This Article 
 Bibliographic References 
 Add to: 
Dynamical Simulation Priors for Human Motion Tracking
Jan. 2013 (vol. 35 no. 1)
pp. 52-65
Marek Vondrak, Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
L. Sigal, Disney Res., Pittsburgh, PA, USA
O. C. Jenkins, Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
We propose a simulation-based dynamical motion prior for tracking human motion from video in presence of physical ground-person interactions. Most tracking approaches to date have focused on efficient inference algorithms and/or learning of prior kinematic motion models; however, few can explicitly account for the physical plausibility of recovered motion. Here, we aim to recover physically plausible motion of a single articulated human subject. Toward this end, we propose a full-body 3D physical simulation-based prior that explicitly incorporates a model of human dynamics into the Bayesian filtering framework. We consider the motion of the subject to be generated by a feedback “control loop” in which Newtonian physics approximates the rigid-body motion dynamics of the human and the environment through the application and integration of interaction forces, motor forces, and gravity. Interaction forces prevent physically impossible hypotheses, enable more appropriate reactions to the environment (e.g., ground contacts), and are produced from detected human-environment collisions. Motor forces actuate the body, ensure that proposed pose transitions are physically feasible, and are generated using a motion controller. For efficient inference in the resulting high-dimensional state space, we utilize an exemplar-based control strategy that reduces the effective search space of motor forces. As a result, we are able to recover physically plausible motion of human subjects from monocular and multiview video. We show, both quantitatively and qualitatively, that our approach performs favorably with respect to Bayesian filtering methods with standard motion priors.
Index Terms:
video signal processing,approximation theory,Bayes methods,feedback,filtering theory,image motion analysis,search problems,Bayesian filtering method,human motion tracking,simulation-based dynamical motion prior,physical ground-person interaction,inference algorithm,kinematic motion model,single articulated human subject,full-body 3D physical simulation-based prior,human dynamics,Bayesian filtering framework,feedback control loop,Newtonian physics,rigid-body motion dynamics approximation,interaction force integration,motor force,human-environment collision detection,motion controller,high-dimensional state space,exemplar-based control strategy,search space,monocular video,multiview video,Kinematics,Tracking,Humans,Dynamics,Joints,Biological system modeling,Trajectory,particle filtering,Articulated tracking,human pose tracking,human motion,physical simulation,physics-based priors,Bayesian filtering
Marek Vondrak, L. Sigal, O. C. Jenkins, "Dynamical Simulation Priors for Human Motion Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 1, pp. 52-65, Jan. 2013, doi:10.1109/TPAMI.2012.61
Usage of this product signifies your acceptance of the Terms of Use.