooth edges are drawn by a novel linking method. Circles are then quickly extracted using isophotes curvature. Around each circle, a square boundary in a pre-calculated proportion to the circle radius is set. In the boundary, the target is identified if certain numbers of lines exist. Based on the circle, the lines, and the target foreground and background intensities, markers are localized. Finally, the target pose is calculated by the Point-3-Perspective algorithm. The algorithm processes 8 frames per second with the target distance ranging from 0.3m to 1.5 m. It generated highprecision poses of above 97.5% on over 100,000 images regardless of camera background, target pose, illumination and motion blur. At 0.3 m, the rotation and translation errors were less than 0.015° and 0.2 mm. The proposed algorithm is very suitable for real-time visual measurement that requires high precision in aerospace.

Show publication details

Burkhardt, Dirk; Pattan, Sachin; Nazemi, Kawa; Kuijper, Arjan

Search Intention Analysis for Task- and User-Centered Visualization in Big Data Applications

2017

Procedia Computer Science [online], Vol.104 (2017), pp. 539-547

International Conference on Tissue Engineering (ICTE) <2016, Riga, Latvia>

A new approach for classifying users' search intentions is described in this paper. The approach uses the parameters: word frequency, query length and entity matching for distinguishing the user's query into exploratory, targeted and analysis search. The approach focuses mainly on word frequency analysis, where different sources for word frequency data are considered such as the Wortschatz frequency service by the University of Leipzig and the Microsoft Ngram service (now part of the Microsoft Cognitive Services). The model is evaluated with the help of a survey tool and few machine learning techniques. The survey was conducted with more than one hundred users and on evaluating the model with the collected data, the results are satisfactory. In big data applications the search intention analysis can be used to identify the purpose of a performed search, to provide an optimal initially set of visualizations that respects the intended task of the user to work with the result data.

Show publication details

Merz, Johannes; Kuijper, Arjan (Betreuer); Getto, Roman (Betreuer)

Simplified Definition of Parameter Spaces of a GML Model Using Sketch-based Interaction

2017

Darmstadt, TU, Master Thesis, 2017

This Master Thesis presents a novel technique to intuitively insert meta-parameters into a procedural GML model with the help of sketch-based interaction. A GML model consist of a sequence of procedural modeling commands, for example extrusions. These are called with a set of local offset values, which can be converted to global space and anchored in the surface mesh of the model. As the global positions do not necessarily lie on the mesh surface, this is done by finding reference vertices. The system uses a mesh deformation technique to deform the evaluated surface of the model and creates a progression of intermediate target meshes. During the deformation, the reference vertices provide the global offset positions, whose path can be approximated by a B-spline. By exchanging the initial values of the commands by this B-spline, a continuous parameter space of the meta-parameter is defined. The deformation process is supported by a mesh segmentation to create pre-defined deformation targets for the user. Using intuitive sketch-based methods, these can be easily adapted to the users needs. The results show that the system closely imitates the mesh deformation with the help of the modeling commands. Furthermore, the system was evaluated to be intuitive and easy to use.

Show publication details

Siegmund, Dirk; Hörr, Oliver; Chiesa, Laura; Gabler, Frank; Braun, Andreas; Kuijper, Arjan

Talis - A Design Study for a Wearable Device to Assist People with Depression

2017

Reisman, Sorel (Ed.) et al.: 2017 IEEE 41st Annual Computer Software and Applications Conference Workshops : COMPSACW. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2017, pp. 543-548

IEEE International COMPSAC Workshop on User Centered Design and Adaptive Systems (UCDAS) <4, 2017, Torino, Italy>

One of the major diseases affecting the global population, depression has a strong emotional impact on its sufferers. In this design study, "Talis" is presented as a wearable device which uses emotion recognition as an interface between patient and machine to support psychotherapeutic treatment. We combine two therapy methods, "Cognitive Behavioral Therapy" and "Well- Being Therapy", with interactive methods thought to increase their practical application potential. In this study, we draw on the results obtained in the area of "affective computing" for the use of emotions in empathic devices. The positive and negative phases experienced by the patient are identified through speech recognition and used for direct communication and later evaluation. After considering the design possibilities and suitable hardware, the future realization of such technology appears feasible. In order to design the wearable, user studies and technical experiments were carried out. The results of these suggest that the device could be beneficial for the treatment of patients with depression.

Show publication details

Gutbell, Ralf; Kühnel, Hannes; Kuijper, Arjan

Texturizing and Refinement of 3D City Models with Mobile Devices

2017

Blanc-Talon, Jacques (Ed.) et al.: Advanced Concepts for Intelligent Vision Systems : 18th International Conference, ACIVS 2017, Antwerp, Belgium, September 18-21, 2017, Proceedings. Springer International Publishing, 2017. (Lecture Notes in Computer Science (LNCS) 10617), pp. 313-324

International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS) <18, 2017, Antwerp, Belgium>

Building recognition from images and video streams of mobile devices to texturize and refine an existing 3D city model is an open challenge, since such models most often do not completely represent the actual buildings. We present ways to extract buildings from images enabling improvement of the existing model. The approach is based on edge detection on images to detect walls, pure use of sensor data by creating an overlay to the video stream with the 3D model renderer from current position by a server, and the use of structure from motion algorithms to create point clouds and recognize a building via the support of the device's sensors. We show that we are thus able to texturize and refine an existing 3D city model.

Show publication details

Damer, Naser; Rhaibani, Chadi Izzou; Braun, Andreas; Kuijper, Arjan

Trust the Biometric Mainstream: Multi-biometric Fusion and Score Coherence

2017

European Association for Speech, Signal and Image Processing (EURASIP): 2017 Proceedings of the 25th European Signal Processing Conference (EUSIPCO), pp. 2191-2195

European Signal Processing Conference (EUSIPCO) <25, 2017, Kos, Greece>

Multi-biometrics aims at building more accurate unified biometric decisions based on the information provided by multiple biometric sources. Information fusion is used to optimize the process of creating this unified decision. In previous works dealing with score-level multi-biometric fusion, the scores of different biometric sources belonging to the comparison of interest are used to create the fused score. This is usually achieved by assigning static weights for the different biometric sources with more advanced solutions considering supplementary dynamic information like sample quality and neighbours distance ratio. This work proposes embedding score coherence information in the fusion process. This is based on our assumption that a minority of biometric sources, which points out towards a different decision than the majority, might have faulty conclusions and should be given relatively smaller role in the final decision. The evaluation was performed on the BioSecure multimodal biometric database with different levels of simulated noise. The proposed solution incorporates, and was compared to, three baseline static weighting approaches. The enhanced performance induced by including the coherence information within a dynamic weighting scheme in comparison to the baseline solution was shown by the reduction of the equal error rate by 45% to 85% over the different test scenarios and proved to maintain high performance when dealing with noisy data.

Show publication details

Wientapper, Folker; Kuijper, Arjan

Unifying Algebraic Solvers for Scaled Euclidean Registration from Point, Line and Plane Constraints

2017

Lai, Shang-Hong (Ed.) et al.: Computer Vision - ACCV 2016. Part V : 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers. Springer International Publishing, 2017. (Lecture Notes in Computer Science (LNCS) 10115), pp. 52-66

Asian Conference on Computer Vision (ACCV) <13, 2016, Taipei, Taiwan>

We investigate recent state-of-the-art algorithms for absolute pose problems (PnP and GPnP) and analyse their applicability to a more general type, namely the scaled Euclidean registration from pointto- point, point-to-line and point-to plane correspondences. Similar to previous formulations we first compress the original set of equations to a least squares error function that only depends on the non-linear rotation parameters and a small symmetric coefficient matrix of fixed size. Then, in a second step the rotation is solved with algorithms which are derived using methods from algebraic geometry such as the Gröbner basis method. In previous approaches the first compression step was usually tailored to a specific correspondence types and problem instances. Here, we propose a unified formulation based on a representation with orthogonal complements which allows to combine different types of constraints elegantly in one single framework. We show that with our unified formulation existing polynomial solvers can be interchangeably applied to problem instances other than those they were originally proposed for. It becomes possible to compare them on various registrations problems with respect to accuracy, numerical stability, and computational speed. Our compression procedure not only preserves linear complexity, it is even faster than previous formulations. For the second step we also derive an own algebraic equation solver, which can additionally handle the registration from 3D point-to-point correspondences, where other solvers surprisingly fail.

Show publication details

Getto, Roman; Kuijper, Arjan; Fellner, Dieter W.

Unsupervised 3D Object Retrieval with Parameter-Free Hierarchical Clustering

2017

Mao, Xiaoyang (Ed.) et al.: CGI 2017. Proceedings of the Computer Graphics International Conference. New York: ACM, 2017. (ACM International Conference Proceedings Series (ICPS) 1368), 6 p.

Computer Graphics International (CGI) <34, 2017, Yokohama, Japan>

In 3D object retrieval, additional knowledge like user input, classification information or database dependent configured parameters are rarely available in real scenarios. For example, meta data about 3D objects is seldom if the objects are not within a well-known evaluation database. We propose an algorithm which improves the performance of unsupervised 3D object retrieval without using any additional knowledge. For the computation of the distances in our system any descriptor can be chosen; we use the Panorama-descriptor. Our algorithm uses a precomputed parameter-free agglomerative hierarchical clustering and combines the information of the hierarchy of clusters with the individual distances to improve a single object query. Additionally, we propose an adaption algorithm for the cases that new objects are added frequently to the database. We evaluate our approach with 6 databases including a total of 13271 objects in 481 classes. We show that our algorithm improves the average precision in an unsupervised scenario without any parameter configuration.

Show publication details

Ruppert, Tobias; Staab, Michael; Bannach, Andreas; Lücke-Tieke, Hendrik; Bernard, Jürgen; Kuijper, Arjan; Kohlhammer, Jörn

Visual Interactive Creation and Validation of Text Clustering Workflows to Explore Document Collections

2017

Wischgoll, Thomas (Ed.) et al.: Visualization and Data Analysis 2017. Springfield: IS&T, 2017. (Electronic Imaging), pp. 46-57

Visualization and Data Analysis (VDA) <2017, Burlingame, CA, USA>

The exploration of text document collections is a complex and cumbersome task. Clustering techniques can help to group documents based on their content for the generation of overviews. However, the underlying clustering workflows comprising preprocessing, feature selection, clustering algorithm selection and parameterization offer several degrees of freedom. Since no "best" clustering workflow exists, users have to evaluate clustering results based on the data and analysis tasks at hand. In our approach, we present an interactive system for the creation and validation of text clustering workflows with the goal to explore document collections. The system allows users to control every step of the text clustering workflow. First, users are supported in the feature selection process via feature selection metrics-based feature ranking and linguistic filtering (e.g., part-of-speech filtering). Second, users can choose between different clustering methods and their parameterizations. Third, the clustering results can be explored based on the cluster content (documents and relevant feature terms), and cluster quality measures. Fourth, the results of different clusterings can be compared, and frequent document subsets in clusters can be identified. We validate the usefulness of the system with a usage scenario describing how users can explore document collections in a visual and interactive way.

Show publication details

Brodkorb, Felix; Kopp, Manuel; Kuijper, Arjan; Landesberger, Tatiana von

Visual Interactive Creation of Geo-located Networks

2017

Linsen, Lars (Ed.) et al.: IVAPP 2017. Proceedings : 8th International Conference on Information Visualization Theory and Applications (VISIGRAPP 2017 Volume 3). SciTePress, 2017, pp. 283-293

International Conference on Information Visualization Theory and Applications (IVAPP) <8, 2017, Porto, Portugal>

Nodes in real world networks often have a geographic position. In many cases such as for simulation or optimization, there is a need for non-trivial synthetic geo-located networks. As synthetic datasets are required to have specific properties such as connectivity and geographic distribution, often networks need to be generated. However, their creation is cumbersome if done purely by hand, and inflexible if done fully automated. Here, we present a framework for creating artificial geographic located networks in a visually interactive way. We designed our framework with the what-you-see-is-what-you-get principle in mind, i.e. showing the (intermediate) results of the interactive creation process at any time and allowing the user to adjust the network iteratively. This design allows our system to be also used as a simple viewer for networks that have incomplete location information. Our approach consists of two steps: (1) Creating the network topology and (2) assigning locations to its nodes. Our half automatic system enables the user to easily set the location of the nodes to predefined areas like countries, states, and urban regions, while still being able to flexibly and interactively control the creation process. We show the utility of our system by creating a real-world-like geo-located network.

Show publication details

Ramalwan, Vinod Singh; Kuijper, Arjan (Betreuer); Burkhardt, Dirk (Betreuer)

Visual Trend Analysis for Instant Analysis in Mobile Environments

2017

Darmstadt, TU, Master Thesis, 2017

Today's rapidly changing markets challenge enterprises to stay up and react early to latest trends, such as technologies and market players. In the past, big players like AOL, Yahoo suffered significant impact in their own businesses due to changes in the market. Hence, detection of trends is crucial to consider upcoming trends as soon as possible. In particular, small and medium enterprises need an easy and early trend detection system. However, such systems must be aligned with their daily business. Analytical observations create significant impact and often prove to be profitable to businesses. However, current solutions need a huge amount of effort to collect data and perform the analysis. To incorporate such a solution, it is essential to have a system that enables to quickly check an upcoming trend without heavy parameterization. More often, analytical observations prove to be especially beneficial in mobile environments, like traveling, where they save time by performing analysis instantly e.g. on a mobile-phone or a tablet. In the past decade, mobile device development has changed the technology market symbolically. However, still today, desktop devices are preferred over mobile devices for visual analysis where device memory, display size, device speed etc. are the major factors contributing to this choice. In this work, I propose a concept aimed at analyzing visual trends in mobile environments which would assist decision makers and business leaders to perform analysis on demand. The proposed concept not only considers the limitations of mobile devices but also utilizes their special features like gesture interactions. This concept integrates a prospect known as a scenario. Each scenario integrates visual metaphors which altogether complete the profile of a subject. A digital library search about research publications was used to choose the subjects in this case. For e.g. checking interesting topics or analyzing topic leaders of certain research area to estimate a technological trend in terms of their relevance and impact. Within the scope of this work, Human-Computer Interaction (HCI) was researched in the context of mobile devices and the supplementary features mobile devices provide in contrast to computers. The already existing techniques and solutions for visual trend analysis were evaluated. A proof-of-concept with a web application for mobile devices was implemented. Finally, the developed mobile web application was evaluated against an existing desktop web application based on same data. This study reveals that the new mobile solution has a significant advantage over the existing desktop solution, and it was preferred by the users. It is concluded that the design, intuitiveness, scenario-based concept of the mobile solution and other complementary features like interactions make it more concrete and goal-oriented.

Show publication details

Sessler, David; Kuijper, Arjan (Betreuer); Bernard, Jürgen (Betreuer)

Visual-Interactive Learning of Time Series Similarity

2017

Darmstadt, TU, Master Thesis, 2017

Similarity is important for the applicability of a series of data analysis tasks. Pattern recognition, clustering and nearest neighbor search require a meaningful similarity function for their functionality. In this work, we consider a similarity function to be meaningful, if it reflects the similarity notion in the minds of the users. Therefore, the design of a similarity function has to incorporate and reflect user's preferences. In this work we focus on the similarity for time-oriented data. The definition of similarity functions for this data type requires a cascade of routines, including preprocessing steps, descriptors, normalization steps, and distance measures. Referring to this cascade, manually choosing appropriate routines matching the user's expectations of time series similarity is a tedious process. We present a visual-interactive approach that identifies meaningful similarity functions for time-oriented data automatically. The core principle is to learn from user-defined labels about the similarity of pairs of time series. Automatic choice of fitting routines allows to match the similarity notion of the users at run time. We implement a labeling interface for pairwise time series, including active learning support to enhance the learning process. Different views allow the analysis of the learning process of similarity for time series data. A list-based ranking interface provides detailed information on the best performing similarity functions. Filtering interfaces allow for detailed analysis of the applicability of routines included in the similarity functions. Furthermore, they provide drill-down functionality that can be used to experiment with different sets of similarity functions, in order to increase the robustness of the prediction. Nearest neighbor search closes the feedback loop and enables the users to validate, if the defined similarity function complies with their notion of similarity. In addition, we demonstrate the applicability of the approach in case studies based on different pre-defined notions of similarity used for labeling. Finally, we evaluate our approach to determine which factors influence the prediction accuracy. In conclusion, our approach extends the classical user-centered and iterative design process to an online learning process that defines similarity functions based on user feedback. We report on an increase in efficiency from a tedious design process for similarity functions, down to a process that only takes minutes of expert time.

Show publication details

Reynolds, Steven Lamarr; Kuijper, Arjan (Betreuer); May, Thorsten (Betreuer)

Visualisierung von zeitlichen, thematischen Änderungen in einem Dokumentenkorpus

2017

Darmstadt, TU, Bachelor Thesis, 2017

Mehrere Dokumente in einem Korpus können mit Themen beschrieben werden. Diese Themen bestehen aus Termen die sich aus den Wörtern der Dokumente bilden. Das Thema der vorliegenden Bachelorarbeit beschäftigt sich mit der Visualisierung der Entwicklung dieser Themen über einen Zeitstrahl. Über mehrere Zeitabschnitte hinweg werden Themen aus Dokumenten generiert. In einer Visualisierung wird die Entwicklung der Themen über diese Zeitabschnitte dargestellt. Dazu wird die Ähnlichkeit zwischen Themen berrechnet und angezeigt. Die Themen werden sortiert um die Visualisierung möglichst visuell und ansprechend darzustellen. Damit können Entwicklungen der Themen betrachtet werden. Das System erlaubt ein späteres austauschen des verwendeten Topic Modeling Verfahrens und ein schnellen Import von Dokumentenkorpera. Die Visualisierung ist unabhängig von dem Topic Modeling Verfahren. Zusätzlich wird mittels Interaktionstechniken eine Visual Analytics Anwendung umgesetzt.

Show publication details

Brodkorb, Felix; Kopp, Manuel; Kuijper, Arjan; Landesberger, Tatiana von

A Modular Rule-Based Visual Interactive Creation of Tree-Shaped Geo-Located Networks

2016

Yetongnon, Kokou (Ed.) et al.: 12th International Conference on Signal-Image Technology & Internet-Based Systems : SITIS 2016. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2016, pp. 397-403

International Conference on Signal Image Technology & Internet-Based Systems (SITIS) <12, 2016, Naples, Italy>

Geo-located networks are analyzed in various domains such as supply chain management. When simulating supply chain processes or when testing geo-visualization techniques, synthetic test datasets are needed. However, real world data are difficult to obtain and artificial data are cumbersome to create manually. In this paper, we present an interactive visual tree network generator that not only generates a network, but also attaches geo-locations to its nodes. We designed a modular rulebased system to control the generation process. A user can interactively use rules to parametrize the data generation process. The user can visually explore and adjust results intermediately after each generation iteration.

Show publication details

Siegmund, Dirk; Fu, Biying; Samartzidis, Timotheos; Wainakh, Aidmar; Kuijper, Arjan; Braun, Andreas

Attack Detection in an Autonomous Entrance System using Optical Flow

2016

7th International Conference on Imaging for Crime Detection and Prevention : ICDP 2016 [online]. [cited 11 July 2017] Available from: [http://digital-library.theiet.org/content/conferences/2016/0006], 2016, 6 p.

International Conference on Imaging for Crime Detection and Prevention (ICDP) <7, 2016, Madrid, Spain>

Unstaffed access control portals are becoming more common in high security areas. Existing systems require expensive hardware, or are sensitive to changing environmental conditions. We present a single camera system for a mantrap which is able to verify that only one individual is in the designated transit area. Our novel approach combines optical flow and machine-learning classification. A database was created that consists of images of attempted attacks and regular verification. The results show that our approach provides competitive results and outperforms detection rates in several attack scenarios.

Show publication details

Hiemenz, Benedikt; Kuijper, Arjan (Betreuer); Krämer, Michel (Betreuer)

Authentication and Searchable Symmetric Encryption for Cloud-Based Storage of Geospatial Data

2016

Darmstadt, TU, Master Thesis, 2016

Many companies outsource their data and computations to the cloud to benefit from a worldwide data access and economic advantages such as a flexible storage management. Since cloud infrastructures are usually provided by third parties, companies must protect their private data before moving them. An example are geospatial data sets storing confidential information about urban areas. To secure these data, we present two security extensions for cloud-based geospatial data storages. First, we introduce an authentication process enabling applications to securely identify their users. We build our approach on token-based techniques but enhance them by essential features such as a revocation mechanism allowing administrators to block certain users at any time. Our extension requires minimal information on the server side and is suitable for distributed environments like a cloud infrastructure. Our main security extension allows users to encrypt their geospatial data and make them searchable at the same time. We develop a Searchable Symmetric Encryption protocol using an index to provide search features on encrypted data. Our approach is dynamic as we do not require an initialization phase and allow users to constantly add new data to the index or remove existing records. In the course of this thesis, we design multiple versions of our protocol differing in their level of security and performance respectively. All of them support boolean expressions as part of the query and geospatial-related search criteria such as bounding boxes. On the client side, our protocol facilitates multi-device support because we only expect cryptographic keys. Our findings indicate that both extensions are suitable for real-world applications in distributed systems but the search in encrypted data requires some more runtime than in plaintext data.

Show publication details

Bartschat, Andreas; Kuijper, Arjan (Betreuer)

Automatic Classification of Cornea Tissues for Autofocus Algorithm

2016

Darmstadt, TU, Master Thesis, 2016

Corneal confocal microscopy (CCM) is a spreading technique for investigations of cellular structures in the human cornea. It is non-invasive and allows in vivo imaging of the different tissue layers in the cornea with high resolution. High expectations are currently placed on CCM, to allow rapid and detailed analysis of pathological alterations affecting the peripheral nerves that innervate the cornea, resulting not only in fast diagnosis, but also providing insights into the progress and severity of diseases like diabetes. For the fast and reliable imaging of the sub-basal nerve plexus (SNP), the layer with the highest density of nerves, the focus must be adapted to compensate anatomical layer irregularities and reversible folds. This thesis analyses classification methods of the anatomical tissues surrounding the SNP, to find reliable and fast classification models, suitable for online focus adaptations of the microscope to the layer of interest based on the predicted tissue type of the current image. The proposed methods are able to achieve accuracies of more than 92% with a runtime of less than 10 ms per image, evaluated on datasets of more than 8000 images as well as successfully applied in studies for the reconstruction of large field of view images of the SNP.

Show publication details

Bartschat, Andreas; Toso, Lorenzo; Stegmaier, Johannes; Kuijper, Arjan; Mikut, Ralf; Köhler, Bernd; Allgeier, Stephan

Automatic Corneal Tissue Classification Using Bag-Of-Visual-Words Approaches

2016

Heizmann, M. (Ed.) et al.: Forum Bildverarbeitung 2016. Karlsruhe: KIT Scientific Publishing, 2016, pp. 245-256

Forum Bildverarbeitung <1, 2016, Karlsruhe, Deutschland>

Corneal confocal microscopy is a promising diagnostic method for peripheral neuropathy. It allows the recording of the sub-basal nerve plexus (SNP) and enables the morphological analysis of peripheral nerves. This work evaluates classification models for real-time evaluation of cornea images in order to find suitable methods for an automatic focus adaptation to the SNP. The analyzed Bag-of-Visual-Words method leads to models with an accuracy of 0.9, even on a small training dataset, and a runtime of 18 ms per image. Furthermore, the analysis of the support vector machine real-valued output shows high potential for the implementation of real-time focus optimization methods.

Show publication details

Kutlucan, Osman; Kuijper, Arjan (Betreuer); Kirchbuchner, Florian (Betreuer)

Barrierefreies Lagersystem zur Unterstützung von Menschen mit eingeschränkter visueller Wahrnehmungsfähigkeit

2016

Darmstadt, TU, Master Thesis, 2016

Im Mittelpunkt dieser Masterarbeit steht die Realisierung eines Lagersystems für Menschen mit eingeschränkter visueller Wahrnehmungsfähigkeit. Das in diesem Rahmen entwickelte Lagersystem verwendet Hand- und Gestenerkennung, Spracherkennung, Sprachsynthese und Sonifikation. Das Ziel des Systems ist es, sowohl eine pervasive Benutzerschnittstelle anzubieten, welche es blinden Benutzern ermöglicht, mit dem Lagerbereich auf eine natürliche Weise zu interagieren, und ein Lagersystem zu haben, welches mit geringem Aufwand konfiguriert werden kann. Daher werden in der Thesis in erster Linie verschiedene verwandte Ansätze und Konzepte betrachtet, woraufhin beschrieben wird, wie das vorgeschlagene Konzept der Thesis entwickelt wurde und warum dieses Konzept sich besser für blinde Benutzer eignet. Um dies zu analysieren, wird das vorgeschlagene System iterativ evaluiert. Im Rahmen der Evaluation wurden Verbesserungsvorschläge aufgenommen, und die Präzision und Effizienz der Implementierung gemessen. Die Ergebnisse der Evaluation dieser Thesis zeigen, dass das Konzept des vorgeschlagenen Systems angemessen ist und von blinden Benutzern gut aufgenommen wird, was z.B. durch einen Teilnehmer der Evaluation bei der Beurteilung eines Subworkflows des Systems mit folgenden Worten bestätigt wurde: "Die Interaktion fühlt sich so an, als wäre man nicht blind". Aber die Implementierung des Systems weist einige Probleme auf, welche sich vorwiegend in der Hand- und Gestenerkennung des Systems zeigen. Mit Behebung dieser Probleme könnte die User Experience einen höheren Grad erreichen, wodurch das System im alltäglichen Leben einsetzbar werden könnte.

Show publication details

Braun, Andreas; Wichert, Reiner; Kuijper, Arjan; Fellner, Dieter W.

Benchmarking Sensors in Smart Environments - Method and Use Cases

2016

Journal of Ambient Intelligence and Smart Environments, Vol.8 (2016), 6, pp. 645-664

Smart environment applications can be based on a large variety of different sensors that may support the same use case, but have specific advantages or disadvantages. Benchmarking can allow determining the most suitable sensor systems for a given application by calculating a single benchmarking score, based on weighted evaluation of features that are relevant in smart environments. This set of features has to represent the complexity of applications in smart environments. In this work we present a benchmarking model that can calculate a benchmarking score, based on nine selected features that cover aspects of performance, the environment and the pervasiveness of the application. Extensions are presented that normalize the benchmark-ing score if required and compensate central tendency bias, if necessary. We outline how this model is applied to capacitive proximity sensors that measure properties of conductive objects over a distance. The model is used to identify existing and find potential new application domains for this upcoming technology in smart environments.

Show publication details

Sheldrick, Peter; Wuest, Harald (Betreuer); Kuijper, Arjan (Betreuer)

CAD-Model Tracking using RGB-D Cameras

2016

Darmstadt, TU, Master Thesis, 2016

This thesis deals with the determination of the six DOF of an RGB-D camera relative to a known CAD-Model. Extracting features in image based tracking with no other input data reduces the achievable precision of tracking. This thesis presents methods that use the whole input frame from a depth camera - these are so called "dense'" methods. Methods such as ICP, that is used in KinectFusion, and depth image warping, which is used in DVO-SLAM, are compared for the task of CAD-Model tracking. Rendering is used for tracking and both GPU implementations such as OpenGL and CPU ray casting is used to track real depth data.

Show publication details

Braun, Andreas; Zander-Walz, Sebastian; Krepp, Stefan; Rus, Silvia; Wichert, Reiner; Kuijper, Arjan

CapTap - Combining Capacitive Gesture Recognition and Acoustic Touch Detection

2016

Matthies, Denys J.C. (Ed.) et al.: iWOAR 2016 : 3rd international Workshop on Sensor-based Activity Recognition and Interaction. New York: ACM Press, 2016. (ACM International Conference Proceedings Series 1183), Art. No. 6, 6 p.

International Workshop on Sensor-based Activity Recognition (iWOAR) <3, 2016, Rostock, Germany>

Capacitive sensing is a common technology for finger-controlled touch screens. The variety of proximity sensors extends the range, thus supporting mid-air gesture interaction and application below any non-conductive materials. However, this comes at the cost of limited resolution for touch detection. In this paper, we present CapTap, which uses capacitive proximity and acoustic sensing to create an interactive surface that combines mid-air and touch gestures, while being invisibly integrated into living room furniture. We introduce capacitive imaging, investigating the use of computer vision methods to track hand and arm positions and present several use cases for CapTap. In a user study we found that the system has average localization errors of 1.5cm at touch distance and 5cm at an elevation of 20cm above the table. The users found the system intuitive and interesting to use.

Show publication details

Maus, Michael; Kuijper, Arjan (Betreuer); Ruppert, Tobias (Betreuer); Lücke-Tieke, Hendrik (Betreuer)

Definition und Visualisierung von zoombaren 2D-Projektionen im Web

2016

Darmstadt, TU, Bachelor Thesis, 2016

Zielsetzung der Arbeit ist die Erforschung und Entwicklung eines web-basierten Visualisierungssystems zum Erstellen und Testen von zoombaren Projektionskarten. Die grundlegende Idee besteht darin einen multidimensionalen Datensatz mithilfe von Projektionsmethoden auf zwei Dimensionen zu projizieren, um sie auf einer 2D-Fläche darzustellen In Anlehnung an die Card, Mackinlay, Shneiderman Visualisierungspipeline ist ein Datenverarbeitungsmodell entwickelt worden. Für die Datenverarbeitung werden verschiedene Distanzmetriken, Dimensionsreduktionsverfahren, Zooming Ansätze sowie Darstellungskonzepte berücksichtigt. Die Besonderheiten sowie Überlegungen der jeweiligen Technologie werden diskutiert. Ein Zooming-Ansatz ermöglicht große Datenmengen auf einer begrenzten Fläche darzustellen. Um Zusammenhänge innerhalb der Daten besser zu visualisieren werden Darstellungskonzepte diskutiert. Die Datenpunkte werden als glyph-basierte Objekte oder mithilfe Colormaps, verschiedenen Formen und Größen dargestellt. Best-Practices über Colormaps werden diskutiert. Um große Datenmengen in Echtzeit darzustellen erfolgt eine Trennung von dem Generierungs- und Visualisierungsprozess. Bei der Generierung werden mithilfe einer tabellarischen Datei und gewählten Konfiguration rechenintensive Transformationsprozesse ausgeführt, um Kartenmaterial zu erzeugen. Ähnlich zu Google-Maps wird das erzeugte Kartenmaterial durch eine Visualisierung dargestellt. Managementkonzepte zur Verwaltung verschiedener Kartensets sowie deren Erzeugung und Darstellung werden präsentiert. Über eine Oberfläche kann der Benutzer Kartenmaterial erzeugen und visualisieren. Der Benutzer lädt eine tabellarische Datei ins System hoch und wählt zwischen verschiedenen Konfigurationsparametern. Anschließend werden diese Informationen verwendet um Kartenmaterial zu erzeugen. Das Kartenmaterial sowie verschiedene Interaktionsmöglichkeiten werden in der Visualisierungsoberfläche bereitgestellt. Anhand verschiedener Anwendungsbeispiele werden die Vorteile dieses Visualisierungssystems präsentiert.

Show publication details

Roskosch, Philipp; Twellmeyer, James; Kuijper, Arjan

Dynamic Sampling for Visual Exploration of Large Dense-Dense Matrices

2016

Yamamoto, Sakae (Ed.): Human Interface and the Management of Information. Proceedings Part I : Information, Design and Interaction. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9734), pp. 308-318

International Conference on Human Interface and the Management of Information (HIMI) <2016, Toronto, ON, Canada>

We present a technique which allows visual exploration of large dense-occupied similarity matrices. It allows the comparison of several dimensions of a multivariate data set. For the visualization, the data are reduced by sampling. The access time to individual elements is an ever increasing problem with increasing matrix size. We examine various database management systems and compare the access times for different problem sizes. The visualization responds to user interaction and allows the focus to specific areas within the data. For this, the data is filtered according to user interests and the visualization is refined with subsamples of the filtered data. The context is preserved in this process. The focus allows the discovery of relationships that would otherwise remain hidden.

Show publication details

Berkei, Sarah; Kuijper, Arjan (Betreuer); Limper, Max (Betreuer)

Effiziente und Vollautomatische Grobausrichtung für den Soll-Ist-Abgleich zwischen CAD-Modellen und Scandaten

2016

Darmstadt, TU, Master Thesis, 2016

Diese Arbeit befasst sich mit der Entwicklung und anschließenden Evaluation eines globalen Registrierungsverfahren zum Soll-Ist-Abgleich zwischen Scandaten und einem CAD-Modell. Dabei liegt der Fokus auf einer effizienten Ausrichtung der Daten zueinander, die schneller als ein manuelles Vorgehen ist. Als Grundlage dient der "4-Point Congruent Sets" Algorithmus, der die Transformation zwischen zwei Punktwolken zueinander berechnet. Im Rahmen dieser Arbeit wird er mit einem klassischen, auf den Anwendungsfall der Arbeit angepassten, Ansatz "RANSAC-based DARCES" evaluiert. Darüber hinaus werden das "Largest Common Pointset" und die "Hausdorff-Distanz" als Bewertungskriterien verglichen, um eine möglichst effiziente und genaue Registrierung zu erreichen. Um das Ergebnis der globalen Registrierung zu bewerten, wird der "Iterative Closest Point" Algorithmus in die globale Registrierung integriert. Zu erkennen ist, dass 4PCS, vor allem auf strukturreichen Oberflächen, mit diesem Ansatz in durchschnittlich 5,5 Sekunden bis zu 74% zuverlässige Ergebnisse liefert. Auf strukturarmen Oberflächen kann mittels des "RANSAC-based DARCES" bis 82% valide Ergebnisse erzielt werden, wobei die Zeit für die Berechnung mit den verwendeten Testmodellen durchschnittlich unter 4 Sekunden lag.

Show publication details

Zeltser, Anton; Kuijper, Arjan (Betreuer); Kähm, Olga (Betreuer)

Entwicklung und Evaluierung eines Systems zur bildbasierten Detektion von Fehlern in Stoffen

2016

Darmstadt, TU, Master Thesis, 2016

Die Algorithmen aus den Bereichen Bildverarbeitung, Computer Vision und Maschinelles Lernen finden in der heutigen Zeit immer häufiger ihre Anwendung bei den Industrieprozessen. In vielen Bereichen der Technik und Industrie sind diese Algorithmen ein wichtiger Bestandteil des Planungs- und Produktionsprozesses geworden. Insbesondere in dem Qualitätskontrollvorgang haben bildbasierte Verfahren eine größere Bedeutung. Diese Verfahren ermöglichen es, die Qualität der Produktion, entsprechend den Qualitätsanforderungen, automatisch und präzise zu überprüfen und mögliche Fehlerteile zu identifizieren. Im Mittelpunkt dieser Masterarbeit steht die Schritt-für-Schritt Entwicklung und Analyse eines Systems (in Form eines Algorithmus) zur bildbasierten Detektion von Fehlern in Materialien. Zur Kontrolle werden gebrauchte Stoffstücke mit folgenden Defekten verwendet: Löcher, Risse und Silikonflecke. Eine Besonderheit bei der Erkennung liegt darin, dass die Materialien im Bild so aussehen, als ob sie unabsichtlich auf einen Tisch geworfen worden sind. Die zu prüfenden Materialien können nicht als eine aufgespannte (2-D) Ebene beschrieben werden. Auf diese Art können vorhandene Textilien im Bild neben Defekten verschiedene Merkmale, wie zum Beispiel Falten oder innere und äußere Ränder, besitzen. Diese zusätzlichen Merkmale könnten irrelevante Informationen für die Suche nach Defekten beinhalten. Um die irrelevante Information zu reduzieren, wird vorgeschlagen, dass ein vorhandenes Bild in Ausschnitte aufgeteilt wird. Damit lässt sich jeder Ausschnitt meistens mit einem Merkmal beschreiben. Diese Bildausschnitte werden als Inputdata für das System genutzt. Ziel der Arbeit ist es, zum einen, mit Hilfe von Algorithmen des Maschinellen Lernens ein System für die Detektion des Defekts in Stoffen aufzubauen,und zum anderen, das System sollte auseinanderhalten, ob ein Stoffstück Verschleiß (Riss oder Loch) oder Silikon besitzt, oder, ob ein Stoffstück fehlerfrei mit Falten ist. Anhand der Ausschnitte wird eine Entscheidung über den Defekt im Bild getroffen. Diese Arbeit zeigt, wie die Algorithmen Local binary patterns in Verbindung mit dem Klassifikationsverfahren Support Vector Machine für die Detektion der Defekte in Stoffen verwendet werden.

Show publication details

Cui, Jian; Kuijper, Arjan; Sourin, Alexei

Exploration of Natural Free-Hand Interaction for Shape Modeling Using Leap Motion Controller

2016

Sourin, Alexei (Ed.) et al.: 2016 International Conference on Cyberworlds : CW 2016. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2016, pp. 41-48

International Conference on Cyberworlds (CW) <2016, Chongqing, China>

In this paper, we propose a web-enabled shape modeling system with natural free-hand interaction, which can be easily learned by users while imposing least mental load on them. The deformation interface allows for performing various deformations, including stretching, compressing, squeezing, enlarging, twisting and tapering, on shapes interactively mimicking how they are done in real life. The manipulation interface allows an object to be directly grabbed and manipulated with either one or two hands, while also smoothly switching between them. Constrained methods are also provided for precise manipulation. An intuitive metaphor is designed to help the users to discover the interaction techniques by themselves without any manuals or instructions. A rendering pipeline, based on function-based extension of VRML/X3D, is designed with hidden complexity to support the proposed functionalities of the system. Hands motions are captured by Leap Motion controller. The user study proves the naturalness of the modeling system, and its easiness to be learned and remembered.

Show publication details

Braun, Andreas; Alekseew, Michael; Kuijper, Arjan

Exploring Machine Learning Object Classification for Interactive Proximity Surfaces

2016

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2016. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9749), pp. 157-167

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <4, 2016, Toronto, Canada>

Capacitive proximity sensors are a variety of the sensing technology that drives most finger-controlled touch screens today. However, they work over a larger distance. As they are not disturbed by non-conductive materials, they can be used to track hands above arbitrary surfaces, creating flexible interactive surfaces. Since the resolution is lower compared to many other sensing technologies, it is necessary to use sophisticated data processing methods for object recognition and tracking. In this work we explore machine learning methods for the detection and tracking of hands above an interactive surface created with capacitive proximity sensors. We discuss suitable methods and present our implementation based on Random Decision Forests. The system has been evaluated on a prototype interactive surface - the CapTap. Using a Kinect-based hand tracking system, we collect training data and compare the results of the learning algorithm to actual data.

Show publication details

Herz, Maximilian; Kuijper, Arjan (Betreuer); Räsch, Sascha (Betreuer)

G-Buffer Compression for Remote Rendering Web Applications

2016

Darmstadt, TU, Master Thesis, 2016

As modern CAD applications need to render big scenes it is necessary to use client-server hybrid rendering to distribute work between two machines. This can reduce the needed bandwith and enhance the rendering performance. One way to implement hybrid rendering is to render the scene into G-Buffers, send them to the client and perform deferred shading there to render the final image. With this approach there is no need to send gigabytes of 3D model data over the network. In this master thesis, we will look into different methods to compress G-Buffer data. The G-Buffer is composed of three parts (object id's, depths, normals). We will analyze to which extend common image compression algorithms like JPEG will work on these parts. There are also methods specifically for compressing normal and depth data which we will look at. We will evaluate selected algorithms to further enhance the overall G-Buffer compression ratio. A server and client application have to be developed in order to evaluate the different compression methods. To ensure that the client runs on a broad range of devices the code will be implemented as a web application using HTML5, Java Script and WebGL. Thus, only methods can be used which enable for a fast decompression even on devices with low computing capabilities. The results of this thesis will be used inside the instant3Dhub system technology, which is developed by the VCST department.

Show publication details

Müller, Martin; Kuijper, Arjan (Betreuer); Landesberger, Tatiana von (Betreuer); Ballweg, Kathrin (Betreuer)

Guidance zur Exploration von Entitätsgraphen aus Textkollektionen für Datenjournalismus

2016

Darmstadt, TU, Bachelor Thesis, 2016

An der TU Darmstadt wird new/s/leak entwickelt, ein Tool welches Journalisten bei der Recherche in großen Dokumentenmengen( wie z.B. den Panama Papers oder den Cablegate-Dokumenten) unterstützt. Beziehungen zwischen Personen, Organisationen, Orten und anderen Dingen die in der Dokumentenmenge erwähnt sind, werden in einem riesigen Graphen erfasst, der teilweise mehr als 100 Millionen Kanten enthält. Der Graph enthält für Journalisten interessante Informationen, die Suche nach diesen Informationen im Graph gleicht jedoch der sprichwörtlichen Suche nach der Nadel im Heuhaufen. Die Visualisierung eines solch riesigen Graphen ist zudem äußerst schwierig. Zur Lösung dieser Probleme eignet sich - wie in der Arbeit gezeigt wird - Guidance. Ein Graph-Guidance-System berechnet für einen gegeben Fokusknoten einen lokalen Teilgraph, der nur einen kleinen Teilausschnitt mit interessanten Verbindungen des kompletten Graphen zeigt. Dieser Teilgraph ist übersichtlich und gut erfassbar. Benutzer können innerhalb des Teilgraphen einen neuen Fokus setzten, was wiederum zu einem neuen, veränderten Teilgraph führt. So kann der große Graph exploriert werden. In dieser Arbeit wurde ein in new/s/leak integriertes Graph-Guidance-System entwickelt welches Journalisten bei der Recherche in großen Dokumentenmengen unterstützt. Zunächst wurden Anforderungen an die Graph-Guidance formuliert und bestehende Graph-Guidance-Systeme analysiert. Da keiner der bestehenden Ansätze ad-hoc die Anforderungen erfüllt, wurde ein neues Graph-Guidance-System entwickelt. Dieses baut vor allem auf den Arbeiten von van Ham und Perer [18] sowie von Kochtchi et al. [12] auf. Die entwickelte Guidance berücksichtigt die verschiedenen Typen, die Knoten besitzen können und ermöglicht Journalisten diese zu gewichten, zudem können Guidance-Schritte auch rückgängig gemacht werden und wiederholt werden. Dies erleichert Journalisten die Arbeit mit dem Graph. Die Journalisten werden des Weiteren bei ihrer Entscheidungsfindung durch Detailformationen zu Knoten unterstützt. Es gibt auch eine sinnvolle Verknüpfung der Netzwerkebene mit der Dokumentenebene. Journalisten können problemlos zu einzelnen Dokumenten gelangen, die mit einem Knoten bzw. einer Kante assoziiert sind. Die Guidance arbeitet mit anderen new/s/leak-Komponenten zusammen. Das Guidance-System ermöglicht Journalisten dank der integrierten Features eine flexible Recherche in der Dokumentenmenge, die Benutzeroberfläche ist dennoch intuitiv und überfordert den Benutzer nicht. Die entwickelte Guidance wurde mit Hilfe von Fallstudien und einer Hands-on Session mit Journalisten evaluiert.

Show publication details

Förster, Tim; Thum, Simon; Kuijper, Arjan

High Availability of Big-Geo-Data as a Platform as a Service

2016

Nah, Fiona Fui-Hoon (Ed.) et al.: HCI in Business, Government, and Organizations: eCommerce and Innovation : HCIBGO 2016 Proceedings Part I. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9751), pp. 306-318

International Conference on Human-Computer Interaction in Business, Government and Organization (HCIBGO) <3, 2016, Toronto, ON, Canada>

There are ever-increasing challenges in the development of spatial data. The data increase rises continuously. The sharp rise in these information collections more and more data storage is required. Furthermore, should the systems have high availability and provide acceptable response time under load. The fulfillment of such requirement can be limited realized with a simple client / server system, since these do not scale well and act slowly in poor conditions. Therefore, more and more applications are deployed in the cloud as a service. This brings many benefits; inter alia, improving the availability and scalability of services. In this work the design decisions is demonstrated using an existing server system that are necessary for the realization of the product in the cloud. This product is then provided as a "Platform as a Service". Here points are as discussed persistence in distributed systems and cloud API design. This is then tested in a distributed system and compared against a simple client / server system. Also, a model is presented, thus the availability of the system is calculated.

Show publication details

Puhl, Julian; Knuth, Martin; Kuijper, Arjan

Image-Based Post-processing for Realistic Real-Time Rendering of Scenes in the Presence of Fluid Simulations and Image-Based Lighting

2016

Bebis, George (Ed.) et al.: Advances in Visual Computing. 12th International Symposium, ISVC 2016 : Proceedings, Part I. Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 10072), pp. 414-425

International Symposium on Visual Computing (ISVC) <12, 2016, Las Vegas, NV, USA>

For real-time fluid simulation currently two methods are available: grid-based simulation and particle-based simulation. They both approximate the simulation of a fluid and have in common that they do not directly generate a visually pleasant surface. Due to time constraints, the subsequent generation of the fluid surface may not consume much time. What is usually generated is an approximate surface, which consists of many individual mesh elements and has no optical properties of a fluid. The visualization of a fluid in image space may contain different detail densities depending on the distance between observer and the fluid. Therefore, filters need to be applied in order to smooth these details to a consistent surface. Many approaches use strong filters in this step, which results in a too smooth surface. To this surface then noise is added in order to give it a rough appearance. To avoid this ad-hoc approach we present a post-processing approach of the direct visualization of the simulation data via image processing applications by both smoothing filters and an image pyramid. Our presented approach based on an image pyramid provides access to various levels of detail. These are used as a controllable low pass filter. Thus, different amounts of smoothing can be selected depending on the distance to the viewer, granting a better surface reconstruction.

Show publication details

Borrmann, Daniel; Kuijper, Arjan (Betreuer); Franek, Andreas (Betreuer)

Incorporating the Unscented Transform in Rao-Blackwellised Visual-Inertial SLAM

2016

Darmstadt, TU, Master Thesis, 2016

Monocular visual-inertial simultaneous localisation and mapping (SLAM) systems use a single camera and inertial sensors to build a sparse map of an environment and to simultaneously estimate the camera's position. Applications can be found, for example, in the robotics domain or in virtual and augmented reality applications. Nowadays, monocular visual SLAM systems are capable of operating in real-time on different platforms. The application of Rao-Blackwellised filtering techniques in visual SLAM has further improved the real-time capability and maximum map size of these systems. In many implementations, extended Kalman filters (EKFs) are used to estimate the camera's pose and landmark positions. Since the required dynamic and measurement functions in a visual SLAM system are usually non-linear, EKF-based implementations need to linearise these functions, which leads to linearisation errors in the state estimate. In these cases, the unscented Kalman filter (UKF) proved to provide better results in many scenarios. In this thesis, the unscented transform (UT) is incorporated into a Rao-Blackwellised visual-inertial SLAM system. It shows how the camera state and landmark positions can be estimated in unscented Rao-Blackwellised filtering. To this end, an appropriate motion model, as well as an inverse depth parametrisation for the landmark estimation, are incorporated into the filter. The proposed filter is tested on a visual-inertial dataset in different setups. Results are given for the UKF-based Rao- Blackwellised filter and an equivalent EKF-based implementation, to enable comparison between the two approaches.

Show publication details

Bergmann, Tim Alexander; Kuijper, Arjan (Betreuer); Rojtberg, Pavel (Betreuer)

Interaktive Echtzeit-Kalibrierung: Herleitung einer Heuristik für eine geleitete flexible Kamerakalibrierung

2016

Darmstadt, TU, Bachelor Thesis, 2016

Diese Arbeit beschäftigt sich mit der Entwicklung einer Heuristik, die unerfahrene Nutzer durch eine flexible Kamerakalibrierung leitet. Hierfür wird ein Qualitätsmaß basierend auf der Arbeit von Hartley und Zisserman [8, S. 138ff] hergeleitet. Dieses Qualitätsmaß wird verwendet, um Nutzern mit Hilfe von Vorschlägen für Kameraposen die Durchführung einer Kalibrierung zu vereinfachen. Durch diese Hilfestellungen gelingt es unerfahrenen Nutzern eine Kamera mit weniger Bildern, aber gleicher Qualität, bezogen auf den Reprojection Error, zu kalibrieren.

Show publication details

Breitfelder, Simon; Kuijper, Arjan (Betreuer); Getto, Roman (Betreuer)

Invertierte GML-Modellierung durch Einpassen und Zusammensetzen von einfachen Strukturen

2016

Darmstadt, TU, Bachelor Thesis, 2016

In dieser Arbeit wird ein Verfahren zur invertierten Modellierung auf Basis von geometrischen Primitiven vorgestellt. Hierbei wird zunächst die Punktwolkenrepräsentation des Eingabemodells durch mehrere Primitive angenähert. Für die so erzeugten Primitive wird eine zusammenhängende Boundary Representation erzeugt, indem Verbindungsstücke eingefügt werden. Die endgültige Ausgabe des Algorithmus ist ein GML-Programm, welches diese Boundary Representation beschreibt.

Show publication details

Braun, Andreas; Majewski, Martin; Wichert, Reiner; Kuijper, Arjan

Investigating Low-Cost Wireless Occupancy Sensors for Beds

2016

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2016. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9749), pp. 26-34

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <4, 2016, Toronto, Canada>

Occupancy sensors are used in care applications to measure the presence of patients on beds or chairs. Sometimes it is necessary to swiftly alert help when patients try to get up, in order to prevent falls. Most systems on the market are based on pressure-mats that register changes in compression. This restricts their use to applications below soft materials. In this work we want to investigate two categories of occupancy sensors with the requirements of supporting wireless communication and a focus on low-cost of the systems. We chose capacitive proximity sensors and accelerometers that are placed below the furniture. We outline two prototype systems and methods that can be used to detect occupancy from the sensor data. Using object detection and activity recognition algorithms, we are able to distinguish the required states and communicate them to a remote system. The systems were evaluated in a study and reached a classification accuracy between 79 % and 96 % with ten users and two different beds.

Show publication details

Spiegelberg, Erik; Kuijper, Arjan (Betreuer); Getto, Roman (Betreuer)

Maschinelles Lernen von parametrischen Modellen zur Klassifizierung von 3D Objekten

2016

Darmstadt, TU, Master Thesis, 2016

Das Ziel dieser Masterarbeit ist es, parametrische Modelle als Datenbasis für maschinelles Lernen zu untersuchen. Dabei wird untersucht wie gut diese Datenbasis zur Klassifikation von 3D Objekten geeignet ist. Als Ansatz für parametrische Modelle wird die Generative-Modelling-Language(GML) verwendet. Diese ermöglicht die Erstellung von parametrischen 3D Modellen. Zunächst wird damit eine Auswahl an Objekten Modelliert und eine Vielzahl von Exemplaren produziert. Zur Transformation der Modelle in lernbare Daten werden die 3D Objekt Deskriptoren PANORAMA und DESIRE verglichen. Als Methoden des maschinellen Lernens werden Varianten von k-Means, SVM und ein Nearest-Neighbor Ansatz Verwendung. Es werden verschiedene Szenarien erstellt, welche die Eignung von GML und PANORAMA für machinelle Lernansätze zeigen. Bei der Auswertung werden verschiedene Teile des PANORAMA Deskriptors auf ihre Klassifizierungseffizienz untersucht. Die Ergebnisse Zeigen das maschinelles Lernen anhand von parametrisch konzeptionierten Modellen zur Klassifikation von realen Objekten geeignet ist.

Show publication details

Limper, Max; Kuijper, Arjan; Fellner, Dieter W.

Mesh Saliency Analysis via Local Curvature Entropy

2016

Santos, Luis Paulo (Ed.) et al.: Eurographics 2016. Short Papers. The Eurographics Association, 2016, pp. 13-16

Annual Conference of the European Association for Computer Graphics (Eurographics) <37, 2016, Lisbon, Portugal>

We present a novel approach for estimating mesh saliency. Our method is fast, flexible, and easy to implement. By applying the well-known concept of Shannon entropy to 3D mesh data, we obtain an efficient method to determine mesh saliency. Comparing our method to the most recent, state-of-the-art approach, we show that results of at least similar quality can be achieved within a fraction of the original computation time. We present saliency-guided mesh simplification as a possible application.

Show publication details

Cui, Jian; Fellner, Dieter W.; Kuijper, Arjan; Sourin, Alexei

Mid-Air Gestures for Virtual Modeling with Leap Motion

2016

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2016. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9749), pp.221-230

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <4, 2016, Toronto, Canada>

We study to which extent Leap Motion can be used for midair interaction while working on various virtual assembling and shape modeling tasks. First, we outline the conceptual design phase, which is done by studying and classification of how human hands are used for various creative tasks in real life. Then, during the phase of the functional design, we propose our hypothesis how to efficiently implement and use natural gestures with Leap Motion and introduce the ideas of the algorithms. Next we describe the implementation phase of the gestures in virtual environment. It is followed by the user study proving our concept.

Show publication details

De Stefano, Antonio; Tausch, Reimar; Santos, Pedro; Kuijper, Arjan; Di Gironimo, Giuseppe; Fellner, Dieter W.; Siciliano, Bruno

Modeling a Virtual Robotic System for Automated 3D Digitization of Cultural Heritage Artifacts

2016

Journal of Cultural Heritage, (2016), 19, pp. 531-537

Complete and detailed 3D-scanning of cultural heritage artifacts is a still time-consuming process that requires skilled operators. Automating the digitization process is necessary to deal with the growing amount of artifacts available. It poses a challenging task because of the uniqueness and variety in size, shape and texture of these artifacts. Scanning devices have usually a limited focus or measurement volume and thus require precise positioning. We propose a robotic system for automated photogrammetric 3D-reconstruction. It consists of a lightweight robotic arm with a mounted camera and a turntable for the artifact. In a virtual 3D-environment, all relevant parts of the system are modeled and monitored. Here, camera views in position and orientation can be planned with respect to the depth of field of the camera, the size of the object and preferred coverage density. Given a desired view, solving inverse kinematics allows for collision-free and stable optimization of joint configurations and turntable rotation. We adopt the closed-loop inverse kinematics (CLIK) algorithm to solve the inverse kinematics on the basis of a particular definition of the orientation error. The design and parameters of the solver are described involving the option to shift the weighting between different parts of the objective function, such as precision or mechanical stability. We then use these kinematic solutions to perform the actual scanning of real objects. We conduct several tests with different kinds of objects showing reliable and sufficient results in positioning and safety. We present a visual comparison involving the real robotic system with its virtual environment demonstrating how view poses for different-sized objects are successfully planned, achieved and used for 3D-reconstruction.

Show publication details

Jun, Luo; Wang, Zhiqian; Shen, Chengwu; Kuijper, Arjan; Zhuoman, Wen; Liu, Shaojin

Modeling and Implementation of Multi-Position Non-Continuous Rotation Gyroscope North Finder

2016

Sensors, Vol.16 (2016), 9, 18 p.

Even when the Global Positioning System (GPS) signal is blocked, a rate gyroscope (gyro) north finder is capable of providing the required azimuth reference information to a certain extent. In order to measure the azimuth between the observer and the north direction very accurately, we propose a multi-position non-continuous rotation gyro north finding scheme. Our new generalized mathematical model analyzes the elements that affect the azimuth measurement precision and can thus provide high precision azimuth reference information. Based on the gyro's principle of detecting a projection of the earth rotation rate on its sensitive axis and the proposed north finding scheme, we are able to deduct an accurate mathematical model of the gyro outputs against azimuth with the gyro and shaft misalignments. Combining the gyro outputs model and the theory of propagation of uncertainty, some approaches to optimize north finding are provided, including reducing the gyro bias error, constraining the gyro random error, increasing the number of rotation points, improving rotation angle measurement precision, decreasing the gyro and the shaft misalignment angles. According them, a north finder setup is built and the azimuth uncertainty of 18" is obtained. This paper provides systematic theory for analyzing the details of the gyro north finder scheme from simulation to implementation. The proposed theory can guide both applied researchers in academia and advanced practitioners in industry for designing high precision robust north finder based on different types of rate gyroscopes.

Show publication details

Fraissinet-Tachet, Matthieu; Schmitt, Michael; Kuijper, Arjan; Wen, Zhuoman

Multi-Camera Piecewise Planar Object Tracking with Mutual Information

2016

Journal of Mathematical Imaging and Vision, Vol.56 (2016), 3, pp. 591-602

Real-time and robust tracking of 3D objects based on a 3D model with multiple cameras is still an unsolved problem albeit relevant in many practical and industrial applications. Major problems are caused by appearance changes of the object. We present a template-based tracking algorithm for piecewise planar objects. It is robust against changes in the appearance of the object (occlusion, illumination variation, specularities). The version we propose supports multiple cameras. The method consists in minimizing the error between the observed images of the object and the warped images of the planes. We use the mutual information as registration function combined with an inverse composition approach for reducing the computational costs and get a near-real-time algorithm. We discuss different hypotheses that can be made for the optimization algorithm.

Show publication details

Mammadova, Chinara; Kuijper, Arjan (Betreuer); Ben Hmida, Helmi (Betreuer)

New Approach for Optimizing Usage of Situation Recognition Algorithms within IoT Domains

2016

Darmstadt, TU, Master Thesis, 2016

Over the past few years technological advancements have supported the growth of the Internet of Things (IoT). The Internet of Things consists of (smart) objects embedded with sensors, actuators and controllers. These objects are connected to the Internet and are able to communicate with each other. The interconnection and communication of objects enable the creation of different application domains within the Internet of Things. Smart living is one of the major application areas for the Internet of Things. Sensors, actuators and controllers in a smart living environment (e.g. smart homes) are deployed anywhere; on objects or even on persons. As sensors have the capability to sense the environment, they can be used to collect useful information on location, motion, temperature, humidity, light, etc. Actuators can perform different actions based on data gathered from sensors, and controllers can process that data. Real-time situation awareness is one of the key tasks in a smart living environment. Real-time recognition of situations is especially important in ambient assisted living environments, where elderly or disabled people need support in their everyday lives. Recognition of situations in real-time enables immediate identification of critical situations and provides just-in-time assistance. To detect situations, data needs to be monitored, collected, analyzed and processed. Due to the increasing number of IoT connected devices, the amount of generated data is increasing too. Processing huge amounts of data is complex due to the inefficiency of continuously-running pattern/situation recognition algorithms, high requirement for processing capability and high frequency of the recognition process. Situation recognition algorithms must be executed constantly to handle the continuously generated data. For real-time recognition of situations in particular, these algorithms need to be executed permanently for all received data. The continuously-running recognition algorithms require high processing capabilities. The resource consumption of these algorithms is especially high when they are running on large sets of data. To overcome these problems there is a need for more intelligent approaches that are able to decide - based on target situation recognition purposes - which data is important and should be processed and which algorithm should be used to process this data. This study proposes an approach for optimizing the usage of situation recognition algorithms in Internet of Things domains. The key idea of our approach is to select important data, based on situation recognition purposes, and to execute the situation recognition algorithms after all relevant data have been collected. The main advantage of our approach is that situation recognition algorithms will not be executed each time new data is received. This allows reduction of the frequency of execution of the situation recognition algorithms, thus saving computational resources, such as CPU, memory, storage, bandwidth and power. Another advantage of our approach is that it can be applied to recognize situations in real-time, which is useful for ambient assisted living environments. We apply the proposed approach to implement a use case scenario on top of the universAAL IoT platform, which is an open-source platform for the development of IoT solutions.

Show publication details

Brodkorb, Felix; Kuijper, Arjan; Andrienko, Gennady; Andrienko, Natalia; Landesberger, Tatiana von

Overview with Details for Exploring Geo-located Graphs on Maps

2016

Information Visualization, Vol.15 (2016), 3, pp. 214-237

Geo-located graph drawings often suffer from map visualization problems, such as overplotting of nodes as well as edges and location of parts of the graph being outside of the screen. One cause of these problems is often an irregular distribution of nodes on the map. Zooming and panning do not solve the problems, as they either only show the overview of the whole graph or only the details of a part of the graph. We present an interactive graph drawing technique that overcomes these problems without affecting the overall geographical structure of the graph. First, we introduce a method that uses insets to visualize details of small or remote areas. Second, to prevent the subgraphs within insets from overplotting and edge crossing, we introduce a local area re-arrangement. Moreover, insets are automatically drawn/hidden and repositioned in accordance with the user's navigation. We test our technique on real-world geo-located graph data and show the effectiveness of our approach for showing overview and details at the same time. Additionally, we report on expert feedback concerning our approach.

Show publication details

Große-Puppendahl, Tobias; Dellangnol, Xavier; Hatzfeld, Christian; Fu, Biying; Kupnik, Mario; Kuijper, Arjan; Hastall, Matthias R.; Scott, James; Gruteser, Marco

Platypus - Indoor Localization and Identification through Sensing Electric Potential Changes in Human Bodies

2016

Balan, Rajesh (Ed.) et al.: Mobile Systems, Applications, and Services : Proceedings of the 14th Annual International Conference on. New York: ACM, 2016, pp. 17-30

International Conference on Mobile Systems, Applications, and Services (MobiSys) <14, 2016, Singapore>

Platypus is the first system to localize and identify people by remotely and passively sensing changes in their body electric potential which occur naturally during walking. While it uses three or more electric potential sensors with a maximum range of 2 m, as a tag-free system it does not require the user to carry any special hardware. We describe the physical principles behind body electric potential changes, and a predictive mathematical model of how this affects a passive electric field sensor. By inverting this model and combining data from sensors, we infer a method for localizing people and experimentally demonstrate a median localization error of 0.16m. We also use the model to remotely infer the change in body electric potential with a mean error of 8.8% compared to direct contact-based measurements. We show how the reconstructed body electric potential differs from person to person and thereby how to perform identification. Based on short walking sequences of 5 s, we identify four users with an accuracy of 94 %, and 30 users with an accuracy of 75%. We demonstrate that identification features are valid over multiple days, though change with footwear.

Show publication details

Zhao, Xueqing; Mavridis, Pavlos; Schreck, Tobias; Kuijper, Arjan

RDEPS: A Combined Reaction-Diffusion Equation and Photometric Similarity Filter for Optical Image Restoration

2016

Bebis, George (Ed.) et al.: Advances in Visual Computing. 12th International Symposium, ISVC 2016 : Proceedings, Part II. Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 10073), pp. 43-54

International Symposium on Visual Computing (ISVC) <12, 2016, Las Vegas, NV, USA>

Restoration of optical images degraded by atmospheric turbulence and various types of noise is still an open problem. In this paper, we propose an optical image restoration method based on a Reaction-Diffusion Equation and Photometric Similarity (RDEPS). We exploit photometric similarity and geometric closeness of the optical image by combining a photometric similarity function and a appropriately defined reaction-diffusion equation. Our resulting RDEPS filter is used to restore images degraded by atmospheric turbulence and noise, including Gaussian noise and impulse noise. Extensive experimental results show that our method outperforms other recently developed methods in terms of PSNR and SSIM. Moreover, the computational efficiency analysis shows that our RDEPS provides efficient restoration of optical images.

Show publication details

Hermanns, Lukas; Franke, Tobias; Kuijper, Arjan

Screen Space Cone Tracing for Glossy Reflections

2016

Shumaker, Randall (Ed.) et al.: Virtual Augmented and Mixed Reality. Proceedings : VAMR 2016. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9740), pp. 308-318

International Conference Virtual Augmented and Mixed Reality (VAMR) <8, 2016, Toronto, ON, Canada>

Indirect lighting (also Global Illumination (GI)) is an important part of photo-realistic imagery and has become a widely used method in real-time graphics applications, such as Computer Aided Design (CAD), Augmented Reality (AR) and video games. Path tracing can already achieve photo-realism by shooting thousands or millions of rays into a 3D scene for every pixel, which results in computational overhead exceeding real-time budgets. However, with modern programmable shader pipelines, a fusion of ray-casting algorithms and rasterization is possible, i.e. methods, which are similar to testing rays against geometry, can be performed on the GPU within a fragment (or rather pixel-) shader. Nevertheless, many implementations for real-time GI still trace perfect specular reflections only. In this work the advantages and disadvantages of different reflection methods are exposed and a combination of some of these is presented, which circumvents artifacts in the rendering and provides a stable, temporally coherent image enhancement. The benefits and failings of this new method are clearly separated as well. Moreover the developed algorithm can be implemented as pure post-process, which can easily be integrated into an existing rendering pipeline.

Show publication details

Siegmund, Dirk; Kuijper, Arjan; Braun, Andreas

Stereo-Image Normalization of Voluminous Objects Improves Textile Defect Recognition

2016

Bebis, George (Ed.) et al.: Advances in Visual Computing. 12th International Symposium, ISVC 2016 : Proceedings, Part I. Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 10072), pp. 181-192

International Symposium on Visual Computing (ISVC) <12, 2016, Las Vegas, NV, USA>

The visual detection of defects in textiles is an important application in the textile industry. Existing systems require textiles to be spread flat so they appear as 2D surfaces, in order to detect defects. In contrast, we show classification of textiles and textile feature extraction methods, which can be used when textiles are in inhomogeneous, voluminous shape. We present a novel approach on image normalization to be used in stain-defect recognition. The acquired database consist of images of piles of textiles, taken using stereo vision. The results show that a simple classifier using normalized images outperforms other approaches using machine learning in classification accuracy.

Show publication details

Kühnel, Hannes; Kuijper, Arjan (Betreuer); Gutbell, Ralf (Betreuer)

Texturizing and Refinement of 3D City Models with Mobile Devices

2016

Darmstadt, TU, Master Thesis, 2016

In this thesis, I investigate the problem of building recognition from images and video streams of mobile devices to texturize and refine an existing 3D city model. These city models have different origins and so different levels of detail. Existing approaches for this problem are analyzed and compared. Since no suitable approach was found, a new one has to be created. Supported by GPS and Gyroscope sensor data there are multiple possibilities to analyze images of the video stream on a 2D and 3D basis. Different ways to extract buildings from images are presented including model refinement. These are based on computer vision technologies such as edge detection on images to detect walls, pure use of sensor data by creating an overlay to the video stream with the 3D model renderer from current position by a server and use of structure from motion algorithms to create point clouds and extract a building from them. Each of the different detectors yields in successful results depending on different properties of a building such as e.g. the presence of adjoining buildings or accuracy of the 3D model. The edge detection modes yield to the highest accuracy, followed by the extraction from point clouds and pure sensor data. Also future work is presented to expand the shown approaches.

Show publication details

Cui, Jian; Kuijper, Arjan; Fellner, Dieter W.; Sourin, Alexei

Understanding People's Mental Models of Mid-Air Interaction for Virtual Assembly and Shape Modeling

2016

Magnenat-Thalmann, Nadia (Conference Chair) et al.: Proceedings of the 29th International Conference on Computer Animation and Social Agents : CASA 2016. New York: ACM, 2016, pp. 139-146

International Conference on Computer Animation and Social Agents (CASA) <29, 2016, Geneva, Switzerland>

Naturalness of the mid-air interaction interface for virtual assembly and shape modeling is important. In order to design an interface perceived as "natural" by most people, common behaviors and mental patterns for mid-air interaction of people have to be recognized, which is an area merely explored yet. This paper serves this purpose of understanding the users' mental interaction models, in order to provide standards and recommendation for devising a natural virtual interaction interface. We tested three kinds of tasks - manipulating tasks, deforming tasks and tool-based operating tasks on 16 participants. We have found that: 1) different features of mental models were observed for different types of tasks. Interaction techniques should be designed to match these features; 2) virtual hand selfavatar helps estimate size of virtual objects, as well as helps plan and visualize the complex process and procedures of a task, which is especially helpful for tool-based tasks; 3) bimanual interaction is witnessed as a dominant interaction mode preferred by the majority; 4) natural gestures for deforming tasks always reflect forces exerted. These suggestions are useful for designing a midair interaction interface matching users' mental models.

Show publication details

Lakhani, Vishal; Kuijper, Arjan (Betreuer); Ruppert, Tobias (Betreuer)

Visual-Interactive Document Classification

2016

Darmstadt, TU, Master Thesis, 2016

In recent years, textual data are stored in a web or document format. These data are stored in an unstructured manner. In Organizing these data in some structured format would help exploiting these information in many applications. However, this task or organizing requires lots of time and human efforts. The Machine can help user to organize these data. User can define some labels and manually assign some documents to these classes. With these manually assigned documents, the machine can build a model that will automatically classify rest of the documents, which have not been labeled by the user. Though machine also requires some human effort to assign label to some documents based on which it can decide to classify rest of the documents. Again, this task requires lots of human effort and it is time consuming too, as human requires some time to manually assign label to documents. The problem is how to get good classification result with less human effort or in other words, in a situation where the user is only required to assign label to only few documents. So, in this thesis, an application is built with user interface to provide the results to the user in an interactive manner. The application takes some input from the user, build a model and then presents results using visualization techniques. Along with the results, suggestions are also provided to the user for the next iteration to build more accurate classifier. A process called Active Learning helps user to build more accurate model. Active learning is a process in which a classifier will interactively query the user to get some desired results on new samples. Active Learning helps users to pick up the most informative sample/document for classification. It provides suggestions to the user to select best document for training. In this thesis, an approach for classifying documents using user's feedback is introduced. Classification results will be provided to the users in an visualization manner. For the next iterations, users are presented with suggestions to pick up the most informative document. This task is done using Active Learning approach. By using the suggestions, user can give his own feedback and help the classifier to build a model which is more accurate. These suggestions are provided to the user in visualization manner. Users will be provided confidence score and colors of the desired class in Graphical User Interface(GUI). Thus, user can easily select the next document as suggested by the model. In this way, overall performance of the classifier will be improved. The model is evaluated using visualization of results; and using some results of consecutive iterations, more accurate model was achieved.

Show publication details

Niese, Christoph; Landesberger, Tatiana von; Kuijper, Arjan

Visualization of Composer Relationships Using Implicit Data Graphs

2016

Yamamoto, Sakae (Ed.): Human Interface and the Management of Information. Proceedings Part II : Applications and Services. Switzerland: Springer International Publishing, 2016. (Lecture Notes in Computer Science (LNCS) 9735), pp. 300-312

International Conference on Human Interface and the Management of Information (HIMI) <2016, Toronto, ON, Canada>

Relationships between classical music composers are known due to explicit historic material, for instance the friendship between Joseph Haydn and Wolfgang Amadeus Mozart, as well as the influence of the latter on Ludwig van Beethoven. While Haydn and Mozart were critics of each others work, Mozart and Beethoven probably never met in person. In spite of that there is an impact on especially the early music of Beethoven. While relationships between well-known composers like the mentioned ones are investigated, it can also be of historic interest to know the roles less-known composers played. Some of them might have a part in a famous persons work but were not further analyzed given the fact that there have been many composers and no hints given to researchers indicating which person would be worth studying. In this work we develop an approach to visually hint possible relationships among a large number of composers. Detailed historic knowledge is not taken into account; the hints are only based on the composer works as well as their lifetimes in order to guess directions of influence.

Show publication details

Beuth, Marcel; Kuijper, Arjan (Betreuer); May, Thorsten (Betreuer)

Visualization of General Graphs with Metro Maps

2016

Darmstadt, TU, Bachelor Thesis, 2016

In this work an algorithm is developed that generates a Metro Map layout for general graphs that is not based on a geographical background. Metro Maps have the great advantage of good and intuitive readability. The developed algorithm is based on the work of Stott et al. The special feature in this work is that the visualized graph is a partial graph of a more complex graph. This embedding has influence to the visualization of the Metro Map.

Show publication details

Staab, Michael Markus; Kuijper, Arjan (Betreuer); Ruppert, Tobias (Betreuer)

Visuell-Interaktive Exploration von Text Clustering Ergebnissen

2016

Darmstadt, TU, Master Thesis, 2016

Digital vorliegende Texte gewinnen immer mehr an Bedeutung und sind gleichzeitig in ihrer Vielzahl und Komplexität für einen Leser nur schwer zu durchschauen. Clustering-Verfahren können hier hilfreich sein: Sie unterstützen den Anwender dabei, Text auf Basis des enthaltenen Inhalts zu gruppieren. Allerdings bestehen dabei viele Abhängigkeiten, die zu potenziell sehr diversen Ergebnissen führen, wobei es immer vom konkreten Einzelfall abhängt, welches Ergebnis als "das beste" anzusehen ist. Deswegen ist es sowohl sinnvoll, mehrere Clusterings mit unterschiedlichen Parametern durchzuführen und zu vergleichen, als auch, den Benutzer aktiv in den Analyseprozess miteinzubeziehen. Ziel dieser Arbeit war es, ein Textclustering-System zu entwickeln, das in der Lage ist, Clusterings mit direkter Interaktion des Benutzers zu erstellen, zu analysieren und zu vergleichen. Hierfür wurde sowohl eine neuartige Version der Featureselektion implementiert als auch sehr viel Wert auf die Visualisierung der einzelnen Prozessabläufe gelegt. Eine anschließende Auswertung kam zu dem Ergebnis, dass die Featureselektion gut funktioniert und die Nützlichkeit des Systems gegeben ist. Für die Zukunft bietet es sich an, die Verfahren im System noch zu erweitern und dem Benutzer die Möglichkeit zu geben, selbst weitere Qualitätsmetriken und Verfahren einzupflegen.

Show publication details

Eckeren, Katharina van; Tausch, Reimar; Santos, Pedro; Kuijper, Arjan; Fellner, Dieter W.

3DHOG for Geometric Similarity Measurement and Retrieval for Digital Cultural Heritage Archives

2015

Guidi, Gabriele (Ed.) et al.: 2015 Digital Heritage International Congress. Volume 2. New York: The Institute of Electrical and Electronics Engineers (IEEE), 2015, pp. 117-120

Digital Heritage International Congress (DH) <2015, Granada, Spain>

With projects such as CultLab3D, 3D Digital preservation of cultural heritage will become more affordable and with this, the number of 3D-models representing scanned artefacts will dramatically increase. However, once mass digitization is possible, the subsequent bottleneck to overcome is the annotation of cultural heritage artefacts with provenance data. Current annotation tools are mostly based on textual input, eventually being able to link an artefact to documents, pictures, videos and only some tools already support 3D models. Therefore, we envisage the need to aid curators by allowing for fast, web-based, semi-automatic, 3D-centered annotation of artefacts with metadata. In this paper we give an overview of various technologies we are currently developing to address this issue. On one hand we want to store 3D models with similarity descriptors which are applicable independently of different 3D model quality levels of the same artefact. The goal is to retrieve and suggest to the curator metadata of already annotated similar artefacts for a new artefact to be annotated, so he can eventually reuse and adapt it to the current case. In addition we describe our web-based, 3D-centered annotation tool with meta- and object repositories supporting various databases and ontologies such as CIDOC-CRM.

Show publication details

Fu, Biying; Große-Puppendahl, Tobias; Kuijper, Arjan

A Gesture Recognition Method for Proximity-Sensing Surfaces in Smart Environments

2015

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2015. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9189), pp. 163-173

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <3, 2015, Los Angeles, CA, USA>

In order to ease the daily activities in life, a growing number of sophisticated embedded systems is integrated into an users environment. People are in need to communicate with the machines embedded in the surroundings via interfaces which should be as natural as possible. A very natural way of interaction can be implemented via gestures. Gestures should be intuitive, easy to interpret and to learn. In this paper, we propose a method for in-the-air gesture recognition within smart environments. The algorithm used to determine the performed gesture is based on dynamic time warping. We apply 12 capacitive proximity sensors as sensing area to collect gestures. The hand positions within a gesture are converted into features which will be matched with dynamic time warping. The gesture carried out above the sensing area are interpreted in realtime. Gestures supported can be used to control various applications like entertainment systems or other home automation systems.

Show publication details

Braun, Andreas; Krepp, Stefan; Kuijper, Arjan

Acoustic Tracking of Hand Activities on Surfaces

2015

Matthies, Denys J.C. (Ed.) et al.: iWOAR 2015 : 2nd international Workshop on Sensor-based Activity Recognition and Interaction. New York: ACM Press, 2015, 5 p.

International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>

Many common forms of activities are tactile in their nature. We touch, grasp, and interact with a plethora of objects every day. Some of those objects are registering our activities, such as the millions of touch screens we are using every day. Adding perception to arbitrary objects is an active area of research, with a variety of technologies in use. Acoustic sensors, such as microphones, react to mechanical waves propagating through a medium. By attaching an acoustic sensor to a surface, we can analyze activities on this medium. In this paper, we present signal analysis and machine learning methods that enable us to detect a variety of interaction events on a surface. We extend from previous work, by combining swipe and touch detection in a single method, for the latter achieving an accuracy between 91% and 99% with a single microphone and 97% to 100% with two microphones.

Show publication details

Wilmsdorff, Julian von; Kuijper, Arjan (Betreuer); Große-Puppendahl, Tobias (Betreuer)

Activity Recognition based on Electric Potential Sensing

2015

Darmstadt, TU, Master Thesis, 2015

Electric fields are influenced by the human body and other conducting materials. This property can be used to detect presence of human bodies. For the detection of presence and activity recognition, mostly capacitive measurement techniques are used. Despite the fact that capacitive sensing is an fairly old technology, since it has been around since the 1920's, it is still a hot topic of ongoing research works. Today, capacitive measurement techniques are used in touch-screens, in the automobile industry and many other fields of Ubiquitous Computing. But a drawback of the capacitive technology is the energy consumption, which is an important aspect of mobile devices. That is why, in this thesis, i investigate the potential of electric potential sensing (EPS), a purely passive capacitive measurement technique, which can be implemented with an extremely low power consumption. First, the most commonly used capacitive measurement techniques will be analyzed and how they work. This is done to understand the pros and cons of electric potential sensing compared to other technologies. After analyzing electric potential sensing and related capacitive measurement techniques, we will have a closer look at some possible areas of application of electric potential sensing in an explorative studie. Hence, multiple experiments, involving electric potential sensing in various environmental settings for different use-case scenarios, will be conducted. This is done to evaluate the best use-case for this technology. Then, after selecting the most suitable use-case for activity recognition with EPS, two sensor systems are developed, discussed and evaluated. At the end, the benefits and limitations of EPS will be concluded with regards to capacitive sensing.

Show publication details

Kirchbuchner, Florian; Große-Puppendahl, Tobias; Hastall, Matthias R.; Distler, Martin; Kuijper, Arjan

Ambient Intelligence from Senior Citizens' Perspectives: Understanding Privacy Concerns, Technology Acceptance, and Expectations

2015

Ruyter, Boris de (Ed.) et al.: Ambient Intelligence : 12th European Conference, AmI 2015. Springer, 2015. (Lecture Notes in Computer Science (LNCS) 9425), pp. 48-59

European Conference on Ambient Intelligence (AmI) <12, 2015, Athens, Greece>

Especially for seniors, Ambient Intelligence can provide assistance in daily living and emergency situations, for example by automatically recognizing critical situations. The use of such systems may involve trade-offs with regard to privacy, social stigmatization, and changes of the well-known living environment. This raises the question of how older adults perceive restrictions of privacy, accept technology, and which requirements are placed on Ambient Intelligent systems. In order to better understand the related concerns and expectations, we surveyed 60 senior citizens. The results show that experience with Ambient Intelligence increases technology acceptance and reduces fears regarding privacy violations and insufficient system reliability. While participants generally tolerate a monitoring of activities in their home, including bathrooms, they do not accept commercial service providers as data recipients. A comparison between four exemplary systems shows that camera-based solutions are perceived with much greater fears than wearable emergency solutions. Burglary detection was rated as similarly important assigned as health features, whereas living comfort features were considered less useful.

Show publication details

Bechtold, Oskar; Kuijper, Arjan (Betreuer); Große-Puppendahl, Tobias (Betreuer)

An Interaction Concept for Wearable Low-resolution LED Displays to Increase Traffic Safety

2015

Darmstadt, TU, Bachelor Thesis, 2015

Traffic safety is a major concern of our society. Especially making traffic safe for weak, nonmotorized traffic participants, such as skaters, bikers and pedestrians, is important as accidents with these often result in serious, if not fatal, injuries. Traffic safety can be improved by attaching LED displays to the body. To demonstrate this a wearable smart light for increased traffic safety has been created that combines acceleration sensors with an array of LEDs. To exemplify the use of the device three apps have been developed. These three apps increase the safety of people wearing the device in traffic. Detailed investigations have been conducted researching the form-factor, favored placement, need for feedback and visibility. This thesis investigates the combination of wearable computing in a way that sensor input gives directly evaluated feedback to the user and surrounding people. It is described how to create a user interface that doesn't utilize an LCD display, but instead shows information on a low-resolution LED display. Also communication between traffic participants, wearing the LED display, is evaluated for different use cases.

Show publication details

Arnold, Fabio; Knuth, Martin (Betreuer); Kuijper, Arjan (Betreuer)

Approximation von Reflexionsmodellen für das interaktive Kleidungsdesign unter natürlicher Beleuchtung: Approximation of Reflection Models for Interactive Clothing Design under Natural Illumination

2015

Darmstadt, TU, Bachelor Thesis, 2015

Im Bereich des virtuellen Prototyping ist die Echtzeitsimulation ein unerlässliches Werkzeug geworden. Neben der schnellen und interaktiven Simulation ist die fotorealistische Darstellung der Materialien ein wichtiger Bestandteil, falls das System für Design- und Simulationszwecke eingesetzt werden soll. Das Ziel hierbei ist es, die Produktentwicklungszeit zu verkürzen. Als problematisch hat sich die Darstellung bereits existierender, physikalischer Materialien erwiesen, da diese zunächst aufwändig erfasst werden müssen. Nach der Erfassung müssen die Messdaten oft in ein Format überführt werden, das für eine Darstellung per Echtzeitrendering geeignet ist. Hierbei gehen üblicherweise viele Details verloren, da ein Echtzeitrenderer aus Geschwindigkeitsgründen ein vereinfachtes Modell der Materialien verwendet. Das Ziel dieser Arbeit ist es, für beliebige gemessene BRDF-Daten, die detaillierte Reflektanzeigenschaften vieler physikalischer Materialien enthalten, eine Approximation zu erforschen, die eine Darstellung mit der in "Efficient Self-Shadowing Using Image-Based Lighting on Glossy Surfaces" beschriebenen Beleuchtungsmethode erlaubt. Mit dieser Methode ist es bereits möglich, Oberflächen stetig von diffus über glänzend bis zu vollständig spiegelnd darzustellen. In dieser Bachelorarbeit wird zu Beginn eine geeignete BRDF-Datenbank ausgewählt. Auf der Grundlage verwandter Arbeiten wird eine Approximationsmethode entwickelt, die auf Basis von gemessenen BRDF, geeignete Parameter für die Renderingmethode ermittelt. Parallel wird zum Vergleich eine Groundtruth-Methode entwickelt, welche die BRDF unabhängig von Geschwindigkeit und Speicherverbrauch möglichst genau approximiert. Mit diesen beiden Methoden werden sowohl qualitative als auch quantitative Vergleiche durchgeführt. Die Implementierung wurde in einem eigens für diese Zwecke entwickeltem Framework vorgenommen, welches den Fokus auf schnelles Prototyping legt. Jedoch sollten sich die entwickelten Verfahren leicht auf andere Frameworks übertragen lassen.

Show publication details

Retz, Reimond; Kuijper, Arjan (Betreuer); Nazemi, Kawa (Betreuer)

Assisted Visual Data Exploration for Discovering Information in Digital Libraries

2015

Darmstadt, TU, Master Thesis, 2015

Human access to data plays an increasing role, due to the existing and increasing amount of data. Different disciplines in computer science face this challenge with a variety of approaches, techniques and systems. One promising way is the visual access to the increasing amount of data. Information visualization and visual analytics technologies enable the process of visual exploration. The advantages of visual exploration are that users can discover new and unknown areas and topics in a certain domain. Today's visualization technologies have various limitations that restrict a real access to huge amount of data for searching, analyzing and exploration purposes. The main limitation is the fact that there exists no approach for the entire process of data transformation with data integration, information extraction and visualization for accessing huge amount of data. Most of the systems use either just one dataset, do not use automatic information extraction for enriching data or make no use of interactive visualization methods. A coherent process for integrating data, extracting information and visualizing the information as proposed for visual analytics is missing for real data and heterogeneous data sources. We propose in this thesis such a coherent model for data from different sources. Our model enhances existing approaches by integrating the entire data transformation process for information visualization to support the exploration process. For this, we use ground-truth data from the DBLP digial library as foundation and integrate data from a variety of resources, such as IEEE Xplore or Springer Link. Our main goal is to make use of the surpluses of the different technologies, such as information visualization, visual analytics, data integration and mining, and models of exploratory search to provide a coherent approach that supports the user in the entire exploration and knowledge acquisition process. We propose in this thesis an approach, that makes use of a reference model of interactive information visualization and enhances it with data integration, text and data mining, and assisted search approaches. Further, we implement our model with real world data and enable a proof of feasibility of the entire proposed approach.

Show publication details

Gutzeit, Enrico; Urban, Bodo (Betreuer); Koch, Reinhard (Betreuer); Kuijper, Arjan (Betreuer)

Automatische bildbasierte Segmentierung organischer Objekte einer gleichartigen Gruppe: Abgeleitet vom Problem der Stammschnittflächensegmentierung

2015

Rostock, Univ., Diss., 2014

Diese Arbeit adressiert die automatische Segmentierung von organo-Gruppen, Gruppen gleichartiger organischer Objekte. Der Fokus wird auf das ähnlich schwere Problem der Stammschnittflächensegmentierung gelegt. Die Segmentierung von multiplen Objekten auf unbekanntem Hintergrund in Einzelbildern ist ein schweres und ungelöstes Problem. Es existieren einige spezielle Ansätze für spezifische Objekte, wie Tomaten, Äpfel oder Fische. Dennoch existiert keine robuste und automatische Methode für Stammschnittflächen oder ein allgemeingültiger Ansatz für organo-Gruppen. Die Segmentierung einer organo-Gruppe ermöglicht Anwendungen zur automatischen Vermessung, Inspektion oder Sortierung. In dieser Arbeit werden, ausgehend vom Problem der Stammschnittflächen, drei Konzepte zur automatischen Segmentierung entwickelt und quantitativ evaluiert. Die Konzepte bauen aufeinander auf und ermöglichen die automatische Segmentierung von Schnittholz oder Stammschnittflächen in Bildern mit unbekanntem Hintergrund. Ausgehend von den Konzepten wird eine allgemeinere Lösung für organo-Gruppen entwickelt und am Beispiel von Plattfischen, Kartoffeln und Äpfeln evaluiert. In den einzelnen Evaluierungen der Konzepte werden gute bis sehr gute Ergebnisse erreicht. Die Ergebnisse sind in ein praxistaugliches System zur Vermessung von Holzpoltern eingeflossen. Die Evaluierung des Systems zeigt, dass die Konzepte zur Anwendung geeignet sind, wenn gewisse Rahmenbedingungen eingehalten werden.

Show publication details

Bernhard, Felix; Kuijper, Arjan (Betreuer); Engelke, Timo (Betreuer)

Benutzerfreundliche Kalibrierung für Tracking von Optical Stereo See-Through Head Worn Displays für Augmented Reality

2015

Darmstadt, TU, Bachelor Thesis, 2015

In recent time devices like Google Glass and Oculus Rift gained a lot of public attention. So the field of Virtual and Augmented Reality has become a more and more attractive field of study. This thesis focuses on the Epson Moverio BT-200, an Optical Stereo See-Through Head Worn Display (OST-HWD or OST-HMD) which can be used for Augmented Reality. Augmented Reality devices like this have to be calibrated. This means, that one has to find a configuration, that aligns the image shown on the displays with the environment, which is observed by the built-in camera. If this is not done, the augmented virtual image would not align with the real world. The process of this calibration approach is divided into two stages, like Owen et al. [24] proposed in earlier work, but with less constrains for the positions of the cameras, which makes it easier to use. The first stage is the hardware calibration. It defines the camera intrinsics, containing focal length and principal point, the camera extrinsics, representing the position of the device in world coordinates, as well as the position of the virtual plane onto which the virtual image is projected. The second stage is the user calibration, which calibrates the eye positions for every individual user. An earlier approach by the Fraunhofer IGD [31][32] has been adopted in this work, aiming at a more user friendly suite for the calibration of OST-HWD devices. Therefor both of the aforementioned stages are combined in a new quick step-by-step installation wizard, which is written in HTML and JavaScript to ensure easy usability. Furthermore the VisionLib, developed by Fraunhofer IGD, is used to for image detection and processing [7]. It has been extended by a new minimization model in order to simplify and robustify the calculations of the virtual plane. In addition to that the required hardware components, including camera and calibration rig, were simplified. The implemented software has been evaluated for its results of the computed virtual plane, intrinsic data and eye positions of the user. Furthermore a user study was conducted to rate the usability of the calibration process.

Show publication details

Braun, Andreas; Wichert, Reiner; Kuijper, Arjan; Fellner, Dieter W.

Capacitive Proximity Sensing in Smart Environments

2015

Journal of Ambient Intelligence and Smart Environments, Vol.7 (2015), 4, pp. 483-510

To create applications for smart environments we can select from a huge variety of sensors that measure environmental parameters or detect activities of different actors within the premises. Capacitive proximity sensors use weak electric fields to recognize conductive objects, such as the human body. They can be unobtrusively applied or even provide information when hidden from view. In the past years various research groups have used this sensor category to create singular applications in this domain. On the following pages we discuss the application of capacitive proximity sensors in smart environments, establishing a classification in comparison to other sensor technologies. We give a detailed overview of the background of this sensing technology and identify specific application domains. Based on existing systems from literature and a number of prototypes we have created in the past years we can specify benefits and limitations of this technology and give a set of guidelines to researchers that are considering this technology in their smart environment applications.

Show publication details

Nose, Jan David; Likavec, Jaromir; Bischof, Christian; Kuijper, Arjan

Centralized Approach for a Unified Wireless Network Access

2015

Yamamoto, Sakae (Ed.): Human Interface and the Management of Information. Proceedings Part I : Information and Knowledge Design. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9172), pp. 547-559

International Conference on Human Interface and the Management of Information (HIMI) <2015, Los Angeles, CA, USA>

In this paper, a concept is presented that allows to deploy a unified wireless network access for all employees in organizations with heterogeneous network environments. It is designed to be easy to implement and to maintain. Also, it focuses on usability, removing the need for manual actions to obtain network access when roaming between locations. The concept has been tested in the Fraunhofer-Gesellschaft, and has proven to solve its requirements. It can be deployed with only a small team thanks to the reduced complexity in the branch locations, and it can also be maintained without much effort since ongoing manual tasks have been avoided. Since it is based on open standards, it can easily be customized to match the requirements of the individual organization, or be extended with future improvements. For research and education organizations it is particularly useful that this concept can be integrated with eduroam seamlessly. This allows not only the own employees to roam between locations, but also guests from other participating institutions.

Show publication details

Wilmsdorff, Julian von; Marinc, Alexander; Kuijper, Arjan

Context-Based Document Management in Smart Living Environments

2015

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2015. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9189), pp. 382-394

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <3, 2015, Los Angeles, CA, USA>

Nowadays an increasingly wide variety of multimedia devices can be networked together in ever-growing smart environments. Although these networks, thanks to mobile technology and Wi-Fi, are almost ubiquitous by now, the players therein are still working largely distinct from one another. To simply play a file on the playback device A, which is originally housed on device B, is therefore a complicated task, despite the theoretical possibility provided by existing networking. Especially playing and viewing files on multimedia devices under various circumstances and limited reproduction capabilities is a non-trivial problem. Current solutions from industry still put little interoperable approaches in proprietary systems. Individual multimedia devices of the same manufacturer can be combined intelligently, but with respect to the usability the system scales poorly, the (also physical) distribution increases the difficulty of access to the functions and control is largely independent of the user's context. In this work, a solution is developed, which focuses in particular on the context-based playback of files: sending video, music, image and text files to output devices with different display options, as well as the distribution of these multimedia files between devices. Activities are centered on a mobile device for visualizing the spatial distribution of all devices, including the user's position and the intuitive movement of files of various types between them.

Show publication details

Thöner, Maik; Kuijper, Arjan

Delta Global Illumination for Mixed Reality

2015

Shumaker, Randall (Ed.) et al.: Virtual, Augmented and Mixed Reality. Proceedings : VAMR 2015. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9179), pp. 108-118

International Conference Virtual Augmented and Mixed Reality (VAMR) <7, 2015, Los Angeles, CA, USA>

The focus point in Mixed Reality applications is the merging of objects from different realities into a new, visibly homogeneous scene. To achieve this, next to a spatial registration, a plausible illumination of the objects is required. While shadows and direct illumination can deliver a realistic look to the objects, adding indirect interaction of illumination will result in a seamless integration of objects, to appear as part of the scene instead of glued-on patches. Mixed Reality systems find appliance in entertainment areas like movies and games, as well as prototype presentations or visualization of planned or damaged constructions. We propose an algorithm based on Voxel Cone Tracing to provide Global Illumination for Mixed Reality that enables diffuse as well as specular lighting and easy to compute soft-shadows.

Show publication details

Rus, Silvia; Sahbaz, Meltem; Braun, Andreas; Kuijper, Arjan

Design Factors for Flexible Capacitive Sensors in Ambient Intelligence

2015

Ruyter, Boris de (Ed.) et al.: Ambient Intelligence : 12th European Conference, AmI 2015. Springer, 2015. (Lecture Notes in Computer Science (LNCS) 9425), pp. 77-92

European Conference on Ambient Intelligence (AmI) <12, 2015, Athens, Greece>

Capacitive sensors in both touch and proximity varieties are becoming more common in many industrial and research applications. Each sensor requires one or more electrodes to create an electric field and measure changes thereof. The design and layout of those electrodes is crucial when designing applications and systems. It can influence range, detectable objects, or refresh rate. In the last years, new measurement systems and materials, as well as advances in rapid prototyping technologies have vastly increased the potential range of applications using flexible capacitive sensors. This paper contributes an extensive set of capacitive sensing measurements with different electrode materials and layouts for two measurement modes - self-capacitance and mutual capacitance. The evaluation of the measurement results reveals how well-suited certain materials are for different applications. We evaluate the characteristics of those materials for capacitive sensing and enable application designers to choose the appropriate material for their application.

Show publication details

Pattan, Sachin; Kuijper, Arjan (Betreuer); Burkhardt, Dirk (Betreuer)

Distributed Search Intention Analysis for User-Centered Visualizations

2015

Darmstadt, TU, Master Thesis, 2015

In recent years, Web Search Engines (WSEs) are the most used Information Retrieval systems around the world. As the information available increases explosively, it becomes more difficult to fetch the information meeting the preferences. This calls for a deep study of knowledge about the users' preknowledge and intentions and hence is a critical area of research in many organizations. There are many existing implementations of search intention analysis in some famous search engines such as Google, Bing etc. There are also several researches which propose few approaches for search intention analysis. Still there is a lack of techniques for intention mining in the field of semantic visualizations as they are designed to provide the visual adaptations especially for Exploratory queries. Hence, it is critical to identify the exploratory and targeted search queries. Also, the advancements in the technologies of distributed software systems make them to be applicable in all the systems which need to do some sort of distribution of load. The search intention analysis requires the distribution of load to do parallel processing of intention mining. In this thesis, a new approach for classifying the search intention of users' in a distributed set up is described along with a deep study on existing approaches with their comparison. The approach uses the efficient parameters: word frequency, query length and entity matching for differentiating the user query into exploratory, targeted and analysis search queries. As the approach focuses mainly on frequency analysis of the words, the same is done with the help of many sources of information such as Wortschatz frequency service by university of Leipzig and the Microsoft Ngram service. The model is evaluated with the help of a survey tool and few Machine Learning techniques. The survey was conducted with more than hundred users and on evaluating the model with the collected data, the results look satisfactory.

Show publication details

Yaqub, Kamran; Kuijper, Arjan (Betreuer); Burkhardt, Dirk (Betreuer)

Distributed Social Media Analysis on Microblog-Services for Policy Modeling

2015

Darmstadt, TU, Master Thesis, 2015

The increase in number of social media users provides the policy maker facility to benefit from this information communication channel. The policy maker from this feedback channel acquires the opinions of citizens and through this active participation of citizens, they are engaged in policy modeling process. The process starts with an acquisition of information, then storage of information and thereafter providing the information for statistics and visualizations. The use case implemented for the proof of concept is Twitter but the proposed system architecture is flexible enough to acquire the information from different social media channels, store the information after extracting the features and applying conversions, provides the information to visualization framework and incorporates distributed processing techniques. There are many existing systems for visualizations and textual content analysis for social media but none of the existing systems provide the facility to explore the whole discussions. The discussion track window provides the policy maker the most relevant and important information in such a way that can be easily explored in roll up and roll down fashion following the strategy to have an overview of information first and then filtered and detailed information on demand. Following this scheme, first topics in hierarchy are presented in discussion track window. Then posts and comments of post along with the sentiment are presented in order of their importance. The dynamic queries using AND, OR and NOT logical operators along with temporal and linked data information is helpful in this regard to get filtered information. The discussion track window eases the task of policy maker to explore information from different dimensions thus analyzing the opinions of citizens to have better orientation towards policy modeling.

Show publication details

Große-Puppendahl, Tobias; Bechtold, Oskar; Strassel, Lukas; Jakob, David; Braun, Andreas; Kuijper, Arjan

Enhancing Traffic Safety with Wearable Low-Resolution Displays

2015

Matthies, Denys J.C. (Ed.) et al.: iWOAR 2015 : 2nd international Workshop on Sensor-based Activity Recognition and Interaction. New York: ACM Press, 2015, 10 p.

International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>

Safety is a major concern for non-motorized traffic participants, such as cyclists, pedestrians or skaters. Due to their weak nature compared to cars, accidents often lead to serious implications. In this paper, we investigate how additional protection can be achieved with wearable displays attached to a person's arm, leg or back. Different to prior work, we present an extensive study on design considerations for wearable displays in traffic. Based on interviews, experiments, and an online questionnaire with more than 100 participants, we identify potential placements, form factors, and use-cases. These findings enabled us to develop a wearable display system for traffic safety, called beSeen. It can be attached to different parts of the human body, such as arms, legs, or the back. Our device unobtrusively recognizes turn indication gestures, braking, and its placement on the body. We evaluate beSeen's performance and show that it can be reliably used for enhancing traffic safety.

Show publication details

Herb, Daniel; Kuijper, Arjan (Betreuer); Tausch, Reimar (Betreuer)

Entwicklung und Evaluation eines echtzeitfähigen Streifenlichtscanners für schnelle und automatisierte 3D-Digitalisierung

2015

Darmstadt, TU, Master Thesis, 2015

Diese Arbeit befasst sich mit der Entwicklung und Evaluation eines echtzeitfähigen Streifenlichtscanners zur schnellen und automatisierten 3D-Digitalisierung. Der konkrete Anwendungsfall besteht in der massenhaften Digitalisierung von Kulturgütern zur Archivierung und Foschungskollaboration. Als Grundlage dient das Flying Triangulation Prinzip, bei dem ein Sensor handgeführt zur Rekonstruktion verwendet werden kann und diese dem Nutzer in Echtzeit zur Verfügung steht. Ein Ziel dieser Arbeit ist die Aufarbeitung, Klarstellung und Verbesserung bestimmter Komponenten in dem Verfahren, so dass ein robuster und automatisierter Einsatz an einem bionisch inspirierten, nachgiebigen Roboterarm möglich ist. So kann durch eine neu entwickelte Modellfunktion die Systemkalibrierung hinsichtlich der zu findenden Parameter deutlich verbessert werden, wodurch aus Nutzersicht eine einfachere Kalibrierung möglich ist. Außerdem wird für die Registrierung ein Verfahren zur globalen Optimierung verwendet, welches bereits während der Datenakquise ausgeführt werden kann, wodurch der Nachverarbeitungsschritt entfällt. Neben dem eigentlichen Verfahren konnte außerdem eine Simulationsumgebung zur Generierung synthetischer Bilddaten sowie ein realer Hardwareaufbau entwickelt werden. In einem Evaluationskapitel werden für die synthetisch generierten Daten unterschiedliche Parameter variiert, um so deren Auswirkungen auf das Rekonstruktionsergebnis zu untersuchen. Abschließend wird mit einem exemplarischen Objekt ein Praxistest mit dem realen Aufbau durchgeführt.

Show publication details

Limper, Max; Brandherm, Florian; Fellner, Dieter W.; Kuijper, Arjan

Evaluating 3D Thumbnails for Virtual Object Galleries

2015

ACM SIGGRAPH: Proceedings Web3D 2015 : 20th International Conference on 3D Web Technology. New York: ACM, 2015, pp. 17-24

International Conference on 3D Web Technology (WEB3D) <20, 2015, Heraklion, Crete, Greece>

Virtual 3D object galleries on the Web nowadays often use realtime, interactive 3D graphics. However, this does usually still not hold for their preview images, sometimes referred to as thumbnails. We provide a technical analysis on the applicability of so-called 3D thumbnails within the context virtual 3D object galleries. Like a 2D thumbnail for an image, a 3D thumbnail acts as a compact preview for a real 3D model. In contrast to an image series, however, it enables a wider variety of interaction methods and rendering effects. By performing a case study, we show that such true 3D representations are, under certain circumstances, even able to outperform 2D image series in terms of bandwidth consumption. We thus present a complete pipeline for generating compact 3D thumbnails for given meshes in a fully automatic fashion.

Show publication details

Loge, Joachim; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

Evaluating Capacitive Distance and Haptic Input Modalities for Sound Synthesis Combined with Augmented Reality

2015

Darmstadt, TU, Master Thesis, 2015

In the last few years, devices such as the Microsoft Kinect or the Leap Motion have enabled affordable gesture tracking in mid-air. While this is a fast and natural form of interaction, many applications can benefit from a combination of mid-air interaction and touch recognition. The CapTap is an interactive table that uses a combination of capacitive proximity sensors and acoustic touch detection, enabling various interaction modes. In this thesis, these capabilities were evaluated in the context of musical control scenarios. The goal of research was to determine the complexity of the interaction modes and gain results about how appealing and motivating the test persons find the musical interaction. Another focus was the comparison of an Augmented Reality visualization with a standard display, to obtain data about the preferred visualization technology. Furthermore, the acoustic touch detection of the CapTap was extended with a fingernail input. The technical evaluation addressed the reliability of three touch inputs and resulted in an average detection rate of 85%. The user-experience evaluation indicated that all modes are highly stimulating and support the need to develop further. While the one- and two-handed mid-air control modes could be utilized without much practice and were rated as being very attractive, the combined touch and mid-air modes received lower ratings. The comparison between an Augmented Reality visualization and a standard computer screen yielded a clear preference for the standard display.

Show publication details

Getto, Roman; Kuijper, Arjan; Landesberger, Tatiana von

Extended Surface Distance for Local Evaluation of 3D Medical Image Segmentations

2015

The Visual Computer, Vol.31 (2015), 6-8, pp. 989-999

Computer Graphics International (CGI) <32, 2015, Strasbourg, France>

The evaluation of 3D medical image segmentation quality requires a reliable detailed comparison of a reference segmentation with an automatic segmentation. It should be able to measure the quality accurately and, thus, to reveal problematic regions. While several (global) measures, providing a single quality value, are available, the only widely used local measure is the Surface Distance (i.e., point-to-surface distance). This measure, however, has significant drawbacks such as asymmetry and underestimation in distant and differently formed regions. Other available measures have limited suitability for 3D medical segmentation evaluation. We present a more reliable distance measure for assessing and analyzing local differences between automatic and reference (i.e., ground truth) 3D segmentations. We identify and overcome Surface Distance drawbacks, esp. in regions with larger dissimilarities. We evaluated our approach on four real medical image datasets. The results indicate that our measure provides more accurate local distance values.

Show publication details

Berndt, Olaf; Lukas, Uwe von; Kuijper, Arjan

Functional Modelling and Simulation of Overall System Ship - Virtual Methods for Engineering and Commissioning in Shipbuilding

2015

Mladenov, Valeri M. (Ed.) et al.: ECMS 2015 : 29th European Conference on Modelling and Simulation, pp. 347-353

European Conference on Modelling and Simulation (ECMS) <29, 2015, Albena/Varna Bulgaria>

Shipbuilding industry is undergoing a change, in which many European shipyards focus on special purpose vessels. This field of shipbuilding places very high demands on engineering, commissioning and operation of the vessels. To support these fields of activity with virtual methods an innovative approach is introduced which strengthens the shipbuilding process by using a uniform common model of the overall system ship. The model is steadily increasing and gets more detailed through the phases of the shipbuilding. The presented approach fills the gap in the virtual support of the complete shipbuilding process, taking into account the specific structural needs - short time, high cost pressure and high quality demands.

Show publication details

Burkhardt, Dirk; Nazemi, Kawa; Zilke, Jan Ruben; Kohlhammer, Jörn; Kuijper, Arjan

Fundamental Aspects for E-Government

2015

Information Resources Management Association (IRMA): Standards and Standardization : Concepts, Methodologies, Tools, and Applications (3 Volumes). IGI Global, 2015, pp. 52-68

The upcoming initiatives using ICT in the government process should strengthen the benefit of e-government in most countries. Since e-government among other e-related terms is a widely (interpreted) term, it is sometimes challenging to understand the objective and goals of an initiative. Therefore, in this chapter, the authors introduce and explain most e-government related terms. Even more, they outline some interesting initiatives and implementations to explain the benefits of using ICT in the government domain. Concrete activities are aligned to the terms to explain their practical use in a better way. The authors conclude with several challenges that arise when thinking of the implementation of e-government services. Overall, this chapter should give a good overall view of e-government and the related issues.

Show publication details

Kuijper, Arjan; Pock, Thomas; Bredies, Kristin; Bischof, Horst

Guest Editorial: Scale Space and Variational Methods

2015

Journal of Mathematical Imaging and Vision, Vol.52 (2015), 1, pp. 1-2

Linking the concept of "scale" in filtering images with a Gaussian kernel to "time" in diffusing (later: evolving) an image driven by the so-called heat equation, a Partial Differential Equation (PDE), has started a fruitful pollination of these two areas. Nowadays, more than 55 years after Iijima's groundbreaking concept, researchers for both communities still benefit from each other. In this special issue we collected 8 papers representing state-of-the-art research covering both areas.

Show publication details

Alekseew, Michael; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

Hochpräzise Algorithmen zur Detektion von Armen für Interaktionssysteme aus kapazitiven Abstandssensoren

2015

Darmstadt, TU, Master Thesis, 2015

In dieser Master-Thesis wird basierend auf den Sensordaten des kapazitiven Nahbereichssystemes CapTap eine Handmittelpunktpositions-Erkennung implementiert und getestet. Dazu werden die 24 Sensorwerte verwendet und Referenzdaten einer Handerkennung über die Microsoft Kinect Version 2 kombiniert. Diese Werte werden in einer Trainingsmatrix zusammengefasst und auf diesen Trainingsdaten eine Random Decision Forest (RDF) Algorithmus trainiert. Dieser RDF wird dann verwendet um alleine von den Sensorwerten auf Handmittelpunktpositionen schließen zu können. Diese Ergebnisse werden wieder mit der Handerkennung durch der Kinect verglichen und ein Schluss Ergebnis gezogen.

Show publication details

Schaller, Andreas; Biedenkapp, Tim; Keil, Jens; Fellner, Dieter W.; Kuijper, Arjan

Immersive Interaction Paradigms for Controlling Virtual Worlds by Customer Devices Exemplified in a Virtual Planetarium

2015

Antona, Margherita (Ed.) et al.: Universal Access in Human-Computer Interaction. Proceedings Part IV : Access to the Human Environment and Culture. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9178), pp. 74-86

International Conference on Universal Access in Human-Computer Interaction (UAHCI) <9, 2015, Los Angeles, CA, USA>

This work provides an insight into the basics of 3D applications in conjunction with various customer devices. In this case, the application is a 3D planetarium of our solar system for a museum. The aim is to create a concept for intuitive and immersive navigation through the virtual planetarium using inexpensive Customer Devices. Visitors should be able to move freely and easily in the solar system. Here, the visitor should be able to focus on the simulation and not quickly lose interest in the complex control application. For this similar approaches and previous research are examined and a new approach is described. As low-cost customer devices, the controller of the Nintendo Wii (Wiimote) and current smartphones are considered in this work. A detailed analysis of these devices is an integral part of this work. Based on the selected devices, there are various possibilities for interaction and resulting interaction concepts. For each device, a concept will be developed to meet the identified needs.

Show publication details

Windisch, Sebastian; Stork, André (Betreuer); Kuijper, Arjan (Betreuer)

Interaktive punktbasierte Visualisierung großer oberflächenbezogener Simulationsdaten

2015

Darmstadt, TU, Master Thesis, 2015

Die verteilte, rechnergestützte Simulation physikalischer Phänomene erzeugt abhängig von der Präzision der Simulation, des betrachteten Zeitintervalls und der Größe des Simulationsbereichs Ergebnisdatensätze, welche aufgrund ihres Datenvolumens schwer zu visualisieren und zu analysieren sind. Dies betrifft insbesondere die interaktive, explorative Analyse mittels konventioneller Arbeitsplatz-PCs, wie sie in Industrie und Forschung regelmäßig eingesetzt wird. Hierbei navigiert ein Benutzer interaktiv durch eine Visualisierung des Datensatzes um relevante Ergebnisse zu lokalisieren. Dies ist ein anwendungsspezifischer Vorgang um zum Beispiel unerwartete Daten zu finden oder solche, die eine Hypothese bestätigen oder widerlegen. Diese Resultatdaten sind häufig zu groß, um sie auf den PC zu übertragen und lokal zu verarbeiten. Limitierende Elemente in diesem Anwendungsszenario sind der lokale Haupt- und Grafikkartenspeicher, die lokale Rechenleistung, sowie die für die Datenübertragung zur Verfügung stehende Netzwerkbandbreite. Es existieren bereits verschiedene Ansätze, welche eine entfernte Visualisierung von großen dreiecksbasierten Modellen oder Szenen ermöglichen, jedoch setzen diese entweder eine langwierige Vorverarbeitung des ganzen Datensatzes voraus oder es besteht eine zu starke Bindung zwischen dem Client und den entfernten Ressourcen, sodass eine entkoppelte lokale Navigation oder lokale Anpassung von Visualisierungsparametern nicht möglich ist. In dieser Arbeit wird ein Ansatz basierend auf den Vorarbeiten von Get et al. [9] und Preiner et al. [17] vorgestellt, prototypisch implementiert und evaluiert. Dieser führt, gesteuert durch den Client, eine blickpunktabhängige punktbasierte Abtastung auf einem entfernten oberflächenbezogenen Simulationsdatensatz aus. Die daraus inkrementell gewonnene Punktwolke aus Simulationsdaten wird in einem Octree, der zwischen Client und Server synchronisiert wird, organisiert und temporär zwischengespeichert. Auf dem Client wird daraufhin mittels eines splatbasierten Rekonstruktionsverfahrens die Oberfläche des Simulationsdatensatzes wiederhergestellt. Mithilfe von Deferred Rendering und Color Mapping kann die Visualisierung der Simulationsdaten anschließend lokal modifiziert werden. Der Ansatz ermöglicht dabei eine Entkopplung der Datenkomplexität und der Renderleistung zwischen Client und Server. Anhand eines kleinen Beispieldatensatzes wird zum Schluss die Praktikabilität des Verfahrens experimentell evaluiert. Eine Evaluierung für große Daten konnte wegen fehlender Verfügbarkeit eines entsprechenden Datensatzes nicht durchgeführt werden. Die direkte Abhängigkeit der interaktiv visualisierbaren Datenmengen von den serverseitig verfügbaren Ressourcen kann jedoch aufgrund der Vorarbeiten von Ge et al. [9] angenommen werden.

Show publication details

Kordek, Andres Felipe; Kuijper, Arjan

Intuitive Placement of Objects in Web-Based CAD Environments

2015

Stephanidis, Constantine (Ed.): HCI International 2015 - Posters' Extended Abstracts. Proceedings Part I : HCI International 2015. Springer International Publishing, 2015. (Communications in Computer and Information Science (CCIS) 528), pp. 414-420

International Conference on Human-Computer Interaction (HCII) <17, 2015, Los Angeles, CA, USA>

We develop a Computer Aided Design (CAD) editor using an open source library, with the aim to minimize the cost in the future, as compared to the development of conventional editors, and to accelerate the expansion by means of standardized languages making the development easier. We focus on snapping, a very important area in computer graphics and without a CAD application inconceivable. CAD applications offer the possibility of snappings to allow the developers an intuitive interaction with the objects in 2D or 3D space. Snapping allows by using constraints the merging of multiple objects into a new object. Two possible approaches for implementing snappings are addressed and presented. Advantages and disadvantages are discussed via a user study.

Show publication details

Reichert, Hermann; Steckenreiter, O. (Betreuer); Sakas, Georgios (Betreuer); Kuijper, Arjan (Betreuer)

Kalibrierung von räumlich verfolgten Ultraschall-Sonden

2015

Darmstadt, TU, Bachelor Thesis, 2015

Das Wissen über die Position von 2D-Ultraschallbildern im 3D-Raum ist eine wertvolle Information, die genutzt wird, um Volumen zu rekonstruieren. Die Positionsbestimmung erfolgt über ein Trackingsystem, welches die Position der Ultraschallsonde verfolgt. Die Beziehung zwischen der Position der Sonde und der Position des eigentlichen Ultraschallbildes wird durch eine Transformationsmatrix beschrieben, die mittels einer Kalibrierung bestimmt werden muss. Diese Arbeit listet verschiedene Kalibrierungsmethoden auf und setzt zwei dieser Verfahren um. Dabei wird die Punkt-Kalibrierung (engl. Cross-wire Calibration) und die bildbasierte Kalibrierung (engl. Image-Based Calibration) implementiert und ausgewertet.

Show publication details

Dolereit, Tim; Lukas, Uwe von; Kuijper, Arjan

New Constraints for Underwater Stereo Calibration

2015

Loncaric, Sven (Ed.) et al.: ISPA 2015 : 9th International Symposium on Image and Signal Processing and Analysis. Zagreb: University of Zagreb, 2015, pp. 176-181

International Symposium on Image and Signal Processing and Analysis (ISPA) <9, 2015, Zagreb, Croatia>

In this paper we present new constraints for calibration of underwater stereo-camera-systems and 3Dreconstruction. These constraints are both intuitive and simple to realize. We show that additionally needed refractive parameters in such a system can be calibrated simultaneously. Our constraints partially build upon each other. A subset of them even enables the calibration from stereo-correspondences alone, making known calibration targets unnecessary.

Show publication details

Tschirsich, Martin; Kuijper, Arjan

Notes on Discrete Gaussian Scale Space.

2015

Journal of Mathematical Imaging and Vision, Vol.51 (2015), 1, pp. 106-123

Gaussian scale space is a well-known linear multi-scale representation for continuous signals. The exploration of its so-called deep structure by tracing critical points over scale has various theoretical applications and allows for the construction of a scale space hierarchy tree. However, implementation issues arise, caused by discretization and quantization errors. In order to develop more robust scale space based algorithms, the discrete nature of computer processed signals has to be taken into account. We propose suitable neighborhoods, boundary conditions, and sampling methods. In analogy to prevalent approaches and inspired by Lindeberg's scale space primal sketch, a discretized diffusion equation is derived, including requirements imposed by the chosen neighborhood and boundary condition. The resulting discrete scale space respects important topological invariants such as the Euler number, a key criterion for the successful implementation of algorithms operating on critical points in its deep structure. Relevant properties of the discrete diffusion equation and the Eigenvalue decomposition of its Laplacian kernel are discussed and a fast and robust sampling method is proposed. We finally discuss properties of topological graphs under the influence of smoothing, setting the stage for more robust deep structure extraction algorithms.

Show publication details

Zhuoman, Wen; Yanjie, Wang; Kuijper, Arjan; Nan, Di; Jun, Luo; Lei, Zhang; Minghe, Jin

On-orbit Real-time Robust Cooperative Target Identification in Complex Background

2015

Chinese Journal of Aeronautics, Vol.28 (2015), 5, pp. 1451-1463

Cooperative target identification is the prerequisite for the relative position and orientation measurement between the space robot arm and the to-be-arrested object. We propose an on-orbit real-time robust algorithm for cooperative target identification in complex background using the features of circle and lines. It first extracts only the interested edges in the target image using an adaptive threshold and refines them to about single-pixel-width with improved non-maximum suppression. Adapting a novel tracking approach, edge segments changing smoothly in tangential directions are obtained. With a small amount of calculation, large numbers of invalid edges are removed. From the few remained edges, valid circular arcs are extracted and reassembled to obtain circles according to a reliable criterion. Finally, the target is identified if there are certain numbers of straight lines whose relative positions with the circle match the known target pattern. Experiments demonstrate that the proposed algorithm accurately identifies the cooperative target within the range of 0.3-1.5 m under complex background at the speed of 8 frames per second, regardless of lighting condition and target attitude. The proposed algorithm is very suitable for real-time visual measurement of space robot arm because of its robustness and small memory requirement.

Show publication details

Karolus, Jakob; Kuijper, Arjan (Betreuer); Fu, Biying (Betreuer)

Opportunities and Applications of Ultrasound Sensing on Unmodified Consumer-grade Smartphones: Möglichkeiten und Anwendungen von Ultraschall Messungen auf nicht modifizierten Smartphones für Endverbraucher

2015

Darmstadt, TU, Master Thesis, 2015

A person's smartphone is a cornucopia of information. Be it personal data extracted from contacts and calendar entries or the current location via GPS. The huge variety of sensors in today's mobile phones makes these devices a prime target for human activity recognition. The smartphone is no longer solely seen as actuator in smart environments, enabling the user to control auxiliary devices and sensors, but can now play a vital part in the network of sensing information itself. Especially in the area of human activity recognition, camera-based or body-worn systems are predominant. While they achieve high accuracy, these methods often suffer from privacy issues or obtrusiveness and consequently social stigma. In this thesis, I present an unobtrusive approach to perceive the vicinity surrounding the phone by leveraging the properties of ultrasound sensing. The device emits ultrasonic waves via its speaker and records the echo via the microphone. By analyzing the received signal, I can deduct certain movements, e.g. gestures performed above the phone, but also more complex motions involving the whole body of the user. I outline various experiments to estimate the feasibility of ultrasound sensing in different scenarios as well as propose an algorithm and mobile application that can classify given gestures and activities performed by the user. The system is able to recognize predefined gestures with an overall accuracy of 81% over six different users and can detect human activities up to 2m away.

Show publication details

Fu, Biying; Karolus, Jakob; Große-Puppendahl, Tobias; Hermann, Jonathan; Kuijper, Arjan

Opportunities for Activity Recognition using Ultrasound Doppler Sensing on Unmodified Mobile Phones

2015

Matthies, Denys J.C. (Ed.) et al.: iWOAR 2015 : 2nd international Workshop on Sensor-based Activity Recognition and Interaction. New York: ACM Press, 2015, 10 p.

International Workshop on Sensor-based Activity Recognition (iWOAR) <2, 2015, Rostock, Germany>

Nowadays activity recognition on smartphones is ubiquitously applied, for example to monitor personal health. The smartphone's sensors act as a foundation to provide information on movements, the user's location or direction. Incorporating ultrasound sensing using the smartphone's native speaker and microphone provides additional means for perceiving the environment and humans. In this paper, we outline possible usage scenarios for this new and promising sensing modality. Based on a custom implementation, we provide results on various experiments to assess the opportunities for activity recognition systems. We discuss various limitations and possibilities when wearing the smartphone on the human body. In stationary deployments, e.g. while placed on a night desk, our implementation is able to detect movements in proximities up to 2m as well as discern several gestures performed above the phone.

Show publication details

Gutzeit, Enrico; Radolko, Martin; Lukas, Uwe von; Kuijper, Arjan

Optimization-based Automatic Segmentation of Organic Objects of Similar Types

2015

Braz, José (Ed.) et al.: VISAPP 2015 - Volume I : Proceedings of the International Conference on Computer Vision Theory and Applications. SciTePress, 2015, pp. 591-598

International Conference on Computer Vision Theory and Applications (VISAPP) <10, 2015, Berlin, Germany>

For the segmentation of multiple objects on unknown background in images, some approaches for specific objects exist. However, no approach is general enough to segment an arbitrary group of organic objects of similar type, like wood logs, apples, or tomatoes. Each approach contains restrictions in the object shape, texture, color or in the image background. Many methods are based on probabilistic inference on Markov Random Fields - summarized in this work as optimization based segmentation. In this paper, we address the automatic segmentation of organic objects of similar types by using optimization based methods. Based on the result of object detection, a fore- and background model is created enabling an automatic segmentation of images. Our novel and more general approach for organic objects is a first and important step in a measuring or inspection system. We evaluate and compare our approaches on images with different organic objects on very different backgrounds, which vary in color and texture. We show that the results are very accurate.

Show publication details

Hammacher, Felix; Rus, Silvia (Betreuer); Kuijper, Arjan (Betreuer)

Physical Simulation- and Reconstruction-framework for Shape Sensing Fabrics

2015

Darmstadt, TU, Master Thesis, 2015

Over the last decade a large number of prototypes for several research areas in the field of shape sensing have been based on optical tracking devices like the Microsoft Kinect. To overcome the disadvantages of such devices, namely immobility and occlusion of tracked objects, another approach, to which only little attention has been given to so far, is the usage of embedded sensors in fabrics. One of the reasons might be the high effort to manufacture such prototypes with uncertain outcome in terms of matching the requirements of certain use cases. To help developing and planning such devices as well as the used software, a simulation- and reconstruction-framework is introduced in this thesis. Furthermore both parts together enable creating software for a use case even before the hardware is ready. An exemplary workflow, demonstrating how the implemented software can support the development of new applications for shape sensing fabrics, is presented with the Sleeping Posture Recognizer. It uses a blanket with embedded acceleration sensors to determine the sleeping posture of the covered person.

Show publication details

Hermanns, Lukas; Kuijper, Arjan (Betreuer); Franke, Tobias (Betreuer)

Screen Space Cone Tracing for Glossy Reflections

2015

Darmstadt, TU, Bachelor Thesis, 2015

Indirect lighting (also Global Illumination (GI)) is an important part of photo-realistic imagery and has become a widely used method in real-time graphics applications, such as Computer Aided Design (CAD), Augmented Realtiy (AR) and video games. Path tracing can already achieve photorealism by shooting thousands or millions of rays into a 3D scene for every pixel, which results in computational overhead exceeding real-time budgets. However, with modern programmable shader pipelines, a fusion of ray-casting algorithms and rasterization is possible, i.e. methods, which are similar to testing rays against geometry, can be performed on the GPU within a fragment (or rather pixel-) shader. Nevertheless, many implementations for real-time GI still trace perfect specular reflections only. In this Bachelor thesis the advantages and disadvantages of different reflection methods are exposed and a combination of some of these is presented, which circumvents artifacts in the rendering and provides a stable, temporally coherent image enhancement. The benefits and failings of this new method are clearly separated as well. Moreover the developed algorithm can be implemented as pure post-process, which can easily be integrated into an existing rendering pipeline. The core idea of this thesis has been presented as a poster at SIGGRAPH 2014 [Hermanns and Franke, 2014].

Show publication details

Frese, Sven; Kuijper, Arjan (Betreuer); Krämer, Michel (Betreuer)

Secure Cloud-Based Risk Assessment for Urban Areas: Sichere cloudbasierte Risikoanalyse für Stadtgebiete

2015

Darmstadt, TU, Master Thesis, 2015

While the number of people living in urban centers has been increasing significantly over the last decades so has the number of overall recorded terroristic events. Especially densely populated areas are vulnerable targets which forces urban planners to carefully consider and evaluate security measures in the planning process. In order to support urban planners in this process, we present a system design for a web application to perform risk assessment for urban areas based on digital city models that is capable of visualizing risk assessment result in the web browser. In addition to a web portal our system consists of a web service based on a mircoservices architecture that uses components of the CityServer3D developed by Fraunhofer IGD to process spatial data. In order to perform risk assessment calculations, the capabilities of the VITRUV Tool developed at Fraunhofer EMI are utilized. We use Ciphertext-Policy Attribute-Based Encryption (CP-ABE) in combination with symmetric encryption to store user data with embedded access policies on scalable cloud storage without disclosing it to unauthorized parties. City object coordinates are encrypted with Order-Preserving Encryption (OPE) in order to support range queries. Our results indicate that our system design is scalable regarding data processing and encryption. However, CP-ABE generates significant overhead and is therefore not suited for embedding complex access policies in ciphertexts without compromising the responsiveness of web applications.

Show publication details

Kuijper, Arjan; Heise, B.; Zhou, Y.; He, L.; Wolinski, H.; Kohlwein, S.

Segmentation of Clustered Cells in Microscopy Images by Geometric PDEs and Level Sets

2015

Paragios, Nikos (Ed.) et al.: Handbook of Biomedical Imaging : Methodologies and Clinical Research. Springer Science+Business Media, 2015, pp. 475-487

With the huge amount of cell images produced in bio-imaging, automatic methods for segmentation are needed in order to evaluate the content of the images with respect to types of cells and their sizes. Traditional PDE-based methods using level-sets can perform automatic segmentation, but do not perform well on images with clustered cells containing sub-structures. We present two modifications for popular methods and show the improved results.

Show publication details

Vahl, Matthias; Lukas, Uwe von; Urban, Bodo; Kuijper, Arjan

Semi-automatic Analysis of Huge Digital Nautical Charts of Coastal Aerial Images

2015

Braz, José (Ed.) et al.: VISAPP 2015 - Volume III : Proceedings of the International Conference on Computer Vision Theory and Applications. SciTePress, 2015, pp. 100-107

International Conference on Computer Vision Theory and Applications (VISAPP) <10, 2015, Berlin, Germany>

Geo-referenced aerial images are available in very high resolution. The automated production and updating of electronic nautical charts (ENC), as well as other products (e.g. thematic maps), from aerial images is a current challenge for hydrographic organizations. Often standard vision algorithms are not reliable enough for robust object detection in natural images. We thus propose a procedure that combines processing steps on three levels, from pixel (low-level) via segments (mid-level) to semantic information (high level). We combine simple linear iterative clustering (SLIC) as an efficient low-level algorithm with a classification based on texture features by supported vector machine (SVM) and a generalized Hough transformation (GHT) for detecting shapes on mid-level. Finally, we show how semantic information can be used to improve results from the earlier processing steps in the high-level step. As standard vision methods are typically much too slow for such huge-sized images and additionally geographical references must be maintained over the complete procedure, we present a solution to overcome these problems.

Show publication details

Strassel, Lukas; Kuijper, Arjan (Betreuer); Große-Puppendahl, Tobias (Betreuer)

Sensing Interactions on Body-worn Low-resolution LED-Displays

2015

Darmstadt, TU, Bachelor Thesis, 2015

Traffic safety is a major concern, especially for non-motorized traffic participants. According to various studies many accidents with cyclists, pedestrians, and athletes are caused due to insufficient visibility in traffic. To increase their visibility, we developed a wearable device which combines a lightweight sensor platform with a RGB LED display to give feedback to the surrounding traffic. This thesis presents a placing recognition for wearable devices, which allows autonomous placement detection utilizing an accelerometer. The data received by placement detection is then used to detect implicit and explicit gestures as a context aware system featuring a brake detection for back mounted devices and a turn indication for arm mounted devices. These gestures can be used to increase the cyclists safety, by using feedback modalities on RGB LED display used to communicate the intended actions to the following traffic. In order to archive low power consumption and a long battery run time, the presented algorithms for gesture recognition are optimized for low performance microcontrollers.

Show publication details

Eicke, Tim Nicolas; Jung, Yvonne; Kuijper, Arjan

Stable Dynamic Webshadows in the X3DOM Framework

2015

Expert Systems with Applications, Vol.42 (2015), 7, pp. 3585-3609

The faithful representation of real-time shadow has become omnipresent in our everyday lives due to modern video games. In the World Wide Web, however, this is different: the representation of three-dimensional scenes in a browser is only a few years old and so far, shadows play at most a minor role. Still, shadows are an important factor in the human perception of three-dimensional worlds, since they increase in general not only the authenticity of a scene, but at the same time provide important clues about where an object is placed in space. The JavaScript-based open-source framework X3DOM plays an essential role in the 3D web development, because it provides an approach for the integration of declarative 3D in HTML5. However, it provides only rudimentary shadow techniques, which are insufficient to today's requirements. In this work, this problem is addressed by first examining existing shadow mapping techniques for their suitability for use in the web. Based on this we provide a concept to improve the shadow representation for X3DOM. We implemented and validated our concept showing the benefit. As a result is now standard part of X3DOM.

Show publication details

Dolereit, Tim; Lukas, Uwe von; Kuijper, Arjan

Underwater Stereo Calibration Utilizing Virtual Object Points

2015

Marine Technology Society (MTS): OCEANS 2015 MTS/IEEE Washington. The Institute of Electrical and Electronics Engineers (IEEE), 2015, 7 p.

MTS/IEEE Oceans Conference and Exhibition (OCEANS) <2015, Genova, Italy>

For 3D-reconstruction of underwater scenes, a camera calibration handling refractive effects is indispensable. We present a novel geometry-based approach for calibration of stereo-camera-systems in a single underwater housing with a flat interface. Our approach consists of three steps. First, we show a hypothesis on how to relate the location of virtual object points non-ambiguously to the true object location in water. Secondly, axis determination and thirdly, distance determination of a refractive interface towards the cameras is performed with the aid of this hypothesis. We propose, that the calibration can be done with just one stereo-view of a known calibration pattern, that axis determination can be done from stereo correspondences alone and that our hypothesis is a valid constraint for stereo 3d-reconstruction. We evaluated our approach on simulated data with ground truth and real data.

Show publication details

Gottschämmer, Patrick; Große-Puppendahl, Tobias; Kuijper, Arjan

User Location Modeling Based on Heterogeneous Data Sources

2015

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2015. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9189), pp. 473-484

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <3, 2015, Los Angeles, CA, USA>

Over the past decade, interest in home automation systems constantly grew. This yields especially for daily life - considering the connection of intelligent everyday devices through the Internet of Things. To allow automatic actions on these devices, user localization systems have become a major input modality for smart home systems. The location of a user (or rather a subject) can be determined by different localization techniques, such as sensitive floor systems, discrete activity sensors like light switches or RSSI-based WLAN/Bluetooth beacons (e.g. smartphones). These heterogeneous data sources provide various means of user location certainty, the ability to identify a user or the ability to recognize multiple subjects in the same location. In order to achieve a higher grade of accuracy, multiple data sources can be combined by location fusioning algorithms. However, to allow the integration of such algorithms on a hardware independent basis, a common user location model is needed, which can represent all important aspects of these localization techniques. This paper investigates the concepts of existing user localization systems and develops a new model to represent the location of subjects based on already existing location models. An implementation is provided based on Eclipse SmartHome, an open-source building automation framework.

Show publication details

Geurts, Alexander; Sakas, Georgios; Kuijper, Arjan; Becker, Meike; Landesberger, Tatiana von

Visual Comparison of 3D Medical Image Segmentation Algorithms Based on Statistical Shape Models

2015

Duffy, Vincent G. (Ed.): Digital Human Modeling. Proceedings Part II : Applications in Health, Safety, Ergonomics and Risk Management: Ergonomics and Health. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9185), pp. 336-344

International Conference on Digital Human Modeling (DHM) <6, 2015, Los Angeles, CA, USA>

3D medical image segmentation is needed for diagnosis and treatment. As manual segmentation is very costly, automatic segmentation algorithms are needed. For finding best algorithms, several algorithms need to be evaluated on a set of organ instances. This is currently difficult due to dataset size and complexity. In this paper, we present a novel method for comparison and evaluation of several algorithms that automatically segment 3D medical images. It combines algorithmic data analysis with interactive data visualization. A clustering algorithm identifies regions of common quality across the segmented data set for each algorithm. The comparison identifies best algorithms per region. Interactive views show the algorithm quality. We applied our approach to a real-world cochlea dataset, which was segmented with several algorithms. Our approach allowed segmentation experts to compare algorithms on regional level and to identify best algorithms per region.

Show publication details

Brakowski, Alexander; Kuijper, Arjan (Betreuer); Maier, Sebastian (Betreuer)

Visual Guidance to Find the Right Spot in the Parameter Space: Visuelle Unterstützung bei der Parameterauswahl

2015

Darmstadt, TU, Bachelor Thesis, 2015

The last few decades brought upon a technological revolution that has been generating data by users with an ever increasing variety of digital devices, resulting in such an incredible volume of data, that we are unable to make any sense of it any more. This trend also does not seem to stop in the near future. This problem requires us to think about new methods to help us explore these large data sets. We already have a lot of Machine learning and Data mining algorithms, that are able to help us find something interesting in the data, but because of their high algorithmic complexity using them can make the data exploration extremely time consuming and frustrating. One solution to decrease the required execution time of these algorithms would be the preprocessing of the data by sampling it before starting the exploration process. That indeed does help, but one issue remains when using the available Machine Learning and Data Mining algorithms: they all have parameters. That is a big problem for most users, because a lot of these parameters require expert knowledge to be able to tune them. Even for expert users a lot of the parameter configurations highly depend on the data. In this work I will present a system that tackles that data exploration process from the angle of parameter space exploration. Here we use the active learning approach and iteratively try to query the user for their opinion of an algorithm execution. For that an end-user only has to express a preference for algorithm results presented to them in form of a visualisations. That way the system is iteratively learning the interest of the end-user, which results in good parameters at the end of the process. A good parametrisation is obviously very subjective here and only reflects the interest of an user. This solution has the nice ancillary property of omitting the requirement of expert knowledge when trying to explore an data set with Data Mining or Machine Learning algorithms. Optimally the end-user does not even know what kind of parameters the algorithms require. Furthermore I present an intuitive frontend that allows an end-user to configure the exploration process, which includes choosing the data and the algorithm that should be used for the exploration. In the end of this thesis I present some interesting use cases for this process.

Show publication details

Maier, Sebastian; Kühnel, Hannes; May, Thorsten; Kuijper, Arjan

Visual Interactive Process Monitoring

2015

Yamamoto, Sakae (Ed.): Human Interface and the Management of Information. Proceedings Part I : Information and Knowledge Design. Springer International Publishing, 2015. (Lecture Notes in Computer Science (LNCS) 9172), pp. 74-85

International Conference on Human Interface and the Management of Information (HIMI) <2015, Los Angeles, CA, USA>

Sensor data has been coined the oil of the 21st century. We present a technique for the visual analysis of multivariate sensor event log data. This technique tackles two challenges: Firstly, in a complex process the relation of causes and effects is often masked by indirections. Secondly, the metrics to measure success might be different from the measures that identify causes. Thus, our approach does not require that all sensor data is equal. Our techniques combines automated and interactive grouping to identify candidate sets sharing properties relevant for cause and effect analysis. Interactive visual probes offer immediate information on the statistical relevance of an identified connection.

Show publication details

Nazemi, Kawa; Retz, Reimond; Burkhardt, Dirk; Kuijper, Arjan; Kohlhammer, Jörn; Fellner, Dieter W.

Visual Trend Analysis with Digital Libraries

2015

Lindstaedt, Stefanie (Ed.) et al.: i-KNOW 2015 : Proceedings of the 15th International Conference on Knowledge Technologies and Data-driven Business. New York: ACM, 2015. (ACM International Conference Proceedings Series 1098), pp. 14:1-14:8

International Conference on Knowledge Management and Data-driven Business (I-KNOW) <15, 2015, Graz, Austria>

The early awareness of new technologies and upcoming trends is essential for making strategic decisions in enterprises and research. Trends may signal that technologies or related topics might be of great interest in the future or obsolete for future directions. The identification of such trends premises analytical skills that can be supported through trend mining and visual analytics. Thus the earliest trends or signals commonly appear in science, the investigation of digital libraries in this context is inevitable. However, digital libraries do not provide sufficient information for analyzing trends. It is necessary to integrate data, extract information from the integrated data and provide effective interactive visual analysis tools. We introduce in this paper a model that investigates all stages from data integration to interactive visualization for identifying trends and analyzing the market situation through our visual trend analysis environment. Our approach improves the visual analysis of trends by investigating the entire transformation steps from raw and structured data to visual representations.

Show publication details

Niese, Christoph; Kuijper, Arjan (Betreuer); Landesberger, Tatiana von (Betreuer)

Visualisation of composer relationships using implicit data graphs

2015

Darmstadt, TU, Bachelor Thesis, 2015

Relationships between classical music composers are known due to explicit historic material, for instance the friendship between Joseph Haydn and Wolfgang Amadeus Mozart, as well as the influence of the latter on Ludwig van Beethoven. While Haydn and Mozart were critics of each other's work, Mozart and Beethoven probably never met in person. In spite of that there is an impact on especially the early music of Beethoven. While relationships between well-known composers like the mentioned ones are investigated, it can also be of historic interest to know the roles less-known composers played. Some of them might have a part in a famous person's work but were not further analysed given the fact that there have been many composers and and no hints given to researchers indicating which person would be worth studying. In this work I develop an approach to visually hint possible relationships among a large number of composers. Detailed historic knowledge is not taken into account, the hints are only based on the composers works as well as their lifetimes in order to guess directions of influence.

Show publication details

Pandikow, Lars; Kuijper, Arjan (Betreuer); Gutbell, Ralf (Betreuer)

Webfähige Visualisierungskomponente für Geoinformationen

2015

Darmstadt, TU, Bachelor Thesis, 2015

Dreidimensionale Kartenvisualisierungen nehmen einen stetig wachsenden Stellenwert im Internet ein. Neben der privaten Nutzung, können sie besonders bei der Planung von Bauprojekten eingesetzt werden, um diese interaktiv und visuell ansprechend zu präsentieren. Steigende Leistungsfähigkeit der Endgeräte und die Etablierung neuer Technologien wie HTML5 und WebGL erlauben dabei eine Plug-in freie Darstellung von 3D Anwendungen direkt im Browser. Bestehenden Softwarelösungen, wie Google Earth oder Cesium, mangelt es entweder an der benötigten Anpassbarkeit oder der realistischen Darstellung der Welt. In dieser Arbeit wird eine browserbasierte Visualisierungskomponente für Geoinformationen konzipiert und ein Prototyp in der Spiele-Engine Unity3D implementiert. Unity5 ermöglicht es die Implementierung in Javascript zu übersetzen und mit WebGL im Browser darzustellen. Ein Vergleich des Prototypen mit Cesium zeigt, dass eine Verbesserung der visuellen Qualität bei gleichzeitig akzeptabler Performance erreicht wird.

Show publication details

Twellmeyer, James; Kuijper, Arjan; Kohlhammer, Jörn

WOW-A-Cluster! A Visual Similarity-Based Approach to Log Exploration

2015

Peters, Christopher E. (Ed.) et al.: Proceedings of SIGRAD 2015. Linköping: Linköping University Electronic Press, 2015. (Linköping Electronic Conference Proceedings 120), pp. 61-64

SIGRAD Conference <14, 2015, Stockholm, Sweden>

We present our work on a visual, similarity-based approach to log file exploration. The use of similarity rather than simple aggregation schemes empowers users to focus on the high-level events behind log entries, rather than the entries themselves. We make use of an accelerated version of TRIAGE to determine the similarity coefficients for each pair of log entries. The model is embedded in an interactive visualization system which enables the fluid interpretation of similarities with the help of a simple clustering approach.

Show publication details

Braun, Andreas; Wichert, Reiner; Kuijper, Arjan; Fellner, Dieter W.

A Benchmarking Model for Sensors in Smart Environments

2014

Aarts, Emile (Ed.) et al.: Ambient Intelligence : European Conference, AmI 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8850), pp. 242-257

European Conference on Ambient Intelligence (AmI) <11, 2014, Eindhoven, The Netherlands>

In smart environments, developers can choose from a large variety of sensors supporting their use case that have specific advantages or disadvantages. In this work we present a benchmarking model that allows estimating the utility of a sensor technology for a use case by calculating a single score, based on a weighting factor for applications and a set of sensor features. This set takes into account the complexity of smart environment systems that are comprised of multiple subsystems and applied in non-static environments. We show how the model can be used to find a suitable sensor for a use case and the inverse option to find suitable use cases for a given set of sensors. Additionally, extensions are presented that normalize differently rated systems and compensate for central tendency bias. The model is verified by estimating technology popularity using a frequency analysis of associated search terms in two scientific databases.

Show publication details

Nazemi, Kawa; Burkhardt, Dirk; Retz, Reimond; Kuijper, Arjan; Kohlhammer, Jörn

Adaptive Visualization of Linked-Data

2014

Bebis, George (Ed.) et al.: Advances in Visual Computing. 10th International Symposium, ISVC 2014 : Proceedings, Part II. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8888), pp. 872-883

International Symposium on Visual Computing (ISVC) <10, 2014, Las Vegas, NV, USA>

Adaptive visualizations reduces the required cognitive effort to comprehend interactive visual pictures and amplify cognition. Although the research on adaptive visualizations grew in the last years, the existing approaches do not consider the transformation pipeline from data to visual representation for a more efficient and effective adaptation. Further todays systems commonly require an initial training by experts from the field and are limited to adaptation based either on user behavior or on data characteristics. A combination of both is not proposed to our knowledge. This paper introduces an enhanced instantiation of our previously proposed model that combines both: involving different influencing factors for and adapting various levels of visual peculiarities, on content, visual layout, visual presentation, and visual interface. Based on data type and users' behavior, our system adapts a set of applicable visualization types. Moreover, retinal variables of each visualization type are adapted to meet individual or canonical requirements on both, data types and users' behavior. Our system does not require an initial expert modeling.

Show publication details

Große-Puppendahl, Tobias; Beck, Sebastian; Wilbers, Daniel; Zeiß, Steeven; Wilmsdorff, Julian von; Kuijper, Arjan

Ambient Gesture-Recognizing Surfaces with Visual Feedback

2014

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8530), pp. 97-108

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <2, 2014, Heraklion, Crete, Greece>

In recent years, gesture-based interaction gained increasing interest in Ambient Intelligence. Especially the success of camera-based gesture recognition systems shows that a great variety of applications can benefit significantly from natural and intuitive interaction paradigms. Besides camera-based systems, proximity-sensing surfaces are especially suitable as an input modality for intelligent environments. They can be installed ubiquitously under any kind of non-conductive surface, such as a table. However, interaction barriers and the types of supported gestures are often not apparent to the user. In order to solve this problem, we investigate an approach which combines a semi-transparent capacitive proximity-sensing surface with an LED array. The LED array is used to indicate possible gestural movements and provide visual feedback on the current interaction status. A user study shows that our approach can enhance the user experience, especially for inexperienced users.

Show publication details

Schader, Philipp; Kuijper, Arjan (Betreuer); Steiger, Martin (Betreuer)

Assistiertes Energiemanagement durch Informationsvisualisierung

2014

Darmstadt, TU, Bachelor Thesis, 2014

Diese Arbeit beschreibt Konzepte zur Visualisierung von Energienetzen sowie zur Darstellung und Parametrisierung von Simulationen solcher. Es werden Darstellungen beschrieben mit denen sich ein Stromnetz darstellen lässt, sodass der Betriebszustand in dem es sich befindet zu erkennen ist. Weiter wird die Integration eines Simulators beschrieben mit dem Ziel ein interaktives System zu gestalten, welches durch die enge Verzahnung der Generierung und Darstellung von Daten, tiefe Einblicke in die Struktur des Versorgungsnetzes ermöglicht. Ein besonderes Augenmerk richtet sich hierbei auf die Möglichkeit die Simulationsergebnisse untereinander vergleichen zu können. Der im Rahmen dieser Arbeit entwickelte Prototyp verwendet die Konzepte auf Pegeldaten deutscher Wasserstraßen und zeigt so dass die Konzepte auch für allgemeine Sensornetzwerke verwendet werden können. Durch die Beschreibung eines konkreten Anwendungsfalls wird die Tauglichkeit der erarbeiteten Konzepte überprüft.

Show publication details

Klamm, Christopher; Kuijper, Arjan (Betreuer); Burkhardt, Dirk (Betreuer)

Ausprägungen elektronischer Beteiligung in Industrie- und Entwicklungsländern: Ein anwendungsorientierter Vergleich am Beispiel Deutschland und Kenia

2014

Darmstadt, TU, Bachelor Thesis, 2014

Partizipation ist ein etabliertes Element der partizipatorischen Demokratie. Immer wieder werden Mechanismen entwickelt, um Partizipation zu erhöhen und zu festigen. Mit Hilfe der voranschreitenden Entwicklung von Informations- und Kommunikationstechnologien, eröffnen sich neue Möglichkeiten von Partizipationsansätzen. Diese finden auch zunehmend weltweiten Einsatz. Neue partizipatorische Formen verwenden ICT als Mittel zur Unterstützung der Partizipation (E-Partizipation). In welche Bahnen E-Partizipation bereits gelenkt wurde ist Gegenstand dieser Arbeit. Sie setzt sich mit der Ausprägung vorhandener E-Partizipationsformen auseinander und betrachtet dabei anwendungsbezogene Projekte. Das Untersuchungsumfeld wurde dabei auf einen Ländervergleich festgelegt. Es handelt sich um einen Vergleich zwischen Deutschland, als repräsentatives Industrieland und Kenia, als Repräsentant für ein Entwicklungsland. Dafür wird, mit Hilfe einer historischen und anwendungsorientierten Betrachtung der E-Partizipation in den Ländern, ein Kontext aufgestellt. Mit dessen Hilfe werden die E-Partizipationsbestrebungen in Deutschland und Kenia anschließend mittels einer aufgestellten Klassifikation vergleichend gegenübergestellt. Die Analyse zeigt, dass deutsche Projekte vermehrt staatlich (Top-Down) initiiert sind, wo-hingegen in Kenia häufiger eine nicht-staatliche Ausrichtung (Ground-Up) existent ist. Weiterhin ist in kenianischen Projekten die Form "Transparenz durch Dritte" stärker ausgeprägt, in Deutschland ist es hingegen die konsultative Form. Im Bereich des fokussierten Bedürfnisses überwiegt in Deutschland die soziale Bedürfnisbefriedung, während in Kenia auch noch Sicherheitsbedürfnisse bedeutsam sind. Im Bereich der ICT-Form zeigt sich eine ähnliche Verteilung innerhalb der Länder bei den Formen Alert, FAQ und Forum. Partielle Unterschiede sind in den Formen Blog und Bewertung ausgeprägt, starke Differenzen existieren dagegen bei den Formen Chat, Umfrage und Spiel als Partizipationsmittel. Für letztere gilt, dass Chat und Umfrage nur in deutschen und das Spiel nur in kenianischen Projekten verwendet wurden.

Show publication details

Brandherm, Florian; Kuijper, Arjan (Betreuer); Limper, Max (Betreuer)

Automatic Appearance-Preserving Generation of Compact 3D Models for the Web

2014

Darmstadt, TU, Bachelor Thesis, 2014

The goal of this thesis was to create a fully automatic processing pipeline to simplify big arbitrary triangle meshes to a degree that can be used inside a web page using WebGL. While the mesh complexity is decreased by orders of magnitude, the original meshes details (e.g. colors, normals) are preserved by capturing them in textures. These textures can then be applied to the simplified mesh to give it an appearance that is similar in detail as the original high resolution mesh. The proposed implementation makes it easy to incorporate such a simplified mesh into a website by providing an exporter that generates a web site with all necessary files in suitable file formats. Simplified, detail-preserving 3D models are generated in multiple independent steps: First, the mesh is simplified with the quadric edge collapse algorithm[9]. Then, a texture atlas is created by segmenting the simplified mesh and parameterizing the individual segments with Least Squares Conformal Maps[14]. After packing the individual segments into a texture atlas, the details of the high-resolution input mesh are captured in textures. At the end of this processing pipeline, the model is exported. The results show that the goal of creating file sizes that are small enough for a web page while preserving a reasonable amount of detail was reached. It is shown that the resulting files can compete with the alternative approach of creating interactive 3Dvisualizations with a series of pre-rendered images. The analysis of the results also shows that there is a lot of potential to increase the file size to detail ratio further.

Show publication details

Neumann, Stephan; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

Automotive Interfaces Using an Interactive Armrest

2014

Darmstadt, TU, Bachelor Thesis, 2014

Due to the rapid technological development of cars and their entertainment and infotainment systems, drivers are confronted with feature-rich interfaces that can become both confusing and distracting. Therefore, new ways of interaction between driver and car have to be developed in order to reduce driver distraction to a minimum. This is relevant to the safety of both the driver and road users surrounding him. In this thesis, gesture based interaction in the automotive is examined. The main focus is gestural interaction using capacitive sensors. In this area, an overview over related work is given. Challenges in developing a capacitive system for gesture based interaction in the automotive environment are presented and discussed. Afterwards, a model for a gesture-based input system using an augmented armrest is proposed. A prototypical system is implemented in order to test the possibilities and limitations of the proposed model. This system is then evaluated in order to test its general viability and to compare different kinds of gestures for interacting with in-car systems.

Show publication details

Große-Puppendahl, Tobias; Herber, Sebastian; Wimmer, Raphael; Englert, Frank; Beck, Sebastian; Wilmsdorff, Julian von; Wichert, Reiner; Kuijper, Arjan

Capacitive Near-Field Communication for Ubiquitous Interaction and Perception

2014

ACM SIGCHI: UbiComp' 14 : Proceedings of the 2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing. New York: ACM Press, 2014, pp. 231-242

International Conference on Ubiquitous Computing (Ubicomp) <16, 2014, Seattle, WA, USA>

Smart objects within instrumented environments offer an always available and intuitive way of interacting with a system. Connecting these objects to other objects in range or even to smartphones and computers, enables substantially innovative interaction and sensing approaches. In this paper, we investigate the concept of Capacitive Near-Field Communication to enable ubiquitous interaction with everyday objects in a short-range spatial context. Our central contribution is a generic framework describing and evaluating this communication method in Ubiquitous Computing. We prove the relevance of our approach by an open-source implementation of a low-cost object tag and a transceiver offering a high-quality communication link at typical distances up to 15 cm. Moreover, we present three case studies considering tangible interaction for the visually impaired, natural interaction with everyday objects, and sleeping behavior analysis.

Show publication details

Burkhardt, Dirk; Nazemi, Kawa; Klamm, Christopher; Kohlhammer, Jörn; Kuijper, Arjan

Comparison of e-Participation Roadmap in Industrial and Developing Countries based on Germany and Kenya

2014

Estevez, Elsa (Ed.) et al.: ICEGOV 2014 : Proceedings of the 8th International Conference on Theory and Practice of Electronic Governance. New York: ACM Press, 2014, pp. 399-402

International Conference on Theory and Practice of Electronic Governance (ICEGOV) <8, 2014, Guimaraes, Portugal>

This paper compares the E-Participation roadmaps of industrial and developing countries, based on Germany and Kenya as representatives. Therefore, the ICT roadmap of each country is de-scribed in a clear shape and with representative E-Participation projects of each country. Based on these projects, the comparison is performed on a categorical level in terms of (1) participation forms, (2) used ICT, and (3) socio-political requirements. After-wards, the results are summarized to determine an overall view on the E-Participation situation in both countries. As a result of the comparison similarities and significant differences will be identified. The results are useful for software developing organizations that want to create ICT governance tools for industrial as well as developing countries and therefore need to consider the characteristics and requirements of both country types.

Show publication details

Dolereit, Tim; Kuijper, Arjan

Converting Underwater Imaging into Imaging in Air

2014

Battiato, Sebastiano (Ed.) et al.: VISAPP 2014 - Volume I : Proceedings of the International Conference on Computer Vision Theory and Applications. SciTePress, 2014, pp. 96-103

International Conference on Computer Vision Theory and Applications (VISAPP) <9, 2014, Lisbon, Portugal>

The application of imaging devices in underwater environments has become a common practice. Protecting the camera's constituent electric parts against water leads to refractive effects emanating from the water-glassair transition of light rays. These non-linear distortions can not be modeled by the pinhole camera model. For our new approach we focus on flat interface systems. By handling refractive effects properly, we are able to convert the problem to imaging conditions in air. We show that based on the location of virtual object points in water, virtual parameters of a camera following the pinhole camera model can be computed per image ray. This enables us to image the same object as if it was situated in air. Our novel approach works for an arbitrary camera orientation to the refractive interface. We show experimentally that our adopted physical methods can be used for the computation of 3D object points by a stereo camera system with much higher precision than with a naive in-situ calibration.

Show publication details

Zander-Walz, Sebastian; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

Curved Large-Area Surfaces for Gestural Interaction

2014

Darmstadt, TU, Bachelor Thesis, 2014

Gestures are a natural and intuitive part of human communication. Since the appearance of smartphones and tablet computers, gestural interaction became suitable to many customers. Usually gesture interaction is implemented using two dimensional planar surfaces, although the natural movement of the human body results in elliptic or spherical paths. This thesis shows a way of equipping large-area curved surfaces with capacitive loading-mode proximity sensors and gesture recognition from theses sensors data. Therefore already existing techniques, wellknown from the use in planar system, were adapted to the use in curved prototypes. To prove the results both, the interaction with the prototype and the gesture recognition have been evaluated and the results discussed.

Show publication details

Liang, Rong-Hao; Chan, Liwei; Tseng, Hung-Yu; Kuo, Han-Chih; Huang, Da-Yuan; Yang, De-Nian; Chen, Bing-Yu; Große-Puppendahl, Tobias; Beck, Sebastian; Wilbers, Daniel; Kuijper, Arjan; Heo, Heejeong; Park, Hyungkun; Kim, Seungki; Chung, Jeeyong; Lee, Geehyuk; Lee, Woohun; Unander-Scharin, Carl; Unander-Scharin, Aasa; Höök, Kristina; Elblaus, Ludvig

Demo Hour

2014

Interactions, Vol.21 (2014), 5, pp.6-9

Conference on Human Factors in Computing Systems (CHI) <32, 2014, Toronto,Canada>

Interactivity is a unique forum of the ACM CHI Conference that showcases hands-on demonstrations, novel interactive technologies, and artistic installations. At CHI 2014, we aimed to create a "one of a CHInd" Interactivity experience with more than 60 interactive exhibits to highlight the diverse group of computer scientists, sociologists, designers, psychologists, artists, and many more that make up the CHI community.

Show publication details

Steiger, Martin; Lücke-Tieke, Hendrik; May, Thorsten; Kuijper, Arjan; Kohlhammer, Jörn

Deterministic Local Layouts through High-Dimensional Layout Stitching

2014

Kurosu, Masaaki (Ed.): Human-Computer Interaction: Part 1 : Theories, Methods, and Tools. HCI International 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8510), pp. 643-651

International Conference on Human-Computer Interaction (HCII) <16, 2014, Heraklion, Crete, Greece>

In this paper we present a layout technique for dynamic views of large static graphs. It aims to minimize changes between two consecutive frames and most importantly, it is deterministic. First, a set of small layout patches is pre-computed. Then, depending on the users view focus, a subset of these patches is selected and connected to generate the final layout. In contrast to the state-of-the-art approach that operates in the 2D screen space only, we perform this process in high-dimensional space before projecting the results into the 2D plane. This gives additional degrees of freedom and consequently a smoother transition process between two consecutive frames. Whenever the user visits an area of the graph for a second time, the layout will still look the same. This enables the user to recognize areas that have already been explored and thus preserve the mental map.

Show publication details

Thürck, Daniel; Widmer, Sven; Kuijper, Arjan; Goesele, Michael

Efficient Heuristic Adaptive Quadrature on GPUs: Design and Evaluation

2014

Wyrzykowski, Roman (Ed.) et al.: Parallel Processing and Applied Mathematics : 10th International Conference 2013. Revised Selected Papers, Part I. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8384), pp. 652-662

International Conference on Parallel Processing and Applied Mathematics (PPAM) <10, 2013, Warsaw, Poland>

Numerical integration is a common sub-problem in many applications. It can be solved easily in CPU-based applications using adaptive quadrature such as the adaptive Simpson's rule. These algorithms rely, however, on error estimation yielding a significant computational overhead. In addition, they require recursive function evaluations, which are not well suited for parallel computation on graphics processing units (GPUs) due to warp divergence issues. In this paper, we introduce heuristic forward quadrature as an alternative that is not only more efficient than traditional methods, but also better suited for accelerated massively-parallel calculation on GPUs. Additionally, we will give an error estimate for our method and demonstrate performance results for 1D and 2D integral applications which show that the algorithm leverages quadrature for the efficient implementation on GPUs.

Show publication details

Knuth, Martin; Altenhofen, Christian; Kuijper, Arjan; Bender, Jan

Efficient Self-Shadowing Using Image-Based Lighting on Glossy Surfaces

2014

Bender, Jan (Ed.) et al.: VMV 2014 : Vision, Modeling, and Visualization. Goslar: Eurographics Association, 2014, pp.159-166

Workshop on Vision, Modeling, and Visualization (VMV) <19, 2014, Darmstadt, Germany>

In this paper we present a novel natural illumination approach for real-time rasterization-based rendering with environment map-based high dynamic range lighting. Our approach allows to use all kinds of glossiness values for surfaces, ranging continuously from completely diffuse up to mirror-like glossiness. This is achieved by combining cosine-based diffuse, glossy and mirror reflection models in one single lighting model. We approximate this model by filter functions, which are applied to the environment map. This results in a fast, image-based lookup for the different glossiness values which gives our technique the high performance that is necessary for real-time rendering. In contrast to existing real-time rasterization-based natural illumination techniques, our method has the capability of handling high gloss surfaces with directional self-occlusion. While previous works exchange the environment map by virtual point light sources in the whole lighting and shadow computation, we keep the full image information of the environment map in the lighting process and only use virtual point light sources for the shadow computation. Our technique was developed for the usage in real-time virtual prototyping systems for garments since here typically a small scene is lit by a large environment which fulfills the requirements for imagebased lighting. In this application area high performance rendering techniques for dynamic scenes are essential since a physical simulation is usually running in parallel on the same machine. However, also other applications can benefit from our approach.

Show publication details

Eckeren, Katharina van; Kuijper, Arjan (Betreuer); Goesele, Michael (Betreuer); Tausch, Reimar (Betreuer)

Entwicklung und Evaluation eines 3D Object Retrieval Systems für digitalisierte Kulturobjekte

2014

Darmstadt, TU, Master Thesis, 2014

Diese Arbeit befasst sich mit dem Aufbau, der Entwicklung und der Auswertung eines 3D Object Retrieval-Systems zur Ähnlichkeitssuche von digitalisierten Kulturobjekten. Nach der Einordnung und Vorstellung des verwendeten Beschreibungsverfahrens für 3D Objekte, namens 3D Histogram of Oriented Gradients (Abk. 3D-HOG) [1][2], in den Kontext des aktuellen State-of-the-Art erfolgt eine Erläuterung jeder verwendeten Komponente des Systems. Neben der ausführlichen Erklärung der Funktionsweise von 3D-HOG und seinen Stärken und Schwächen wurde für seine Auswertung eine Datengrundlage, bestehend aus 3D Kulturobjekten mit einer sehr hohen Polygonnetzauflösung, erstellt. Die Auswertung betrachtet verschiedene Parameterangaben und benutzt zur anfänglichen Bewertung das Maß der R-Precision [3]. Durch die Anpassung der Blocknormalisierung, der Zellenanzahl und der Gradientenfeldgröße, die drei wichtigsten Parameter des 3D-HOG Verfahrens, konnte die R-Precision von 0.799 auf 0.888 verbessert werden. Außerdem zeigte sich, dass die Polygonnetzauflösung der Objekte von sekundärer Bedeutung ist, da sie kaum einen Einfluss auf die Ergebnisse der gewählten Beschreibungsverfahren hat.

Show publication details

Steiger, Martin; Hutter, Marco; Schader, Philipp; Kohlhammer, Jörn; Kuijper, Arjan

Exploring Simulation in Sensor Network Models

2014

Bender, Jan (Ed.) et al.: VMV 2014 : Vision, Modeling, and Visualization. Goslar: Eurographics Association, 2014, pp. 135-142

Workshop on Vision, Modeling, and Visualization (VMV) <19, 2014, Darmstadt, Germany>

Simulation is an important measure to estimate different properties of a planned network such as throughput and cost. However, many parameters need to be adjusted to approximate real-world conditions properly. In this paper we present a visualization system that visually supports and guides the analysis of (physical) network simulation problems. Automatic optimizers run as a black box giving an (locally) optimal result in terms of the underlying simulation model and parameter configuration. This is often not ideal for practical usage. Our system assists the user in the process of comparing different simulations to quickly achieve the optimal configuration in terms of user preference. It highlights differences between simulation runs and indicates which parameter modification leads to the best improvement. We expect that this results in large time savings for the domain expert while configuring the simulation system.

Show publication details

Burkhardt, Dirk; Nazemi, Kawa; Zilke, Jan Ruben; Kohlhammer, Jörn; Kuijper, Arjan

Fundamental Aspects for E-Government

2014

Sonntagbauer, Peter et al.: Handbook of Research on Advanced ICT Integration for Governance and Policy Modeling. Hershey, Pennsylvania: IGI Global, 2014, pp. 1-18

The upcoming initiatives using ICT in the government process should strengthen the benefit of E-Government in most countries. Since E-Government among other e-related terms is a widely (interpreted) term, it is sometimes challenging to understand the objective and goals of an initiative. Therefore in this paper we introduce and explain the most E-Government related terms. Even more, we outline some interesting initiatives and implementations to explain the benefits of using ICT in the government domain. So next to the term description, concrete activities will be aligned to the terms to explain the practical use in a better way. We conclude with several challenges that arise when thinking of the implementation of E-Government services. Overall this chapter should give a good overall view about E-Government and the relating issues.

Show publication details

Yoon, Sang Min; Graf, Holger; Kuijper, Arjan

Hierarchical Image Representation using 3D Camera Geometry for Content-based Image Retrieval

2014

Engineering Applications of Artificial Intelligence, Vol.30 (2014), pp. 235-241

In this paper we present a hierarchical image representation methodology by clustering images with 3D camera geometry in order to efficiently retrieve the images according to user's viewpoint. The framework of our proposed technique is composed of two steps: first the visual correlation analysis between images in a large database is determined by the estimated 3D camera geometry and second images are classified using a constrained agglomerative hierarchical image clustering method to retrieve the images the users search. The constrained agglomerative hierarchical image clustering method provides balanced hierarchical layers, independent of the number of images within the cluster. It also provides a convenient way to browsing, navigating, and categorizing of the images with various viewpoints, illumination, and partial occlusion.

Show publication details

Förster, Tim; Thum, Simon (Betreuer); Kuijper, Arjan (Betreuer)

Hochverfügbarkeit (Analytisch) von Big-Geo-Data als Platform as a Service

2014

Darmstadt, TU, Bachelor Thesis, 2014

Es gibt stetig wachsende Herausforderungen in der Entwicklung von Geodaten. Die Datenzunahme steigt kontinuierlich. Durch den starken Anstieg dieser Informationsansammlungen wird immer mehr Datenspeicher benötigt. Des Weiteren sollen die Systeme eine hohe Verfügbarkeit aufweisen und unter Last eine akzeptable Reaktionszeit liefern. Die Erfüllung solcher Anforderung lassen sich nur begrenzt mit einem einfachen Client/Server-System realisieren, da diese nicht gut skalieren und unter schlechten Bedingungen langsam agieren. Daher werden immer mehr Applikationen in der Cloud als Service bereitgestellt. Dies bringt viele Vorteile; unter anderem die Verbesserung der Verfügbar- und Skalierbarkeit des Services. In dieser Arbeit wird anhand eines existierenden Server-Systems die Designentscheidungen gezeigt, die für eine Realisierung des Produktes in der Cloud notwendig sind. Dieses Produkt wird dann als "Platform as a Service" bereitgestellt. Dabei werden Punkte wie, Persistierung im verteilten System und Cloud-API Gestaltung besprochen. Anschließend wird dies in einem verteilten System getestet und gegenüber ein einfaches Client/Server-System verglichen. Ebenfalls wird ein Model vorgestellt, womit die Verfügbarkeit des Systems kalkuliert wird.

Show publication details

Herrmann, Daniel; Turba, Martin; Kuijper, Arjan; Schweizer, Immanuel

Inbound Interdomain Traffic Engineering with LISP

2014

Aschenbruck, Nils (Ed.) et al.: Proceedings of the 39th Annual IEEE Conference on Local Computer Networks : LCN 2014. New York: IEEE, Inc., 2014, pp. 458-461

Annual IEEE Conference on Local Computer Networks (LCN) <39, 2014, Edmonton, Canada>

Stub autonomous systems usually utilize multiple links to single or multiple ISPs. Today, inbound traffic engineering is considered hard, as there is no direct way to influence routing decisions on remote systems with BGP. Current traffic engineering methods built on top of BGP are heuristic and time-consuming. The Locator/Identifier Separation Protocol (LISP) promises to change that. In this paper, we conduct the first comprehensive evaluation of LISP and its built-in traffic engineering methods on a real-world testbed. First, we compare LISP to plain BGP and BGP advertising more specific prefixes. This comparison shows that LISP allows effective load-balancing with an accuracy of approximately 5%, while being easier to configure than BGP and its variants. Further experiments show that these results are independent from the number of concurrent streams.

Show publication details

Landesberger, Tatiana von; Fiebig, Sebastian; Bremm, Sebastian; Kuijper, Arjan; Fellner, Dieter W.

Interaction Taxonomy for Tracking of User Actions in Visual Analytics Applications

2014

Huang, Weidong (Ed.): Handbook of Human Centric Visualization. Berlin, Heidelberg, New York: Springer, 2014, pp. 653-670

In various application areas (social science, transportation, or medicine) analysts need to gain knowledge from large amounts of data. This analysis is often supported by interactive Visual Analytics tools that combine automatic analysis with interactive visualization. Such a data analysis process is not streamlined, but consists of several steps and feedback loops. In order to be able to optimize the process, identify problems, or common problem solving strategies, recording and reproducibility of this process is needed. This is facilitated by tracking of user actions categorized according to taxonomy of interactions. Visual Analytics includes several means of interaction that are differentiated according to three fields: information visualization, reasoning, and data processing. At present, however, only separate taxonomies for interaction techniques exist in these three fields. Each taxonomy covers only a part of the actions undertaken in Visual Analytics. Moreover, as they use different foundations (user intentions vs. user actions) and employ different terminology, it is not clear to what extent they overlap and cover the whole Visual Analytics interaction space. We therefore first compare them and then elaborate a new integrated taxonomy in the context of Visual Analytics. In order to show the usability of the new taxonomy, we specify it on visual graph analysis and apply it to the tracking of user interactions in this area.

Show publication details

Maus, Steffen; Kuijper, Arjan (Betreuer); Rus, Silvia (Betreuer)

Klassifizierung von Liegepositionen mittels kapazitiver Näherungssensorik

2014

Darmstadt, TU, Bachelor Thesis, 2014

In den vergangenen Jahren hat die Verwendung von kapazitiver Sensorik in kleinen elektronischen Endgeräten stark zugenommen, zudem spielt sie auch bei Ubiquitous Computing immer mehr eine bedeutende Rolle. Im Bezug auf die Reichweite der Sensorik ist es mittlerweile möglich, auf Objekte in einer Entfernung von bis zu 50 cm zu reagieren. Diese Bachelorarbeit behandelt die Klassifizierung von Liegepositionen mittels kapazitiver Sensorik. Das Hauptaugenmerk liegt dabei auf Anwendungsfällen aus der Medizin und der Analyse, wie zuverlässig ein solches System die Liegepositionen von Patienten erkennt. Zum Erlangen der Rohdaten befindet sich auf der Matratze Bettlaken mit einem groben Gitter aus Elektroden, wodurch an jedem Schnittpunkt des Gitters ein kapazitiver Wert gemessen werden kann. Die Rohdaten aus diesem Versuchsaufbau werden zur Klassifizierung der Liegeposition verwendet.

Show publication details

Lerch, Patrick; Landesberger, Tatiana von (Betreuer); Kuijper, Arjan (Betreuer)

Layoutalgorithmus für Visualisierung von Mustern in Ausfalleffektgraphen

2014

Darmstadt, TU, Bachelor Thesis, 2014

Heutzutage werden immer mehr und größere Datenmengen abgespeichert und verarbeitet. Abhängigkeiten zwischen diesen Daten können durch gerichtete Graphen visualisieren werden. Mit Hilfe von Graphen besteht die Möglichkeit, Ausfallsimulationen für einzelne Knoten durchzuführen, um den Dominoeffekt, der durch den Ausfall dieses einen Knotens entsteht, abzuschätzen. Durch solch eine Simulation entsteht der Ausfalleffektgraph, welcher sich besonders gut in einem hierarchischen Layout darstellen lässt. Die ordentliche Darstellung eines solchen gerichteten hierarchischen Graphen erfordert einen guten Algorithmus zur Minimierung der Kantenkreuzungen. Mit beispielsweise der Barycenter, Median oder Sifting Heuristik existieren für dieses Problem schon eine große Vielzahl an unterschiedlichsten Algorithmen. Jedoch spezialisiert sich noch keiner dieser Verfahren auf das planare Darstellen einzelner Blöcke, Subgraphen oder Muster bei der Kantenkreuzungsreduktion. Diese Arbeit adressiert genau dieses Problem. Hauptkriterium dieser Thesis ist vorher definierte Subgraphen, Blöcke oder Muster bei der Minimierung der Kantenkreuzungen zu präferieren und trotzdem noch die Anzahl an Kantenkreuzungen im Gesamtgraphen minimal zu halten.

Show publication details

Puhl, Julian; Kuijper, Arjan (Betreuer); Knuth, Martin (Betreuer)

Materialsysteme für das realistische Echtzeit-Rendering von Szenen in Anwesenheit von Flüssigkeitssimulationen und Image-Based Lighting

2014

Darmstadt, TU, Bachelor Thesis, 2014

Für eine Simulation einer Flüssigkeit in Echtzeit werden aktuell Verfahren angewandt, die entweder das Modell diskretisieren und somit gitterbasiert arbeiten oder die einzelnen Atome zu größeren Partikeln zusammenfassen und so das Verhalten simulieren. Beiden Ansätzen ist gemein, dass als Ergebnis keine glatte Oberfläche vorliegt, sondern eine angenäherte, die uneben ist, aus vielen einzelnen Elementen besteht und zudem keine optischen Eigenschaften einer Flüssigkeit besitzt. Aus Zeitgründen darf die nachfolgende Generierung der Oberfläche nicht sehr zeitaufwendig sein. Aus diesem Grund wird in dieser Arbeit die Nachbearbeitung der Daten via Bildverarbeitung unter der Anwendung von Glättungsfiltern sowie einer Bildpyramide untersucht. Die Pyramide bietet Zugriff auf verschiedene Detailstufen. Hierdurch können unterschiedliche Glättungen in Abhängigkeit von der Entfernung zum Betrachter gewählt werden. Viele Verfahren filtern hier sehr stark und fügen nachträglich wieder ein Rauschen ein, um eine nicht ganz so glatte Oberfläche zu simulieren. In Szenen, bei denen die simulierte Flüssigkeit seitlich betrachtet wird, können sowohl nahe als auch weiter entfernte Partikel nahe beieinander existieren. Hier spielt das Verfahren seine Stärke aus gleichzeitig auf unterschiedlich stark gefilterte Werte zugreifen zu können.

Show publication details

Nazemi, Kawa; Kuijper, Arjan; Hutter, Marco; Kohlhammer, Jörn; Fellner, Dieter W.

Measuring Context Relevance for Adaptive Semantics Visualizations

2014

Lindstaedt, Stefanie (Ed.) et al.: i-KNOW 2014 : Proceedings of the 14th International Conference on Knowledge Technologies and Data-driven Business. New York: ACM, 2014. (ACM International Conference Proceedings Series 889), Article 14, 8 p.

International Conference on Knowledge Technologies and Data-driven Business (I-KNOW) <14, 2014, Graz, Austria>

Semantics visualizations enable the acquisition of information to amplify the acquisition of knowledge. The dramatic increase of semantics in form of Linked Data and Linked-Open Data yield search databases that allow to visualize the entire context of search results. The visualization of this semantic context enables one to gather more information at once, but the complex structures may as well confuse and frustrate users. To overcome the problems, adaptive visualizations already provide some useful methods to adapt the visualization on users' demands and skills. Although these methods are very promising, these systems do not investigate the relevance of semantic neighboring entities that commonly build most information value. We introduce two new measurements for the relevance of neighboring entities: The Inverse Instance Frequency allows weighting the relevance of semantic concepts based on the number of their instances. The Direct Relation Frequency inverse Relations Frequency measures the relevance of neighboring instances by the type of semantic relations. Both measurements provide a weighting of neighboring entities of a selected semantic instance, and enable an adaptation of retinal variables for the visualized graph. The algorithms can easily be integrated into adaptive visualizations and enhance them with the relevance measurement of neighboring semantic entities. We give a detailed description of the algorithms to enable a replication for the adaptive and semantics visualization community. With our method, one can now easily derive the relevance of neighboring semantic entities of selected instances, and thus gain more information at once, without confusing and frustrating users.

Show publication details

Hutter, Marco; Knuth, Martin; Kuijper, Arjan

Mesh Partitioning for Parallel Garment Simulation

2014

Skala, Vaclav (Ed.): WSCG 2014. Communication Papers Proceedings : 22nd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. Plzen: University of West Bohemia, 2014, pp. 125-133

International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) <22, 2014, Plzen, Czech Republic>

We present a method for partitioning meshes that allows a simple and efficient parallel implementation of different simulation methods. It is based on a generalization of the concept of independent sets from graph theory to sets of simulation elements. The general description makes it versatile and flexibly applicable in existing simulation systems. Every simulation method that formerly worked by sequentially processing a set of simulation elements can now be parallelized by partitioning the underlying set, without affecting the behavior of the simulated model.

Show publication details

Kopp, Manuel Georg Maria; Kuijper, Arjan (Betreuer); Bremm, Sebastian (Betreuer); Landesberger, Tatiana von (Betreuer)

Methoden und visuell interaktive Werkzeuge zur automatischen Generierung von Graphen mit geografischem Bezug

2014

Darmstadt, TU, Master Thesis, 2014

Analyse oder Simulation von Zuliefernetzwerken werden oftmals durch grafische Darstellungen unterstützt. Dafür werden die Erstellung der Lieferstrukturen sowie die GEO-Position der einzelnen Lieferanten benötigt. Die Generierung der zugehörigen Graphen mit geografischem Bezug sollte nach Möglichkeit weitestgehend automatisiert erfolgen. Eine automatisierte Verortung steht Graphengeneratoren derzeit nicht zur Verfügung. Es kann daher sehr zeitaufwändig sein, wenn die Verortung eines Knotens verändert wird. Bei den aktuellen Verfahren müssen alle mit diesem Knoten verbundenen Knoten manuell auf ihre Lokalisation überprüft und ggf. manuell angepasst werden. In dieser Arbeit wird ein Weg aufgezeigt Graphen mit geografischem Bezug zu generieren, um diese manuellen Überprüfungen und Anpassungen zu automatisieren. Um dies zu erreichen wurde eine Datenbasis aus öffentlich zugänglichen Daten generiert. Diese beinhaltet eine politisch basierte hierarchische Aufteilung der Welt, aus der generierte Knoten automatisch verortet werden. Darüber hinaus wurden Regeln definiert, um statische Beziehungseigenschaften von Knoten zu ersetzen. Auf diese Weise werden Struktur-, Knoten- oder Kanteneigenschaften des zu erstellenden Graphen mit geografischem Bezug festgelegt. Die Regeln können interaktiv unter Verwendung einer Visualisierung manipuliert werden. Dadurch ist es möglich generisch verschiedene Graphen mit geografischem Bezug ohne großen Aufwand zu erstellen. Den Abschluss bildet ein Beispielszenario, dass unter Verwendung einiger der Regeln mehrere Graphen mit geografischem Bezug generiert. Anschließend werden diese zu einem Gesamtgraphen zusammengefasst um das gesamte Szenario darzustellen.

Show publication details

Ackermann, Jens; Langguth, Fabian; Fuhrmann, Simon; Kuijper, Arjan; Goesele, Michael

Multi-View Photometric Stereo by Example

2014

3DV 2014 - Volume I : 2014 International Conference on 3D Vision. Los Alamitos, Calif.: IEEE Computer Society, 2014, pp. 259-266

International Conference on 3D Vision (3DV) <2, 2014, Tokyo, Japan>

We present a novel multi-view photometric stereo technique that recovers the surface of textureless objects with unknown BRDF and lighting. The camera and light positions are allowed to vary freely and change in each image. We exploit orientation consistency between the target and an example object to develop a consistency measure. Motivated by the fact that normals can be recovered more reliably than depth, we represent our surface as both a depth map and a normal map. These maps are jointly optimized and allow us to formulate constraints on depth that take surface orientation into account. Our technique does not require the visual hull or stereo reconstructions for bootstrapping and solely exploits image intensities without the need for radiometric camera calibration. We present results on real objects with varying degree of specularity and show that these can be used to create globally consistent models from multiple views.

Show publication details

Fraissinet-Tachet, Matthieu; Kuijper, Arjan (Betreuer); Schmitt, Michael (Betreuer)

Mutual Information-Based Piecewise Planar Object Tracking

2014

Darmstadt, TU, Master Thesis, 2014

This master thesis deals with a template based tracking algorithm for piecewise planar objects. It is robust against changes in the appearance of the object (occlusion, illumination variation, specularities). The version that we propose supports multiple cameras. The method consists in minimizing the error between the observed images of the object and the warped images of the planes. We use for that an estimation of the pose of the object, which is to say a rigid 3D transformation. The robustness is obtained by using the mutual information as registration function. The main drawback of the mutual information is that it has a high computation complexity. We use an inverse composition approach for the warp update, so that pre-computations can be done and it decreases the complexity of the algorithm. We develop a way of computing the warp update and analyse the impact of this initiative on the optimization process. We also determine the optimal parameters for running the algorithms.

Show publication details

Butt, Moazzam; Henniger, Olaf; Nouak, Alexander; Kuijper, Arjan

Privacy Protection of Biometric Templates

2014

Stephanidis, Constantine (Ed.): HCI International 2014 - Posters' Extended Abstracts. Proceedings Part I : HCI International 2014. Berlin, Heidelberg, New York: Springer, 2014. (Communications in Computer and Information Science (CCIS) 434), pp. 153-158

International Conference on Human-Computer Interaction (HCII) <16, 2014, Heraklion, Crete, Greece>

Although many biometric characteristics are not secrets, biometric reference data (also known as biometric templates) need to be stored securely and to be protected against unauthorized use. For this purpose, biometric template protection techniques have been developed that do not only prevent privacy leakage and provide confidentiality of the stored biometric templates, but address also problems like identity theft and cross-matching of biometric templates stored in different systems. This paper describes the security and privacy risks associated with storing biometric data and highlights the necessity of using biometric template protection as a potential remedy to these risks. Privacy considerations are discussed with respect to using fingerprint verification for access control to a public outdoor swimming pool.

Show publication details

Rus, Silvia; Große-Puppendahl, Tobias; Kuijper, Arjan

Recognition of Bed Postures Using Mutual Capacitance Sensing

2014

Aarts, Emile (Ed.) et al.: Ambient Intelligence : European Conference, AmI 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8850), pp. 51-66

European Conference on Ambient Intelligence (AmI) <11, 2014, Eindhoven, The Netherlands>

In recent years, mutual capacitive sensing made significant advances in the field of gathering implicit contextual data. These systems find broad usage in pervasive activity-recognition systems, installed stationary or made portable. In the domain of context recognition new ways of interaction with the environment opened up since conductive objects can be detected under certain conditions at distances up to 50 cm. This paper investigates an approach to recognize bed postures using mutual capacitance sensing. The overall goal is to develop a technological concept that can be applied to recognize bed postures of patients in elderly homes. The use of this contextual data may lead to many desired benefits in elderly care e.g. the better prevention of decubitus ulcer, a condition caused by prolonged pressure on the skin resulting in injuries to skin and underlying tissues. For this, we propose a low-cost grid of crossed wires of 48 measurement points placed between the mattress and the bed sheet. The experimental results analyze a set of five lying positions. We achieved for all tested individuals an accuracy of 80.76% and for several individuals of the same bodysize an accuracy of 93.8%.

Show publication details

Prediger, Mark; Braun, Andreas; Marinc, Alexander; Kuijper, Arjan

Robot-Supported Pointing Interaction for Intelligent Environments

2014

Streitz, Norbert (Ed.) et al.: Distributed, Ambient, and Pervasive Interactions : DAPI 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8530), pp. 172-183

International Conference on Distributed, Ambient and Pervasive Interactions (DAPI) <2, 2014, Heraklion, Crete, Greece>

A natural interaction with appliances in smart environment is a highly desired form of controlling the surroundings using intuitively learned interpersonal means of communication. Hand and arm gestures, recognized by depth cameras, are a popular representative of this interaction paradigm. However they usually require stationary units that limit applicability in larger environments. To overcome this problem we are introducing a self-localizing mobile robot system that autonomously follows the user in the environment, in order to recognize performed gestures independent from the current user position. We have realized a prototypical implementation using a custom robot platform and evaluated the system with various users.

Show publication details

Eicke, Tim Nicolas; Jung, Yvonne; Kuijper, Arjan

Robust Real-Time Shadows for Dynamic 3D Scenes on the Web

2014

Stephanidis, Constantine (Ed.): HCI International 2014 - Posters' Extended Abstracts. Proceedings Part I : HCI International 2014. Berlin, Heidelberg, New York: Springer, 2014. (Communications in Computer and Information Science (CCIS) 434), pp. 574-578

International Conference on Human-Computer Interaction (HCII) <16, 2014, Heraklion, Crete, Greece>

The authentic display of shadows by modern video games has long become a matter of course. On the web however, this is somewhat different: the rendering of three dimensional scenes in the browser has only in recent years been on the rise. At best, shadows have only played a minor part in that development, despite their importance regarding recognition of spacial relationships in human vision and general increase of a scene's authenticity. An important part in the development of web-based 3D is played by the open-source JavaScript framework X3DOM, as it provides an approach for the integration of declarative 3D in HTML5. However the framework too only offers rudimentary shadow rendering techniques that hardly meet today's demands. This work tackles this issue by first examining existing shadow mapping techniques for their suitability in the web context and based on that developing and implementing a concept for the enhancement of shadow display in X3DOM.

Show publication details

Stein, Christian; Limper, Max; Kuijper, Arjan

Spatial Data Structures for Accelerated 3D Visibility Computation to Enable Large Model Visualization on the Web.

2014

Polys, Nicholas F. (General Chair) et al.: Proceedings Web3D 2014 : 19th International Conference on 3D Web Technology. New York: ACM, 2014, pp. 53-61

International Conference on 3D Web Technology (WEB3D) <19, 2014, Vancouver, BC, Canada>

The visualization of massive 3D models is an intensively examined field of research. Due to their rapidly growing complexity of such models, visualisation them in real-time will never be possible through a higher speed of rasterization alone. Instead, a practical solution has to reduce the amount of data to be processed, using a fast visibility determination. In recent years, the combination of Javascript and WebGL raised attention for the possibility of rendering hardware-accelerated 3D graphics directly in the browser. However, when compared to desktop applications, they are still fighting with their disadvantages of a generally slower execution speed, or a downgraded set of functionality. We demonstrate the integration of spatial data structures, computed on the client side, using latest technology trends to mitigate the shortcomings of the 3D Web environment. We employ comparably small bounding volume hierarchies to accelerate our visibility determination, as well as to enable specific culling techniques. This allows for an interactive visualization of such massive 3D data sets. Our in-depth analysis of different data structures and environments shows which combination of data structure and visibility determination techniques are currently the best fit for the Web.

Show publication details

Ettl, Anne-Sophie; Kuijper, Arjan

Text and Image Area Classification in Mobile Scanned Digitised Documents

2014

International Journal of Applied Pattern Recognition, Vol.1 (2014), 2, pp.173-198

Post processing and automatic interpretation of images plays an increasingly important role in the mobile area. Both for the efficient compression and for the automatic evaluation of text, it is useful to store text content as textual information rather than as graphics information. For this purpose pictures from magazines are recorded with the camera of a smartphone and classified according to text and image areas. In this work established desktop procedures are presented and analysed in terms of their applications on mobile devices. Based on these methods, an approach for image segmentation and classification on mobile devices is developed, taking into account the limited resources of these mobile devices.

Show publication details

Aderhold, Andreas; Wilkosinska, Katarzyna; Corsini, Massimiliano; Jung, Yvonne; Graf, Holger; Kuijper, Arjan

The Common Implementation Framework as Service - Towards Novel Applications for Streamlined Presentation of 3D Content on the Web

2014

Marcus, Aaron (Ed.): Design, User Experience, and Usability. Proceedings Part II : User Experience Design for Diverse Interaction Platforms and Environments. DUXU 2014. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8518), pp. 3-14

International Conference on Design, User Experience and Usability (DUXU) <3, 2014, Heraklion, Crete, Greece>

We solve a standing issue of the recently published Common Implementation Framework (CIF) for Online Virtual Museums: programmatic access to the transcoding, optimization and template rendering infrastructure of the CIF. We propose a method that enables researchers and developers to build novel systems on top of the CIF infrastructure beyond its current Cultural Heritage workflow. Therefore, we introduce a way to programmatically access the powerful backend of the CIF through a universal access layer, addressable by standards like HTTP and the JSON Data Interchange Format. In order to demonstrate our approach, we present two different use cases in which the CIF pipeline is utilized as a service through the proposed resource-based access layer: a native mobile iOS application for browsing 3D model repositories realizing just-in-time optimization of large models, and a MeshLab plugin to asynchronously convert and prepare a model for the Web.

Show publication details

Braun, Andreas; Schmidt, Sönke; Kuijper, Arjan; Neumann, Stephan; Wichert, Reiner

Towards Interactive Car Interiors - the Active Armrest

2014

ACM SIGCHI: NordiCHI '14 : Proceedings of the 8th Nordic Conference on Human-Computer Interaction: Fun, Fast, Foundational. New York: ACM, 2014, pp. 911-914

Nordic Conference on Human-Computer Interaction (NordiCHI) <8, 2014, Helsinki, Finland>

Modern cars are often equipped with touch-based interaction systems, such as touchscreens or touchpads. However, they are typically exposed within the car environment. In this paper, we present the Active Armrest. This regular car armrest is equipped with capacitive proximity sensors that combine limb detection and recognition of gestures. The sensors are designed for invisible integration into existing environments and can be used to create interactive surfaces in a car. We investigate two different types of gestural interaction, touch gestures with the arm lifted and free-air finger gestures performed above the interactive area, while the arm stays on the armrest. The system was integrated into a prototype and tested for gesture recognition precision and usability.

Show publication details

Krepp, Stefan; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

Unsichtbare Erkennung von Berührungen über akustisches Tracking

2014

Darmstadt, TU, Master Thesis, 2014

Die unsichtbare Integration von Eingabegeräten in die natürliche Umgebung der Nutzer ist eine große Herausforderung, die allerdings große Chancen bietet. Allgegenwärtige Eingabegeräte besitzen das Potential gewohnte Interaktionsmuster zu durchbrechen. Eingabegeräte wie klassische Fernbedienungen für Fernseher könnten bald der Vergangenheit angehören. Ein Türöffner für unsichtbare Benutzerschnittstellen sind akustische Sensoren, die sich kostengünstig und einfach installieren lassen und fast jede Oberfläche zu einem Eingabegerät machen können. In dieser Arbeit wurde ein akustisches Berührungserkennungssystem entwickelt, das die Erkennung und Unterscheidung verschiedener Impact-Gesten und Wischgesten ermöglicht und sich unsichtbar in bestehende Möbel integriert. Dabei wurde ein bestehender Ansatz erweitert. Erste Nutzerstudien unterstreichen die Machbarkeit des verfolgten Ansatzes. Zudem konnte gezeigt werden, dass akustische Berührungserkennung einen Mehrwert für andere Technologien bedeuten kann. So konnte gezeigt werden, dass die Interaktionsgeschwindigkeit eines kapazitiven Gestenerkennungssystems durch die Integration akustischer Berührungserkennung erhöht werden kann.

Show publication details

Gottschämmer, Patrick; Große-Puppendahl, Tobias (Betreuer); Kuijper, Arjan (Betreuer)

User Location Modeling Based on Heterogeneous Data Sources

2014

Darmstadt, TU, Bachelor Thesis, 2014

Over the past decade, interest in home automation systems constantly grew. Especially in the daily life with the connection of intelligent everyday devices through the Internet of Things. To allow automatic actions on these devices, user localization systems have become a major input modality for smart home systems. The location of a user (or rather a subject) can be determined by different localization techniques, such as sensitive floor systems, discrete activity sensors like light switches or RSSI-based WLAN/Bluetooth beacons (e.g. smartphones). These heterogeneous data sources provide various means of user location certainty, the ability to identify a user or the ability to recognize multiple subjects in the same location. In order to achieve a higher grade of accuracy, multiple data sources can be combined by location fusioning algorithms. However, to allow the integration of such algorithms on hardware independent basis, a common user location model is needed, which can represent all important aspects of these localization techniques. Furthermore, the overall system needs to be easily extendable with new methods of localization. This Bachelor thesis will investigate the concepts of existing user localization systems as well as develop a new model to represent the location of subjects based on already existing location models. A reference implementation will be provided based on Eclipse SmartHome, an open source building automation framework. The implementation integrates multiple data sources within the Living Lab of Fraunhofer IGD, in particular a capacitive localization system, intelligent light switches and WLAN beacons. Furthermore, a simple location fusioning algorithm will be presented based on the implemented user location model as a proof of concept.

Show publication details

Nazemi, Kawa; Retz, Wilhelm; Kohlhammer, Jörn; Kuijper, Arjan

User Similarity and Deviation Analysis for Adaptive Visualizations

2014

Yamamoto, Sakae (Ed.): Human Interface and the Management of Information. Proceedings Part I : Information and Interaction for Learning, Culture, Collaboration and Business.. Berlin, Heidelberg, New York: Springer, 2014. (Lecture Notes in Computer Science (LNCS) 8521), pp. 64-75

International Conference on Human Interface and the Management of Information (HIMI) <2014, Heraklion, Crete, Greece>

Adaptive visualizations support users in information acquisition and exploration and therewith in human access of data. Their adaptation effect is often based on approaches that require the training by an expert. Further the effects often aim to support just the individual aptitudes. This paper introduces an approach for modeling a canonical user that makes the predefined training-files dispensable and enables an adaptation of visualizations for the majority of users. With the introduced user deviation algorithm, the behavior of individuals can be compared to the average user behavior represented in the canonical user model to identify behavioral anomalies. The further introduced similarity measurements allow to cluster similar deviated behavioral patterns as groups and provide them effective visual adaptations.

Show publication details

Kirchbuchner, Florian; Kuijper, Arjan (Betreuer); Große-Puppendahl, Tobias (Betreuer)

User Tracking and Behavior Recognition Based on a Capacitive Indoor Localization System

2014

Darmstadt, TU, Master Thesis, 2014

This thesis focused on tracking and analyzing the behavior of elderly people by using in-home monitoring systems. The goal was to add a localization component to an existing system for fall detection as well as to assess the elderly's acceptance of such systems and the corresponding loss of privacy. Therefore, this thesis analyzed the demands on monitoring and technical assistance systems and discussed different models of acceptance measuring. Furthermore, existing approaches to user tracking and behavior analysis are examined. On this basis, an implementation of the tracking functionality, based on a capacitive sensor system, was proposed and evaluated. In addition, a survey among elderly people was conducted by the author and the results are presented in detail. The findings of this thesis showed that capacitive sensing in combination with particle filtering was suitable for user tracking. Moreover, the results of the study emphasized that senior citizens were indeed willing to accept a certain loss of privacy but distinguished between different services and systems. It was also shown that the capacitive system used for this study was received positively in comparison to other systems.

Show publication details

Bernard, Jürgen; Sessler, David; Ruppert, Tobias; Davey, James; Kuijper, Arjan; Kohlhammer, Jörn

User-Based Visual-Interactive Similarity Definition for Mixed Data Objects - Concept and First Implementation

2014

Skala, Vaclav (Ed.): WSCG 2014. Communication Papers Proceedings : 22nd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. Plzen: University of West Bohemia, 2014, pp. 329-338

International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) <22, 2014, Plzen, Czech Republic>

The definition of similarity between data objects plays a key role in many analytical systems. The process of similarity definition comprises several challenges as three main problems occur: different stakeholders, mixed data, and changing requirements. Firstly, in many applications the developers of the analytical system (data scientists) model the similarity, while the users (domain experts) have distinct (mental) similarity notions. Secondly, the definition of similarity for mixed data types is challenging. Thirdly, many systems use static similarity models that cannot adapt to changing data or user needs. We present a concept for the development of systems that support the visual-interactive similarity definition for mixed data objects emphasizing 15 crucial steps. For each step different design considerations and implementation variants are presented, revealing a large design space. Moreover, we present a first implementation of our concept, enabling domain experts to express mental similarity notions through a visual-interactive system. The provided implementation tackles the different-stakeholders problem, the mixed data problem, and the changing requirements problem. The implementation is not limited to a specific mixed data set. However, we show the applicability of our implementation in a case study where a functional similarity model is trained for countries as objects.

Show publication details

Sessler, David; Kuijper, Arjan (Betreuer); Bernard, Jürgen (Betreuer)

User-centered Interactive Similarity Definition for Complex Data Objects

2014

Darmstadt, TU, Bachelor Thesis, 2014

The definition of similarity between data objects plays a key role for the applicability of many analytical systems. Similarity measures are used for prominent data analysis tasks like nearest neighbor search, clustering, or pattern recognition. These tasks are applied in many scientific domains like Information Retrieval, Data Mining, Machine Learning, Information Visualization and Visual Analytics. The data used for the calculation of similarity can either be of uniform attribute type (like numerical, ordinal, categorical or binary) or consist of combinations thereof (mixed data). The process of similarity definition comprises several challenges which I aim to tackle in this work. To start with, in many applications the developers (data experts) of the analytical system are not necessarily the users (domain experts) of the system. A problem arises, because data experts implement the functional similarity specification for domain experts. The functional similarity specification, however, should reflect the similarity notion in the minds of domain experts. Therefore the domain experts should be involved in the similarity generation process. The second challenge refers to the similarity definition for mixed data. A variety of similarity definitions for numerical, categorical or binary data exist. However, the similarity definition based on mixed data is cumbersome because of the complexity of the data. Finally, there are two possibilities when the similarity can be defined, namely at compile time or at run time. Today, many analytical systems define the similarity at compile time. However, the similarity notion of domain experts or the data set may vary over time. This would require a new specification of the functional similarity and a new compilation of the system. The definition of similarity at run time would solve this problem. I present a visual-interactive system that enables domain experts to define a similarity measure that reflects their similarity notion. The system is applicable for mixed data sets. Domain experts can align objects in a visual interface to generate feedback. Dynamic recalculation of the functional similarity specification allows to match the similarity notion of domain expert at run time. This way the functional similarity specification can be adjusted at any time. Further, I provide a visual-interactive mode which enables the data expert to explore the similarity definition process of the domain expert. In addition, I evaluate the system to assess the quality of the similarity concept as well as the feedback generation process. The results of the evaluation illustrate both: the validity of my solution as well as extension possibilities depending on the complexity of the given user feedback. In two case studies I show the applicability of the system. Both use cases show that the 'mental' similarity notion of users can be captured by the similarity concept. The results of the evaluation and the observations made in the case studies can be applied to improve the system or be used as a baseline for future approaches for user-centered interactive similarity definition for complex data objects.

Show publication details

Kühnel, Hannes; Kuijper, Arjan (Betreuer); Maier, Sebastian (Betreuer); May, Thorsten (Betreuer)

Visual Interactive Process Monitoring

2014

Darmstadt, TU, Bachelor Thesis, 2014

In this work, a visual analytics tool is developed which enables automatic analysis of processes, which are defined by the user, of monitoring systems. This tool provides reports of the performance and sequence of process steps and allows a more detailed analysis of user interactions. Based on technologies of visual analytics and information visualization, data sets can be analyzed and presented visually for deeper analysis. This includes a directed node-link diagram, that represents the process model and diagrams for metadata such as the performance of each step. The objective is to be able to handle even large amounts of data and to compare a state of the process with the desired process state. The incoming data are event data consisting of logs from events which represent process steps used in a process containing a timestamp and other information like e.g. money or duration. The problem which has to be solved is to handle the information extracted from event data and to find complex, direct and indirect relations between process steps by giving an overview using a node-link diagram with weighted edges to represent the transitions from one process step to another and providing interaction techniques. Additional the information has to be analyzed according to chosen indicators (e.g. duration or money) and to compare different types of process runs with each other, e.g. separating complete and incomplete runs, to possibly find these relations which can be indicators for an incomplete run. As a result the tool gives the ability to choose different runs to compare them and simultaneously compares the chosen indicators. Furthermore, the tool was evaluated to find out, if it is possible to solve this problems by using this tool.

Show publication details

Lenz, Olav; Landesberger, Tatiana von (Betreuer); Kuijper, Arjan (Betreuer)

Visueller Vergleich von Ausfall-Effekten in mehreren Datensätzen

2014

Darmstadt, TU, Master Thesis, 2014

Es ist einige Jahre her, seitdem die Finanzkrise begonnen hat und die weltweiten Finanznetzwerke zu wackeln begannen. Politik und Unternehmen machten große Versprechungen, die Stabilität der Finanznetzwerke zu verbessern und die Finanzmärkte stärker zu reglementieren. Jetzt stellen sich die Fragen, ob sich wirklich etwas verändert hat, ob sich so etwas heute wiederholen könnte und wie stark die Auswirkungen wären. Auch angesichts der aktuellen Eurokrise sind Fragestellungen, welche die Stabilität der weltumspannenden Finanznetzwerke betreffen, hoch relevant. Zur Beurteilung, ob Maßnahmen die gewünschten Erfolge bringen, ist die Untersuchung der Entwicklung dieser Netzwerke über die Zeit besonders interessant. Mit Hilfe der bestehenden Systeme [Die11, vLDBF13] und [Len12] lassen sich viele Fragestellungen in Bezug auf Ausfall- Effekte in Finanzsystemen beantworten. Dabei ist es möglich, die Ausfall-Effekte mit verschiedenen Parametern zu simulieren und die Ergebnisse mit Hilfe visueller Analyse zu analysieren. Der Schwerpunkt liegt bei diesen Systemen allerdings auf der Simulation und Analyse eines einzelnen Finanznetzwerks. Einen direkten Vergleich von mehreren Finanzsystemen ermöglichen diese Systeme nicht. In Rahmen dieser Arbeit wird, auf der Basis der bereits existierenden Systeme [Die11, vLDBF13, Len12] und [LKB+14], ein System entwickelt, dass die Ausfall-Effekte von zwei oder mehr Netzwerken miteinander vergleichen kann. Dieser Vergleich von mehreren Datensätzen soll die Analyse von Zeitreihen bzw. Vergleichsgruppen ermöglichen. Dies kann beispielsweise dabei helfen zu untersuchen, wie sich die Auswirkungen der Ausfall-Effekte über einen Zeitraum hinweg verändert haben. Dazu wird eine Analysepipeline entwickelt, welche die Analyse vereinfacht und die Beantwortung der Fragestellungen unterstützt. Der Schwerpunkt liegt auf der Betrachtung von Ähnlichkeiten und Unterschieden in den Ausfall-Effekten. Dabei ist die Verwendung geeigneter Vergleichsansätze wichtig, um in einer großen Menge an Ausfall- Effekt-Graphen Ähnlichkeiten zu finden und näher untersuchen zu können. Als Basis für den Vergleich werden sowohl bekannte knoten- und musterbezogene Informationen, als auch strukturelle und metrikbasierte Vergleiche von Graphen herangezogen. Neben den Finanznetzwerken wird in dieser Arbeit auch eine andere Anwendungsdomäne beschrieben. Die Untersuchung von Sequenzen aus Aminosäuren und dort stattfindenden Mutationen stellt für die Biologie einen sehr wichtigen Forschungsbereich dar. Solche Untersuchungen werden beispielsweise benötigt, um geeignete Medikamente gegen Viruserkrankungen zu entwickeln. Die dort auftretenden Mutationsgraphen sind mit den Ausfall-Effekt-Graphen in Finanznetzwerken vergleichbar. Aus diesem Grund lassen sich die Konzepte sehr gut übertragen.

Show publication details

Bender, Jan; Kuijper, Arjan; Landesberger, Tatiana von; Theisel, Holger; Urban, Philipp; Fellner, Dieter W.; Goesele, Michael; Roth, Stefan

VMV 2014: Vision, Modeling, and Visualization

2014

Goslar : Eurographics Association, 2014

Workshop on Vision, Modeling, and Visualization (VMV) <19, 2014, Darmstadt, Germany>

VMV is a unique event that brings together scientists and practicioners interested in the interdisciplinary fields of computer vision and computer graphics, with special emphasis on the link between the disciplines. It offers researchers the opportunity to discuss a wide range of different topics within an open, international and interdisciplinary environment, and has done so successfully for many years.

Show publication details

Kuijper, Arjan; Schwarzkopf, Andreas; Kalbe, Thomas; Bajaj, Chandrajit L.; Roth, Stefan; Goesele, Michael

3D Anisotropic Diffusion on GPUs by Closed-Form Local Tensor Computations

2013

Numerical Mathematics, Vol.6 (2013), 1, pp. 72-94

We present an efficient implementation of volumetric anisotropic image diffusion filters on modern programmable graphics processing units (GPUs), where the mathematics behind volumetric diffusion is effectively reduced to the diffusion in 2D images. We hereby avoid the computational bottleneck of a time consuming eigenvalue decomposition in R3. Instead, we use a projection of the Hessian matrix along the surface normal onto the tangent plane of the local isodensity surface and solve for the remaining two tangent space eigenvectors. We derive closed formulas to achieve this and prevent the GPU code from branching. We show that our most complex volumetric anisotropic diffusion filters gain a speed up of more than 600 compared to a CPU solution.

Show publication details

Beck, Sebastian; Kuijper, Arjan (Betreuer); Große-Puppendahl, Tobias (Betreuer)

A Gesture Recognition Device with Visual Feedback Based on Capacitive Proximity Sensing

2013

Darmstadt, TU, Bachelor Thesis, 2013

In this thesis, a novel gesture recognition device - called Rainbowfish - with visual feedback is presented. Rainbowfish is able to recognize objects like a human hand with its sensors. A software running on the computer evaluates the provided sensor data and triggers lighting animations on Rainbowfish's surface. This visual feedback facilitates a closer interaction between the device and the user if no additional feedback like a graphical user interface is provided. An evaluation shows that the system can raise the usability of gesture recognition applications based on capacitive proximity sensors. Especially in cases when the user experiences usage problems, the feedback, as the defining factor, decreases the estrangement between the user and the device. The user study reveals that the visual feedback has a positive impact on a user's intrinsic motivation, encouraging the user to keep on using the application.

Show publication details

Thürck, Daniel; Kuijper, Arjan (Betreuer)

A Well-Posed Parameter-Free Model for Nonlinear Diffusion and its Applications in Mobile Image Processing

2013

Darmstadt, TU, Bachelor Thesis, 2013

Images and videos today represent our most important media. Recently, taking pictures and recording videos with mobile phones and uploading them to the internet has become common, especially in social networks. However, due to low-quality CCD sensors, those pictures often suffer from noise. A solution here would be to use quite well-known image processing algorithms, especially anisotropic diffusion. The most famous model, the Perona and Malik equation, unfortunately is ill-posed and thus is problematic. In this work, we present an alternative model for anisotropic diffusion that is constructed in a bottom-up fashion for denoising and well-posedness. The problem of setting the matching input parameters for denoising is tackled by the use of machine learning techniques. Ultimately, we present a prototypical implementation on embedded hardware that shows that the use of such sophisticated techniques is possible for mobile use.

Show publication details

Steger, Sebastian; Bozoglu, Y. Nazli; Kuijper, Arjan; Wesarg, Stefan

Application of Radial Ray Based Segmentation to Cervical Lymph Nodes in CT Images

2013

IEEE Transactions on Medical Imagaing, Vol.32 (2013), 5, pp. 888-900

The 3D-segmentation of lymph nodes in CT images is required for staging and disease progression monitoring. Major challenges are shape and size variance, as well as low contrast, image noise, and pathologies. In this paper, radial ray based segmentation is applied to lymph nodes: From a seed point, rays are cast into all directions and an optimization technique determines a radius for each ray based on image appearance and shape knowledge. Lymph node specific appearance cost functions are introduced and their optimal parameters are determined. For the first time, the resulting segmentation accuracy of different appearance cost functions and optimization strategies are compared. Further contributions are extensions to reduce the dependency on the seed point, to support a larger variety of shapes, and to enable interaction. The best results are obtained using graph-cut on a combination of the direction weighted image gradient and accumulated intensities outside a predefined intensity range. Evaluation on 100 lymph nodes shows that with an average symmetric surface distance of 0.41 mm the segmentation accuracy is close to manual segmentation and outperforms existing radial ray and model based methods. The method's inter-observer-variability of 5.9% for volume assessment is lower than the 15.9% obtained using manual segmentation.

Show publication details

Nose, Jan David; Kuijper, Arjan (Betreuer)

Centralized Approach for a Site Independent Wireless Network Access: Introduction of a Concept for a Unified Network Access in the Fraunhofer-Gesellschaft

2013

Darmstadt, TU, Bachelor Thesis, 2013

In the last years, the number of mobile devices has grown exponentially, especially the number of mobile phones and smartphones. To aid in the modern workflows, they rely on a stable and fast network access. This paradigm shift proves to be a problem for many institutions, as often not enough expertise exists to extend the existing cable-based networks by a secure, wireless network access for mobile devices. The Fraunhofer-Gesellschaft with over 60 institutes is no exception. Because every institute operates its own network, the infrastructure of Fraunhofer is heterogeneous, and a broad range of individual solutions has been developed. The second problem is the demand for a unified network access for all Fraunhofer employees. Solutions for a unified network design, as proposed by market leaders, are not applicable to the Fraunhofer- Gesellschaft due to its unique structure. For this reason, a concept is developed and tested in this thesis that provides all employees with a unified network access. The central issues of the concept are practicability and security. As only limited resources in form of time and personnel are available, the concept must be realizable without much effort in the single institute, to be applicable to all institutes and the whole Fraunhofer-Gesellschaft. This goal is only reachable if the concept addresses the different network designs and wireless LAN solutions that exist in Fraunhofer. Because of the research done by the Fraunhofer-Gesellschaft, internal resources and personal data must be secured. This is especially true for the transport of user credentials through untrusted networks, e.g. the Internet. As out-of-the-box solutions, proposed by network vendors, are not applicable due to Fraunhofer's unique structure, a custom solution must be developed. In this thesis, a concept concerning this unique structure is proposed. It fulfills the technical requirements like security and privacy, as well as organizational requirements like limited resources. The concept, and interrelated processes, get tested in one institute, and conclusively discussed in the context of practicability for the whole Fraunhofer-Gesellschaft.

Show publication details

Ettl, Anne-Sophie; Zeilner, Axel; Köster, Ralf; Kuijper, Arjan

Classification of Text and Image Areas in Digitized Documents for Mobile Devices

2013

Battiato, Sebastiano (Ed.) et al.: VISAPP 2013 - Volume II : Proceedings of the International Conference on Computer Vision Theory and Applications. SciTePress, 2013, pp. 88-91

International Conference on Computer Vision Theory and Applications (VISAPP) <8, 2013, Barcelona, Spain>

Post processing and automatic interpretation of images plays an increasingly important role in the mobile area. Both for the efficient compression and for the automatic evaluation of text, it is useful to store text content as textual information rather than as graphics information. For this purpose pictures from magazines are recorded with the camera of a smartphone and classified according to text and image areas. In this work established desktop procedures are presented and analyzed in terms of their applications on mobile devices. Based on these methods, an approach for image segmentation and classification on mobile devices is developed, taking into account the limited resources of these mobile devices.

Show publication details

Kuijper, Arjan; Havukkala, Ilkka

Comparing Bitmapped Microrna Structure Images using Mutual Symmetry

2013

International Journal of Image and Graphics, Vol.13 (2013), 3, 26 p.

We present a high-throughput method for analyzing large-scale bitmapped bio-data: processing of elongated molecular structures by 2D images and analyzing their shapes for chemoinformatics databases. Two-dimensional structure databases are transfered to bitmap images - a commonly used visualization widely spread online. Then, an efficient clustering of the molecular structures is achieved by a mutual symmetry-based binary matrix representation of the shapes. We present a method to compute the difference between two of such representations and evaluate its performance with respect to time and quality of matching. In our tests we use two bitmap databases, one containing true human microRNA folded 2D structures and one with claimed human microRNA folded 2D structures. We show the stability of the matching with respect to parameterization and orientation of the shapes. Our method enables a good automatic clustering of structures with high visual similarity.

Show publication details

Thürck, Daniel; Kuijper, Arjan

Cosine-Driven Non-linear Denoising

2013

Aurélio, Campilho (Ed.) et al.: Image Analysis and Recognition : 10th International Conference, ICIAR 2013. Berlin; Heidelberg; New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 7950), pp. 245-254

International Conference on Image Analysis and Recognition (ICIAR) <10, 2013, Povoa do Varzim, Portugal>

The Perona-Malik model is an effective but ill-posed model for denoising digital images by anisotropic diffusion. Instead of complex regularizations, we propose a new continuous model which is well-posed and show that it is nevertheless effective for denoising. In addition, an extension of our model offers the possibility of inducing a convergence for the discretization. A comparison to the original Perona-Malik model is carried out using an human vision-centered quality index which shows the improvements of our model when it comes to denoising.

Show publication details

Pohst, Maximilian; Davey, James (Betreuer); Ruppert, Tobias (Betreuer); Kuijper, Arjan (Betreuer)

Definition eines Evaluierungsprozesses für Visual-Analytics-Expertenlösungen

2013

Darmstadt, TU, Studienarbeit, 2013

Heutzutage werden riesige Datenmengen produziert. Es ist wichtig diese Daten interpretieren zu können. Visual Analytics Systeme helfen dabei, große Datenbestände nutzbar zu machen. Die Systeme können sich je nach Einsatzgebiet stark unterscheiden. Damit Benutzer produktiv mit den Systemen arbeiten können, ist es wichtig, dass die Systeme auf unterschiedliche Kriterien wie Benutzbarkeit, Effizienz, Robustheit oder Angemessenheit evaluiert werden. In dieser Arbeit werden Modelle zum Thema Evaluierung von Visual Analytics Systemen vorgestellt. Die vorgeschlagenen Methoden und Heuristiken werden untersucht und bewertet. Aus den gewonnen Erkenntnissen werden schließlich praxisorientierte Richtlinien abgeleitet, die helfen sollen, Systeme in Zukunft systematischer auszuwerten. Am Ende der Arbeit wird ein exemplarischer Projektablauf vorgestellt an dem die Richtlinien angewandt werden.

Show publication details

Thöner, Maik; Kuijper, Arjan (Betreuer); Franke, Tobias (Betreuer)

Delta Global Illumination for Mixed Reality

2013

Darmstadt, TU, Master Thesis, 2013

The focus point in Mixed Reality applications is the merging of objects from different realities into a new, visibly homogeneous scene. To achieve this, next to a spatial registration, a plausible illumination of the objects is required. While shadows and direct illumination can deliver a realistic look to the objects, adding indirect interaction of illumination will result in a seamless integration of objects, to appear as part of the scene instead of glued-on patches. Mixed Reality systems find appliance in entertainment areas like movies and games, as well as prototype presentations or visualization of planned or damaged constructions. We propose an algorithm based on Voxel Cone Tracing to provide Global Illumination for Mixed Reality that enables diffuse as well as specular lighting and easy to compute soft-shadows.

Show publication details

Tschirsich, Martin; Kuijper, Arjan

Discrete Deep Structure

2013

Kuijper, Arjan (Ed.) et al.: Scale Space and Variational Methods in Computer Vision : 4th International Conference, SSVM 2013. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 7893), pp. 343-354

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) <4, 2013, Leibnitz, Austria>

The discrete scale space representation L of f is continuous in scale t. A computational investigation of L however must rely on a finite number of sampled scales. There are multiple approaches to sampling L differing in accuracy, runtime complexity and memory usage. One apparent approach is given by the definition of L via discrete convolution with a scale space kernel. The scale space kernel is of infinite domain and must be truncated in order to compute an individual scale, thus introducing truncation errors. A periodic boundary condition for f further complicates the computation. In this case, circular convolution with a Laplacian kernel provides for an elegant but still computationally complex solution. Applied in its eigenspace however, the circular convolution operator reduces to a simple and much less complex scaling transformation. This paper details how to efficiently decompose a scale of L and its derivative Qt L into a sum of eigenimages of the Laplacian circular convolution operator and provides a simple solution of the discretized diffusion equation, enabling for fast and accurate sampling of L.

Show publication details

Roskosch, Philipp; Davey, James (Betreuer); Kuijper, Arjan (Betreuer)

Dynamisches Sampling zur Visuellen Exploration von Großen Dicht-Besetzten Matrizen

2013

Darmstadt, TU, Bachelor Thesis, 2013

In dieser Bachelorarbeit präsentiere ich eine Technik, die die visuelle Exploration von großen dicht-besetzten Ähnlichkeitsmatrizen ermöglicht. Sie erlaubt den Vergleich mehrerer Dimensionen eines multivariaten Datensatzes. Für die Visualisierung werden die Daten durch Sampling reduziert. Die Zugriffszeit auf einzelne Elemente ist mit steigender Matrixgröße ein immer größer werdendes Problem. Ich untersuche verschiedene Datenbankmanagementsysteme und vergleiche die Zugriffszeiten bei verschiedenen Problemgrößen. Die Visualisierung reagiert auf Interaktion des Benutzers und ermöglicht den Fokus auf bestimmte Bereiche innerhalb der Daten. Dafür werden die Daten nach Benutzerinteresse gefiltert und die Visualisierung mit Subsamples der gefilterten Daten verfeinert. Der Kontext bleibt bei diesem Prozess erhalten. Der Fokus ermöglicht die Entdeckung von Zusammenhängen, die sonst im Verborgenen bleiben.

Show publication details

Schwenk, Karsten; Voss, Gerrit; Behr, Johannes; Jung, Yvonne; Limper, Max; Herzig, Pasquale; Kuijper, Arjan

Extending a Distributed Virtual Reality System with Exchangeable Rendering Back-Ends

2013

The Visual Computer, Vol.29 (2013), 10, pp. 1039-1049

We present an approach to integrate multiple rendering back-ends under a common application layer for distributed systems. The primary goal was to find a practical and nonintrusive way to use potentially very different renderers in heterogeneous computing environments without impairing their strengths and without burdening the back-ends or the application with details of the cluster environment. Our approach is based on a mediator layer that handles multithreading, clustering, and the synchronization between the application's and the back-end's scene. We analyze the proposed approach with an implementation for a state-of-the- art distributed VR/AR system. In particular, we present two case studies and an example application.

Show publication details

Glaser, Christian; Kuijper, Arjan (Betreuer); Kähm, Olga (Betreuer); Damer, Naser (Betreuer)

Face Liveness Detection Against Image and Video Spoofing Attacks

2013

Darmstadt, TU, Master Thesis, 2013

Many situations require users to log into a computer system. For example to perform private tasks like banking, social interaction or to get access to a secured area. Conventional security driven systems have the disadvantage that passwords or keycards are needed. These passwords or keycards can get lost or stolen resulting in a security risk. To overcome this drawback biometrics use the characteristics of the human body to grand access to a computer system. Beside fingerprint or iris recognition face detection is a popular biometric trait. The reason therefore is that it requires only a usual camera. Most of the current systems have a camera build in anyway. Also face recognition is not very intrusive to the user, which gives a high acceptability of face recognition is biometric trait. In the past though face recognition systems could easily be tricked due to spoofing attempts using pictures or videos of the authenticate user. This thesis analyses current algorithms to counter such spoofing attempts and presents a novel approach. The presented approach will use Machine Learning and Computer Vision to utilize an algorithms by Wu et al. [WRS 12] that can magnify subtle changes in videos to reveal the human pulse. An evaluation of the feasibility of this approach will be given.

Show publication details

Limper, Max; Jung, Yvonne; Behr, Johannes; Sturm, Timo; Franke, Tobias; Schwenk, Karsten; Kuijper, Arjan

Fast, Progressive Loading of Binary-Encoded Declarative-3D Web Content

2013

IEEE Computer Graphics and Applications, Vol.33 (2013), 5, pp. 26-36

The encoding of scene-graph related structured data along with unstructured vertex data within the same descriptive elements of a scene is a major drawback of XML based model formats (such as X3D or Collada) and declarative 3D approaches. Web browsers have to download the complete scene before being able to further process the structure of the document. By introducing Sequential Image Geometry (SIG) containers and explicit binary containers we were able to overcome this limitation. They are wellaligned to buffer structures on the GPU, enabling fast decoding and GPU upload. We improve the image-based approach significantly and introduce a new method called Progressive Binary Geometry (PBG) which enables a simple yet highly progressive transmission of arbitrary mesh data.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

Human Action Recognition Based on Skeleton Splitting

2013

Expert Systems with Applications, Vol.40 (2013), 17, pp. 6848-6855

Human action recognition, defined as the understanding of the human basic actions from video streams, has a long history in the area of computer vision and pattern recognition because it can be used for various applications. We propose a novel human action recognition methodology by extracting the human skeletal features and separating them into several human body parts such as face, torso, and limbs to efficiently visualize and analyze the motion of human body parts. Our proposed human action recognition system consists of two steps: (i) automatic skeletal feature extraction and splitting by measuring the similarity between neighbor pixels in the space of diffusion tensor fields, and (ii) human action recognition by using multiple kernel based Support Vector Machine. Experimental results on a set of test database show that our proposed method is very efficient and effective to recognize the actions using few parameters.

Show publication details

Kuijper, Arjan

Image Processing by Minimising Lp Norms

2013

Zhuravlev, Yuri I. (Ed.): Pattern Recognition and Image Analysis. Berlin, Heidelberg, New York: Springer, 2013, pp. 226-235

In this work, we take a novel line of approaches to evolve images. It is motivated by the total variation method, known for its denoising and edge-preserving effect. Our approach generalises the TV method by taking a general Lp norm of the gradients instead of the L¹ in the TV method. We generalise this method in a series of first and second order derivatives in terms of gauge coordinates. This method also incorporates the well-known blurring by a Gaussian filter and the balanced forward-backward diffusion. The method and its properties are briefly discussed. The practical results are visualised on a real-life image, showing the expected behaviour. When a constraint is added that penalises the distance of the results to the input image, one can vary the desired amount of blurring and denoising.

Show publication details

Herrmann, Daniel; Kuijper, Arjan (Betreuer); Schweizer, Immanuel (Betreuer); Turba, Martin (Betreuer)

Incoming Interdomain Traffic Engineering with LISP: Evaluation of LISP Traffic Engineering Capabilities Compared with BGP for Stub AS

2013

Darmstadt, TU, Bachelor Thesis, 2013

With the ever increasing volume of internet traffic, traffic engineering in stub AS gets more and more important. While it is considered easy today to perform outgoing traffic engineering with methods like BGP, traffic engineering in the incoming direction is commonly known to be much more difficult, because there is no way to directly influence the traffic in remote systems. Current traffic engineering methods of BGP are commonly heuristic and time-consuming, furthermore, they only provide inaccurate results. In this thesis we evaluate the Locator/Identifier Separation Protocol (LISP) and its built-in traffic engineering methods. Therefore, we conduct multiple experiments in which we compare BGP and its "advertisement of more specific prefixes" and "AS Path Prepending" (ASPP) variants to LISP. This comparison shows that LISP allows effective load-balancing with an accuracy of 5% while still being easier to configure than BGP and its variants. Also it requires less memory capacity on the routers, because they do not have to keep the full BGP routing table. These results are independent from parameters like the traffic pattern, the number of concurrent streams and still hold true for completely random traffic.

Show publication details

Retz, Wilhelm; Nazemi, Kawa (Betreuer); Kuijper, Arjan (Betreuer)

Integration heterogener Methoden der Empfehlungssysteme zur Visualisierungsadaption

2013

Darmstadt, TU, Diplomarbeit, 2013

Die stetig wachsende Menge der Daten in digitalen Archiven und insbesondere im Web stellt eine große Herausforderung für Informations- und Kommunikationstechnologien. Dabei spielt insbesondere der menschliche Zugang zu den Informationen eine wesentliche Rolle. Verschiedene Ansätze setzen sich mit dem menschlichen Zugang zu den Daten auseinander. So werden etwa Daten für das semantische Web semi-automatisiert formalisiert und mit "Bedeutung" angereichert. Informationsvisualisierung und Visual Analytics beschäftigt sich mit der visuellen Aufbereitung, um den Zugang zu den Daten zu ermöglichen, zu erleichtern und Lösungswege für verschiedenartige Aufgaben mit großen Daten zu ermöglichen. Empfehlungssysteme bieten Technologien und Ansätze an, um Daten mit einer Metrik zu versehen und ein entsprechendes Ranking für die Datenentitäten zu vergeben. Bei all diesen Verfahren und Ansätzen steht der Mensch im Vordergrund. Insbesondere Empfehlungssysteme analysieren fortlaufend den Menschen und seinen Umgang mit Daten und Systemen. Die Darstellung dieser Empfehlungssysteme ist jedoch oft auf gewichtete Listen beschränkt. Die Vorteile der explorativen Ansätze der Informationsvisualisierung finden kaum Anwendung. Wobei die Ansätze der Informationsvisualisierung, insbesondere zur Lösung von komplexen kognitiven Aufgaben, oft Expertenwissen voraussetzt. Das sehr junge Gebiet der adaptiven Visualisierungen beschäftigt sich daher mit der Frage, wie die Informationsvisualisierung auf die Bedürfnisse der jeweiligen Benutzer eingehen kann. Dabei werden Ansätze, die auch in Empfehlungssysteme eingesetzt werden, in die Informationsvisualisierung übertragen. Dies erfolgt oft mit dem Hintergrund die Menge auf Datenebene zu reduzieren. Jene Ansätze, die das Benutzungsverhalten im Vergleich zu anderen Benutzern messen und auswerten, werden in existierenden Systemen nicht eingesetzt. Die vorliegende Diplomarbeit stellt ein Verfahren vor, das die Methoden der kollaborativen Empfehlungssysteme auf adaptive Visualisierungen überträgt. Dabei werden lediglich implizite Benutzungsinformationen verwendet, um eine Rollen- und Gruppenzuweisung vorzunehmen und in einem Benutzermodell zu überführen und Visualisierungen in verschiedenen Abstraktionsstufen and individuelle Benutzer und Benutzergruppen zu adaptieren.

Show publication details

Kordek, Andres Felipe; Limper, Max (Betreuer); Kuijper, Arjan (Betreuer)

Intuitive Platzierung von Objekten in webbasierten CAD-Umgebungen

2013

Darmstadt, TU, Bachelor Thesis, 2013

Diese Bachelorarbeit vergleicht durch eine Benutzerevaluation die Usability zweier Ansätze des Snappings. Ein während der Arbeit entstandener Editor soll als Testumgebung dienen. Die Arbeit ist in mehrere Abschnitte unterteilt. Vorab findet eine kurze Einführung über den Editor und die dafür verwendeten Technologien statt. Im darauf folgenden Abschnitt werden verwandte Dokumentationen angesprochen und es findet eine kurze Einführung über die mathematischen Hintergründe in der Computergrafik statt. Als nächstes folgt die Implementierung und die genauere Beschreibung beider Ansätze. Abschließend werden beide Implementierungen durch eine Benutzerevaluation auf ihre Usability getestet und miteinander verglichen. Zum Schluss werden die Ergebnisse ausgewertet und daraus wird zu allerletzt ein Fazit gezogen.

Show publication details

Thürck, Daniel; Kuijper, Arjan

Lazy Nonlinear Diffusion Parameter Estimation

2013

Petrosino, Alfredo (Ed.): Image Analysis and Processing - ICIAP 2013. Proceedings Part I. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 8156), pp. 211-220

International Conference of Image Analysis and Processing (ICIAP) <17, 2013, Naples, Italy>

Perona-Malik diffusion is a well-known type of nonlinear diffusion that can be used for image segmentation and denoising. The process itself needs an parameter k to decide which edges will be retained and which can be blurred and a stopping time tS. Although there have been investigations on how to set these parameters, especially for regularized diffusion models, as well as different criteria for the optimal stopping time have been suggested, there is yet no quick and conclusive way to estimate both parameters - or to reduce the search space at least. In this paper, we show that Gaussian noise characteristics of an image and the diffusion parameters for an optimal optical result can be estimated based on the image histogram. We demonstrate the effectiveness of lazy learning in this area and develop a custom feature weighting algorithm.

Show publication details

Damer, Naser; Führer, Jan Benedikt; Kuijper, Arjan

Missing Data Estimation in Multi-biometric Identification and Verification

2013

IEEE Biometrics Council: 2013 IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications : BioMS 2013. New York: IEEE, Inc., 2013, pp. 41-45

IEEE Workshop on Biometric Measurements and Systems for Security and Medical Applications (BioMS) <4, 2013, Naples, Italy>

In the practical use of multi-biometric solutions, biometric sources involved in producing the verification or identification decision do occasionally fail to produce results. This work discusses solutions for missing data in multi-biometric score-level fusion. A missing data estimation solution based on support vector regression was presented in this work and compared to four baseline solutions. The evaluation was carried under both the verification and the identification scenarios in an effort to show the effect of missing data estimation on the relatively understudied multi-biometric identification scenario. Evaluation was performed on the Biosecure DS2 score database and satisfying performance was achieved under both biometric scenarios.

Show publication details

Engelke, Timo; Becker, Mario; Wuest, Harald; Keil, Jens; Kuijper, Arjan

MobileAR Browser - A Generic Architecture for Rapid AR-multi-level Development

2013

Expert Systems with Applications, Vol.40 (2013), 7, pp. 2704-2714

We present our novel generic approach for interfacing web components on mobile devices in order to rapidly develop Augmented Reality (AR) applications using HTML5, JavaScript, X3D and a vision engine. A general concept is presented exposing a generalized abstraction of components that are to be integrated in order to allow the creation of AR capable interfaces on widely available mobile devices. Requirements are given, yielding a set of abstractions, components, and helpful interfaces that allow rapid prototyping, research at application level, as well as commercial applications. A selection of various applications (also commercial) using the developed framework is given, proving the generality of the architecture of our MobileAR Browser. Using this concept a large number of developers can be reached. The system is designed to work with different standards and allows for domain separation of tracking algorithms, render content, interaction and GUI design. This can potentially help groups of developers and researchers with different competences creating their application in parallel, while the declarative content remains exchangeable.

Show publication details

Schmitt, Nikolas; Knuth, Martin (Betreuer); Kuijper, Arjan (Betreuer)

Multilevel Cloth Simulation Through GPU Surface Sampling

2013

Darmstadt, TU, Master Thesis, 2013

Nowadays, cloth simulation is more and more common technique used in garment industry. Most available simulation systems use triangular mesh models due to their flexibility for the mesh generation. However, using regular grids opens the door for many optimizations. Connectivity is implicit, warp and weft directions of the cloth are aligned to grid edges and distances between particles are equal, which gives valuable speed advances for the computations. This work focusses in combining both grid model types into one hybrid simulation system. The presented system features CPU computations for a low-resolution triangle mesh. Additionally, a GPU-based method is performed efficiently on a high-resolution grid representation. This improves the fine details of the garment. Coupling is performed by a texture based approach for fast up and down projections of the hybrid grid simulation system. The flexible system allows individual computation types to be performed on different architectures, data representations and detail levels. The results show the ability to handle simulations with more than 250k particles in real-time, featuring the new hierarchical solver in conjunction with GPU collision handling.

Show publication details

Schmitt, Nikolas; Knuth, Martin; Bender, Jan; Kuijper, Arjan

Multilevel Cloth Simulation using GPU Surface Sampling

2013

Bender, Jan (Ed.) et al.: VRIPHYS 13: 10th Workshop in Virtual Reality Interactions and Physical Simulations. Goslar: Eurographics Association, 2013, pp. 1-10

International Workshop in Virtual Reality Interaction and Physical Simulations (VRIPhys) <10, 2013, Lille, France>

Today most cloth simulation systems use triangular mesh models. However, regular grids allow many optimizations as connectivity is implicit, warp and weft directions of the cloth are aligned to grid edges and distances between particles are equal. In this paper we introduce a cloth simulation that combines both model types. All operations that are performed on the CPU use a low-resolution triangle mesh while GPU-based methods are performed efficiently on a high-resolution grid representation. Both models are coupled by a sampling operation which renders triangle vertex data into a texture and by a corresponding projection of texel data onto a mesh. The presented scheme is very flexible and allows individual components to be performed on different architectures, data representations and detail levels. The results are combined using shader programs which causes a negligible overhead. We have implemented CPU-based collision handling and a GPU-based hierarchical constraint solver to simulate systems with more than 230k particles in real-time.

Show publication details

Gross, Richard; Bockholt, Ulrich; Biersack, Ernst W.; Kuijper, Arjan

Multimodal Kinect-Supported Interaction for Visually Impaired Users

2013

Stephanidis, Constantine (Ed.) et al.: Universal Access in Human-Computer Interaction: Part I : Design Methods, Tools, and Interaction Techniques for eInclusion. 7th International Conference, UAHCI 2013. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 8009), pp. 500-509

International Conference on Universal Access in Human-Computer Interaction (UAHCI) <7, 2013, Las Vegas, NV, USA>

This paper discusses Kreader, a proof-of-concept for a new interface for blind or visually impaired users to have text read to them. We use the Kinect device to track the user`s body. All feedback is presented with auditory cues, while a minimal visual interface can be turned on optionally. Interface elements are organized in a list manner and placed ego-centric, in relation to the user's body. Moving around in the room does not change the element's location. Hence visually impaired users can utilize their "body-sense" to find elements. Two test sessions were used to evaluate Kreader. We think the results are encouraging and provide a solid foundation for future research into such an interface, that can be navigated by sighted and visually impaired users.

Show publication details

Thürck, Daniel; Kuijper, Arjan

Nonlinear Diffusion at your Fingertips: Theory and Mobile Applications

2013

Loncaric, Sven (Ed.) et al.: ISPA 2013 : 8th International Symposium on Image and Signal Processing and Analysis, pp. 807-812

International Symposium on Image and Signal Processing and Analysis (ISPA) <8, 2013, Trieste, Italy>

Through affordable smartphones and lower costs for mobile internet access, mobile communication by moving and still pictures has become a commonplace. However, while most phones offer a camera for taking pictures, the image processing capabilities are relatively sparse. The challenges that arise with real-time image handling are not yet countered by complex techniques. Because of the limited computation power, simple algorithms were used. In this paper, we will show that the technique of nonlinear diffusion can be used in (near) real-time on most smartphone's GPUs if being implemented in an OpenGL ES shader. The presented implementation is then used for several image-related tasks, namely denoising, deblocking and upscaling directly on the phone. As the performance evaluation shows, anisotropic diffusion offers a nice framework for complex mobile image handling in several arising problem areas.

Show publication details

Kuijper, Arjan

On the Local Form and Transitions of Pre-symmetry Sets

2013

Journal of Mathematical Imaging and Vision, Vol.45 (2013), 1, pp. 13-30

Symmetry is an important cue in shape analysis. It has led to the definition of popular shape descriptors like the medial axis. Its properties have been analyzed with a superset, called the symmetry set which represents the midpoints of circles that are at least bitangent to a shape. In this work we investigate the pre-symmetry set. This set considers the pairs of points at which the bitangent contact occurs. One thus obtains pairwise symmetric points of a 2D shape. A closed 2D shape has a parameterization P with finite length. Its pre-symmetry can therefore be represented by a symmetric diagram curves formed from the pairs of points (pi,pj ) ? S1 ×S1. We discuss the properties of the pre-symmetry set visualized by this diagram. We firstly give the so-called transitions changes caused by a perturbation of the shape and show the changes of the curves in the pre-symmetry set diagram. Secondly, we investigate curves that are spanned by all points on the shape. We name the curves essential loops and discuss their properties and transitions. As one important result we show that there are either zero or two essential loops. In the latter case a part of the medial axis is spanned by an essential loop and can therefore be considered as the main axis of the medial axis. As application of pre-symmetry sets, we discuss two possibilities for shape matching based on representations of the pre-symmetry set. The first shape descriptor we present is given by a circular diagram representing the shape, with a set of points representing the extrema of the curvature in the order they appear on the shape. They are pairwise connected and endowed with a length measure. This descriptor is directly related to the curves and their lengths in the presymmetry set diagram. The second descriptor is given by a binary array representing the areas enclosed by the curves in the pre-symmetry set diagram. It is area based and relates to the geometric derivation of the symmetry set.

Show publication details

Große-Puppendahl, Tobias; Berghöfer, Yannick; Braun, Andreas; Wimmer, Raphael; Kuijper, Arjan

OpenCapSense: A Rapid Prototyping Toolkit for Pervasive Interaction Using Capacitive Sensing

2013

IEEE International Conference on Pervasive Computing and Communications. Proceedings : PerCom 2013. Los Alamitos, Calif.: IEEE Computer Society Press, 2013, pp. 151-158

International Conference on Pervasive Computing and Communications (PerCom) <11, 2013, San Diego, CA, USA>

Capacitive sensing allows the creation of unobtrusive user interfaces that are based on measuring the proximity to objects or recognizing their dielectric properties. Combining the data of many sensors, applications such as in-the-air gesture recognition, location tracking or fluid-level sensing can be realized. We present OpenCapSense, a highly flexible opensource toolkit that enables researchers to implement new types of pervasive user interfaces with low effort. The toolkit offers a high temporal resolution with sensor update rates up to 1 kHz. The typical spatial resolution varies between one millimeter at close object proximity and around one centimeter at distances of 35 cm or above.

Show publication details

Landesberger, Tatiana von; Andrienko, Gennady; Andrienko, Natalia; Bremm, Sebastian; Kirschner, Matthias; Wesarg, Stefan; Kuijper, Arjan

Opening Up the "Black Box" of Medical Image Segmentation with Statistical Shape Models

2013

The Visual Computer, Vol.29 (2013), 9, pp. 893-905

The importance of medical image segmentation increases in fields like treatment planning or computer aided diagnosis. For high quality automatic segmentations, algorithms based on statistical shape models (SSMs) are often used. They segment the image in an iterative way. However, segmentation experts and other users can only asses the final segmentation results, as the segmentation is performed in a "black box manner". Users cannot get deeper knowledge on how the (possibly bad) output was produced. Moreover, they do not see whether the final output is the result of a stabilized process. We present a novel Visual Analytics method, which offers this desired deeper insight into the image segmentation. Our approach combines interactive visualization and automatic data analysis. It allows the expert to assess the quality development (convergence) of the model both on global (full organ) and local (organ areas, landmarks) level. Thereby, local patterns in time and space, e.g., non-converging parts of the organ during the segmentation, can be identified. The localization and specifications of such problems helps the experts creating segmentation algorithms to identify algorithm drawbacks and thus it may point out possible ways how to improve the algorithms systematically. We apply our approach on real-world data showing its usefulness for the analysis of the segmentation process with statistical shape models.

Show publication details

Kuijper, Arjan

Preface to the Special Issue on Cyberworlds 2012

2013

The Visual Computer, Vol.29 (2013), 10, pp. 1025-1026

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

Short introduction to the special issue; abstracts of the provided extended versions of six papers presented at the International Conference on Cyberworlds 2012, Darmstadt, Germany.

Show publication details

Majewski, Martin; Braun, Andreas; Marinc, Alexander; Kuijper, Arjan

Providing Visual Support for Selecting Reactive Elements in Intelligent Environments

2013

Gavrilova, Marina L. (Ed.) et al.: Transactions on Computational Science XVIII : Special Issue on Cyberworlds. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 7848), pp. 248-263

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

When realizing gestural interaction in a typical living environment there often is an offset between user-perceived and machine-perceived direction of pointing, which can hinder reliable selection of elements in the surroundings. This work presents a support system that provides visual feedback to a freely gesturing user; thus enabling reliable selection of and interaction with reactive elements in intelligent environments. We have created a prototype that is showcasing this feedback method based on gesture recognition using the Microsoft Kinect and visual support provision using a custom built laser-robot. Finally an evaluation has been performed, in order to prove the efficiency of such a system, acquire usability feedback and determine potential learning effects for gesture-based interaction.

Show publication details

Führer, Jan Benedikt; Damer, Naser (Betreuer); Kuijper, Arjan (Betreuer)

Qualitätsbasierte Informationsfusion auf der Bewertungsebene innerhalb der multimodalen biometrischen Identifikation

2013

Darmstadt, TU, Master Thesis, 2013

Im Laufe der Zeit haben sich biometrische Erkennungsverfahren als zuverlässiges Mittel zum Zwecke der Zugangskontrolle zu physikalischen und virtuellen Bereichen entwickelt. Die Schwächen unimodaler Systeme werden dabei oft durch multimodale Ansätze verbessert, insbesondere ermöglichen diese einen robusteren Registrierungsprozess, erhöhte Sicherheit gegenüber gefälschten Identitäten und eine höhere Erkennungsgenauigkeit. Die vorliegende Arbeit beschäftigt sich mit der Frage, wie Qualitätsinformationen über die extrahierten Merkmale zu einer weiteren Verbesserung der multimodalen biometrischen Identifikation beitragen können. Dabei liegt die Idee zugrunde, dass Merkmale von höherer Qualität auch eine höhere Zuverlässigkeit im Hinblick auf deren Klassifikation zusichern, diese also stärker in den Entscheidungsprozess eingebunden werden sollten als Merkmale von geringerer Qualität. Zur Überprüfung dieser Annahme wurde ein auf dem Gradientenverfahren basierender Fusionsmechanismus um die Berücksichtigung von Qualitätsinformationen erweitert und dessen Erkennungsperformanz unter verschiedenen Konditionen, darunter im Besonderen das Vorhandensein fehlender Bewertungsmaße, mit dem ursprünglichen Algorithmus verglichen.

Show publication details

Bauer, Fabian; Knuth, Martin (Betreuer); Kuijper, Arjan (Betreuer)

Realistic Realtime Rendering of Garment with Transparency and Ambient Occlusion

2013

Darmstadt, TU, Master Thesis, 2013

To simulate behaviour and appearance of clothing articels the garment industry relies on CAD programs 3D garment design like Clo3D [21]. These simulation programs allow the designer to test out different parameters and applications of the garment instead of producing several real-world prototypes. From modeling human characters to shading cloth material BRDF and BSSRDF these programs require state-of-the-art rendering and animation systems to closely reflect cloth material attributes. The physics simulation for one part is responsible for the movement of the cloth under different environmental situations. The lighting solution of the rendering pipeline must be able to simulate different material effects like physically based reflections, refraction, sub-surface scattering, transparency. To give a plausible environment induces look to the rendered meshes global illumination techniques can be applied as well to test the materials lighting behaviour for different scenes. Common in other fields like movie rendering and video games many of these required techniques can be adopted to achieve the desired effect.

Show publication details

Rus, Silvia; Große-Puppendahl, Tobias (Betreuer); Kuijper, Arjan (Betreuer)

Recognition of Lying Postures Using Capacitive Proximity Sensing

2013

Darmstadt, TU, Master Thesis, 2013

In recent years, capacitive proximity sensing made significant advances in the field of gathering implicit contextual data. These systems find broad usage in pervasive activity-recognition systems, installed stationary or made portable. In the domain of context recognition new ways of interaction with the environment opened up since conductive objects can be detected under certain conditions at distances up to 50 cm. This master's thesis investigates an approach to recognize lying positions using capacitive proximity sensing. The overall goal is to develop a technological concept that can be applied to recognize lying postures of patients in elderly homes. Using this contextual data may lead to many desired benefits in elderly care. For example, the occurrence of Decubitus, a condition caused by prolonged pressure on the skin resulting in injuries to skin and underlying tissues, can be avoided better by knowing how the patient is bedded. In order to achieve a desired high resolution, the multiple access schemes CDMA and FDMA are investigated as a basis for capacitive proximity measurements. For this purpose CDMA has been implemented using Gold Codes while the correlation serves the purpose of a measure. In a test setup measurements for CDMA and FDMA have been conducted. They lead to the conclusion that at close distances FDMA has a slightly better spatial resolution than CDMA but as the distance increases the spatial resolution of FDMA will be twice as high as the one of CDMA. The real-world setup achieves a resolution of 48 measurement points, by applying a low-cost grid of crossed wires under the slatted frame of a bed. The experimental results show that the presented approach and the decisions derived from the evaluation of multiple access schemes lead to a well-suitable system for recognizing lying postures.

Show publication details

Stocklöw, Carsten; Grguric, Andrej; Dutz, Tim; Vandommele, Tjark; Kuijper, Arjan

Resource Management for Multimodal and Multilingual Adaptation of User Interfaces in Ambient Assisted Living Environments

2013

Stephanidis, Constantine (Ed.) et al.: Universal Access in Human-Computer Interaction: Part III : Applications and Services for Quality of Life. 7th International Conference, UAHCI 2013. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 8011), pp. 97-106

International Conference on Universal Access in Human-Computer Interaction (UAHCI) <7, 2013, Las Vegas, NV, USA>

Providing multimodal user interfaces in Ambient Assisted Living scenarios is a challenging task due to large variety of modalities and languages that can be used as well as impairments and preferences of end users. Creating an application that can cope with this multitude of presentation possibilities is highly complex. However, by separating the application from the presentation layer and representing the dialog in an abstract form, it is possible to perform adaptations according to the output parameters. In this work, we present the concept for a Resource Server for multimodal and distributed systems which are capable of storing different kinds of resources and associated metadata, and adapting abstract dialogs. We propose the introduction of a presentation identifier as placeholder for a set of concrete resources, a two-stage mapping between identifiers, and a selection algorithm to cope with the problem of multiple matching resources.

Show publication details

Prediger, Mark; Kuijper, Arjan (Betreuer); Marinc, Alexander (Betreuer)

Robot-aided Pointing Gesture Recognition in Intelligent Environments

2013

Darmstadt, TU, Bachelor Thesis, 2013

In research field of Intelligent Environments explicit control of contained devices is a major topic. Hand and arm gestures represent an intuitive way to select and control devices and can be gathered by inexpensive depth cameras like the Microsoft Kinect. But for covering multiple rooms several depth cameras are required, resulting in increasing costs and complexity of such a system in larger home areas. To face this problem we use a mobile robot to permanently follow and track the user. The user can simply point from any place at a device in the environment with his arm to control it. Therefore the robot is equipped with a consumer depth camera used to perform gesture recognition and self-localization for computing the global pointing direction. The pointing direction is communicated to the system of the Intelligent Environment which checks for intersection with known devices and changes their state. To prove the feasibility of our approach we realized a prototypical implementation using a real robot and evaluated it with a group of candidates. Finally we compared it with a gesture control system using multiple cameras focusing on user acceptance and costs.

Show publication details

Eicke, Tim Nicolas; Jung, Yvonne; Kuijper, Arjan

Robuste Echtzeitschatten für dynamische 3D-Szenen im Web

2013

Latoschik, Marc Erich (Ed.) et al.: Virtuelle und Erweiterte Realität : 10. Workshop der GI-Fachgruppe VR/AR. Aachen: Shaker, 2013. (Berichte aus der Informatik), pp. 85-96

Workshop der GI-Fachgruppe VR/AR: Virtuelle und Erweiterte Realität <10, 2013, Würzburg, Germany>

In diesem Beitrag wird ein auf Shadow Mapping beruhendes Konzept zur Darstellung von qualitativ hochwertigen Echtzeitschatten im Web vorgestellt. Hierbei werden sowohl allgemeine Shadow-Mapping-Problemfälle als auch webspezifische Limitierungen beleuchtet. Schließlich werden die Ergebnisse der Anwendung des Konzepts in X3DOM, einem Framework zur Darstellung von 3D-Inhalten im Webbrowser, präsentiert und diskutiert.

Show publication details

Eicke, Tim Nicolas; Kuijper, Arjan (Betreuer); Jung, Yvonne (Betreuer)

Robuste Echtzeitschatten für dynamische 3D-Szenen im Web

2013

Darmstadt, TU, Bachelor Thesis, 2013

Die glaubwürdige Darstellung von Echtzeitschatten ist in unserem Alltag durch moderne Videospiele längst zu einer Selbstverständlichkeit geworden. Im Web sieht dies jedoch anders aus: Die Darstellung von dreidimensionalen Szenerien im Browser ist erst seit wenigen Jahren im Kommen, Schatten spielen dabei bislang allenfalls eine untergeordnete Rolle. Dabei stellen Schatten einen wichtigen Faktor bei der menschlichen Wahrnehmung von dreidimensionalen Welten dar, denn sie erhöhen nicht nur allgemein die Authentizität einer Szene, sondern liefern zugleich wichtige Anhaltspunkte darüber, wo ein Objekt im Raum platziert ist. Eine wesentliche Rolle in der Entwicklung von webbasiertem 3D kommt dem JavaScript-basierten Open-Source- Framework X3DOM zu, da es einen Ansatz zur Einbindung von deklarativem 3D in HTML5 liefert. Jedoch bietet auch dieses bislang nur rudimentäre Schattenwurftechniken, die heutigen Ansprüchen kaum mehr gerecht werden. Im Rahmen dieser Arbeit wird dieses Problem angegangen, indem zunächst bestehende Shadow-Mapping- Techniken auf ihre Eignung zur Nutzung im Webkontext untersucht werden. Darauf basierend wird ein Konzept zur Verbesserung der Schattendarstellung in X3DOM ausgearbeitet und schließlich implementiert.

Show publication details

Kuijper, Arjan; Bredies, Kristin; Pock, Thomas; Bischof, Horst

Scale Space and Variational Methods in Computer Vision: 4th International Conference, SSVM 2013

2013

Berlin, Heidelberg, New York : Springer, 2013

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) <4, 2013, Leibnitz, Austria>

Lecture Notes in Computer Science (LNCS) 7893

This book constitutes the refereed proceedings of the 4th International Conference on Scale Space Methods and Variational Methods in Computer Vision, SSVM 2013, held in Schloss Seggau near Graz, Austria, in June 2013. The 42 revised full papers presented were carefully reviewed and selected 69 submissions. The papers are organized in topical sections on image denoising and restoration, image enhancement and texture synthesis, optical flow and 3D reconstruction, scale space and partial differential equations, image and shape analysis, and segmentation

Show publication details

Bauer, Fabian; Knuth, Martin; Kuijper, Arjan; Bender, Jan

Screen-Space Ambient Occlusion Using A-Buffer Techniques

2013

IEEE Computer Society: 13th International Conference on Computer-Aided Design and Computer Graphics. Proceedings : CAD / Graphics 2013. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2013, pp. 140-147

International Conference on Computer-Aided Design and Computer Graphics <13, 2013, Hong Kong, China>

Computing ambient occlusion in screen-space (SSAO) is a common technique in real-time rendering applications which use rasterization to process 3D triangle data. However, one of the most critical problems emerging in screen-space is the lack of information regarding occluded geometry which does not pass the depth test and is therefore not resident in the G-buffer. These occluded fragments may have an impact on the proximity-based shadowing outcome of the ambient occlusion pass. This not only decreases image quality but also prevents the application of SSAO on multiple layers of transparent surfaces where the shadow contribution depends on opacity. We propose a novel approach to the SSAO concept by taking advantage of per-pixel fragment lists to store multiple geometric layers of the scene in the G-buffer, thus allowing order independent transparency (OIT) in combination with high quality, opacity-based ambient occlusion (OITAO). This A-buffer concept is also used to enhance overall ambient occlusion quality by providing stable results for low-frequency details in dynamic scenes. Furthermore, a flexible compression-based optimization strategy is introduced to improve performance while maintaining high quality results.

Show publication details

Binotto, Alecio; Wehrmeister, Marco A.; Kuijper, Arjan; Pereira, Carlos Eduardo

Sm@rtConfig: A Context-Aware Runtime and Tuning System Using an Aspect-Oriented Approach for Data Intensive Engineering Applications

2013

Control Engineering Practice, Vol.21 (2013), 2, pp. 204-217

Distributing the workload upon all available Processing Units (PUs) of a high-performance heterogeneous platform (e.g., PCs composed by CPU-GPUs) is a challenging task, since the execution cost of a task on distinct PUs is non-deterministic and affected by parameters not known a priori. This paper presents Sm@rtConfig, a context-aware runtime and tuning system based on a compromise between reducing the execution time of engineering applications and the cost of tasks' scheduling on CPU-GPUs' platforms. Using Model-Driven Engineering and Aspect Oriented Software Development, a high-level specification and implementation for Sm@rtConfig has been created, aiming at improving modularization and reuse in different applications. As case study, the simulation subsystem of a CFD application has been developed using the proposed approach. These system's tasks were designed considering only their functional concerns, whereas scheduling and other non-functional concerns are handled by Sm@rtConfig aspects, improving tasks modularity. Although Sm@rtConfig supports multiple PUs, in this case study, these tasks have been scheduled to execute on an platform composed by one CPU and one GPU. Experimental results show an overall performance gain of 21.77% in comparison to the static assignment of all tasks only to the GPU.

Show publication details

Stein, Christian; Kuijper, Arjan (Betreuer); Limper, Max (Betreuer)

Spatial Data Structures for Efficient Visualization of Massive 3D Models on the Web: Räumliche Datenstrukturen zur effizienten Visualisierung riesiger 3D-Modelle im Web

2013

Darmstadt, TU, Master Thesis, 2013

The visualization of massive 3d models, mostly CAD data, consisting of several millions of triangles is still an intensively examined field of research. Compared to the constant performance increase of 3d graphics cards, their complexity grows even faster. Therefore, the problem of rendering such models at an interactive framerate is not to be solved by a higher speed of rasterization all alone. Recently, the combination of Javascript and WebGL gained a lot of attention for the possibility of using hardware acceleration when rendering 3d graphics directly in the browser. However, due to these technologies' limitations of a generally way slower execution speed or a downgraded set of functionality, the previously stated problem gets intensified when transfered to the web environment. A practical solution has to shrink the amount of data to be processed by an intelligent selection. This thesis addresses the application area of Just-In-Browser visualization of these kinds of 3d models. Therefore, spatial data structures and hardware supported visibility determination are evaluated for their applicability and benefit in the web context. To allow for an instant viewing, any time-consuming optimizations are spared. In return, a decrease in correctness of the generated images is accepted. The possibly unstructured scene data is transformed into an optimized representation which employs the spatial data structures in the process of visibility determination. A selection of spatial data structures and culling techniques are evaluated across different environments. Additionally, a feedback controlled adjustment for the culling parameters is introduced.

Show publication details

Große-Puppendahl, Tobias; Braun, Andreas; Kamieth, Felix; Kuijper, Arjan

Swiss-Cheese Extended: An Object Recognition Method for Ubiquitous Interfaces based on Capacitive Proximity Sensing

2013

Bodker, Susanne (Ed.) et al.: CHI 2013. Changing Perspective : The 31st Annual CHI Conference on Human Factors in Computing Systems. New York: ACM Press, 2013, pp. 1401-1410

Conference on Human Factors in Computing Systems (CHI) <31, 2013, Paris, France>

Swiss-Cheese Extended proposes a novel real-time method for recognizing objects with capacitive proximity sensors. Applying this technique to ubiquitous user interfaces, it is possible to detect the 3D-position of multiple human hands in different configurations above a surface that is equipped with a small number of sensors. The retrieved object configurations can significantly improve a user's interaction experience or an application's execution context, for example by detecting multi-hand zoom and rotation gestures or recognizing a grasping hand. We emphasize the broad applicability of the proposed method with a study of a multi-hand gesture recognition device. Swiss-Cheese Extended proposes a novel real-time method for recognizing objects with capacitive proximity sensors. Applying this technique to ubiquitous user interfaces, it is possible to detect the 3D-position of multiple human hands in different configurations above a surface that is equipped with a small number of sensors. The retrieved object configurations can significantly improve a user's interaction experience or an application's execution context, for example by detecting multi-hand zoom and rotation gestures or recognizing a grasping hand. We emphasize the broad applicability of the proposed method with a study of a multi-hand gesture recognition device.

Show publication details

Herber, Sebastian; Kuijper, Arjan (Betreuer); Große-Puppendahl, Tobias (Betreuer)

Tangible Interaction Using Capacitive Near-Field Communication

2013

Darmstadt, TU, Bachelor Thesis, 2013

Tangible user interfaces recently gained popularity as they offer an intuitive and natural way of interaction. In this thesis, a novel approach to tangible user interfaces using capacitive sensing is presented. In the past, capacitive sensing has been applied to proximity sensing, touch and gesture recognition and more purposes. The system developed in this project enables communication over several centimeters using capacitive coupling. In contrast to other close-range transmission technologies (e.g. inductive NFC), the capacitive domain offers several interesting properties, which can be exploited to create a richer interaction experience with less effort in hardware and cost. A platform consisting of hardware, software and a broadcast protocol is introduced and investigated in detail. It features low-powered tags, which are attached to objects for tangible interaction. The tags are equipped with sensors to increase their functionality and allow users to perform gestures with the associated objects.

Show publication details

Chingovska, Ivana; Yang, Jinwei; Lei, Zhen; Yi, Dong; Li, Stan Z.; Kähm, Olga; Glaser, Christian; Damer, Naser; Kuijper, Arjan; Nouak, Alexander; Komulainen, Jukka; Pereira, Tiago de Freitas; Gupta, Shubham; Khandelwal, Shubham; Bansal, Shubham; Rai, Ayush; Krishna, Tarun; Goyal, Dushyant; Waris, Muhammad-Adeel; Zhang, Honglei; Ahmad, Iftikhar; Kiranyaz, Serkan; Gabbouj, Moncef; Tronci, Roberto; Pili, Maurizio; Sirena, Nicola; Roli, Fabio; Galbally, Javier; Fierrez, Julian; Pinto, Allan; Pedrini, Helio; Schwartz, William Robson; Rocha, Anderson; Anjos, André; Marcel, Sébastien

The 2nd Competition on Counter Measures to 2D Face Spoofing Attacks

2013

Ortega-Garcia, Javier (Ed.) et al.: 2013 International Conference on Biometrics (ICB). New York: IEEE Press, 2013, 6 p.

IAPR International Conference on Biometrics (ICB) <6, 2013, Madrid, Spain>

As a crucial security problem, anti-spoofing in biometrics, and particularly for the face modality, has achieved great progress in the recent years. Still, new threats arrive in form of better, more realistic and more sophisticated spoofing attacks. The objective of the 2nd Competition on Counter Measures to 2D Face Spoofing Attacks is to challenge researchers to create counter measures effectively detecting a variety of attacks. The submitted propositions are evaluated on the Replay-Attack database and the achieved results are presented in this paper.

Show publication details

Kahn, Svenja; Bockholt, Ulrich; Kuijper, Arjan; Fellner, Dieter W.

Towards Precise Real-Time 3D Difference Detection for Industrial Applications

2013

Computers in Industry, Vol.64 (2013), 9, pp. 1115-1128

3D difference detection is the task to verify whether the 3D geometry of a real object exactly corresponds to a 3D model of this object. We present an approach for 3D difference detection with a hand-held depth camera. In contrast to previous approaches, with the presented approach geometric differences can be detected in real-time and from arbitrary viewpoints. The 3D difference detection accuracy is improved by two approaches: first, the precision of the depth camera's pose estimation is improved by coupling the depth camera with a high precision industrial measurement arm. Second, the influence of the depth measurement noise is reduced by integrating a 3D surface reconstruction algorithm. The effects of both enhancements are quantified by a ground-truth based quantitative evaluation, both for a time-of-flight (SwissRanger 4000) and a structured light depth camera (Kinect). With the proposed enhancements, differences of few millimeters can be detected from 1 m measurement distance.

Show publication details

Gavrilova, Marina L.; Tan, C.J. Kenneth; Kuijper, Arjan

Transactions on Computational Science XVIII: Special Issue on Cyberworlds

2013

Berlin, Heidelberg, New York : Springer, 2013

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

Lecture Notes in Computer Science (LNCS) 7848

Created intentionally or spontaneously, cyberworlds are information spaces and communities that immensely augment the way we interact, participate in business, and receive information throughout the world. Cyberworlds seriously impact our lives and the evolution of the world economy by taking such forms as social networking services, 3D shared virtual communities, and massively multiplayer online role-playing games. The current volume is devoted to the topic of security in virtual worlds. It is comprised of 14 excellent papers selected from 75 submissions to "The International Conference on Cyberworlds 2012", held in Darmstadt, Germany, September 25 - 27, 2012. The articles appearing in this special issue are revised and extended versions of a selection of papers presented at CW 2012. The papers were selected based on reviewers' comments, on the quality of the oral presentations, and the conference delegates' feedback.

Show publication details

Steiger, Martin; Lücke-Tieke, Hendrik; May, Thorsten; Kuijper, Arjan; Kohlhammer, Jörn

Using Layout Stitching to Create Deterministic Local Graph Layouts

2013

Oliveira, Manuel M. (Ed.) et al.: WSCG 2013. Full Papers. Proceedings : The 21st International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. Plzen: University of West Bohemia, 2013, pp. 1-9

International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) <21, 2013, Plzen, Czech Republic>

Dynamic graph layouts are often used to position nodes in local views of large graphs. These layouts can be optimized to minimize changes when navigating to other parts of the graph. Dynamic graph layout techniques do not, however, guarantee that a local layout is recognizable when the user visits the same area twice. In this paper we present a method to create stable and deterministic layouts of dynamic views of large graphs. It is based on a well-known panorama-stitching algorithm from the image processing domain. Given a set of overlapping photographs it creates a larger panorama that combines the original images. In analogy to that our algorithm stitches pre-computed layouts of subgraphs to form a larger, single layout. This deterministic approach makes structures and node locations persistent which creates identical visual representations of the graph. This enables the user to recognize previously encountered parts and to decide whether a certain part of a dataset has already been explored before or not.

Show publication details

Ruppert, Tobias; Bernard, Jürgen; Ulmer, Alex; Kuijper, Arjan; Kohlhammer, Jörn

Visual Access to Optimization Problems in Strategic Environmental Assessment

2013

Bebis, George (Ed.) et al.: Advances in Visual Computing. 9th International Symposium, ISVC 2013 : Proceedings, Part II. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 8034), pp. 361-372

International Symposium on Visual Computing (ISVC) <9, 2013, Rethymnon, Crete, Greece>

The complexity of actual decision making problems especially in the field of policy making is increasing due to conflicting aspects to be considered. Methods from the field of strategic environmental assessment consider environmental, economic, and social impacts caused by political decisions. This makes the analysis of reasonable decisions more complex. Mathematical models like optimization can help to balance conflicting aspects. Although they are not easy to understand, these complex models and the resulting policy options have to be reviewed by the decision makers. In this work we present a visual-interactive interface to an optimization system capable of solving multidimensional decision problems. The interface enables visual access to the complex optimization models, and the analysis of alternative solutions. As a result strategic environmental assessment can be included in the decision making process. An evaluation in the domain of regional energy planning underlines the usability and usefulness of the visual interface.

Show publication details

Ulmer, Alex; Ruppert, Tobias (Betreuer); Kuijper, Arjan (Betreuer)

Visual Analysis of Multidimensional Optimization Problems

2013

Darmstadt, TU, Bachelor Thesis, 2013

This work presents a visual interface to access an optimization system to solve multidimensional decision problems. Today the complexity of decision making problems is generally high because many aspects have to be considered. Especially in the policy making process substantial decisions require profound knowledge. Strategic environmental assessment plays an important role in this process. The duty to consider environmental impacts caused by political decisions is obliged by law in many countries. This makes the decision making process more complex and requires better methods to find a solution. With optimization it is possible to create mathematical models that weight out multidimensional decisions. The models and the produced solutions have to be reviewed by the decision makers but they are not easy-to-understand. In my approach I design and implement a visual-interactive application that enables the visual access to complex optimization models, and the analysis of alternative solutions. It makes use of approved visualization techniques and state of the art methodologies to make abstract information transparent. This conveys the knowledge behind the decision options in a reasonable way. Contributions are a visual-interactive interface that enables the visual access to complex optimization models, and the analysis of alternative solutions. In this way strategic environmental assessment can be improved and the policy maker is able to understand where policy options originated. The evaluation of the prototype revealed that the interface offers an easy access to alternative solutions and gives more insight to the process behind finding policy options.

Show publication details

Landesberger, Tatiana von; Bremm, Sebastian; Kirschner, Matthias; Wesarg, Stefan; Kuijper, Arjan

Visual Analytics for Model-based Medical Image Segmentation: Opportunities and Challenges

2013

Expert Systems with Applications, Vol.40 (2013), 12, pp. 4934-4943

Segmentation of medical images is a prerequisite in clinical practice. Many segmentation algorithms use statistical shape models. Due to the lack of tools providing prior information on the data, standard models are frequently used. However, they do not necessarily describe the data in an optimal way. Model-based segmentation can be supported by Visual Analytics tools, which give the user a deeper insight into the correspondence between data and model result. Combining both approaches, better models for segmentation of organs in medical images are created. In this work, we identify the main tasks and problems in model-based image segmentation. As a proof of concept, we show that already small visual-interactive extensions can be very beneficial. Based on these results, we present research challenges for Visual Analytics in this area.

Show publication details

Burkhardt, Dirk; Nazemi, Kawa; Stab, Christian; Steiger, Martin; Kuijper, Arjan; Kohlhammer, Jörn

Visual Statistics Cockpits for Information Gathering in the Policy-Making Process

2013

Bebis, George (Ed.) et al.: Advances in Visual Computing. 9th International Symposium, ISVC 2013 : Proceedings, Part II. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 8034), pp. 86-97

International Symposium on Visual Computing (ISVC) <9, 2013, Rethymnon, Crete, Greece>

A major step in ICT-driven policy making is information gathering. During this phase, analysts and experts have to deal with a high number of statistical data which they use as a basis to identify problems and find appropriate solutions. This paper introduces a statistical data model to support these analysts and experts. It allows for handling the complexity (i.e. the dimensions) of the data for the visualizations. In particular, it helps to use the same data for two-dimensional, but also multi-dimensional statistics visualizations. Based on this statistic data model we introduce an interactive approach of visual statistics cockpits. This results in highly interactive statistics visualization cockpits that enable both analysts and experts to improve problem assessment and solution finding.

Show publication details

Zilke, Jan Ruben; Kuijper, Arjan (Betreuer); Burkhardt, Dirk (Betreuer)

Visualisierung und Analyse von politischen Daten unter Verwendung von Linked Open Government Data

2013

Darmstadt, TU, Bachelor Thesis, 2013

Die Nutzung des Internets durch den öffentlichen Sektor nimmt immer mehr zu. Im Rahmen von EGovernment werden Bürgern mehr und mehr Dienstleistungen online zur Verfügung gestellt, die bisher einen Besuch beim zuständigen Amt erforderten. Auch, um Bürger stärker in das politische Geschehen einzubeziehen, wird auf das Internet zurückgegriffen. Regierungen publizieren im Netz massenhaft erhobene Daten und ermöglichen so die Analyse der aktuellen politischen Lage. Hier soll Bürgern die Möglichkeit gegeben werden, Auffälligkeiten zu identifizieren, Verbesserungspotenziale zu erkennen und Veränderungsprozesse anzustoßen, also aktiv in die politische Tagesordnung einzugreifen und diese mitzugestalten. Für die Analyse politischer Daten ist es sinnvoll, Visualisierungen als Hilfsmittel einzusetzen. Damit wird eine effizientere Untersuchung der Datenbasis ermöglicht. Derzeit mangelt es allerdings an Visualisierungen, die die Besonderheiten des öffentlichen Sektors berücksichtigen. Das umfasst einerseits die fehlende Nutzung von Wissen, das bereits mit Linked Open Government Data abgebildet wird. Andererseits bleiben Visualisierungen hinter ihren Möglichkeiten zurück was die direkte Förderung von mehr Bürgerbeteiligung anbelangt. Andere Visualisierungen erschweren die Analyse durch den nur halbherzigen Einsatz von Interaktionsmöglichkeiten. Um diesem Mangel entgegenzutreten wird in dieser Arbeit ein Modell zur visuellen Unterstützung von Policy Modeling vorgestellt, das die Charaktereigenschaften von E-Government und den zugehörigen Daten in Form von Linked Open Government Data berücksichtigt. Hier wird auf den Einsatz vielfältiger Interaktionsmöglichkeiten gesetzt, um eine visuelle Analyse möglichst effektiv zu gestalten. Zentraler Bestandteil des Modells ist außerdem die Integration von Partizipationswerkzeugen mit dem Zweck, eine möglichst direkte Gelegenheit zu schaffen, erlangtes Wissen weiterzugeben und Lösungsvorschläge zu diskutieren. Der Aufbau der Arbeit ist wie folgt: Nach einer kurzen Einleitung in die Ziele der Thesis folgt die Vorstellung des Themas E-Government und der zugehörigen Charakteristika. Anschließend wird genauer untersucht, welche Daten im E-Government-Umfeld vorhanden sind und in welcher Form sie zur Verfügung stehen. Das darauf folgende Kapitel stellt vor, wie Visualisierungen bisher von der öffentlichen Hand eingesetzt werden und gibt Ratschläge, wie diese in Zukunft verbessert werden könnten. Diese Empfehlungen werden dann unter Beachtung des E-Government-Kontextes in einem Modell zur visuellen Unterstützung von Policy Modeling formalisiert. Es folgt eine theoretische Evaluierung des Modells anhand des FUPOL-Projektes, bevor die Arbeit mit einem Fazit beendet wird.

Show publication details

Brodkorb, Felix; Landesberger, Tatiana von (Betreuer); Kuijper, Arjan (Betreuer)

Visualisierung von Graphen mit geographischem Bezug

2013

Darmstadt, TU, Master Thesis, 2013

Bei Graphen mit geographischem Bezug gibt es Probleme, wenn sie auf einer Karte visualisiert werden sollen. Die Probleme sind Overplotting von Knoten und Kanten, sowie Teile des Graphen, die außerhalb des Bildschirms liegen. Die Ursache ist eine ungleichmäßige Verteilung der Knoten. In dieser Arbeit werden Visualisierungsmethoden vorgestellt, die diese Probleme versuchen zu lösen, ohne dass dabei die geographische Struktur des Graphen zu stark verändert wird. Dazu werden die Knoten in eine Cluster-Hierarchie eingefügt, die auf der politischen Einteilung der Welt basiert. Mit den Clustern können dann die Knoten eines Gebiets zu einem Superknoten zusammengefügt werden. Knoten, die sich außerhalb des Bildschirms befinden, werden als Proxy-Knoten am Bildschirmrand dargestellt. Um Details von kleinen oder entfernten Gebieten sehen zu können, werden Insets verwendet. Dabei handelt es sich um kleine Fenster, die auf der Karte dargestellt werden und die entsprechenden Teile des Graphen und das dazugehörige Gebiet anzeigen. Damit diese Teilgraphen nicht unter Overplotting oder Kantenüberschneidungen leiden, wird lokales Lügen verwendet. Diese Technik verändert das Layout des Graphen in kleinen Gebieten, wo die exakte Position von Knoten nicht wichtig ist, so, dass Overplotting und Kantenüberschneidungen minimiert werden. Dazu werden noch Filter verwendet, mit denen der Benutzer den Graph vereinfachen kann, um die direkte und indirekte Nachbarschaft von einzelnen Knoten hervorheben zu können. Die Techniken werden auf Beispielgraphen angewendet, die auf realen Daten basieren, und die Ergebnisse werden diskutiert.

Show publication details

Klowsky, Ronny; Kuijper, Arjan; Goesele, Michael

Weighted Patch-Based Reconstruction: Linking (Multi-view) Stereo to Scale Space

2013

Kuijper, Arjan (Ed.) et al.: Scale Space and Variational Methods in Computer Vision : 4th International Conference, SSVM 2013. Berlin, Heidelberg, New York: Springer, 2013. (Lecture Notes in Computer Science (LNCS) 7893), pp. 234-245

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) <4, 2013, Leibnitz, Austria>

Surface reconstruction using patch-based multi-view stereo commonly assumes that the underlying surface is locally planar. This is typically not true so that least-squares fitting of a planar patch leads to systematic errors which are of particular importance for multi-scale surface reconstruction. In a recent paper, we determined the modulation transfer function of a classical patch-based stereo system. Our key insight was that the reconstructed surface is a box-filtered version of the original surface. Since the box filter is not a true low-pass filter this causes high-frequency artifacts In this paper, we propose an extended reconstruction model by weighting the least-squares fit of the 3D patch. We show that if the weighting function meets specified criteria the reconstructed surface is the convolution of the original surface with that weighting function. A choice of particular interest is the Gaussian which is commonly used in image and signal processing but left unexploited by many multi-view stereo algorithms. Finally, we demonstrate the effects of our theoretic findings using experiments on synthetic and real-world data sets.

Show publication details

Schreiber, Dominik; Kuijper, Arjan (Betreuer); Tazari, Mohammad-Reza (Betreuer)

Zugriffskontrolle in Intelligenten Umgebungen

2013

Darmstadt, TU, Bachelor Thesis, 2013

Das Ziel dieser Arbeit ist, die Sicherheit in intelligenten Umgebungen zu analysieren, Bedrohungen zu beschreiben, und eine Zugriffskontrolle als Lösung zu konzipieren. Dies ist entscheidend, da intelligente Umgebungen immer mehr Einzug in den Alltag der Menschen erhalten und ihnen dort sehr verantwortungsvolle Aufgaben übertragen werden, bei denen eine Fehlfunktion oder ein Angriff besonders dramatische Folgen hat. In dieser Arbeit wird zunächst der aktuelle Stand zur Sicherheit in verteilten, intelligenten Umgebungen beschrieben, dann auf die Middleware universAAL und andere verteilte Umgebungen eingegangen, und eine Zugriffskontrolllösung für das Senden und Empfangen von Nachrichten innerhalb der Umgebung konzipiert, bei der der Nutzer bei der Installation für jede Nachricht das Empfangen erlaubt oder verbietet. Die Realisierung auf Basis von universAAL wird dargestellt und besprochen, die Probleme die dabei auftraten, und aufgrund derer eine Evaluierung der Realisierung nicht möglich war, werden benannt. Das Ergebnis der Arbeit ist, dass Zugriffskontrolle in verteilten Umgebungen eine entscheidende Rolle spielt, bisher wenig funktionierende Implementierungen existieren, und eine Realisierung auf Basis einer Manifest-Datei, bei der der Nutzer bei der Installation eine Policy erstellt, möglich ist.

Show publication details

Kuijper, Arjan; Sourin, Alexei; Fellner, Dieter W.

2012 International Conference on Cyberworlds. Proceedings: Cyberworlds 2012

2012

Los Alamitos, Calif. : IEEE Computer Society Conference Publishing Services (CPS), 2012

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

Created intentionally or spontaneously, cyberworlds are information spaces and communities that immensely augment the way we interact, participate in business and receive information throughout the world. Cyberworlds seriously impact our lives and the evolution of the world economy by taking such forms as social networking services, 3D shared virtual communities and massively multiplayer online role-playing games. Cyberworlds 2012 was held 25-27 September 2012 and was organized by Fraunhofer IGD and TU Darmstadt, Germany, in cooperation with EUROGRAPHICS Association and supported by the IFIP Workgroup Computer Graphics and Virtual Worlds.

Show publication details

Tschirsich, Martin; Kuijper, Arjan

A Discrete Scale Space Neighborhood for Robust Deep Structure Extraction

2012

Gimel'farb, Georgy (Ed.) et al.: Structural, Syntactic, and Statistical Pattern Recognition : Joint IAPR International Workshop SSPR & SPR 2012. Berlin, Heidelberg, New York: Springer, 2012. (Lecture Notes in Computer Science (LNCS) 7626), pp. 126-134

The Joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR) <14, 2012, Hiroshima, Japan>

Linear or Gaussian scale space is a well known multi-scale representation for continuous signals. The exploration of its so-called deep structure by tracing critical points over scale has various theoretical applications and allows for the construction of a scale space hierarchy tree. However, implementational issues arise, caused by discretization and quantization errors. In order to develop more robust scale space based algorithms, the discrete nature of computer processed signals has to be taken into account. Aiming at a computationally practicable implementation of the discrete scale space framework, we investigated suitable neighborhoods, boundary conditions and sampling methods. We show that the resulting discrete scale space respects important topological invariants such as the Euler number, a key criterion for the successful implementation of algorithms operating on its deep structure. We discuss promising properties of topological graphs under the influence of smoothing, setting the stage for more robust deep structure extraction algorithms.

Show publication details

Kuijper, Arjan; Schwarzkopf, Andreas; Kalbe, Thomas; Goesele, Michael

Efficient Volumetric Anisotropic Diffusion Computation on GPUs

2012

Proceedings in Applied Mathematics and Mechanics, Vol.12 (2012), 1, pp. 737-738

Annual Meeting of the International Association of Applied Mathematics and Mechanics (GAMM) <83, 2012, Darmstadt, Germany>

We present an efficient implementation of volumetric anisotropic image diffusion on modern programmable graphics processing units (GPUs). We avoid the computational bottleneck of a time consuming eigenvalue decomposition in R3. Instead, we use a projection of the Hessian matrix along the surface normal onto the tangent plane of the local isodensity surface and solve for the remaining two tangent space eigenvectors. We derive closed formulas to achieve this resulting in efficient GPU code. Our most complex volumetric anisotropic diffusion gains a speed up of more than 600 compared to a CPU solution [1].

Show publication details

Altenhofen, Christian; Kuijper, Arjan (Betreuer); Knuth, Martin (Betreuer)

Effiziente Selbstschattierung in Szenen mit bildbasierter Beleuchtungsinformation und glänzenden Materialien

2012

Darmstadt, TU, Master Thesis, 2012

Beim Design und Virtual Prototyping von Produkten werden heutzutage oftmals interaktive Computersimulationen eingesetzt. Um die Vorstellungen des Designers möglichst realitätsnah wiedergeben zu können, müssen diese Simulatoren über eine qualitativ hochwertige und plausible Beleuchtung verfügen. Hinzu kommt eine möglichst hohe Flexibilität bezüglich der Gestaltung der Oberflächen und der Wahl der verwendeten Materialien. In den meisten Fällen ermöglichen die verwendeten Simulatoren zusätzlich die direkte Manipulation der Geometrie oder Anordnung der Objekte durch den Benutzer. Es gibt bereits Verfahren, die solche dynamischen Szenen mit bildbasierten Beleuchtungsinformationen in Echtzeit beleuchten und Schattenwürfe berechnen können; die so genannten "Image Based Directional Occlusion" Verfahren (IBDO). Allerdings sind sie bezüglich der Materialien der zu beleuchtenden Objekte sehr eingeschränkt: Sie unterstützen nur diffuse und leicht glänzende Materialien; für hoch glänzende und spiegelnde Oberflächen sind sie nicht geeignet. In dieser Arbeit wird ein neues Beleuchtungssystem vorgestellt, das ähnlich wie die IBDO Algorithmen viele Lichtquellen aus einer Environment Map erzeugt, diese dann jedoch nicht direkt zur Beleuchtung der Szene, sondern lediglich zum Sammeln der Verdeckungsinformationen verwendet. Für die eigentliche Beleuchtung werden wie beim Environment Mapping die Farbwerte über einen oberflächenabhängigen Sample- Vektor aus der Environment Map (EM) ausgelesen. Die über die Lichtquellen gesammelten Verdeckungsinformationen in Form von Variance Shadow Maps (VSMs) werden dazu eingesetzt, nicht sichtbare Teile der EM dynamisch auszublenden. Die geforderte Flexibilität in der Materialwahl wird durch verschiedene MipMap Stufen der EM gewährleistet. Das Beleuchtungssystem verbindet somit die freie Materialwahl des Environment Mappings mit der bildbasierten Schattenberechnung der IBDO Verfahren. Die verwendeten VSMs bieten einen weichen Schattenwurf bei vergleichsweise geringem Rechenaufwand, verlieren aber bei niedrigen Auflösungen wichtige Details bei der Selbstschattierung. Die Steuerung der Reflektivität der Objekte über MipMaps erlaubt einen fließenden Übergang von 100% spiegelnd bis 100% diffus. Zusätzlich können Algorithmen zur Manipulation der Oberflächengeometrie, wie beispielsweise Bump-, Normalund Displacement-Mapping sowie Tesselierung, problemlos vorgelagert werden; das Beleuchtungssystem ist kompatibel. Der entscheidende Faktor für die Performance des Verfahrens ist die Zahl der verwendeten Lichtquellen. Für angemessene Mengen (100 bis 200) liefert es auf aktueller Mittelklasse-Hardware (z.B. AMD Radeon HD6850 oder NVIDIA Geforce GTX 280) interaktive Bildraten. Die hohe Zahl der benötigten Texturen und die damit verbundene Menge an Grafikspeicher sowie die zwanghafte Aufteilung des Renderings in mehrere Render-Passes stellen jedoch einen Nachteil gegenüber den oben erwähnten IBDO Verfahren dar.

Show publication details

Ebinger, Peter; Kuijper, Arjan; Wolthusen, Stephen

Enhanced Location Tracking for Tactical MANETs based on Particle Filters and Additional Information Sources

2012

2012 Military Communications and Information Systems Conference (MCC). Los Alamitos, Calif.: IEEE Computer Society, 2012, 8 p.

Military Communications and Information Systems Conference (MCC) <13, 2012, Gdansk, Poland>

The networking capabilities of tactical mobile ad-hoc networks (MANETs) provide the basis to enhance robustness and accuracy of Blue Force Tracking (BFT) where existing BFT mechanisms are unavailable, unreliable, or simply not sufficiently accurate (owing to factors such as update frequencies and the need for back-link availability). BFT is an essential element to any tactical environment given its ability to contribute to situational awareness at all levels. Tactical environments are characterized by spectrum contention, jamming and other factors limiting the ability of naive approaches, e. g. in urban environments and broken terrain. Unlike previous work this paper aims to provide MANET-based BFT without the requirement of line-of-sight (LOS) links or backend infrastructure which is robust against temporal disruption of network connectivity. These results are achieved by distributedly fusing sensor data and additional information sources across the tactical MANET using techniques also employed in robotics and object tracking. Our contribution is the provision of enhanced BFT mechanisms exploiting networking capabilities of tactical MANETs and data fusion mechanisms based on Sequential Monte Carlo methods, specifically particle filters, incorporating additional information such as mission information (e. g. mobility models) and topographic data. We demonstrate that the use of these techniques enhances both accuracy and robustness as compared to standard BFT by using a simulation environment with various mobility and radio propagation characteristics.

Show publication details

Kahn, Svenja; Kuijper, Arjan

Fusing Real-Time Depth Imaging with High Precision Pose Estimation by a Measurement Arm

2012

Kuijper, Arjan (Ed.) et al.: 2012 International Conference on Cyberworlds. Proceedings : Cyberworlds 2012. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2012, pp. 256-260

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

Recently, depth cameras have emerged which capture dense depth images in real-time. To benefit from their 3D imaging capabilities in interactive applications which support an arbitrary camera movement, the position and orientation of the depth camera needs to be robustly estimated in realtime for each captured depth image. Therefore, this paper describes how to combine a depth camera with a mechanical measurement arm to fuse real-time depth imaging with realtime, high precision pose estimation. Estimating the pose of a depth camera with a measurement arm has three major advantages over 2D/3D image based optical pose estimation: The measurement arm has a very precise guaranteed accuracy better than 0.1mm, the pose estimation accuracy is not influenced by the captured scene and the computational load is much lower than for optical pose estimation, leaving more processing power for the applications themselves.

Show publication details

Schreck, Tobias; Scherer, Maximilian; Walter, Michael; Bustos, Benjamin; Yoon, Sang Min; Kuijper, Arjan

Graph-Based Combinations of Fragment Descriptors for Improved 3D Object Retrieval

2012

ACM SIGMM: MMSys '12 : Proceedings of the 3rd Multimedia Systems Conference. New York: ACM, 2012, pp. 23-28

Multimedia Systems Conference (MMSys) <3, 2012, Chapel Hill, NC, USA>

3D Object Retrieval is an important field of research with many application possibilities. One of the main goals in this research is the development of discriminative methods for similarity search. The descriptor-based approach to date has seen a lot of research attention, with many different extraction algorithms proposed. In previous work, we have introduced a simple but effective scheme for 3D model retrieval based on a spatially fixed combination of 3D object fragment descriptors. In this work, we propose a novel flexible combination scheme based on finding the best matching fragment descriptors to use in the combination. By an exhaustive experimental evaluation on established benchmark data we show the capability of the new combination scheme to provide improved retrieval effectiveness. The method is proposed as a versatile and inexpensive method to enhance the effectiveness of a given global 3D descriptor approach.

Show publication details

Ettl, Anne-Sophie; Kuijper, Arjan (Betreuer)

Klassifikation von Bildbereichen in digitalisierten Dokumenten zur Anwendung auf mobilen Geräten

2012

Darmstadt, TU, Bachelor Thesis, 2012

Die weiterführende Verarbeitung und maschinelle Interpretation von Bildmaterial spielt eine immer wichtigere Rolle im Mobile-Bereich. Sowohl für die effiziente Kompression als auch für die maschinelle Auswertung von Texten bietet es sich an, Textinhalte nicht als Grafik, sondern als Textinformation zu speichern. Hierzu soll mit der Kamera eines Smartphones aufgenommenes Bildmaterial von Magazinen nach Text- und Bildbereichen klassifiziert werden. In der Arbeit werden etablierte Desktop-Verfahren vorgestellt und hinsichtlich ihrer Anwendungsmöglichkeiten auf Mobilgeräten untersucht. Im Anschluss wird ein Ansatz für ein Verfahren zur Bildsegmentierung entwickelt, das die begrenzten Ressourcen der mobilen Geräte berücksichtigt. Eine prototypische Implementierung wird in Python mithilfe der OpenCV-Bibliothek realisiert.

Show publication details

Wilmsdorff, Julian von; Marinc, Alexander (Betreuer); Kuijper, Arjan (Betreuer)

Kontextbasiertes Dokumentenmanagement in intelligenten Wohnumgebungen

2012

Darmstadt, TU, Bachelor Thesis, 2012

Heutzutage werden vermehrt verschiedenste Multimediageräte miteinander in immer weiter wachsenden intelligenten Umgebungen vernetzt. Obwohl diese Netze heutzutage Dank mobiler Technik und WLAN fast omnipräsent sind, arbeiten die darin enthaltenen Abspielgeräte immer noch weitgehend distinkt voneinander. Das einfache Abspielen einer Datei auf dem Wiedergabegerät A, die ursprünglich auf Gerät B beherbergt wird, ist daher, trotz der theoretisch vorhandenen Möglichkeit durch die Vernetzung, eine komplizierte Aufgabe geworden. Besonders das Abspielen und Anzeigen von Dateien auf Multimediageräten mit verschiedenen, unter Umständen begrenzten Wiedergabefähigkeiten ist ein nicht triviales Problem. Aktuelle Lösungen aus der Industrie setzen hier momentan noch auf wenig interoperable Ansätze in proprietären Systemen. Einzelne Multimediageräte gleicher Hersteller lassen sich so zwar intelligent verbinden, gerade mit Hinsicht auf die Benutzbarkeit skaliert das System jedoch schlecht, die (auch physikalische) Verteilung erhöht die Schwierigkeit des Zugangs zu den Funktionen und die Steuerung ist weitgehend unabhängig vom Kontext des Benutzers. In dieser Arbeit wird daher eine Lösung entwickelt, deren Fokus insbesondere auf dem kontextbasierten Abspielen von Dateien liegt. Genauer auf dem Wiedergeben von Video-, Musik-, Bild- sowie Textdateien auf Ausgabegeräten mit unterschiedlichen Darstellungsmöglichkeiten, sowie der Verteilung dieser Multimediadateien zwischen den Geräten. Im Zentrum steht hierbei ein mobiles Gerät zur Visualisierung der räumlichen Verteilung aller Geräte unter Einbeziehung der Position des Benutzers und der intuitiven Verschiebung von Dateien verschiedener Typen zwischen diesen.

Show publication details

Vandommele, Tjark; Kuijper, Arjan (Betreuer); Stocklöw, Carsten (Betreuer)

Konzeption und Implementierung eines Ressource Servers für multimodale Benutzungsschnittstellen in verteilten Umgebungen

2012

Darmstadt, TU, Bachelor Thesis, 2012

Intelligente verteilte Umgebungen spielen vor allem im Bereich der alltäglichen Unterstützung von Menschen mit Assistenzbedarf eine immer größere Rolle. Mit ihrer Hilfe wird versucht, diesen Menschen so lange wie möglich ein selbstbestimmtes Leben in der gewohnten Umgebung zu ermöglichen. Problematisch bei diesen Systemen ist der enorme Aufwand, der für die Entwicklung neuer Anwendungen benötigt wird. Ein Teil dieses Aufwandes entsteht dadurch, dass es nicht immer möglich ist, die üblichen Schnittstellen für die Interaktion zwischen System und Anwender zu nutzen. Häufig müssen zu diesem Zweck alternative Modalitäten verwendet werden, um die eingeschränkten Fähigkeiten eines Benutzers zu berücksichtigen. Dies führt dazu, dass Anwendungs-Entwickler neue Bedienkonzepte für ihre Produkte entwickeln müssen. Darüber hinaus verursacht eine hohe Diversität möglicher Geräte, die in einer verteilten Umgebung für die Interaktion mit dem Anwender genutzt werden können, dass selbst innerhalb einer Modalität unterschiedliche Präsentationen der Schnittstellen benötigt werden. Als Resultat daraus müssen bei der Entwicklung einer Anwendung für ein solches System große Mengen unterschiedlicher Ressourcen zur Verfügung gestellt werden. Dies ist nicht nur sehr aufwändig, es ist sogar fast unmöglich, jede mögliche Situation vorherzusehen und die entsprechenden Ressourcen bereitzustellen. In dieser Arbeit wird als Lösungsansatz für diese Problematik ein Ressource-Server vorgeschlagen. Diese Komponente soll in eine verteilte Umgebung integriert werden und dort die Verwaltung aller Ressourcen sicherstellen. Dies beinhaltet die Speicherung der Ressourcen, die Verteilung an Komponenten, die sie benötigen, und eine Möglichkeit, neue Ressourcen in das System zu integrieren. Somit sind Entwickler in der Lage, ihr Produkt nachträglich an ein spezielles System anzupassen. Des Weiteren können dadurch Dritt-Entwickler den Ressource-Server nutzen, um eigene Lösungen für spezielle Benutzergruppen in das System zu integrieren.

Show publication details

Tschirsich, Martin; Kuijper, Arjan

Laplacian Eigenimages in Discrete Scale Space

2012

Gimel'farb, Georgy (Ed.) et al.: Structural, Syntactic, and Statistical Pattern Recognition : Joint IAPR International Workshop SSPR & SPR 2012. Berlin, Heidelberg, New York: Springer, 2012. (Lecture Notes in Computer Science (LNCS) 7626), pp. 162-170

The Joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR) <14, 2012, Hiroshima, Japan>

Linear or Gaussian scale space is a well known multi-scale representation for continuous signals. However, implementational issues arise, caused by discretization and quantization errors. In order to develop more robust scale space based algorithms, the discrete nature of computer processed signals has to be taken into account. Aiming at a computationally practicable implementation of the discrete scale space framework we used suitable neighborhoods, boundary conditions and sampling methods. In analogy to prevalent approaches, a discretized diffusion equation is derived from the continuous scale space axioms adapted to discrete two-dimensional images or signals, including requirements imposed by the chosen neighborhood and boundary condition. The resulting discrete scale space respects important topological invariants such as the Euler number, a key criterion for the successful implementation of algorithms operating on its deep structure. In this paper, relevant and promising properties of the discrete diffusion equation and the eigenvalue decomposition of its Laplacian kernel are discussed and a fast and robust sampling method is proposed. One of the properties leads to Laplacian eigenimages in scale space: Taking a reduced set of images can be considered as a way of applying a discrete Gaussian scale space.

Show publication details

Klowsky, Ronny; Kuijper, Arjan; Goesele, Michael

Modulation Transfer Function of Patch-based Stereo Systems

2012

IEEE Computer Society: IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2012. New York: IEEE, 2012, pp. 1386-1393

Conference on Computer Vision and Pattern Recognition (CVPR) <30, 2012, Providence, RI, USA>

A widely used technique to recover a 3D surface from photographs is patch-based (multi-view) stereo reconstruction. Current methods are able to reproduce fine surface details, they are however limited by the sampling density and the patch size used for reconstruction. We show that there is a systematic error in the reconstruction depending on the details in the unknown surface (frequencies) and the reconstruction resolution. For this purpose we present a theoretical analysis of patch-based depth reconstruction. We prove that our model of the reconstruction process yields a linear system, allowing us to apply the transfer (or system) function concept. We derive the modulation transfer function theoretically and validate it experimentally on synthetic examples using rendered images as well as on photographs of a 3D test target. Our analysis proves that there is a significant but predictable amplitude loss in reconstructions of fine scale details. In a first experiment on real-world data we show how this can be compensated for within the limits of noise and reconstruction accuracy by an inverse transfer function in frequency space.

Show publication details

Gross, Richard; Bockholt, Ulrich (Betreuer); Kuijper, Arjan (Betreuer)

Multimodal Kinect-supported Interaction for the Visually Impaired

2012

Darmstadt, TU, Master Thesis, 2012

This thesis suggests a new computer interface, specifically targeted at blind and visually impaired people. We use the Microsoft Kinect to track a user's position and have implemented a novel spatial interface to control text-to-speech synthesis of a document. Which actions are executed is solely determined through hand movements in relation to the body. All feedback for the actions is given in auditory form, through synthesized speech or earcons. Earcons are brief, unique sounds that convey information. Visually impaired or blind users do not have to point or remember keyboard commands, but can use their proprioceptive sense to effectively explore documents and execute actions. The test results are encouraging. Even when participants found themselves lost they were always able to find their way back to an interface state they knew how to navigate. Furthermore, most negative feedback can be attributed to the current technical limitations and not the spatial interface itself.

Show publication details

Schwenk, Karsten; Kuijper, Arjan; Behr, Johannes; Fellner, Dieter W.

Practical Noise Reduction for Progressive Stochastic Ray Tracing with Perceptual Control

2012

IEEE Computer Graphics and Applications, Vol.32 (2012), 6, pp. 46-55

A proposed method reduces noise in stochastic ray tracing for interactive progressive rendering. The method accumulates high-variance light paths in a separate buffer, which is filtered by a high-quality edge-preserving filter. Then, this method adds a combination of the noisy unfiltered samples and the less noisy (but biased) filtered samples to the low-variance samples to form the final image. A novel per-pixel blending operator combines both contributions in a way that respects a user-defined threshold on perceived noise. This method can provide fast, reliable previews, even in the presence of complex features such as specular surfaces and high-frequency textures. At the same time, it's consistent in that the bias due to filtering vanishes in the limit.

Show publication details

Zhou, Xuebing; Kuijper, Arjan; Busch, Christoph

Retrieving Secrets from Iris Fuzzy Commitment

2012

Jain, Anil K. (Ed.) et al.: The 5th IAPR International Conference on Biometrics 2012. Proceedings : ICB 2012. New York: IEEE Press, 2012, pp. 238-244

IAPR International Conference on Biometrics (ICB) <5, 2012, New Delhi, India>

Iris patterns contain rich discriminative information and can be efficiently encoded in a compact binary form. These nice properties allow smooth integration with the fuzzy commitment scheme. Instead of storing iris codes directly, a random secret can be derived such that user privacy can be preserved. Despite the successful implementation, the dependency existing in iris codes can strongly reduce the security of fuzzy commitment. This paper shows that the distribution of iris codes complies with the Markov model. Additionally, an algorithm retrieving secrets from the iris fuzzy commitment scheme is proposed. The experimental results show that with knowledge of the iris distribution secrets can be recovered with low complexity. This work shows that distribution analysis is essential for security assessment of fuzzy commitment. Ignoring the dependency of binary features can lead to overestimation of the security.

Show publication details

Li, Bin; Schreck, Tobias; Godil, Afzal; Alexa, Marc; Boubekeur, T.; Bustos, Benjamin; Chen, J.; Eitz, M.; Furuya, T.; Hildebrand, K.; Huang, S.; Johan, H.; Kuijper, Arjan; Ohbuchi, R.; Richter, R.; Saavedra, J. M.; Scherer, Maximilian; Yanagimachi, T.; Yoon, G. J.; Yoon, Sang Min

SHREC' 12 Track: Sketch-Based 3D Shape Retrieval

2012

European Association for Computer Graphics (Eurographics): Eurographics 2012 Workshop on 3D Object Retrieval : EG 3DOR 2012. Goslar: Eurographics Association, 2012. (Eurographics Workshop and Symposia Proceedings Series), pp. 109-118

Eurographics Workshop on 3D Object Retrieval (EG 3DOR) <5, 2012, Cagliari, Italy>

Sketch-based 3D shape retrieval has become an important research topic in content-based 3D object retrieval. The aim of this track is to measure and compare the performance of sketch-based 3D shape retrieval methods implemented by different participants over the world. The track is based on a new sketch-based 3D shape benchmark, which contains two types of sketch queries and two versions of target 3D models. In this track, 7 runs have been submitted by 5 groups and their retrieval accuracies were evaluated using 7 commonly used retrieval performance metrics. We hope that the benchmark, its corresponding evaluation code, and the comparative evaluation results of the state-of-the-art sketch-based 3D model retrieval algorithms will contribute to the progress of this research direction for the 3D model retrieval community.

Show publication details

Lücke-Tieke, Hendrik; May, Thorsten (Betreuer); Kuijper, Arjan (Betreuer)

Stabiles Graph-Layout Basierend auf Lokalen Layouts

2012

Darmstadt, TU, Bachelor Thesis, 2012

Das Ziel einer Datenanalyse ist die Gewinnung von Wissen. Neben der vollautomatischen Analyse ist die interaktive Analyse dieser Daten ein vielversprechender Ansatz, denn sie ermöglicht es, die Vorteile des Menschen gegenüber rein maschinengestützter Verarbeitung zu nutzen. Vorteile wie robuste Wahrnehmung, visuelle Intelligenz und die Fähigkeit zur Entscheidung auf Basis ungenauer Informationen können genutzt werden, um den Wissensgewinn zu beschleunigen. Dies ist allerdings nur nutzbar, wenn umgekehrt der Analyst bei der Entwicklung und Evaluation von Hypothesen unterstützt wird. Eine Form der Unterstützung bietet die grafische Visualisierung von Netzwerken als Diagramme. Diese sogenannten Node-Link-Diagramme stellen Zusammenhänge zwischen Datenpunkten (Nodes) durch Linien (Links) dar, die diese miteinander verbinden. Die Effektivität einer visuellen Analyse mit Hilfe von Node-Link-Diagrammen wird 2 Faktoren stark beeinflusst: die Nachvollziehbarkeit von Zusammenhängen und die Übersichtlichkeit der Visualisierung. Dabei kann die Übersichtlichkeit durch die Menge der dargestellten Daten gesteuert werden. Die Nachvollziehbarkeit von Zusammenhängen hängt hingegen von der Positionierung der Datenpunkte ab. Viele Visualisierungsverfahren für Node-Link-Diagramme betrachten den gesamten Datensatz und erzeugen daraus eine Gesamtdarstellung, ein sogenanntes globales Layout. Dieses globale Layout erleichtert dem Betrachter die Orientierung, denn jeder Datenpunkt befindet sich immer an der gleichen Position. Ein Analyst kann sich so auf den Lageplan in seinem Kopf verlassen, die Visualisierung ist in diesem Sinne stabil. Dies ist allerdings ein Kompromiss auf Kosten der Genauigkeit lokaler Zusammenhänge. Doch genau diese Zusammenhänge können relevant sein und bedürfen daher einer gesonderten Betrachtung ohne Abhängigkeiten oder Einflüsse des restlichen Graphen. Ein solcher, unabhängig berechneter Ausschnitt wird als lokales Layout bezeichnet. Mit Unterstützung von interaktiven Explorationsverfahren kann die Übersichtlichkeit eines Node-Link- Diagramms gewährleistet werden. Dabei erkundet der Benutzer das Netzwerk schrittweise und kann so die Komplexität der Visualisierung steuern. Die statische, interaktive Exploration eines Graphen wird durch Filterung des globalen Layouts realisiert. Die dynamische, interaktive Exploration eines Graphen basiert dagegen auf einem modifizierten lokalen Layout. Mit jeder Änderung des darzustellenden Ausschnitts wird ein neues lokales Layout berechnet, welches dem vorherigen Layout ähnelt. Mit diesem Verfahren können lokale Zusammenhänge übersichtlich und nachvollziehbar visualisiert werden. Aber unterschiedliche Explorationsverläufe resultieren in unterschiedlichen Layouts, der Transfer des Wissens aus einer Exploration auf eine andere Exploration ist schwierig. Gibt es also eine Methode, die die Vorteile beider Verfahren verbinden kann? Eine Methode, die es dem Anwender erlaubt, sich auf seine Orientierung zu verlassen und trotzdem lokale Zusammenhänge des betrachteten Ausschnitts übersichtlich darzustellen? Dieser Frage widmet sich die vorliegende Arbeit. Es wird ein Ansatz zur Verschmelzung von Fotografien auf Node-Link-Diagramme übertragen, so dass 2 lokale Layouts zueinander ausgerichtet und miteinander verschmolzen werden können. Im Anschluss wird dieses Verfahren dann so erweitert, dass auch beliebige Mengen von lokalen Layouts miteinander verschmolzen werden können.

Show publication details

Gimel'farb, Georgy; Hancock, Edwin; Imiya, Atsushi; Kuijper, Arjan; Kudo, Mineichi; Omachi, Shinichiro; Windeatt, Terry; Yamada, Keiji

Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshop SSPR & SPR 2012

2012

Berlin, Heidelberg, New York : Springer, 2012

The Joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR) <14, 2012, Hiroshima, Japan>

Lecture Notes in Computer Science (LNCS) 7626

This volume constitutes the refereed proceedings of the Joint IAPR International Workshops on Structural and Syntactic Pattern Recognition (SSPR 2012) and Statistical Techniques in Pattern Recognition (SPR 2012), held in Hiroshima, Japan, in November 2012 as a satellite event of the 21st International Conference on Pattern Recognition, ICPR 2012. The 80 revised full papers presented together with 1 invited paper and the Pierre Devijver award lecture were carefully reviewed and selected from more than 120 initial submissions. The papers are organized in topical sections on structural, syntactical, and statistical pattern recognition, graph and tree methods, randomized methods and image analysis, kernel methods in structural and syntactical pattern recognition, applications of structural and syntactical pattern recognition, clustering, learning, kernel methods in statistical pattern recognition, kernel methods in statistical pattern recognition, as well as applications of structural, syntactical, and statistical methods.

Show publication details

Tschirsich, Martin; Kuijper, Arjan (Betreuer)

The Discrete Scale Space as a Base for Robust Scale Space Algorithms

2012

Darmstadt, TU, Bachelor Thesis, 2012

Linear or gaussian scale space is a well known multi-scale representation for continuous signals. The exploration of its so-called deep structure by tracing critical points over scale has various theoretical applications and allows for the construction of a scale space hierarchy tree. However, implementational issues arise, caused by discretization and quantization errors. In order to develop more robust scale space based algorithms, the discrete nature of computer processed signals has to be taken into account. We believe that the most suitable way to do this is via porting concepts and algorithms from the continuous to the spatially discrete scale space with continuous scale parameter. Aiming at a computationally practicable implementation of the discrete scale space framework, suitable neighborhoods, boundary conditions and sampling methods are proposed. In analogy to prevalent approaches, a discretized diffusion equation is derived from the continuous scale space axioms adapted to discrete two-dimensional images or signals, including requirements imposed by the chosen neighborhood and boundary condition. The resulting discrete scale space respects important topological invariants such as the euler number, a key criterion for the successfull implementation of algorithms operating on its deep structure. Relevant and promising properties of the discrete diffusion equation and the eigenvalue decomposition of its laplacian kernel are discussed and a fast and robust sampling method is proposed. We finally discuss promising properties of topological graphs under the influence of smoothing, setting the stage for more robust deep structure extraction algorithms.

Show publication details

Prithviraj, Jain Lalit; Seibert, Helmut; Kuijper, Arjan

Towards Reconstructing a 3D Face Model from an Uncontrolled Video Sequence

2012

Kuijper, Arjan (Ed.) et al.: 2012 International Conference on Cyberworlds. Proceedings : Cyberworlds 2012. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2012, pp. 273-277

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

A pipeline for reconstructing the 3D face model from an uncontrolled video sequence is presented which involves three major steps. Firstly, a generic deformable 3D face model is built from the 3D scans of one hundred individuals. Secondly, the 3D faceshape from a video sequence is constructed by estimating poses of images using structure-from-motion technique and dense correspondences between those images by employing Huber-L1 optical flow algorithm. Finally, the generated generic deformable 3D face model can be fitted to the reconstructed 3D face-shape from a video sequence provided that the deviation from the real 3D face is less than certain thresholds. The application is developed to reconstruct the 3D face-shape in nearly uncontrolled environment so the results cannot be expected to be very accurate. We discuss the steps taken to perform the first and second steps. The factors affecting the depth estimation in face region cause major accuracy problems. They are analyzed and possible improvements to enhance the 3D face-shape reconstruction are presented.

Show publication details

Fischer, Arthur; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer)

Unterstützung von zielbasierter Interaktion durch gestenerkennende Zeigegeräte

2012

Darmstadt, TU, Bachelor Thesis, 2012

In der heutigen Zeit steigt die Anzahl intelligenter Systeme rapide an und klassische Eingabemethoden, wie Mäuse und Tastaturen, verlieren mehr und mehr an Bedeutung. Neue und zielbasierte Interaktionssysteme, wie Gestik und Sprache, erlauben eine natürlichere Steuerung von verschiedenen Geräten in diesen Umgebungen. Allerdings sind diese anfällig für Ungenauigkeiten bei der Eingabe durch den Benutzer, sowie für Fehldeutungen der Intention des Benutzers durch das System. Im Rahmen dieser Arbeit wird untersucht, wie Gestik und Sprache verwendet werden können, um in multimodalen und intelligenten Systemen eine intentionsbasierte Interaktion zu realisieren. Dabei wird gezeigt, wie die Kombination beider Eingabemethoden jeweilige Unsicherheiten beseitigt und die Intentionserkennung verbessert werden kann. Zusätzlich wird gezeigt, wie unter der Berücksichtigung von Kontextinformationen, über den Zustand der Umgebung, die Fehldeutungen, seitens des Systems, signifikant reduziert werden können. Es wird gezeigt, wie die Spracheingaben des Benutzers, als unterstützende Eingaben, die virtuelle Repräsentation der Umgebung innerhalb des Systems beeinflussen und Ungenauigkeiten der Zeigegesten kompensieren können. Anhand eines prototypischen Systems werden die dargestellten Konzepte untersucht. Zusätzlich hat eine kleine Gruppe von Testpersonen dieses prototypische System auf ihre Benutzbarkeit geprüft. Die Evaluation dieser Testreihe hat die erwartete Verbesserung der Intentionserkennug bestätigt.

Show publication details

Majewski, Martin; Braun, Andreas; Marinc, Alexander; Kuijper, Arjan

Visual Support System for Selecting Reactive Elements in Intelligent Environments

2012

Kuijper, Arjan (Ed.) et al.: 2012 International Conference on Cyberworlds. Proceedings : Cyberworlds 2012. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2012, pp. 251-255

International Conference on Cyberworlds (CW) <11, 2012, Darmstadt, Germany>

Concerning gestural interaction in realistic environments there often is an offset between perceived and actual direction of pointing that makes it difficult to reliably select elements in the environment. This work presents a visual support system that provides feedback to a user gesturing freely in an environment and thus enabling reliable selection of and interaction with reactive elements in intelligent environments. A prototype has been created that is showcasing this feedback method based on gesture recognition using the Microsoft Kinect and feedback provision using a custom laser-robot. Finally an evaluation has been performed, in order to prove the efficiency of such a system, acquire usability feedback and determine potential learning effects for gesture-based interaction.

Show publication details

Majewski, Martin; Kuijper, Arjan (Betreuer); Braun, Andreas (Betreuer); Marinc, Alexander (Betreuer)

Visual-aided Selection of Reactive Elements in Intelligent Environments: Visuell gestützte Selektion reaktiver Elemente in intelligenten Umgebungen

2012

Darmstadt, TU, Bachelor Thesis, 2012

Since the vision of the vanishing, ubiquitous computer was formulated in the 1990s, Intelligent Environments have become the main topic of many research efforts. Interacting with Intelligent Environments is preferably following the multi-modal interaction paradigm such as the notable research on natural interaction that allows communication through facial expressions, voice commands and gestures. Gestural interaction in terms of pointing for selection is the main focus of this thesis. Although being regarded as intuitive for the user, it leads to a significant offset between the user's intention and the system's interpretation. This offset makes interaction with reactive elements in Intelligent Environments unintuitive and hardly predictable if no guidance is provided to the user. This thesis shows the challenges during the pointing for selection process, including the drawbacks of current guiding systems and presents a concept for solving these challenges with a ubiquitous visual guiding system. This system supports marker-free, full-body gestural interaction in Intelligent Environments by providing a visual cue on the location the user is currently pointing at. We expect this system to place the users in a situation where they are able to correct their pointing themselves, without extensive training of user or machine. This results in a more accurate and intuitive selection of reactive elements in Intelligent Environments. A prototype system - the E.A.G.L.E. - was build to realize this concept using a robotic laser pointing system. A comparative evaluation with a group of 20 subjects was performed to confirm our expectations regarding the intention-to-interpretation offset and the effects of the self-correction process caused by the visual cue, resulting in a significant gain in accuracy.

Show publication details

Schwarzkopf, Andreas; Kalbe, Thomas; Bajaj, Chandrajit L.; Kuijper, Arjan; Goesele, Michael

Volumetric Nonlinear Anisotropic Diffusion on GPUs

2012

Bruckstein, Alfred M. (Ed.) et al.: Scale Space and Variational Methods in Computer Vision. Proceedings : SSVM 2011. Berlin, Heidelberg, New York: Springer, 2012. (Lecture Notes in Computer Science (LNCS) 6667), pp. 62-73

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) <3, 2011, Ein-Gedi, Israel>

We present an efficient implementation of volumetric nonlinear anisotropic image diffusion on modern programmable graphics processing units (GPUs). We avoid the computational bottleneck of a time consuming eigenvalue decomposition in R3. Instead, we use a projection of the Hessian matrix along the surface normal onto the tangent plane of the local isodensity surface and solve for the remaining two tangent space eigenvectors. We derive closed formulas to achieve this resulting in efficient GPU code. We show that our most complex volumetric nonlinear anisotropic diffusion gains a speed up of more than 600 compared to a CPU solution.

Show publication details

Bender, Jan; Kuijper, Arjan; Fellner, Dieter W.; Guérin, Eric

VRIPHYS 12: 9th Workshop in Virtual Reality Interactions and Physical Simulations

2012

Goslar : Eurographics Association, 2012

International Workshop in Virtual Reality Interaction and Physical Simulations (VRIPhys) <9, 2012, Lyon, France>

The workshop on Virtual Reality Interactions and Physical Simulations (VRIPHYS) is one of the well established international conferences in the field of computer animation and virtual reality. Since 2004, this annual workshop has provided an opportunity for researchers in computer animation and virtual reality to present and discuss their latest results, and to share ideas for potential directions of future research.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

3D Model Retrieval Using the Histogram of Orientation of Suggestive Contours

2011

Bebis, George (Ed.) et al.: Advances in Visual Computing. 7th International Symposium, ISVC 2011 : Proceedings, Part II. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6939), pp. 367-376

International Symposium on Visual Computing (ISVC) <7, 2011, Las Vegas, NV, USA>

The number of available 3D models in various areas increases steadily. Efficient methods to search for 3D models by content, rather than textual annotations, are crucial. For this purpose, we propose a content based 3D model retrieval system using the Histogram of Orientation (HoO) from suggestive contours and their diffusion tensor fields. Our approach to search and automatically return a set of 3D mesh models from a large database consists of three major steps: (1) suggestive contours extraction from different viewpoints to extract features of the query 3D model; (2) HoO descriptor computation by analyzing the diffusion tensor fields of the suggestive contours; (3) similarity measurement to retrieve the models and the most probable view-point. Our proposed 3D model retrieval system is very efficient to retrieve the 3D models even though there are variations of shape and pose of the models. Experimental results are presented and indicate the effectiveness of our approach, competing with the current - more complicated - state of the art method and even improving results for several classes.

Show publication details

Huff, Rafael; Gierlinger, Thomas; Kuijper, Arjan; Stork, André; Fellner, Dieter W.

A Comparison of xPU Platforms Exemplified with Ray Tracing Algorithms

2011

IEEE Computer Society: XIII Symposium on Virtual Reality : SVR 2011. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2011, pp. 1-8

Symposium on Virtual Reality (SVR) <13, 2011, Uberlandia, Brazil>

Over the years, faster hardware - with higher clock rates - has been the usual way to improve computing times in computer graphics. Aside from highly costly parallel solutions only affordable by big industries - like the movie industry -, there was no alternative available to desktop users. Nevertheless, this scenario is dramatically changing with the introduction of more and more parallelism in current desktop PCs. Multi-core CPUs are a common basis in current PCs and the power of modern GPUs - which have been multi-core for a long time now - is getting unveiled to developers. nVidia's CUDA is a powerful weapon to explore GPUs parallelism. Yet, its specific target - nVidia graphic cards only - does not provide any solution to other parallel hardware present. OpenCL is a new royalty-free cross-platform intended to be portable across different hardware manufacturers or even different platforms. In this paper we focus on a comparison of advantages and disadvantages of xPU platforms with OpenCL and CUDA in terms of time efficiency. As an example application we use ray tracing algorithms. Three kinds of ray tracers have to be developed in order to conduct a fair comparison: one is CPU based, while the other two are GPU based - using CUDA and OpenCL, respectively. At the end, a comparison is done between them and results are presented and analyzed showing that the CUDA implementation has the best frame rate, but is very closely followed by the OpenCL implementation. Visually, results are identical, showing the high potential of OpenCL as an alternative for CUDA with identical performance.

Show publication details

Breyer, Matthias; Nazemi, Kawa; Stab, Christian; Burkhardt, Dirk; Kuijper, Arjan

A Comprehensive Reference Model for Personalized Recommender Systems

2011

Smith, Michael J. (Ed.) et al.: Human Interface and the Management of Information: Part I : Interacting with Information. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6771), pp. 528-537

Symposium on Human Interface <2011, Orlando, FL, USA>

Existing reference models for recommender systems are on an abstract level of detail or do not point out the processes and transitions of recommendation systems. However, this information is relevant for developers to design or improve recommendation systems. Even so, users need some background information of the calculation process to understand the process and accept or configure these systems proper. In this paper we present a comprehensive reference model for recommender systems which conjuncts the recommendation processes on an adequate level of detail. To achieve this, the processes of content-based and collaboration-based systems are merged and extended by the transitions and phases of hybrid systems. Furthermore, the algorithms which can be applied in the phases of the model are examined to identify the data flow between these phases. With our model those information of the recommendation calculation process can be identified, which encourages the traceability and thus the acceptance of recommendations.

Show publication details

Nazemi, Kawa; Stab, Christian; Kuijper, Arjan

A Reference Model for Adaptive Visualization Systems

2011

Jacko, Julie A. (Ed.): Human-Computer Interaction: Part I : Design and Development Approaches. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6761), pp. 480-489

International Conference on Human-Computer Interaction (HCII) <14, 2011, Orlando, FL, USA>

One key issue of both Information Visualization as well as Adaptive User Interfaces is information overload. While both disciplines have already devised well performing algorithms, methods and applications, a real merging has not taken place yet. Only a few attempts bring the surplus values of both disciplines together, whereas a fine-grained investigation of visualization parameterization is not investigated. Today's systems focus either on the adaptation of visualization types or the parameterization of visualizations. This paper presents a reference Model for Adaptive Visualization Systems (MAVS) that allows the adaptation of both the visualization type and the visualization parameterization. Based on this model, a framework for the adaptive visualization of semantics data will be derived. A use case describing the interaction with an "adaptive visualization cockpit" covering different visualization metaphors concludes the paper.

Show publication details

Nazemi, Kawa; Burkhardt, Dirk; Praetorius, Alexander; Breyer, Matthias; Kuijper, Arjan

Adapting User Interfaces by Analyzing Data Characteristics for Determining Adequate Visualizations

2011

Kurosu, Masaaki (Ed.): Human Centered Design : Second International Conference: HCD 2011. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6776), pp. 566-575

International Conference on Human Centered Design (HCD) <2, 2011, Orlando, FL, USA>

Today the information visualization takes in an important position, because it is required in nearly every context where large databases have to be visualized. For this challenge new approaches are needed to allow the user an adequate access to these data. Static visualizations are only able to show the data without any support to the users, which is the reason for the accomplished researches to adaptive user-interfaces, in particular for adaptive visualizations. By these approaches the visualizations were adapted to the users' behavior, so that graphical primitives were change to support a user e.g. by highlighting user-specific entities, which seems relevant for a user. This approach is commonly used, but it is limited on changes for just a single visualization. Modern heterogeneous data providing different kinds of aspects, which modern visualizations try to regard, but therefore a user often needs more than a single visualization for making an information retrieval. In this paper we describe a concept for adapting the user-interface by selecting visualizations in dependence to automatically generated data characteristics. So visualizations will be chosen, which are fitting well to the generated characteristics. Finally the user gets an aquatically arranged set of visualizations as initial point of his interaction through the data.

Show publication details

Binotto, Alecio; Pereira, Carlos Eduardo; Kuijper, Arjan; Stork, André; Fellner, Dieter W.

An Effective Dynamic Scheduling Runtime and Tuning System for Heterogeneous Multi and Many-Core Desktop Platforms

2011

Thulasiraman, Parimala (Ed.) et al.: Proceedings 2011 IEEE International Conference on High Performance Computing and Communications : HPCC 2011. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2011, pp. 78-85

IEEE International Conference on High Performance Computing and Communications (HPCC) <13, 2011, Banff, Alberta, Canada>

A personal computer can be considered as a one-node heterogeneous cluster that simultaneously processes several application tasks. It can be composed by, for example, asymmetric CPU and GPUs. This way, a high-performance heterogeneous platform is built on a desktop for data intensive engineering calculations. In our perspective, a workload distribution over the Processing Units (PUs) plays a key role in such systems. This issue presents challenges since the cost of a task at a PU is non-deterministic and can be affected by parameters not known a priori. This paper presents a context-aware runtime and tuning system based on a compromise between reducing the execution time of engineering applications - due to appropriate dynamic scheduling - and the cost of computing such scheduling applied on a platform composed of CPU and GPUs. Results obtained in experimental case studies are encouraging and a performance gain of 21.77% was achieved in comparison to the static assignment of all tasks to the GPU.

Show publication details

Klose, Stefan; Gerhardt, Jeremie; Engelke, Timo; Kuijper, Arjan

Automatic Multi-projector Calibration: A Review of Systems for Non-experienced Users

2011

Richard, Paul (Ed.) et al.: GRAPP 2011 : Proceedings of the International Conference on Computer Graphics Theory and Applications. Portugal: SciTePress, 2011, pp. 286-295

International Conference on Computer Graphics Theory and Applications (GRAPP) <6, 2011, Vilamoura, Algarve, Portugal>

Multi-projector systems are widely used in many application areas. Such systems are for instance employed to increase the brightness or the resolution of projected images. Intrinsic to multi-projector systems are problems like geometric misalignment, especially when projecting onto complex arbitrarily formed projection surfaces, and photometric deviations. Therefore, several difficult calibration tasks (geometry, brightness, color) have to be performed. A high-quality and easy-to-use calibration process is the key to good usability for untrained or unexperienced users. Due to the fact that manual calibration is time-consuming and imprecise, automatic approaches were developed in recent years. This paper analyzes the most popular state-of-the-art algorithms and setups with respect to their advantages and disadvantages. We summarize the general working principles of calibration algorithms and provide an outlook into the fields in which the described algorithms are most useful.

Show publication details

Gutzeit, Enrico; Ohl, Stephan; Voskamp, Jörg; Kuijper, Arjan; Urban, Bodo

Automatic Wood Log Segmentation Using Graph Cuts

2011

Richard, Paul (Ed.) et al.: Computer Vision, Imaging and Computer Graphics. Theory and Applications : Theory and Applications. Berlin, Heidelberg, New York: Springer, 2011. (Communications in Computer and Information Science 229), pp. 96-109

International Joint Conference on Computer Vision and Computer Graphics Theory and Applications (VISIGRAPP) <5, 2010, Angers, France>

Segmenting foreground from background automatically is an active field of research. The graph cut approach is one of the promising methods to solve this problem. This approach requires that the weights of the graph are chosen optimally in order to obtain a good segmentation. We address this challenge focusing on the automatic segmentation of wood log images. We present a novel method based on density estimation to obtain information about both foreground and background. With this information the weights in the graph cut method can be set automatically. In order to validate our results, we use four different methods to set these weights. We show that of these approaches, our new method obtains the best results.

Show publication details

Jung, Yvonne; Kuijper, Arjan; Fellner, Dieter W.; Kipp, Michael; Miksatko, Jan; Gratch, Jonathan; Thalmann, Daniel

Believable Virtual Characters in Human-Computer Dialogs

2011

John, Nigel (Co-Chair) et al.: Eurographics 2011. State of the Art Reports (STARs). Eurographics Association, 2011, pp. 75-100

Eurographics <32, 2011, Llandudno, UK>

For many application areas, where a task is most naturally represented by talking or where standard input devices are difficult to use or not available at all, virtual characters can be well suited as an intuitive man-machine-interface due to their inherent ability to simulate verbal as well as nonverbal communicative behavior. This type of interface is made possible with the help of multimodal dialog systems, which extend common speech dialog systems with additional modalities just like in human-human interaction. Multimodal dialog systems consist at least of an auditive and graphical component, and communication is based on speech and nonverbal communication alike. However, employing virtual characters as personal and believable dialog partners in multimodal dialogs entails several challenges, because this requires not only a reliable and consistent motion and dialog behavior but also regarding nonverbal communication and affective components. Besides modeling the "mind" and creating intelligent communication behavior on the encoding side, which is an active field of research in artificial intelligence, the visual representation of a character including its perceivable behavior, from a decoding perspective, such as facial expressions and gestures, belongs to the domain of computer graphics and likewise implicates many open issues concerning natural communication. Therefore, in this report we give a comprehensive overview how to go from communication models to actual animation and rendering.

Show publication details

Burkhardt, Dirk; Breyer, Matthias; Glaser, Christian; Nazemi, Kawa; Kuijper, Arjan

Classifying Interaction Methods to Support Intuitive Interaction Devices for Creating User-Centered-Systems

2011

Stephanidis, Constantine (Ed.): Universal Access in Human-Computer Interaction: Part I : Design for All and eInclusion. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6765), pp. 20-29

International Conference on Universal Access in Human-Computer Interaction (UAHCI) <6, 2011, Orlando, FL, USA>

Nowadays a wide range of input devices are available to users of technical systems. Especially modern alternative interaction devices, which are known from game consoles etc., provide a more natural way of interaction. But the support in computer programs is currently a big challenge, because a high effort is to invest for developing an application that supports such alternative input devices. For this fact we made a concept for an interaction system, which supports the use of alternative interaction devices. The interaction-system consists as central element a server, which provides a simple access interface for application to support such devices. It is also possible to address an abstract device by its properties and the interaction-system overtakes the converting from a concrete device. For realizing this idea, we also defined a taxonomy for classifying interaction devices by its interaction method and in dependence to the required interaction results, like recognized gestures. Later, by using this system, it is generally possible to develop a user-centered system by integrating this interaction-system, because an adequate integration of alternative interaction devices provides a more natural and easy to understand form of interaction.

Show publication details

Wientapper, Folker; Wuest, Harald; Kuijper, Arjan

Composing the Feature Map Retrieval Process for Robust and Ready-to-Use Monocular Tracking

2011

Computers & Graphics, Vol.35 (2011), 4, pp. 778-788

This paper focuses on the preparative process of natural feature map retrieval for a mobile camera-based tracking system. We cover the most important aspects of a general purpose tracking system including the acquisition of the scene's geometry, tracking initialization and fast and accurate frame-by-frame tracking. To this end, several state-of-the-art techniques - each targeted at one particular subproblem - are fused together, whereby their interplay and complementary benefits form the core of the system and the thread of our discussion. The choice of the individual sub-algorithms in our system reflects the scarcity of computational resources on mobile devices. In order to allow a more accurate, more robust and faster tracking during run-time, we therefore transfer the computational load into the preparative customization step wherever possible. From the viewpoint of the user, the preparative stage is kept very simple. It only involves recording the scene from various viewpoints and defining a transformation into a target coordinate frame via manual definition of only a few 3D to 3D point correspondences. Technically, the image sequence is used to (1) capture the scene's geometry by a SLAM-Method and subsequent refinement via constrained Bundle Adjustment, (2) to train a Randomized-Trees classifier for wide-baseline tracking initialization, and (3) to analyze the view-point dependent visibility of each feature. During run-time, robustness and performance of the frame-to-frame tracking are further increased by fusing inertial measurements within a combined pose estimation.

Show publication details

Schaller, Andreas; Biedenkapp, Tim; Keil, Jens (Betreuer); Kuijper, Arjan (Betreuer)

Immersive Interaktionsparadigmen zur Steuerung virtueller Welten durch Customer Devices

2011

Darmstadt, TU, Bachelor Thesis, 2011

Diese Arbeit gibt einen Einblick in die Grundlagen der 3D-Anwendungen im Zusammenspiel mit verschiedenen Customer Devices. In diesem Fall ist die Anwendung ein 3D-Planetarium unseres Sonnensystems für ein Museum. Ziel ist es, ein Konzept zur intuitiven und immersiven Navigation durch das virtuelle Planetarium mittels preiswerte Customer Devices zu erstellen. Die Besucher sollen sich frei und ohne großen Aufwand im Sonnensystem bewegen können. Dabei soll sich der Besucher auf die Simulation konzentrieren können und nicht durch komplexe Steuerung schnell das Interesse an der Anwendung verlieren. Dafür werden vergleichbare Ansätze und der bisherige Forschungsstand untersucht und ein neuer Ansatz beschrieben. Als kostengünstige Customer Devices werden in dieser Arbeit die Controller der Nintendo Wii (Wiimote) und aktuelle Smartphones betrachtet. Eine genaue Analyse dieser Geräte ist Bestandteil dieser Arbeit. Ausgehend von den gewählten Geräten gibt es verschiedene Interaktionsmöglichkeiten und daraus resultierende Interaktionskonzepte. Für jedes Gerät soll ein Konzept entwickelt werden, das die gestellten Ansprüche erfüllt.

Show publication details

Stab, Christian; Nazemi, Kawa; Breyer, Matthias; Burkhardt, Dirk; Kuijper, Arjan

Interacting with Semantics and Time

2011

Jacko, Julie A. (Ed.): Human-Computer Interaction: Part IV : Users and Applications. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6764), pp. 520-529

International Conference on Human-Computer Interaction (HCII) <14, 2011, Orlando, FL, USA>

Time appears in many different semantic information systems like historical databases, multimedia systems or social communities as a common attribute. Beside the temporal information, the resources in these domains are categorized in a domain-specific schema and interconnected by semantic relations. Nevertheless, the high potential of these systems is not yet exhausted completely. Even today most of these knowledge systems present timedependent semantic knowledge in textual form, what makes it difficult for the average user to understand temporal structures and dependencies. For bridging this gap between human and computer and for simplifying the exploration of time-dependent semantic knowledge, we developed a new interactive timeline visualization called SemaTime. The new designed temporal navigation concept offers an intuitive way for exploring and filtering time-depended resources. Additionally SemaTime offers navigation and visual filtering methods on the conceptual layer of the domain and is able to depict semantic relations. In this paper we describe the conceptual design of SemaTime and illustrate its application potentials in semantic search environments.

Show publication details

Nazemi, Kawa; Breyer, Matthias; Forster, Jeanette; Burkhardt, Dirk; Kuijper, Arjan

Interacting with Semantics: A User-Centered Visualization Adaptation Based on Semantics Data

2011

Smith, Michael J. (Ed.) et al.: Human Interface and the Management of Information: Part I : Interacting with Information. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6771), pp. 239-248

Symposium on Human Interface <2011, Orlando, FL, USA>

Semantically annotated data gain more and more importance in future information acquiring processes. Especially the Linked Open Data (LOD) format has already experienced a great growth. However, the user-interfaces of web-applications mostly do not reflect the added value of semantics data. The following paper describes a new approach of user-centered data-adaptive semantics visualization, which makes use of the advantages of semantics data combined with an adaptive composition of information visualization techniques. It starts with a related work section, where existing LOD systems and information visualization techniques are described. After that, the new approach will bridge the gap between semantically annotated data (LOD) and information visualization and introduces a visualization system that adapts the composition of visualizations based on the underlying data structure. A case study of an example case will conclude this paper.

Show publication details

Marinc, Alexander; Stocklöw, Carsten; Braun, Andreas; Limberger, Carsten; Hofmann, Cristian Erik; Kuijper, Arjan

Interactive Personalization of Ambient Assisted Living Environments

2011

Smith, Michael J. (Ed.) et al.: Human Interface and the Management of Information: Part I : Interacting with Information. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6771), pp. 567-576

Symposium on Human Interface <2011, Orlando, FL, USA>

Ambient Assisted Living (AAL) comprises methods, systems, and services applied to improve the quality of daily life for humans, especially elderly people. Recent research emphasizes the implementation of comprehensive AAL platforms which control all technological components included in the entire environment such as one's apartment. The behavior of the system is often determined by a specific set of rules. Thus, personalization according to the person's needs and preferences includes a configuration of the given rule system. Assuming that configuration is not only conducted by technical staff but also by the person him or herself, this process can be regarded as complex, requiring technical knowledge. In this work, we present an interactive and architectural approach to support at the personalization of an AAL system by different types of users.

Show publication details

Jung, Yvonne; Graf, Holger; Behr, Johannes; Kuijper, Arjan

Mesh Deformations in X3D via CUDA with Freeform Deformation Lattices

2011

Shumaker, Randall (Ed.): Virtual and Mixed Reality - Systems and Applications: Part II : International Conference, Virtual and Mixed Reality 2011. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6774), pp. 343-351

International Conference on Virtual and Mixed Reality (VMR) <4, 2011, Orlando, FL, USA>

In this paper we present a GPU-accelerated implementation of the well-known freeform deformation algorithm to allow for deformable objects within fully interactive virtual environments. We furthermore outline how our real-time deformation approach can be integrated into the X3D standard for more accessibility of the proposed methods. The presented technique can be used to deform complex detailed geometries without pre-processing the mesh by simply generating a lattice around the model. The local deformation is then computed for this lattice instead of the complex geometry, which efficiently can be carried out on the GPU using CUDA.

Show publication details

Nazemi, Kawa; Burkhardt, Dirk; Breyer, Matthias; Kuijper, Arjan

Modeling Users for Adaptive Semantics Visualizations

2011

Stephanidis, Constantine (Ed.): Universal Access in Human-Computer Interaction: Part II : Users Diversity. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6766), pp. 88-97

International Conference on Universal Access in Human-Computer Interaction (UAHCI) <6, 2011, Orlando, FL, USA>

The automatic adaptation of information visualization systems to the requirements of users plays a key-role in today's research. Different approaches from both disciplines try to face this phenomenon. The modeling of user is an essential part of a user-centered adaptation of visualization. In this paper we introduce a new approach for modeling users especially for semantic visualization systems. The approach consists of a three dimensional model, where semantic data, user and visualization are set in relation in different abstraction layer.

Show publication details

Kuijper, Arjan

Non-IAPR Workshop Report: DAGM2010: 32nd Annual Symposium of the German Association for Pattern Recognition

2011

IAPR Newsletter, Vol.33 (2011), 1, pp. 22-25

DAGM is the German section of the IAPR. Every year a conference is held in Germany (or one of the surrounding countries). This year, DAGM took place in Darmstadt. The main conference was preceded by a day at Fraunhofer IGD with a workshop on "Pattern Recognition for IT Security".

Show publication details

Zhou, Xuebing; Kuijper, Arjan; Veldhuis, Raymond; Busch, Christoph

Quantifying Privacy and Security of Biometric Fuzzy Commitment

2011

IEEE Computer Society: International Joint Conference on Biometrics 2011 : IJCB 2011. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2011, 8 p.

International Joint Conference on Biometrics (IJCB) <2011, Washington, DC, USA>

Fuzzy commitment is an efficient template protection algorithm that can improve security and safeguard privacy of biometrics. Existing theoretical security analysis has proved that although privacy leakage is unavoidable, perfect security from information-theoretical points of view is possible when bits extracted from biometric features are uniformly and independently distributed. Unfortunately, this strict condition is difficult to fulfill in practice. In many applications, dependency of binary features is ignored and security is thus suspected to be highly overestimated. This paper gives a comprehensive analysis on security and privacy of fuzzy commitment regarding empirical evaluation. The criteria representing requirements in practical applications are investigated and measured quantitatively in an existing protection system for 3D face recognition. The evaluation results show that a very significant reduction of security and enlargement of privacy leakage occur due to the dependency of biometric features. This work shows that in practice, one has to explicitly measure the security and privacy instead of trusting results under non-realistic assumptions.

Show publication details

Wientapper, Folker; Wuest, Harald; Kuijper, Arjan

Reconstruction and Accurate Alignment of Feature Maps for Augmented Reality

2011

IEEE Computer Society: 3DIMPVT 2011 : International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2011, pp. 140-147

International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission (3DIMPVT) <1, 2011, Hangzhou, China>

This paper focuses on the preparative process of retrieving accurate feature maps for a camera-based tracking system. With this system it is possible to create ready-touse Augmented Reality applications with a very easy setup work-flow, which in practice only involves three steps: filming the object or environment from various viewpoints, defining a transformation between the reconstructed map and the target coordinate frame based on a small number of 3D-3D correspondences and, finally, initiating a feature learning and Bundle Adjustment step. Technically, the solution comprises several sub-algorithms. Given the image sequence provided by the user, a feature map is initially reconstructed and incrementally extended using a Simultaneous-Localization-and-Mapping (SLAM) approach. For the automatic initialization of the SLAM module, a method for detecting the amount of translation is proposed. Since the initially reconstructed map is defined in an arbitrary coordinate system, we present a method for optimally aligning the feature map to the target coordinated frame of the augmentation models based on 3D-3D correspondences defined by the user. As an initial estimate we solve for a rigid transformation with scaling, known as Absolute Orientation. For refinement of the alignment we present a modification of the well-known Bundle Adjustment, where we include these 3D-3D-correspondences as constraints. Compared to ordinary Bundle Adjustment we show that this leads to significantly more accurate reconstructions, since map deformations due to systematic errors such as small camera calibration errors or outliers are well compensated. This again results in a better alignment of the augmentations during run-time of the application, even in large-scale environments.

Show publication details

Reidt, Steffen; Ebinger, Peter; Kuijper, Arjan; Wolthusen, Stephen

Resource-Constrained Signal Propagation Modeling for Tactical Mobile Ad Hoc Networks

2011

IEEE Computer Society: Proceedings of the 2011 IEEE 1st International Network Science Workshop : NSW 2011. Printing House, 2011, pp. 67-74

IEEE International Network Science Workshop (NSW) <1, 2011, West Point, NY, USA>

Connectivity and security of tactical mobile ad hoc networks (MANETs) can be enhanced significantly by explicit consideration of radio propagation as this not only allows determination of route feasibility and minimization of radio frequency power, but also avoids detectability of emanations. Tactical MANETs (and increasingly general MANETs) typically have geolocation and terrain information available, however as they are likely to be deployed in urban, broken, or indoor environments, simple Free Space or Two-Ray Ground models are not adequate. Although highly accurate radio propagation models exist, they require considerable computational resources and are hence unsuitable for incorporation into real-time protocols, particularly on resource-constrained platforms such as MANET nodes. We therefore propose a simplified, scalable ray-optical radio frequency propagation model that incorporates a Two-Ray Ground model and takes reflections and deflections on terrain features into account. Although our proposed model does not incorporate a comprehensive model of all physical effects, we argue that the approximation provided by our model is sufficient and suitable for the purposes of enhancing network performance and accuracy in the frequency range currently used by wireless networks. The model was incorporated in the NS-2 simulator and validated both using simulation and experimentally.

Show publication details

Burkhardt, Dirk; Breyer, Matthias; Nazemi, Kawa; Kuijper, Arjan

Search Intention Analysis for User-Centered Adaptive Visualizations

2011

Stephanidis, Constantine (Ed.): Universal Access in Human-Computer Interaction: Part I : Design for All and eInclusion. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6765), pp. 317-326

International Conference on Universal Access in Human-Computer Interaction (UAHCI) <6, 2011, Orlando, FL, USA>

Searching information on web turned to a matter of course in the last years. The visualization and filtering of the results of such search queries plays a key-role in different disciplines and is still today under research. In this paper a new approach for classifying the search intention of users' is presented. The approach uses existing and easy parameters for a differentiation between explorative and targeted search. The results of the classification are used for a differentiated presentation based on graphical visualization techniques.

Show publication details

Burkhardt, Dirk; Nazemi, Kawa; Breyer, Matthias; Stab, Christian; Kuijper, Arjan

SemaZoom: Semantics Exploration by Using a Layer-Based Focus and Context Metaphor

2011

Kurosu, Masaaki (Ed.): Human Centered Design : Second International Conference: HCD 2011. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6776), pp. 491-499

International Conference on Human Centered Design (HCD) <2, 2011, Orlando, FL, USA>

The Semantic Web is a powerful technology for organizing the data in our information based society. The collection and organization of information is an important step for showing important information to interested people. But the usage of such semantic-based data sources depends on effective and efficient information visualizations. Currently different kinds of visualizations in general and visualization metaphors do exist. Many of them are also applied for semantic data source, but often they are designed for semantic web experts and neglecting the normal user and his perception of an easy useable visualization. This kind of user needs less information, but rather a reduced qualitative view on the data. These two aspects of large amount of existing data and one for normal users easy to understand visualization is often not reconcilable. In this paper we create a concept for a visualization to show a bigger set of information to such normal users without overstraining them, because of layer-based data visualization, next to an integration of a Focus and Context metaphor.

Show publication details

Prithviraj, Jain Lalit; Kuijper, Arjan (Betreuer); Seibert, Helmut (Betreuer)

Shape Optimization of a Deformable 3D Face Model with Respect to Multiple 2D Views

2011

Sankt Augustin, Hochschule Bonn-Rhein-Sieg, Master Thesis, 2011

In a face or facial expression recognition system, one of the key requirements is the proper generation of a face model. An approach for reconstructing the 3D face model from a video sequence is presented within this thesis. A generic deformable 3D face model is built from the 3D scans of one hundred individuals. This generic 3D face model allows modelling the variation in the face-shape of different people. It can be fitted to the reconstructed 3D face-shape of an individual from a video sequence provided that the deviation from the real 3D face is less than certain thresholds. The methodology for reconstructing the 3D face-shape from a video sequence is provided. A structure-from-motion technique is used to estimate the poses of images in a video sequence. The estimated poses are optimized further by applying a bundle adjustment technique. Finally the dense correspondences between the images are estimated by employing Huber-L1 optical flow algorithm. With the optimized pose parameters and dense correspondences between the images, dense 3D face-shapes are reconstructed from a video sequence. The application is developed to reconstruct the 3D face-shape in nearly uncontrolled environment where challenges exists due to varying lightning conditions, the non steady camera movement while capturing a video sequence and other factors using most promising state-of-the-art algorithm. Given the nearly uncontrolled conditions we were able to estimate a point cloud representing the face shape, but the results are not as accurate as expected. The related state-of-the-art algorithms used here have not been considered for such challenging conditions. The factors affecting the depth estimation in face region are analyzed and possible improvements to enhance the 3D face-shape reconstruction are presented within in this thesis.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

Sketch-based 3D Model Retrieval Using Compressive Sensing Classification

2011

Electronics Letters, Vol.47 (2011), 21, pp. 1181-1183

A sketch-based 3D model retrieval methodology by using compressive sensing (CS) is presented. The approach to search and automatically return a set of 3D mesh models from a large database consists of histogram of oriented gradient feature extraction from projected images of 3D models, and CS based classification technique. Experimental results show that the proposed 3D model retrieval is very efficient to search for the 3D models from user-drawn sketches including the variation of shape, pose, and view-points.

Show publication details

Glaser, Christian; Burkhardt, Dirk (Betreuer); Kuijper, Arjan (Betreuer)

System zur benutzerbezogenen Interaktion

2011

Darmstadt, TU, Bachelor Thesis, 2011

Moderne Interaktionsgeräte orientieren sich bei der Interaktion zunehmend an der natürlich menschlichen Interaktion, wie beispielsweise über Gesten. Dieser Trend begann 2006 insbesondere durch den Verkaufserfolg der Spielekonsole Wii von Nintendo und dem dazugehörigen gestenbasierten Controller, der WiiMote. Hierbei war es erstmals möglich Spiele komplett über Gesten zu bedienen. Der Vorteil dieser modernen Interaktion ist die einfachere und leicht verständlichere Kommunikation zwischen und Mensch und Maschine. Im Gegensatz zu solchen proprietären Systemen, die mittels speziell aufeinander abgestimmten Hardware und Software arbeiten, sind im PC Bereich gestenbasierte Steuerungen selten verwendet. Der Grund liegt in einer fehlenden zentralen Unterstützung, so dass Anwendungsentwickler solche Geräte für jede Anwendung individuell berücksichtigen müssen. Dies stellt aber einen großen zusätzlichen Aufwand dar, der selten im Rahmen der Softwareentwicklung berücksichtigt wird. Aus diesem Grund gibt es auch nur wenige Umsetzungen von Anwendungen, die alternative Eingabegeräte unterstützen. Zumeist handelt es sich bei solchen Anwendungen um Spezialsoftware, für deren Zweck die Eingabegeräte und Einbindung der Geräte optimiert sind. Die vorliegende Arbeit sieht daher als Ziel die Entwicklung eines Konzepts für eine zentrale Unterstützung moderner alternativer Eingabegeräte. Hierfür muss zusätzlich eine Klassifikation entwickelt werden, die eine Organisation der verschiedenen Eingabegeräte unter Berücksichtigung der Interaktionsmethoden und benötigtem Interaktionsergebnis (z.B. Koordinaten, erkannte Geste) erlaubt und so eine spätere Einbindung in eine Anwendung vereinfacht und fördert. Mittels dieses Konzepts ist es möglich ein System zu entwickeln, das alle Geräte und deren Interaktionsformen organisiert. Ein Entwickler ist damit in der Lage, unter Verwendung der bereitgestellten Schnittstellen, diese Eingabegeräte in seine Anwendung einzubinden und sie als Kommunikationsmittel für den Nutzer bereitstellen. Zur Entwicklung eines solchen Systems werden zunächst theoretische Ansätze aus dem Bereich der Mensch-Computer-Interaktion betrachtet, die als Grundlage für die methodische Anwendung dienen soll. Dies umfasst auch eine Betrachtung aktuell verfügbarer alternativer Eingabegeräte. Ausgehend von den gewonnenen Erkenntnissen werden insbesondere aktuelle Klassifikationskonzepte, sowie Umsetzungen von Interaktionssystemen betrachtet. Die gesammelten Erkenntnisse werden herangezogen, um ein Konzept für ein Interaktionssystem zu entwickelt und deren zugrundeliegenden Organisation der zu unterstützenden Eingabegeräte. Auf Basis dieses Konzeptes folgt abschließend eine Beschreibung der prototypisch technischen Umsetzung, unter der beispielhaften Verwendung der WiiMote.

Show publication details

Hartmann, Philip; Kahn, Svenja (Betreuer); Kuijper, Arjan (Betreuer)

Tiefenbild basierte markerlose Erfassung menschlicher Bewegungen anhand von medialen Achsen

2011

Darmstadt, TU, Master Thesis, 2011

In dieser Arbeit wird ein neuer Ansatz im Bereich des markerlosen Motion Capturing vorgestellt, der die Bewegung der Arme, Beine und des Oberkörpers erfasst. Die Erfassung der Bewegung erfolgt dabei in Echtzeit aus den 3D-Messdaten einer Tiefenkamera. Die Tiefendaten sind unvollständig, da die Kamera die Szene nur aus einer Blickrichtung erfassen kann. Der Algorithmus nutzt die zylinderähnliche Form der Arme, Beine und des Oberkörpers aus und berechnet aus den Tiefenbildern die mediale Achse der Körperteile. Für eine effiziente Bestimmung der medialen Achsen werden die räumlichen Nachbarschaftsinformationen der Tiefenbilder ausgenutzt. Die Bewegung wird auf ein virtuelles Skelett abgebildet, indem die Knochen entsprechend der medialen Achsen ausgerichtet werden. Die Bestimmung der Pose erfolgt von Bild zu Bild, so dass eine berechnete Pose als zusätzliche Eingabe für das nächste Bild dient.

Show publication details

Hartmann, Philip; Kahn, Svenja; Bockholt, Ulrich; Kuijper, Arjan

Towards Symmetry Axis based Markerless Motion Capture

2011

Bender, Jan (Ed.) et al.: VRIPHYS 11: 8th Workshop in Virtual Reality Interactions and Physical Simulations. Goslar: Eurographics Association, 2011, pp. 73-82

International Workshop in Virtual Reality Interaction and Physical Simulations (VRIPhys) <8, 2011, Lyon, France>

A natural interaction with virtual environments is one of the key issues for the usability of Virtual Reality applications. Device-free, intuitive interactions with the virtual world can be achieved by capturing the movements of the user with markerless motion capture. In this work we present a markerless motion capture approach which can be used to estimate the human body pose in real-time with a single depth camera. The presented approach requires neither a 3D shape model of the tracked person nor a training phase in which body shapes are learned a priori. Instead, it analyzes the curvature of the human body to estimate the symmetry axes of the body joints. These symmetry axes are then used to calculate the pose of the tracked human in real-time. The presented approach was evaluated qualitatively with a time-of-flight and a Kinect depth camera. Furthermore, quantitative simulation results show that the proposed approach is promising for depth cameras which can reliably capture the surface curvature (and thus the normals) of a person and which have a resolution of at least 320x240 pixel.

Show publication details

Nazemi, Kawa; Breyer, Matthias; Kuijper, Arjan

User-Oriented Graph Visualization Taxonomy: A Data-Oriented Examination of Visual Features

2011

Kurosu, Masaaki (Ed.): Human Centered Design : Second International Conference: HCD 2011. Berlin, Heidelberg, New York: Springer, 2011. (Lecture Notes in Computer Science (LNCS) 6776), pp. 576-585

International Conference on Human Centered Design (HCD) <2, 2011, Orlando, FL, USA>

Presenting information in a user-oriented way has a significant impact on the success and comprehensibility of data visualizations. In order to correctly and comprehensibly visualize data in a user-oriented way data specific aspects have to be considered. Furthermore, user-oriented perception characteristics are decisive for the fast and proper interpretation of the visualized data. In this paper we present a taxonomy for graph visualization techniques. On the one hand it provides the user-oriented identification of applicable visual features for given data to be visualized. On the other hand the set of visualization techniques is enclosed which supports these identified visual features. Thus, the taxonomy supports the development of user-oriented visualizations by examination of data to obtain a beneficial association of data to visual features.

Show publication details

Pelzer, Matthias; Kahn, Svenja (Betreuer); Kuijper, Arjan (Betreuer)

Vergleichende Evaluation der Rekonstruktionsgenauigkeit von Structure-from-Motion und Tiefenkameras anhand eines Messarmes

2011

Darmstadt, TU, Bachelor Thesis, 2011

Die 3D-Koordinaten von Punkten auf einer Objektoberfläche können entweder mit einer Tiefenkamera gemessen oder durch Structure-from-Motion Verfahren aus mehreren 2D Bildern rekonstruiert werden. In dieser Arbeit wird vergleichend evaluiert, welche Genauigkeit mit diesen beiden Verfahren erreicht werden kann. Für eine aussagekräftige Evaluierung muss die Kamerapose zur Berechnung der (echten) 3D-Referenzdaten bekannt sein. Während in vorhergehenden Ansätzen die Kamerapose bildbasiert (z.B. anhand eines Marker Trackers) geschätzt wurde, wird die Kamerapose in dieser Arbeit anhand eines hochpräzisen Faro-Messarms bestimmt. Hierdurch wird eine höhere Genauigkeit erreicht als bei Bestimmung der Kamerapose anhand eines Marker Trackers, was die Aussagekraft der Evalierungsergebnisse erhöht.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

View-based 3D Model Retrieval using Compressive Sensing Based Classification

2011

Loncaric, Sven (Ed.) et al.: ISPA 2011 : 7th International Symposium on Image and Signal Processing and Analysis. Zagreb: University of Zagreb, 2011, pp. 437-442

International Symposium on Image and Signal Processing and Analysis (ISPA) <7, 2011, Dubrovnik, Croatia>

The number of available 3D models in various areas increases steadily. Efficient methods to search for 3D models by content, rather than textual annotations, are crucial. For this purpose, we propose content based 3D model retrieval using a compressive sensing technique which is very efficient in classification by using only few input information. Our approach to search and automatically return a set of 3D mesh models from a large database consists of three major steps: (1) suggestive contours extraction from different viewpoints to extract features of the query 3D model; (2) descriptor computation by analyzing the Histogram of Oriented Gradients of the suggestive contours in the space of diffusion tensor fields; and (3) compressive sensing based machine learning to retrieve the models and the most probable view-point. Experimental results show that our proposed 3D model retrieval system is very effective to retrieve the 3D models, even though there are variations of shape and pose of the models.

Show publication details

Landesberger, Tatiana von; Kuijper, Arjan; Schreck, Tobias; Kohlhammer, Jörn; van Wijk, Jarke; Fekete, Jean-Daniel; Fellner, Dieter W.

Visual Analysis of Large Graphs: State-of-the-Art and Future Research Challenges

2011

Computer Graphics Forum, Vol.30 (2011), 6, pp. 1719-1749

The analysis of large graphs plays a prominent role in various fields of research and is relevant in many important application areas. Effective visual analysis of graphs requires appropriate visual presentations in combination with respective user interaction facilities and algorithmic graph analysis methods. How to design appropriate graph analysis systems depends on many factors, including the type of graph describing the data, the analytical task at hand and the applicability of graph analysis methods. The most recent surveys of graph visualization and navigation techniques cover techniques that had been introduced until 2000 or concentrate only on graph layouts published until 2002. Recently, new techniques have been developed covering a broader range of graph types, such as timevarying graphs. Also, in accordance with ever growing amounts of graph-structured data becoming available, the inclusion of algorithmic graph analysis and interaction techniques becomes increasingly important. In this State-of-the-Art Report, we survey available techniques for the visual analysis of large graphs. Our review first considers graph visualization techniques according to the type of graphs supported. The visualization techniques form the basis for the presentation of interaction approaches suitable for visual graph exploration. As an important component of visual graph analysis, we discuss various graph algorithmic aspects useful for the different stages of the visual graph analysis process. We also present main open research challenges in this field.

Show publication details

Zhou, Xuebing; Araujo Sanchez, Silvia; Kuijper, Arjan

3D Face Recognition with Local Binary Patterns

2010

Echizen, Isao (Ed.) et al.: Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Proceedings : IIH-MSP 2010. Los Alamitos, Calif.: IEEE Computer Society, 2010, pp. 329-332

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP) <6, 2010, Darmstadt, Germany>

Human faces are one of the most important and most popular biometric modalities to recognize individuals in a broad range of applications. So far, Local Binary Patterns have been applied to face recognition based on 2D illumination images and near infrared images, showing good robustness, discriminative ability and computational efficiency. In this paper, this method is extended to 3D face images. We investigate the influence of several parameters of this method and show improvements in the recognition rates, proving that this new method is a very promising approach for 3D face recognition.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

3D Human Action Recognition Using Model Segmentation

2010

Aurélio, Campilho (Ed.) et al.: Image Analysis and Recognition. Proceedings, Part I : 7th International Conference, ICIAR 2010. Berlin; Heidelberg; New York: Springer, 2010. (Lecture Notes in Computer Science (LNCS) 6111), pp. 189-199

International Conference on Image Analysis and Recognition (ICIAR) <7, 2010, Povoa de Varzim, Portugal>

This paper addresses a learning-based human action recognition system from multiple images based on integrating features of segmented 3D human body parts such as face, torso, and limbs. The innovation of our proposed 3D human action recognition system consists of three parts: (1) 3D reconstruction of the target object by tracking the position of a target object in a scene to voxelize the accurate 3D human model, (2) Human body model segmentation into several human body parts using ellipsoidal models in the space of second-order three dimensional diffusion tensor fields, and (3) Classification and recognition of human actions from features of the segmented human model using Multiple-Kernel based Support Vector Machine. Experimental results on a set of test volume data show that our proposed method is very efficient to visualize and recognize the human action using few parameters which are independent to partial occlusion, dimension, and viewpoint.

Show publication details

Wendt, Lars Henning; Stork, André; Kuijper, Arjan; Fellner, Dieter W.

3D Reconstruction from Line Drawings

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 65-71

International Conference on Computer Graphics Theory and Applications (GRAPP) <5, 2010, Angers, France>

In this work we introduce an approach for reconstructing digital 3D models from multiple perspective line drawings. One major goal is to keep the required user interaction simple and at a minimum, while making no constraints to the objects shape. Such a system provides a useful extension for digitalization of paper-based styling concepts, which today is still a time consuming process. In the presented method the line drawings are first decomposed in curves assembling a network of curves. In a second step, the positions for the endpoints of the curves are determined in 3D, using multiple sketches and a virtual camera model given by the user. Then the shapes of the 3D curves between the reconstructed 3D endpoints are inferred. This leads to a network of 3D curves, which can be used for first visual evaluations in 3D. During the whole process only little user interaction is needed, which only takes place in the pre- and post-processing phases. The approach has been applied on multiple sketches and it is shown that the approach creates plausible results within reasonable timing.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

3D Volume Data Segmentation from Superquadric Tensor Analysis

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 72-75

International Conference on Computer Graphics Theory and Applications (GRAPP) <5, 2010, Angers, France>

The segmentation of 3D target objects into coherent subregions is one of the most important issues in computer graphics as it is applied in many applications, such as medical model visualization and analysis, 3D model retrieval and recognition, skeleton extraction, and collision detection. The goal of 3D segmentation is to separate the volume or mesh data into several subregions which have similar characteristics. In this paper, we present an efficient and accurate 3D model segmentation methodology by merging and splitting the subregions in a 3D model. Our innovative 3D model segmentation system consists of two steps: i) the ellipsoidal decomposition of unorganized 3D object using properties of three dimensional second-order diffusion tensor fields, and ii) The iteratively merging and splitting of subregions of the 3D model by measuring the similarity between neighboring regions. Experimental results are conducted to evaluate the performance of our methodology using 3D models from well-known databases and 3D target objects that are reconstructed from image sequences.

Show publication details

Huff, Rafael; Neves, Tiago; Gierlinger, Thomas; Kuijper, Arjan; Stork, André; Fellner, Dieter W.

A General Two-Level Acceleration Structure for Interactive Ray Tracing on the GPU

2010

Computer Graphics Society (CGS): Computer Graphics International 2010. Short Papers : CGI [online]. [cited 01 February 2011] Available from: http://cgi2010.miralab.unige.ch/CGI_ShortPapersD4.html, 2010, 4 p.

Computer Graphics International (CGI) <28, 2010, Singapore>

Despite the superior image quality generated by ray tracing, programmers of time-critical applications have historically avoided it because of its computational costs. Nowadays, the hardware of modern desktops allows the execution of realtime ray tracers but requires a specialized implementation based on specific characteristics of each application, such as scene complexity, kinds of motion, ray distribution, model structure and hardware. The evaluation and development of these requirements are complex and time-consuming, especially for developers with no familiarity in rendering algorithms and graphics hardware programming. The aim of our work is to provide a general and practical method to efficiently execute interactive ray tracing in most systems. We considered the most common aspects of current computer graphics applications, like the use of a scene graph and support to static and dynamic objects. In addition, we also took into account the common desktop hardware. This led us to the development of a special acceleration structure and its implementation on the GPU. In this paper, we present the development of our work showing the combination of different techniques and our results.

Show publication details

Knuth, Martin; Kohlhammer, Jörn; Kuijper, Arjan

A Geometry-Shader-Based Adaptive Mesh Refinement Scheme Using Semiuniform Quad/Triangle Patches and Warping

2010

Erleben, Kenny (Ed.) et al.: VRIPHYS 10: 7th Workshop in Virtual Reality Interactions and Physical Simulations. Goslar: Eurographics Association, 2010, pp. 21-29

International Workshop in Virtual Reality Interaction and Physical Simulations (VRIPhys) <7, 2010, Copenhagen, Denmark>

In the field of garment simulation the resolution of the simulation mesh has a direct impact on visual quality. Unfortunately, an increase in mesh resolution introduces a much higher computational cost and potentially causes instability inside the simulation. In addition, it increases the amount of data sent to the renderer for visualisation. Therefore, a GPU-based refinement of the simulated mesh has several advantages, since all additional data is generated immediately before rendering. This allows an increase in visual quality without adding to computational costs for the simulation process or bandwidth necessary for rendering. In this paper we present a view-dependent, adaptive tessellation method designed for the geometry processing stage of modern GPUs. It uses uniform meshes internally, removing the necessity to store external patches. Since we deal with a local refinement scheme, sudden changes in the mesh structure size on adjacent patches may occur incidentally. To reduce this effect as far as possible, we control the triangle density distribution of the refinement process inside a refined triangle patch.

Show publication details

Schwenk, Karsten; Franke, Tobias; Drevensek, Timm; Kuijper, Arjan; Bockholt, Ulrich; Fellner, Dieter W.

Adapting Precomputed Radiance Transfer to Real-time Spectral Rendering

2010

Lensch, Hendrik P. A. (Ed.) et al.: Eurographics 2010. Short Papers, pp. 49-52

Eurographics <31, 2010, Norrköping, Sweden>

Spectral rendering takes the full visible spectrum into account when calculating light-surface interaction and can overcome the well-known deficiencies of rendering with tristimulus color models. We present a variant of the precomputed radiance transfer algorithm that is tailored towards real-time spectral rendering on modern graphics hardware. Our method renders diffuse, self-shadowing objects with spatially varying spectral reflectance properties under distant, dynamic, full-spectral illumination. To achieve real-time frame rates and practical memory requirements we split the light transfer function into an achromatic part that varies per vertex and a wavelength-dependent part that represents a spectral albedo texture map. As an additional optimization, we project reflectance and illuminant spectra into an orthonormal basis. One area of application for our research is virtual design applications that require relighting objects with high color fidelity at interactive frame rates.

Show publication details

Binotto, Alecio; Pedras, Bernardo; Götz, Marcelo; Kuijper, Arjan; Pereira, Carlos Eduardo; Stork, André; Fellner, Dieter W.

Effective Dynamic Scheduling on Heterogeneous Multi/Manycore Desktop Platforms

2010

Bentes, Cristiana (Ed.) et al.: SBAC-PADW 2010 : 1st Workshop on Applications for Multi and Many Core Architectures (WAMMCA). Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2010, pp. 37-42

Workshop on Applications for Multi and Many Core Architectures (WAMMCA) <1, 2010, Petrópolis, Brazil>

GPUs (Graphics Processing Units) have become one of the main co-processors that contributed to desktops towards high performance computing. Together with multicore CPUs and other co-processors, a powerful heterogeneous execution platform is built on a desktop for data intensive calculations. In our perspective, we see the modern desktop as a heterogeneous cluster that can deal with several applications' tasks at the same time. To improve application performance and explore such heterogeneity, a distribution of workload over the asymmetric PUs (Processing Units) plays an important role for the system. However, this problem faces challenges since the cost of a task at a PU is non-deterministic and can be influenced by several parameters not known a priori, like the problem size domain. We present a context-aware architecture that maximizes application performance on such platforms. This approach combines a model for a first scheduling based on an offline performance benchmark with a runtime model that keeps track of tasks' real performance. We carried a demonstration using a CPU-GPU platform for computing iterative SLEs (Systems of Linear Equations) solvers using the number of unknowns as the main parameter for assignment decision. We achieved a gain of 38.3% in comparison to the static assignment of all tasks to the GPU (which is done by current programming models, such as OpenCL and CUDA for Nvidia).

Show publication details

Knuth, Martin; Kohlhammer, Jörn; Kuijper, Arjan

Embedding Hierachical Deformation within a Realtime Scene Graph: A Simple Approach for Embedding GPU-based Realtime Deformations using Trilinear Transformations Embedded in a Scene Graph

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 246-253

International Conference on Computer Graphics Theory and Applications (GRAPP) <5, 2010, Angers, France>

Scene graphs are widely used as a description of spatial relations between objects in a scene. Current scene graphs use linear transformations for this purpose. This limits the relation of two objects in the hierarchy to simple transformations like sheer, translation, rotation and scaling. In contrast to this, we want to represent and control deformations that result from propagating the dynamics of objects to deformable attached objects. Our solution is to replace the linear 4x4 matrix-based transformation of a scene graph by a more generic trilinear transformation. The linear transformation allows the composition of the transformation hierarchy into one transformation. Our approach additionally allows the handling of deformations on the same level. Building on this concept we present a system capable of real-time rendering. The computations of the applied deformations of the scene graph are performed in real-time on the GPU. We allow the approximation of arbitrary nonlinear transformations and deformations by utilising grids of trilinear transformations in our system. As an application we show geometric attachments on deformable objects and their deformation on a scene graph level.

Show publication details

Seibert, Helmut; Hildenbrand, Dietmar; Becker, Meike; Kuijper, Arjan

Estimation of Curvatures in Point Sets Based on Geometric Algebra

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 12-19

International Conference on Computer Vision Theory and Applications (VISAPP) <5, 2010, Angers, France>

For applications like segmentation, feature extraction and classification of point sets it is essential to know the principal curvatures and the corresponding principal directions. For the purpose of curvature estimation conformal geometric algebra promises to be a natural mathematical language: Local curvatures can be described with the help of osculating circles or spheres. On one hand, conformal geometric algebra is able to directly compute with these geometric objects, as well as with lines and planes needed for the description of vanishing curvature. On the other hand, distance measures for fitting these objects into point sets can be handled in a linear way, leading to efficient algorithms. In this paper we use conformal geometric algebra advantageously in order to locally compute continuous curvatures as well as principal curvatures of point sets without the need of costly pre-processing of raw data. We show results on artificial and real data. Numerical verification on artificial data shows the accuracy of our approach.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

Human Action Recognition Using Segmented Skeletal Features

2010

Institute of Electrical and Electronics Engineers (IEEE): 20th International Conference on Pattern Recognition. Proceedings : ICPR 2010. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2010, pp. 3740-3743

International Conference on Pattern Recognition (ICPR) <20, 2010, Istanbul, Turkey>

We present a novel human action recognition system based on segmented skeletal features which are separated into several human body parts such as face, torso and limbs. Our proposed human action recognition system consists of two steps: (i) automatic skeletal feature extraction and splitting by measuring the similarity in the space of diffusion tensor fields, and (ii) multiple kernel Support Vector Machine based human action recognition. Experimental results on a set of test database show that our proposed method is very efficient and effective to recognize human actions using few parameters, independent of dimensions, shadows, and viewpoints.

Show publication details

Binotto, Alecio; Daniel, Christian G.; Weber, Daniel; Kuijper, Arjan; Stork, André; Pereira, Carlos Eduardo; Fellner, Dieter W.

Iterative SLE Solvers over a CPU-GPU Platform

2010

IEEE Computer Society: Proceedings 2010 12th IEEE International Conference on High Performance Computing and Communications : HPCC 2010. Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2010, pp. 305-313

IEEE International Conference on High Performance Computing and Communications (HPCC) <12, 2010, Melbourne, Australia>

GPUs (Graphics Processing Units) have become one of the main co-processors that contributed to desktops towards high performance computing. Together with multi-core CPUs, a powerful heterogeneous execution platform is built for massive calculations. To improve application performance and explore this heterogeneity, a distribution of workload in a balanced way over the PUs (Processing Units) plays an important role for the system. However, this problem faces challenges since the cost of a task at a PU is non-deterministic and can be influenced by several parameters not known a priori, like the problem size domain. We present a comparison of iterative SLE (Systems of Linear Equations) solvers, used in many scientific and engineering applications, over a heterogeneous CPU-GPUs platform and characterize scenarios where the solvers obtain better performances. A new technique to improve memory access on matrix vector multiplication used by SLEs on GPUs is described and compared to standard implementations for CPU and GPUs. Such timing profiling is analyzed and break-even points based on the problem sizes are identified for this implementation, pointing whether our technique is faster to use GPU instead of CPU. Preliminary results show the importance of this study applied to a real-time CFD (Computational Fluid Dynamics) application with geometry modification.

Show publication details

Schwenk, Karsten; Kuijper, Arjan; Bockholt, Ulrich

Modeling Wavelength-Dependent BRDFs as Factored Tensors for Real-Time Spectral Rendering

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 165-172

International Conference on Computer Graphics Theory and Applications (GRAPP) <5, 2010, Angers, France>

Spectral rendering takes the full visible spectrum into account when calculating light-surface interaction and can overcome the well-known deficiencies of rendering with tristimulus color models. In this paper we show how to represent wavelength-dependent BRDFs as factored tensors. We use this representation for realtime spectral rendering on modern graphics hardware. Strong data compression and fast rendering times are achieved for mostly diffuse and moderately glossy isotropic surfaces. The method can handle high-resolution tabulated BRDFs, including non-reciprocal ones, which makes it well-suited for measured data. We analyze our approach numerically and visually. One area of application for our research is virtual design applications that require high color fidelity at interactive frame rates.

Show publication details

Yoon, Sang Min; Kuijper, Arjan

Object Retrieval Based on User-Drawn Sketches

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 292-299

International Conference on Computer Vision Theory and Applications (VISAPP) <5, 2010, Angers, France>

Sketches drawn by users are one of the most intuitive forms of Human Computer Interaction. Users can easily express their intention by sketching simple hand-drawn lines. In this paper, we consider the problem of target object detection and retrieval from a query by a sketch which is not in the database. Our novel approach consists of three steps: (1) Preprocessing to extract the skeletal features from a sketched query using size normalization, labelling, and binarization, (2) Skeletal feature extraction of query and data images in the space of diffusion tensor fields, and (3) Similarity measure using tensorial information between sketched query and database to retrieve the most similar target object in database. Experiments are conducted to evaluate the performance of our methodology, which shows to be an efficient and mature retrieval system.

Show publication details

Huff, Rafael; Neves, Tiago; Gierlinger, Thomas; Kuijper, Arjan; Stork, André; Fellner, Dieter W.

OpenCL vs. CUDA for Ray Tracing

2010

Brazilian Computer Society (SBC): XII Symposium on Virtual and Augmented Reality : SVR 2010. Brazil: Everton Cavalcante, 2010, 4 p.

Symposium on Virtual and Augmented Reality (SVR) <12, 2010, Natal, Brazil>

For many years the Graphics Processing Unit (GPU) of common desktops was just used to accelerate certain parts of the graphics pipeline. After developers had access to the native instruction set and memory of the massive parallel computational elements of GPUs a lot has changed. GPUs became powerful and programmable. Nowadays two SDKs are most used for GPU programming: CUDA and OpenCL. CUDA is the most adopted general purpose parallel computing architecture for GPUs but is restricted to Nvidia graphic cards only. In contrast, OpenCL is a new royalityfree framework for parallel programming intended to be portable across different hardware manufacturers or even different platforms. In this paper, we evaluate both solutions considering a typical parallel algorithm: Ray Tracing. We show our performance results and experiences on developing both implementations that could be easily adapted to solve other problems.

Show publication details

Goesele, Michael; Roth, Stefan; Kuijper, Arjan; Schiele, Bernt; Schindler, Konrad

Pattern Recognition 2010. Proceedings: 32nd DAGM Symposium

2010

Berlin, Heidelberg, New York : Springer, 2010

Annual Symposium of the German Association for Pattern Recognition (DAGM) <32, 2010, Darmstadt, Germany>

Lecture Notes in Computer Science (LNCS) 6376

The technical program covered all aspects of pattern recognition and, to name only a few areas, ranged from 3D reconstruction, to object recognition and medical applications.

Show publication details

Zagar, Bernhard; Kuijper, Arjan; Sahbi, Hichem

Proceedings of the Seventh IASTED International Conference on Signal Processing, Pattern Recognition, and Applications: SPPRA 2010

2010

Anaheim : Acta Press, 2010

IASTED International Conference on Signal Processing, Pattern Recognition, and Application (SPPRA) <7, 2010, Innsbruck, Austria>

Show publication details

Yoon, Sang Min; Kuijper, Arjan

Query-by-Sketch based Image Retrieval using Diffusion Tensor Fields

2010

Djemal, Khalifa (Ed.) et al.: 2nd International Conference on Image Processing Theory, Tools and Applications : IPTA 2010. Los Alamitos, Calif.: IEEE Computer Society Press, 2010, pp. 343-348

International Conference on Image Processing Theory, Tools and Applications (IPTA) <2, 2010, Paris, France>

A user-drawn sketch is one of the most intuitive forms of Human Computer Interaction. Users can express their intention by sketching the specific characteristics of a target object as a rough and simple black and white hand-drawn draft image. Recent advances of tablet PC and multi-touch screen technology raised increasing interest on how users might search and retrieve the desired images in databases from a simple sketched image. In this paper, we present a new approach for content based image retrieval from a query by sketchy draft images which are not in the database. Our innovation to sketch based image retrieval systems consists of three steps: (i) Image database configuration using size normalization, edge detection, and hierarchical image classification, (ii) Tensorial feature extraction of query and image data in the topology of second-order symmetric diffusion tensor fields, and (iii) Similarity measure using eigen-features between sketched query and databases to retrieve the most similar target object. Experiments are conducted to evaluate the performance of our methodology showing an efficient and mature image retrieval system.

Show publication details

Gutzeit, Enrico; Ohl, Stephan; Kuijper, Arjan; Voskamp, Jörg; Urban, Bodo

Setting Graph Cut Weights for Automatic Foreground Extraction in Wood Log Images

2010

Institute for Systems and Technologies of Information, Control and Communication (INSTICC): VISIGRAPP 2010. Proceedings : International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. INSTICC Press, 2010, pp. 60-67

International Conference on Computer Vision Theory and Applications (VISAPP) <5, 2010, Angers, France>

The automatic extraction of foreground objects from the background is a well known problem. Much research has been done to solve the foreground/background segmentation with graph cuts. The major challenge is to determine the weights of the graph in order to obtain a good segmentation. In this paper we address this problem with a focus on the automatic segmentation of wood logs. We introduce a new solution to get information about foreground and background. This information is used to set the weights of the graph cut method. We compare four different methods to set these weights and show that the best results are obtained with our novel method, which is based on density estimation.

Show publication details

Echizen, Isao; Pan, Jeng-Shyang; Fellner, Dieter W.; Nouak, Alexander; Kuijper, Arjan; Jain, Lakhmi C.

Sixth International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Proceedings: IIH-MSP 2010

2010

Los Alamitos, Calif. : IEEE Computer Society, 2010

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP) <6, 2010, Darmstadt, Germany>

Signal Processing (IIH-MSP-2010), it is our pleasure to present to you the conference proceedings. Multimedia technologies with an increasing level of intelligence are emerging to enable the process of creating a global information infrastructure that will interconnect heterogeneous computer networks and various forms of information technologies around the world. IIHMSP-2010, which is the sixth edition of the IIHMSP series of conferences, is intended as an international forum for researchers and professionals in all area of information hiding and multimedia signal processing. The major areas covered at the conference and presented in the proceedings include: · Information Hiding and Security · Multimedia Signal Processing and Networking · Bio-Inspired Multimedia Technologies and Systems

Show publication details

Yoon, Sang Min; Scherer, Maximilian; Schreck, Tobias; Kuijper, Arjan

Sketch-Based 3D Model Retrieval using Diffusion Tensor Fields of Suggestive Contours

2010

ACM SIGMM: Proceedings of the ACM Multimedia 2010 International Conference : MM'10. New York: ACM, 2010, pp. 193-200

ACM International Conference on Multimedia (MM) <18, 2010, Firenze, Italy>

The number of available 3D models in various areas increases steadily. Effective methods to search for those 3D models by content, rather than textual annotations are crucial. For this purpose, we propose a new approach for content based 3D model retrieval by hand-drawn sketch images. This approach to retrieve visually similar mesh models from a large database consists of three major steps: (1) suggestive contour renderings from different viewpoints to compare against the user drawn sketches; (2) descriptor computation by analyzing diffusion tensor fields of suggestive contour images, or the query sketch respectively; (3) similarity measurement to retrieve the models and the most probable view-point from which a model was sketched. Our proposed sketch based 3D model retrieval system is very robust against variations of shape, pose or partial occlusion of the user drawn sketches. Experimental results are presented and indicate the effectiveness of our approach for sketch-based 3D model retrieval.

Show publication details

Burisch, Michael; Guerrero Ichaso, David; Kuijper, Arjan

Stripe Propagation for Color Encoded Structured Light

2010

Fifth International Symposium on 3D Data Processing, Visualization and Transmission. Proceedings [online]. [cited 17 January 2011] Available from: http://campwww.informatik.tu-muenchen.de/3DPVT2010/data/media/e-proceeding/index.html, 2010, 8 p.

International Symposium on 3D Data Processing, Visualization and Transmission (3DPVT) <5, 2010, Paris, France>

We present a method to improve surface reconstruction using color encoded structured light. A video camera is used to obtain a color encoded pattern projected onto the object using a projector. A multi-stage method is presented to reconstruct the surface from the captured pattern. It consists of i) a robust edge detection step, ii) a color decoding using feedback from previous stripes and iii) a propagation step to detect errors and propagate detected stripes. Using feedback and propagation we can reconstruct areas where regular color detection fails by bridging small gaps which happen due to illumination variations or noise. The reconstruction results are illustrated for human skin.

Show publication details

Zhou, Xuebing; Kuijper, Arjan; Busch, Christoph

Template Protection for 3D Face Recognition

2010

Oravec, Milos (Ed.): Face Recognition. Sciyo, 2010, pp. 315-328

The human face is one of the most important biometric modalities for automatic authentication. Three-dimensional face recognition exploits facial surface information. In comparison to illumination based 2D face recognition, it has good robustness and high fake resistance, so that it can be used in high security areas. Nevertheless, as in other common biometric systems, potential risks of identity theft, cross matching and exposure of privacy information threaten the security of the authentication system as well as the user's privacy. As a crucial supplementary of biometrics, the template protection technique can prevent security leakages and protect privacy. In this chapter, we show security leakages in common biometric systems and give a detailed introduction on template protection techniques. Then the latest results of template protection techniques in 3D face recognition systems are presented. The recognition performances as well as the security gains are analyzed.

Show publication details

Landesberger, Tatiana von; Kuijper, Arjan; Schreck, Tobias; Kohlhammer, Jörn; van Wijk, Jarke; Fekete, Jean-Daniel; Fellner, Dieter W.

Visual Analysis of Large Graphs

2010

Hauser, Helwig (Ed.) et al.: Eurographics 2010. State of the Art Reports (STARs), pp. 113-136

Eurographics <31, 2010, Norrköping, Sweden>

The analysis of large graphs plays a prominent role in various fields of research and is relevant in many important application areas. Effective visual analysis of graphs requires appropriate visual presentations in combination with respective user interaction facilities and algorithmic graph analysis methods. How to design appropriate graph analysis systems depends on many factors, including the type of graph describing the data, the analytical task at hand, and the applicability of graph analysis methods. The most recent surveys of graph visualization and navigation techniques were presented by Herman et al. [HMM00] and Diaz [DPS02]. The first work surveyed the main techniques for visualization of hierarchies and graphs in general that had been introduced until 2000. The second work concentrated on graph layouts introduced until 2002. Recently, new techniques have been developed covering a broader range of graph types, such as time-varying graphs. Also, in accordance with ever growing amounts of graph-structured data becoming available, the inclusion of algorithmic graph analysis and interaction techniques becomes increasingly important. In this State-of-the-Art Report, we survey available techniques for the visual analysis of large graphs. Our review firstly considers graph visualization techniques according to the type of graphs supported. The visualization techniques form the basis for the presentation of interaction approaches suitable for visual graph exploration. As an important component of visual graph analysis, we discuss various graph algorithmic aspects useful for the different stages of the visual graph analysis process.

Show publication details

Kalbe, Thomas; Fuhrmann, Simon; Uhrig, Stefan; Zeilfelder, Frank; Kuijper, Arjan

A New Projection Method for Point Set Surfaces

2009

European Association for Computer Graphics (Eurographics): Eurographics 2009 - Annex : Tutorials, State of the Art Reports, Short Papers, Medical Prize, Education Papers, Areas Papers, EG Workshop on Natural Phenomena. Aire-la-Ville: Eurographics Association, 2009, pp. 77-80

Eurographics <30, 2009, München, Germany>

A successful approach in triangulating point set surfaces is to apply operations, like a projection operator for advancing front algorithms, directly to Moving-Least Squares (MLS) surfaces. The MLS method naturally handles noisy input data and is especially useful for point clouds derived from real-world solids. Unfortunately, MLS is computationally extensive and complex. We present a novel projection method that does not require solving a nonlinear optimization problem as MLS does. We create a polynomial approximation of the surface similar to MLS but our method adapts the degree of the polynomial with respect to the points to be approximated. The approximated points are iteratively collected compromising connectivity information. We enhance the orientation of the local coordinate system to further improve the method. The results confirm that our method is more robust and also accelerates triangulation due to a preprocessing step that needs to be done only once per data set.

Show publication details

Zhou, Xuebing; Wolthusen, Stephen; Busch, Christoph; Kuijper, Arjan

A Security Analysis of Biometric Template Protection Schemes

2009

Mohamed, Kamel (Ed.) et al.: Image Analysis and Recognition : 6th International Conference, ICIAR 2009. Berlin; Heidelberg; New York: Springer, 2009. (Lecture Notes in Computer Science (LNCS) 5627)

International Conference on Image Analysis and Recognition (ICIAR) <6, 2009, Halifax, Canada>

Biometric features provide considerable usability benefits. At the same time, the inability to revoke templates and likelihood of adversaries being able to capture features raise security concerns. Recently, several template protection mechanisms have been proposed, which provide a one-way mapping of templates onto multiple pseudo-identities. While these proposed schemes make assumptions common for cryptographic algorithms, the entropy of the template data to be protected is considerably lower per bit of key material used than assumed owing to correlations arising from the biometric features. We review several template protection schemes and existing attacks followed by a correlation analysis for a selected biometric feature set and demonstrate that these correlations leave the stream cipher mechanism employed vulnerable to, among others, known plaintext-type attacks.

Show publication details

Reitz, Thorsten; Kuijper, Arjan

Applying Instance Visualisation and Conceptual Schema Mapping for Geodata Harmonisation

2009

Sester, Monika (Ed.) et al.: Advances in GIScience : Proceedings of the 12th AGILE Conference. Berlin; Heidelberg; New York: Springer, 2009. (Lecture Notes in Geoinformation and Cartography (LNGC)), pp. 173-194

Conference on Geographic Information Science (AGILE) <12, 2009, Hannover, Germany>

This paper gives an introduction to concepts for a better expert knowledge extraction for geodata harmonisation. Geodata harmonisation involves overcoming heterogeneities on the syntactic, schematic and semantic levels, but user interaction is mostly required for the semantic in-teroperability level. Consequently, the goal is to provide tools to geodomain experts which allow them to use their knowledge to describe the conceptual schemas of their domain as well as alignments to other domain's conceptual schemas in a sufficiently expressive way without becoming experts in ontology engineering. We describe an approach for this that includes both visual analysis on the basis of geospatial instances and specific interaction guidance processes. Based on this approach, a prototypical implementation of a tool called the HUMBOLDT Alignment Editor (HALE) is introduced.

Show publication details

Kuijper, Arjan

Deep Structure, Singularities, and Computer Vision

2009

Graz, TU, Habil.-Schrift, 2009

Since several decades computers are obtaining a more and more prominent place in society. Increasing computational possibilities combined with expanding storage potentialities in the field of computer vision urge for methods that can perform the tasks of identifying, comparing, and classifying objects in digital data automatically. In order to be highly user-independent and trustworthy stable for cost and time saving purposes, many methods combine sophisticated knowledge of different areas of mathematics, computer science, and human perception. In this work the mathematical concept of Singularities takes a prominent role. It describes situations that are special in some sense. A simple example is given by a topographical map with height lines describing a mountain landscape. Almost all lines are simply connected, but there are some special cases: at certain positions the lines reduce to a point, for instance at a mountain top, while at other locations (at passes) they intersect themselves. Furthermore, the height lines can have sharp corners and shown maximal and minimal bending. These features involve so-called critical points, the locally special points. A second concept used in this work is the reduction of structure. Again (topographic) maps serve as an example. The larger the scales on which they are drawn, the less the details are visible, but the more the main structure is kept. This effect is known as scale space. Instead of considering the image at one particular scale, or even a set of scales, the continuum of images at all scales, the Deep Structure, is taken.

Show publication details

Zhou, Xuebing; Wolthusen, Stephen; Busch, Christoph; Kuijper, Arjan

Feature Correlation Attack on Biometric Privacy Protection Schemes

2009

Pan, Jeng-Shyang (Ed.) et al.: Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing. Proceedings : IIH-MSP 2009. New York: IEEE, Inc., 2009, pp. 1061-1065

International Conference on Intelligent Information Hiding and Multimedia Signal Processing (IIH-MSP) <5, 2009, Kyoto, Japan>

Privacy protection techniques are an important supplementary of biometric systems. Their main purpose is to prevent security leakages in common biometric systems and to preserve the user's privacy. However, when cryptographic functions are used in the algorithms, randomness of biometric features is strictly required from the security point of view. This randomness is hard to achieve in many feature extraction algorithms, especially for those using the local information of biometric modality. In this paper we discuss privacy protection based on a fuzzy extractor. We show that the security of the algorithm is strongly reduced when statistical properties of biometric features as well as the details of the algorithm are known. An attack exploiting feature correlation is demonstrated.

Show publication details

Kuijper, Arjan

Transitions of a Multi-scale Image Hierarchy Tree

2009

Tai, Xue-Cheng (Ed.) et al.: Scale Space and Variational Methods in Computer Vision. Proceedings. Berlin, Heidelberg, New York: Springer, 2009. (Lecture Notes in Computer Science (LNCS) 5567), pp. 844-855

International Conference on Scale Space and Variational Methods in Computer Vision (SSVM) <2, 2009, Voss, Norway>

In this work we describe the possible transitions for the hierarchical structure that describes an image in Gaussian scale space. Until now, this tree structure has only been used for topological segmentation. In order to perform image matching and retrieval tasks based on this structure, one needs to know which transitions are allowed when the structure is changed under influence of one control parameter. We present a list of such transitions, enabling tree edit distance operations.

Show publication details

Kuijper, Arjan

Visual Computing in Darmstadt Germany: Fraunhofer IGD

2009

IAPR Newsletter, Vol.31 (2009), 4, pp. 3-6

This article continues the Global Pattern Recognition series that focused initially on national laboratories.

Vorlesungen

Zeit

Institut

Titel

Sommer 2013

Technische Universität Darmstadt, DE

20-00-0014 Einführung in Human Computer Systems

Sommer 2013

Technische Universität Darmstadt, DE

20-00-0469 Scale Space and PDE methods in image analysis and processing

Sommer 2012

Technische Universität Darmstadt, DE

20-00-0014 Einführung in Human Computer Systems

Sommer 2012

Technische Universität Darmstadt, DE

20-00-0469 Scale Space and PDE methods in image analysis and processing

Sommer 2011

Technische Universität Darmstadt, DE

20-00-0014 Einführung in Human Computer Systems

Sommer 2011

Technische Universität Darmstadt, DE

20-00-0469 Scale Space and PDE methods in image analysis and processing

Sommer 2010

Technische Universität Darmstadt, DE

469.3 Scale Space and PDE methods in image analysis and processing

Sommer 2009

Technische Universität Darmstadt, DE

469.1 Scale Space and PDE methods in image analysis and processing

Sommer 2008

Technische Universität Graz, AT

710.100 Mathematische Grundlagen in Vision & Grafik: Scale Space and PDE methods in image analysis and processing

Sommer 2008

Johannes Kepler Universität Linz, AT

323035 Exercises in Mathematics for Chemists 2

Sommer 2007

Johannes Kepler Universität Linz, AT

323022 Level Set Methods and Dynamic Impicit Surfaces in Comp. Vision and Comp. Physic

Winter 2006

Johannes Kepler Universität Linz, AT

323014 Image analysis

Winter 2003

IT-Universität Kopenhagen, DK

Scale Space Theory

Winter 1998, 1999, 2000

Universität Utrecht, NL

Algorithmen & Datastructuren

Sommer 2000, 2001

Universität Utrecht, NL

Beschrijven en bewijzen

Sommer 1998

Universität Utrecht, NL

Software Tools