Exploiting Single View Geometry in Pan-Tilt-Zoom Camera Networks

International audiencePTZ (pan-tilt-zoom) camera networks have an important role in surveillance systems. They have the ability to direct the attention to interesting events that occur in the scene. In order to achieve such behavior the cameras in the network use a process known as sensor slaving: one (or more) master camera monitors a wide area and tracks moving targets so as to provide the positional information to one (or more) slave camera. The slave camera foveates at the targets in high resolution. In this paper, we propose a simple method to solve two typical problems that are the basic building blocks to create high level functionality in PTZ camera networks: the computation of the world to image homographies and the computation of camera to camera homographies. The first one is used for computing the image sensor observation model in sequential target tracking, the second one is used for camera slaving. Finally a cooperative tracking approach exploiting the use of both homographies is presented