PhysicsBased Person Tracking Using Simplified LowerBody Dynamics.pdf

Physics-Based Person Tracking Using Simplified Lower-Body Dynamics Marcus A. Brubaker, David J. Fleet, Aaron Hertzmann Department of Computer Science University of Toronto {mbrubake,fleet,hertzman}@cs.toronto.edu Abstract We introduce a physics-based model for 3D person tracking. Based on a biomechanical characterization of lower-body dynamics, the model captures important phys- ical properties of bipedal locomotion such as balance and ground contact, generalizes naturally to variations in style due to changes in speed, step-length, and mass, and avoids common problems such as footskate that arise with existing trackers. The model dynamics comprises a two degree-of- freedom representation of human locomotion with inelastic Figure 1. The Anthropomorphic Walker (left) and our Kinematic Model (right). ground contact. A stochastic controller generates impulsive forces during the toe-off stage of walking and spring-like ing to model full-body dynamics, our approach is inspired forces between the legs. A higher-dimensional kinematic by simplified biomechanical models of human locomotion observation model is then conditioned on the underlying [4, 5, 14, 17]. For example, the Anthropomorphic Walker dynamics. We use the model for tracking walking people [14, 15], shown in Fig. 1, exhibits human-like walking, in- from video, including examples with turning, occlusion, and cluding an inverted pend