• Publikationen
Show publication details

Radolko, Martin; Farhadifard, Fahimeh; Lukas, Uwe von

Change Detection in Crowded Underwater Scenes Via an Extended Gaussian Switch Model Combined with a Flux Tensor Pre-segmentation

2017

Imai, Francisco (Ed.) et al.: VISAPP 2017. Proceedings : 12th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2017 Volume 4). SciTePress, 2017, pp. 405-415

International Conference on Computer Vision Theory and Applications (VISAPP) <12, 2017, Porto, Portugal>

In this paper a new approach for change detection in videos of crowded scenes is proposed with the extended Gaussian Switch Model in combination with a Flux Tensor pre-segmentation. The extended Gaussian Switch Model enhances the previous method by combining it with the idea of the Mixture of Gaussian approach and an intelligent update scheme which made it possible to create more accurate background models even for difficult scenes. Furthermore, a foreground model was integrated and could deliver valuable information in the segmentation process. To deal with very crowded areas in the scene - where the background is not visible most of the time - we use the Flux Tensor to create a first coarse segmentation of the current frame and only update areas that are almost motionless and therefore with high certainty should be classified as background. To ensure the spatial coherence of the final segmentations, the N2Cut approach is added as a spatial model after the background subtraction step. The evaluation was done on an underwater change detection datasets and showed significant improvements over previous methods, especially in the crowded scenes.

Show publication details

Farhadifard, Fahimeh; Radolko, Martin; Lukas, Uwe von

Single Image Marine Snow Removal based on a Supervised Median Filtering Scheme

2017

Imai, Francisco (Ed.) et al.: VISAPP 2017. Proceedings : 12th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2017 Volume 4). SciTePress, 2017, pp. 280-287

International Conference on Computer Vision Theory and Applications (VISAPP) <12, 2017, Porto, Portugal>

Underwater image processing has attracted a lot of attention due to the special difficulties at capturing clean and high quality images in this medium. Blur, haze, low contrast and color cast are the main degradations. In an underwater image noise is mostly considered as an additive noise (e.g. sensor noise), although the visibility of underwater scenes is distorted by another source, termed marine snow. This signal disturbs image processing methods such as enhancement and segmentation. Therefore removing marine snow can improve image visibility while helping advanced image processing approaches such as background subtraction to yield better results. In this article, we propose a simple but effective filter to eliminate these particles from single underwater images. It consists of different steps which adapt the filter to fit the characteristics of marine snow the best. Our experimental results show the success of our algorithm at outperforming the existing approaches by effectively removing this phenomenon and preserving the edges as much as possible.

Show publication details

Farhadifard, Fahimeh; Radolko, Martin

Adaptive UW Image Deblurring via Sparse Representation

2016

Santos, Luis Paulo (Ed.) et al.: Eurographics 2016. Short Papers. The Eurographics Association, 2016, pp. 41-44

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

We present an adaptive underwater (UW) image deblurring algorithm based on sparse representation where a blur estimation is used to guide the algorithm for the best image reconstruction. The strong blur in this medium is caused by forward scatter and is challenging since it increases by camera scene distance. It is a common practice to use methods such as dark channel prior to estimate the depth map, and use this information to improve the image quality. However, we found it not successful in the case of blur since these methods are based on haze phenomenon. We propose a simple but effective algorithm via sparse representation which establishes a blur strength estimation and uses this information for adaptive deblurring. Extensive experiments manifest the effectiveness of our method in case of small but challenging blur changes.

Show publication details

Radolko, Martin; Lukas, Uwe von; Farhadifard, Fahimeh

Dataset on Underwater Change Detection

2016

Marine Technology Society (MTS): OCEANS 2016 MTS/IEEE Monterey. The Institute of Electrical and Electronics Engineers (IEEE), 2016, 8 p.

MTS/IEEE Oceans Conference and Exhibition (OCEANS) <2016, Monterey, CA, USA>

The detection of moving objects in a scene is a well researched but depending on the concrete research still often a challenging computer vision task. Usually it is the first step in a whole pipeline and all following algorithms (tracking, classification etc.) are dependent on the accuracy of the detection. Hence, a good pixel-precise segmentation of the objects of interest is mandatory for many applications. However, the underwater environment has mostly been neglected so far and there exists no common dataset to evaluate different algorithms under the harsh underwater conditions and therefore a comprehensive evaluation is impossible. In this paper, we present an underwater change detection dataset consisting of five videos and hundreds of handsegmented groundtruth images as well as a survey of different underwater image enhancement techniques and their impact on segmentation algorithms.

Show publication details

Radolko, Martin; Farhadifard, Fahimeh

Using Trajectories Derived by Dense Optical Flows as a Spatial Component in Background Subtraction

2016

Pan, Zhigeng (Ed.) et al.: WSCG 2016. Full Papers Proceedings : 24th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision. [cited 04 January 2017] Available from http://wscg.zcu.cz/DL/wscg DL.htm: University of West Bohemia, 2016. (Computer Science Research Notes (CSRN) 2601), pp. 1-7

International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) <24, 2016, Plzen, Czech Republic>

Foreground-Background Segregation has been intensively researched in the last decades as it is an important first step in many Computer Vision tasks. Nonetheless, there are still many open questions in this area and in this paper we focus on a special surveillance scenario where a static camera monitors a predefined region. This restrain makes some aspects easier and good results could be achieved with Background Subtraction methods. However, these only work pixelwise and lack the spatial component completely. We suggest an approach to add the crucial spatial information to the segmentations with Dense Optical Flows. For this, a number of successive images are taken from the video to compute the Trajectories of the pixels through these frames. This enables us to fuse the information from the several images and use this for segmentation. The algorithm was evaluated on a video from a surveillance camera and showed promising results.

Show publication details

Radolko, Martin

Comparison of Spatial Models for Foreground-Background Segmentation in Underwater Videos

2015

Schulz, Hans-Jörg (Ed.) et al.: Proceedings of the International Summer School on Visual Computing 2015. Stuttgart: Fraunhofer Verlag, 2015, pp. 91-100

International Summer School on Visual Computing <1, 2015, Rostock, Germany>

The low-level task of foreground-background segregation is an important foundation for many high-level computer vision tasks and has been intensively researched in the past. Nonetheless, unregulated environments usually impose challenging problems, especially the difficult and often neglected underwater environment. There, among others, the edges are blurred, the contrast is impaired and the colors attenuated. Our approach to this problem uses an efficient Background Subtraction algorithm and evaluates it in combination with different spatial models.

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

Radolko, Martin; Farhadifard, Fahimeh; Gutzeit, Enrico; Lukas, Uwe von

Real Time Video Segmentation Optimization with a Modified Normalized Cut

2015

Loncaric, Sven (Ed.) et al.: ISPA 2015 : 9th International Symposium on Image and Signal Processing and Analysis. Zagreb: University of Zagreb, 2015, pp. 31-36

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

The low-level task of foreground-background segregation is an important foundation for many high-level computer vision tasks and has been intensively researched in the past. Nonetheless, unregulated environments usually impose challenging problems and often particular difficulties arise from real time requirements. In this paper we propose a new energy function to evaluate the spatial relations in a segmentation. It is based on the Normalized Cut but adapted these principles to the usage of videos instead of single images. This makes it possible to get a comparable spatial-accuracy as in state of the art approaches (e.g. Markov Random Fields). However, the optimized hierarchical local minimization process for our energy function is at least two orders of magnitude faster. In combination with an efficient Background Subtraction this results in an accurate real time video segmentation algorithm even for high definition videos.

Show publication details

Radolko, Martin; Gutzeit, Enrico

Video Segmentation via a Gaussian Switch Background Model and Higher Order Markov Random Fields

2015

Braz, José (Ed.) et al.: VISAPP 2015 - Volume I : Proceedings of the International Conference on Computer Vision Theory and Applications. SciTePress, 2015, pp. 537-544

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

Foreground-background segmentation in videos is an important low-level task needed for many different applications in computer vision. Therefore, a great variety of different algorithms have been proposed to deal with this problem, however none can deliver satisfactory results in all circumstances. Our approach combines an efficient novel Background Substraction algorithm with a higher order Markov Random Field (MRF) which can model the spatial relations between the pixels of an image far better than a simple pairwise MRF used in most of the state of the art methods. Afterwards, a runtime optimized Belief Propagation algorithm is used to compute an enhanced segmentation based on this model. Lastly, a local between Class Variance method is combined with this to enrich the data from the Background Substraction. To evaluate the results the difficult Wallflower data set is used.