A Multi-Camera Tracking System That Can Always Select a Better View to Perform Tracking

Date Added: Jul 2009
Format: PDF

In this paper, the authors propose a new multiple-camera people tracking system that is equipped with the following functions: can handle long-term occlusions, complete occlusions, and unpredictable motions; can detect arbitrary sized foreground objects; can detect objects with much faster speed. The main contribution of our method is twofold: an M-to-one relationship with only point homography matching for occlusion detection can achieve efficiency; a view-hopping technique based on Object Motion Probability (OMP) is proposed to automatically select an appropriate observation view for tracking a human subject.