Moving Human Body Detection in Video Sequences

A human body detection algorithm based on the combination of moving information with shape information is proposed in the paper. Firstly, Eigen-object computed from three frames in the initial video sequences is used to detect the moving object. Secondly, the shape information of human body is used to classify human and other object. Furthermore, the occlusion between two objects during a short time is processed by using continues multiple frames. The advantages of the algorithm are accurately moving object detection, and the detection result doesn´t effect by body pose. Moreover, as the shadow of moving object has been eliminated in the detection step, the human body extracted doesn´t effect by shadow.