REAL TIME HUMAN BODY TRACKING USING WAVENET

摘要

Human body tracking is useful in applications like medical diagnostic, human computer interface, visual surveillance etc. In this paper, a trajectory-learning algorithm using wavenet is proposed to track human body in real time without sacrificing accuracy. Human body is located within a small searching window using color and shape as heuristic. The location and size of the searching window are estimated using the proposed wavenet-based algorithm. The effectiveness and efficiency of the proposed tracking system were tested. The results show that the proposed system can track the human body in real time under various conditions including clutter background, background with distractor, and scene with object occlusion.