Autonomous scene monitoring system based on multiviewpoint images

We propose an incrementation of automated monitoring system using multiple cameras embedded in the environment. At first, the object intuding to a sensitive area is detected using planar view-volume intersection method. It assumes no prior knowledge and stably detects any object crossing into the monitored area. Then the whole shape of the object is measured using multiple stereo cameras. The region of object is extracted using improved background subtraction method using disparity images, and measured range images are aligned using common coordinate system. Finally, the motion of the object is tracked using generated CG images.