2D recovery of human posture

Research on human motion analysis has motivated increasing interest among image processing researchers. In this paper, a method of 2D recovery of human posture is proposed. The recovery process is as follows: first, the image sequences that involve human motion are acquired by single camera, and the body region is extracted from the image by background subtraction. The silhouette surrounding the region of the body is represented by FCC (Freeman Chain Code). Then each part of the body is labeled, and the coordinates of joints among the parts are retrieved. Thus the sequence of 2D human skeletons is recovered from the image sequence. This paper gives the tracking results for three different kinds of human motion. The 2D human skeletons can be successfully retrieved in the whole course of the complex movement. This proves that the system has certain advantages and fascinating applications. It is a basic and important step toward the recognition of human motion.