Human tracking in crowded environment with stereo cameras

In this paper, a human detection and tracking system in a crowded environment is presented. The biggest challenge of the system is to detect occluded people from the captured video where visible information of the occluded people in a camera is reduced. Many researchers proposed to reconstruct the occluded information from other cameras which are installed in the same place with different viewing angles, but, hardware cost and computation cost will be increased. In this paper, a stereo camera system is used with a novel occlusion model to solve the occlusion problem. Result shows that it significantly reduces the hardware cost and computation cost of the system while maintaining a good tracking result under severe occlusions.