On pixel count based crowd density estimation for visual surveillance

Surveillance systems for public security are going beyond the conventional CCTV. A new generation of systems relies on image processing and computer vision techniques, deliver more ready-to-use information, and provide assistance for early detection of unusual events. Crowd density is a useful source of information because unusual crowdedness is often related to unusual events. Previous works on crowd density estimation either ignore perspective distortion or perform the correction based on incorrect formulation. Also there is no investigation on whether the geometric correction derived for the ground plane can be applied to human objects standing upright to the plane. This paper derives the relation for geometric correction for the ground plane and proves formally that it can be directly applied to all the foreground pixels. We also propose a very efficient implementation because it is important for a real-time application. Finally a time-adaptive criterion for unusual crowdedness detection is described.