In this paper we address the problem of predicting human body configurations and appearance for the task of human motion tracking in video. Unlike many previous approaches that relied on simplified body models, we are able to use detailed modelsof body shape. Having rendered the body model onto the current video frame we make use of the optical flow information to propagate the body configuration to the next image frame Parameters are estimated via a robust optimization technique which is basedon a Kalman filter approach to the prediction of body configurations m the space of articulated body motions. Results are shown demonstrating the effectiveness of our approach.
展开▼