• Publikationen
Show publication details

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

Change Detection and Blob Tracking of Fish in Underwater Scenarios

2019

Computer Vision, Imaging and Computer Graphics – Theory and Applications

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

In this paper, the difficult task of detecting fishes in underwater scenarios is analyzed with a special focus on crowded scenes where the differentiation between separate fishes is even more challenging. An extension for the Gaussian Switch Model is developed for the detection which applies an intelligent update scheme to create more accurate background models even for difficult scenes. To deal with very crowded areas in the scene we use the Flux Tensor to create a first coarse segmentation and only update areas that are with high certainty background. The spatial coherency is increased by the N2Cut, which is a Ncut adaption to change detection. More relevant information are gathered with a novel blob tracker that uses a specially developed energy function and handling of errors during the change detection. This method keeps the generality of the whole approach so that it can be used for any moving object. The proposed algorithm enabled us to get very accurate underwater segmentations as well as precise results in tracking scenarios.

Show publication details

Farhadifard, Fahimeh; Urban, Bodo [Examiner]; Lukas, Uwe von [Betreuer]; Koch, Reinhard [Betreuer]

Underwater Image Restoration: Super-resolution and Deblurring via Sparse Representation and Denoising by Means of Marine Snow Removal

2018

Rostock, Univ., Diss., 2018

Underwater imaging has been widely used as a tool in many fields, such as marine industry, deep-sea mining, aquaculture and water assessment. However, a major issue is the quality of the resulting images and videos. Due to the light’s interaction with water and its constituents, the acquired underwater images and videos often suffer from a significant amount of scatter (blur and haze) and noise. Furthermore, since data transmission from the equipment mounted under water to the station above water is still a challenge, usually a compressed and low-resolution version of the data is transferred. In the light of these issues, this thesis considers the problems of low-resolution, blurred and noisy underwater images and proposes several approaches to improve the quality of such images/video frames. This is undertaken through two main contributions. The first major contribution of this work is the super-resolution and deblurring of single underwater images. This is done by using a set of compact high and low-resolution cluster dictionaries where sparse representation is used as the regularizer. Since such an approach inevitably calls for a model selection criterion in both learning and reconstruction stages, a scaleinvariance model is proposed to properly establish the link between the low and high-resolution feature spaces. The subject of the second major contribution is image denoising. Besides additive noises such as sensor noise, the visibility in underwater images is reduced by the presence of suspended particles in water. This represents an unwanted signal, which is also disruptive for advanced computer vision tasks, such as segmentation. Since this phenomenon is a real signal and part of the scene, two-fold approaches consisting of first detection and then removal of such particles, are proposed. To avoid the uncertainty introduced by using local information for restoration, some global priors of the scene are learned, which are then used to estimate the parts of the scene that are covered by the particles. For this, a Gaussian-based background subtraction approach is proposed to obtain static features of the scene. These are used as training data for learning the priors. Quantitative and qualitative experiments conducted over real and simulated underwater images and video frames validate the success of the proposed approaches at improving the image resolution and deblurring image features significantly as well as detecting and removing marine particles, while the object edges are preserved.

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

VISAPP 2017. Proceedings

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

Marine Snow Detection and Removal: Underwater Image Restoration using Background Modeling

2017

WSCG 2017. Full Papers Proceedings

International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision (WSCG) <25, 2017, Plzen, Czech Republic>

It is a common problem that images captured underwater (UW) are corrupted by noise. This is due to the light absorption and scattering by the marine environment; therefore, the visibility distance is limited up to few meters. Despite blur, haze, low contrast, non-uniform lightening and color cast which occasionally are termed noise, additive noises, such as sensor noise, are the center of attention of denoising algorithms. However, visibility of UW scenes is distorted by another source termed marine snow. This signal not only distorts the scene visibility by its presence but also disturbs the performance of advanced image processing algorithms such as segmentation, classification or detection. In this article, we propose a new method that removes marine snow from successive frames of videos recorded UW. This method utilizes the characteristics of such a phenomenon and detects it in each frame. In the meanwhile, using a background modeling algorithm, a reference image is obtained. Employing this image as a training data, we learn some prior information of the scene and finally, using these priors together with an inpainting algorithm, marine snow is eliminated by restoring the scene behind the particles.

Show publication details

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

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

2017

VISAPP 2017. Proceedings

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

Eurographics 2016. Short Papers

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

OCEANS 2016 MTS/IEEE Monterey

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

WSCG 2016. Full Papers Proceedings

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.

978-80-86943-57-2

Show publication details

Farhadifard, Fahimeh; Zhou, Zhiliang; Lukas, Uwe von

Learning-based Underwater Image Enhancement with Adaptive Color Mapping

2015

ISPA 2015

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

Blurring and color cast are two of the most challenging problems for underwater imaging. The poor quality hinders the automatic segmentation or analysis of images. In this paper, we describe an image enhancement method to reduce the blurring and color cast of the underwater medium. It is a twofolded approach; First, a color correction algorithm is applied to correct the color cast and produce a natural appearance of the sub-sea images. Second, a pair of learned dictionaries based on sparse representation are applied to sharpen the image and enhance the details. Our strategy is a single image approach that does not require additional knowledge of environment such as depth, distance object/camera or water quality. The experimental results show that the proposed method can efficiently enhance almost every underwater image; And offers a quality that is typically sufficient for the high level computer vision algorithms.

Show publication details

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

Real Time Video Segmentation Optimization with a Modified Normalized Cut

2015

ISPA 2015

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

Farhadifard, Fahimeh

Underwater Image Restoration: Effect of Different Dictionaries

2015

Proceedings of the International Summer School on Visual Computing 2015

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

Ocean engineering has a strong need for clear and high quality underwater images. Capturing a clear scene underwater is not a trivial task since color cast and scattering caused by light attenuation and absorption are common. The poor quality hinders the automatic segmentation or analysis of the images. In this work, an image restoration based on compressive sensing is reported which tackles with blurring caused by light scattering and provides better structural details. Furthermore, the effects of different dictionaries on the quality of restoration is studied. The aim is to use a single degraded underwater image and improve the image quality without any prior knowledge about the scene such as depth, camera-scene distance or water quality.