Volker Eiselein

Learn More
The presented work is motivated by the problem of local motion estimation via robust regression with linear models. In order to increase the robustness of the motion estimates we propose a novel Robust Local Optical Flow approach based on a modified Hampel estimator. We show the deficiencies of the least squares estimator used by the standard KLT tracker(More)
This paper presents an overview of the Visual Privacy Task (VPT) of MediaEval 2014, its objectives, related dataset, and evaluation approaches. Participants in this task were required to implement a privacy filter or a combination of filters to protect various personal information regions in video sequences as provided. The challenge was to achieve an(More)
This paper describes a robust method for the local optical flow estimation and the KLT feature tracking performed on the GPU. Therefore we present an estimator based on the L norm with robust characteristics. In order to increase the robustness at discontinuities we propose a strategy to adapt the used region size. The GPU implementation of our approach(More)
Convolutional neural networks are a popular choice for current object detection and classification systems. Their performance improves constantly but for effective training, large, hand-labeled datasets are required. We address the problem of obtaining customized, yet large enough datasets for CNN training by synthesizing them in a virtual world, thus(More)
In this paper we improve a human detector by means of crowd density information. Human detection is especially challenging in crowded scenes which makes it important to introduce additional knowledge into the detection process. We compute crowd density maps in order to estimate the spatial distribution of people in the scene and show how it is possible to(More)
In this paper we present a decentralized surveillance network composed of IP video cameras, analysis devices and a central node which collects information and displays it in a 3D model of the complete area. The exchange of information between all components in the surveillance network takes place according to the ONVIF specification, therefore ensuring(More)
While various privacy protection filters have been proposed in the literature, little importance has been given to the context relevance of these filters. In this paper, we specifically focus on the dependency between privacy preservation and crowd density. We show that information about the crowd density in a scene can be used in order to adjust the level(More)
Detecting people carrying objects is a commonly formulated problem which results can be used as a first step in order to monitor interactions between people and objects in computer vision applications. In this paper we propose a novel method for this task. By using gray-value information instead of the contours obtained by a segmentation process we build up(More)