Automatic Detection of Unexpected Events in Dense Areas for Videosurveillance Applications
Bertrand Luvison, Thierry Château, Jean‐Thierry Lapresté, Patrick Sayd, Quoc Cuong · InTech eBooks · 2011
Intelligent videosurveillance is largely developping due to both the increasing population, especially in cities, and the exploding number of videosurveillance cameras deployed. When interesting to dense areas, mainly two kinds of scenes come to mind : crowd scenes and traffic ones. A usual treatment on these videos, usually done by security officers, is to monitore several video streams looking for anomalities. A survey of Dee & Velastin (2008) report a camera to screen ratio between 1:4 in best cases and 1:78 in worst ones. As a consequence, the chances to react quickly to an event are very low. This is the reason why this task need to be assisted. Nevertheless automatically detecting anomalies in these kinds of video is particularly difficult because of the large amount of information to be processed simultaneously and the complexity of the scenes. Most of computer vision methods perform well in visual surveillance applications where the number of objects is low. Individuals can be successfully detected and tracked in scenarios where they appear in images with a sufficient resolution, and in the case of very limited and/or temporary occlusions. However, in crowded scenes, such as in public areas (for example, airports, stations, shopping malls), the video analysis task becomes much more complex. Abnormal behaviour definition is very scene and context dependent. Objects of interest may be small with respect of the global view, and only partially visible thus very difficult to model. Moreover, permanent interaction between individuals in a crowd even complicates the analysis.