Estimating articulated human pose from video using shape context

Recovery of 3D body pose is a fundamental problem for human motion analysis in many applications such as motion capture, vision interface, visual surveillance, and gesture recognition. In this paper, we present a new image-based approach to infer 3D human structure parameters from uncalibrated video. The estimation is example based. First, we acquire a special motion database through an off-line motion capture process. Second, given an uncalibrated motion video, we abstract the viewpoint and then the silhouettes database associated with 3D poses is built by projecting each data of the 3D motion database into 2D plane. Next, with the image silhouettes, the unknown structure parameters are inferred by performing a similarity search in the silhouettes database. We pay more attention on how to retrieving 3D body pose by matching 2D silhouette based on shape context. Through a lot of experiments, the results we got are really satisfying. To accelerate the process of calculating the distance in shape context, we use PCA (principal components analysis) to reduce the computation of complexity. We use trampoline sport, which is an example of complex human motion, to demonstrate the effectiveness of our approach and compare the results with those obtained with Hu moments method