Ivo Keller

Image browsing with PCA-assisted user-interaction

User interfaces for sophisticated search engines must offer users quick and easy access to the objects to be visualized. We present a browsing tool which arranges images with respect to the user search intention in a continuous and intuitive manner in real time. Since the capacity of the visual human system is higher for spatial information, we prefer a virtual 3D space for the visualization. Because our image features are described in terms of very high-dimensional MPEG-7 descriptors, we have to reduce them to only three dimensions for visual presentation. The dimension reduction is realized by an appropriate weighting of the high-dimensional descriptor components corresponding to a modification of the covariance-matrix used for principal component analysis (PCA). In addition, this modification allows us to overcome a problem arising from equally sized eigenvalues and provides varying eigenspaces nearly continuously. The technique introduced is a general approach, which can be combined with other relevance feedback methods.

Adaptively Splitted GMM With Feedback Improvement for the Task of Background Subtraction

Per pixel adaptive Gaussian mixture models (GMMs) have become a popular choice for the detection of change in the video surveillance domain because of their ability to cope with many challenges characteristic for surveillance systems in real time with low memory requirements. Since their first introduction in the surveillance domain, GMM has been enhanced in many directions. In this paper, we present a study of some relevant GMM approaches and analyze their underlying assumptions and design decisions. Based on this paper, we show how these systems can be further improved by means of a variance controlling scheme and the incorporation of region analysis-based feedback. The proposed system has been thoroughly evaluated using the extensive data set of the IEEE Workshop on Change Detection, showing an outranking performance in comparison with state-of-the-art methods.

A Lagrangian framework for video analytics

The extraction of motion patterns from image sequences based on the optical flow methodology is an important and timely topic among visual multi media applications. In this work we will present a novel framework that combines the optical flow methodology from image processing with methods developed for the Lagrangian analysis of time-dependent vector fields. The Lagrangian approach has been proven to be a valuable and powerful tool to capture the complex dynamic motion behavior within unsteady vector fields. To come up with a compact and applicable framework, this paper will provide concepts on how to compute trajectory-based Lagrangian measures in series of optical flow fields, a set of basic measures to capture the essence of the motion behavior within the image, and a compact hierarchical, feature-based description of the resulting motion features. The resulting framework will bee shown to be suitable for an automated image analysis as well as compact visual analysis of image sequences in its spatio-temporal context. We show its applicability for the task of motion feature description and extraction on different temporal scales, crowd motion analysis, and automated detection of abnormal events within video sequences.

Human action recognition using Lagrangian descriptors

Human action recognition requires the description of complex motion patterns in image sequences. In general, these patterns span varying temporal scales. In this context, Lagrangian methods have proven to be valuable for crowd analysis tasks such as crowd segmentation. In this paper, we show that, besides their potential in describing large scale motion patterns, Lagrangian methods are also well suited to model complex individual human activities over variable time intervals. We use Finite Time Lyapunov Exponents and time-normalized arc length measures in a linear SVM classification scheme. We evaluated our method on the Weizmann and KTH datasets. The results demonstrate that our approach is promising and that human action recognition performance is improved by fusing Lagrangian measures.

Robust local optical flow estimation using bilinear equations for sparse motion estimation

This article presents a theoretical framework to decrease the computation effort of the Robust Local Optical Flow method which is based on the Lucas Kanade method. We show mathematically, how to transform the iterative scheme of the feature tracker into a system of bilinear equations and thus estimate the motion vectors directly by analyzing its zeros. Furthermore, we show that it is possible to parallelise our approach efficiently on a GPU, thus, outperforming the current OpenCV-OpenCL implementation of the pyramidal Lucas Kanade method in terms of runtime and accuracy. Finally, an evaluation is given for the Middlebury Optical Flow and the KITTI datasets.

Spatio-temporal crowd density model in a human detection and tracking framework

Recently significant progress has been made in the field of person detection and tracking. However, crowded scenes remain particularly challenging and can deeply affect the results due to overlapping detections and dynamic occlusions. In this paper, we present a method to enhance human detection and tracking in crowded scenes. It is based on introducing additional information about crowds and integrating it into the state-of-the-art detector. This additional information cue consists of modeling time-varying dynamics of the crowd density using local features as an observation of a probabilistic function. It also involves a feature tracking step which allows excluding feature points attached to the background. This process is favorable for the later density estimation since the influence of features irrelevant to the underlying crowd density is removed. Our proposed approach applies a scene-adaptive dynamic parametrization using this crowd density measure. It also includes a self-adaptive learning of the human aspect ratio and perceived height in order to reduce false positive detections. The resulting improved detections are subsequently used to boost the efficiency of the tracking in a tracking-by-detection framework. Our proposed approach for person detection is evaluated on videos from different datasets, and the results demonstrate the advantages of incorporating crowd density and geometrical constraints into the detection process. Also, its impact on tracking results have been experimentally validated showing good results. HighlightsWe model time-varying dynamics of the crowd density using feature tracks.We incorporate the crowd measure into the state-of-the-art detector.We extend the improved detections to tracking in a tracking-by-detection framework.We obtain better results compared to the baseline methods of detection and tracking.

On building decentralized wide-area surveillance networks based on ONVIF

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 interoperability between products complying with the specification and flexibility regarding the integration of new devices and services. The collected information is displayed in a 3D model of the surveilled area, therefore providing a comfortable overview of the activity in large environments and offering the user an intuitive way to eventually interact with network devices.

Video indexing and summarization as a tool for privacy protection

The ever increasing number of surveillance camera networks being deployed all over the world has resulted in a high interest in the development of algorithms to automatically analyze the video footage, but has also opened new questions as how to efficiently manage the vast amount of information generated and, more important, how to protect the privacy of the individuals being recorded in their daily life. In this paper, we present a survey on video summarization techniques developed in order to efficiently access to the points of interest in the video footage. Thereby, we emphasize on the links that these techniques show with the task of privacy protection and draw lines of future research directions to incorporate indexing and summarization as tools for privacy protection by design.

Enhancing human detection using crowd density measures and an adaptive correction filter

In this paper we present a method of improving 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 enhance the detection results of a state-of-the-art human detector by this information. The proposed method applies a self-adaptive, dynamic parametrization and as an additional contribution uses scene-adaptive learning of the human aspect ratio in order to reduce false positive detections in crowded areas. We evaluate our method on videos from different datasets and demonstrate how our system achieves better results than the baseline algorithm.

A motion-enhanced hybrid Probability Hypothesis Density filter for real-time multi-human tracking in video surveillance scenarios

The Probability Hypothesis Density (PHD) filter is a multi-object Bayes filter which has been recently becoming popular in the tracking community especially for its linear complexity and its ability to filter out a high amount of clutter. However, its application to Computer Vision scenarios can be difficult as it requires high detection probabilities. Many human detectors suffer from a significant miss-match rate which causes problems for the PHD filter. This article presents an implementation of a Gaussian Mixture PHD (GM-PHD) filter which is enhanced by Optical Flow information in order to account for missed detections. We give a detailed mathematical discussion for the parameters of the proposed system and justify our results by extensive tests showing the performance in several contexts and on different datasets.