Abstract
A human pose often conveys not only the configuration of the body parts, but also implicit predictive information about the ensuing motion. This dynamic information can benefit vision applications which lack explicit motion cues. The human visual system can easily perceive the dynamic information in still images. However, computational algorithms to infer and utilize it in computer vision applications are limited. In this paper, we propose a probabilistic framework to infer the dynamic information associated with a human pose. The inference problem is posed as a nonparametric density estimation problem on a non-Euclidean manifold of linear dynamical models. Since direct modeling is intractable, we develop a data driven approach, estimating the density for the test sample under consideration. Statistical inference on the estimated density provides us with quantities of interest like the most probable future motion of the human and the amount of motion information conveyed by a pose. Our experiments demonstrate that the extracted motion information benefits numerous applications in computer vision. In particular, the predicted future motion is useful for activity recognition, human trajectory synthesis, and motion prediction.