Tracking individuals in surveillance video of a high-density crowd

Abstract

Video cameras are widely used for monitoring public areas, such as train stations, airports and shopping centers. When crowds are dense, automatically tracking individuals becomes a challenging task. We propose a new tracker which employs a particle filter tracking framework, where the state transition model is estimated by an optical-flow algorithm. In this way, the state transition model directly uses the motion dynamics across the scene, which is better than the traditional way of a pre-defined dynamic model. Our result shows that the proposed tracker performs better on different tracking challenges compared with the state-of-the-art trackers, while also improving on the quality of the result.

Behavioral profiling in CCTV cameras by combining multiple subtle suspicious observations of different surveillance operators

“…We will focus on how well the correct person can be retrieved in a database, and how this affects the percentage of detected offenders and innocent people for various tag thresholds and number of participants. The alert system allows an analysis of the worst-case scenario, since in an operational system the matching could be improved by tracking [9] or spatio-temporal information [3].…”

Automatische gedragsanalyse voor effectiever cameratoezicht in de openbare ruimte

“…Hoe hoger deze wordt, hoe moeilijker het is om goed onderscheid te maken tussen individuen en hoe minder functionaliteit VCA kan leveren. Door waargenomen dominante looprichtingen in een druk gebied kunnen individuen beter worden gevolgd in de menigte (Hu et al, 2012;Thida et al, 2013). Ook de invloed van het weer en de tijd van de dag zijn van belang als de ruimte buiten is, of althans veel zicht naar buiten heeft.…”

Finding suspects in multiple cameras for improved railway protection

“…Experiments with human operators showed that the system leads to a significant reduction of missed people by using the interactive functionality, especially for large time intervals [5]. The tracking system was integrated and validated in a crowded [13] [19] shopping mall in the Netherlands, in collaboration with five SMEs [4]. The system performed consistently and robustly.…”