Physics-Based Human Pose Tracking

Human motion tracking from single-view 2D measurements contains inherent ambiguities, due to depth ambiguities and the indirect relation of pixel intensities to 3D poses. Prior models of human poses and motion show great promise in resolving these difficulties, by biasing inference toward the most probable configurations. The main challenge is to describe models that accurately describe how people move: in general, we expect that better prior models will give better tracking results.

[1]  David J. Fleet,et al.  Priors for people tracking from small training sets , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[2]  Pascal Fua,et al.  Hierarchical implicit surface joint limits for human body tracking , 2005, Comput. Vis. Image Underst..

[3]  Russ Tedrake,et al.  Efficient Bipedal Robots Based on Passive-Dynamic Walkers , 2005, Science.

[4]  Cristian Sminchisescu,et al.  Generative modeling for continuous non-linearly embedded visual inference , 2004, ICML.

[5]  Cristian Sminchisescu,et al.  Variational mixture smoothing for non-linear dynamical systems , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[6]  A. Elgammal,et al.  Inferring 3D body pose from silhouettes using activity manifold learning , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[7]  Cristian Sminchisescu,et al.  Kinematic jump processes for monocular 3D human tracking , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[8]  David J. Fleet,et al.  Hybrid Monte Carlo filtering: edge-based people tracking , 2002, Workshop on Motion and Video Computing, 2002. Proceedings..

[9]  Arthur D Kuo,et al.  Energetics of actively powered locomotion using the simplest walking model. , 2002, Journal of biomechanical engineering.

[10]  Gill A. Pratt,et al.  Legged robots at MIT: what's new since Raibert? , 2000, IEEE Robotics Autom. Mag..

[11]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[12]  David J. Fleet,et al.  Stochastic Tracking of 3D Human Figures Using 2D Image Motion , 2000, ECCV.

[13]  Zoran Popovic,et al.  Physically based motion transformation , 1999, SIGGRAPH.

[14]  Hans-Hellmut Nagel,et al.  Tracking Persons in Monocular Image Sequences , 1999, Comput. Vis. Image Underst..

[15]  Tad McGeer,et al.  Passive Dynamic Walking , 1990, Int. J. Robotics Res..

[16]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[17]  David J. Fleet,et al.  Stochastic Tracking of 3D Human Figures Using 2D Image Motion , 2000, ECCV.

[18]  Vladimir Pavlovic,et al.  A dynamic Bayesian network approach to figure tracking using learned dynamic models , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.