A dynamic Bayesian network approach to figure tracking using learned dynamic models

The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However most work on tracking and synthesizing figure motion has employed either simple, generic dynamic models or highly specific hand-tailored ones. Recently, a broad class of learning and inference algorithms for time-series models have been successfully cast in the framework of dynamic Bayesian networks (DBNs). This paper describes a novel DBN-based switching linear dynamic system (SLDS) model and presents its application to figure motion analysis. A key feature of our approach is an approximate Viterbi inference technique for overcoming the intractability of exact inference in mixed-state DBNs. We present experimental results for learning figure dynamics from video data and show promising initial results for tracking, interpolation, synthesis, and classification using learned models.

[1]  R. E. Kalman,et al.  New Results in Linear Filtering and Prediction Theory , 1961 .

[2]  R. Kalman,et al.  New results in linear prediction and filtering theory Trans. AMSE , 1961 .

[3]  H. Rauch.  Solutions to the linear smoothing problem , 1963 .

[4]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[5]  R. Shumway,et al.  Dynamic linear models with switching , 1991 .

[6]  Radford M. Neal.  Connectionist Learning of Belief Networks , 1992, Artif. Intell..

[7]  Yaakov Bar-Shalom,et al.  Estimation and Tracking: Principles, Techniques, and Software , 1993 .

[8]  Radford M. Neal.  A new view of the EM algorithm that justifies incremental and other variants , 1993 .

[9]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[10]  Chang‐Jin Kim,et al.  Dynamic linear models with Markov-switching , 1994 .

[11]  David C. Brogan,et al.  Animating human athletics , 1995, SIGGRAPH.

[12]  Stephen M. Omohundro,et al.  Nonlinear manifold learning for visual speech recognition , 1995, Proceedings of IEEE International Conference on Computer Vision.

[13]  Ioannis A. Kakadiaris,et al.  Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selection , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Geoffrey E. Hinton,et al.  Switching State-Space Models , 1996 .

[15]  Zoubin Ghahramani,et al.  Learning Dynamic Bayesian Networks , 1997, Summer School on Neural Networks.

[16]  James M. Rehg,et al.  Singularity analysis for articulated object tracking , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[17]  Alex Pentland,et al.  Dynamic models of human motion , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[18]  Michael Isard,et al.  Learning Multi-Class Dynamics , 1998, NIPS.

[19]  Michael Isard,et al.  A mixed-state condensation tracker with automatic model-switching , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[20]  Geoffrey E. Hinton,et al.  A View of the Em Algorithm that Justifies Incremental, Sparse, and other Variants , 1998, Learning in Graphical Models.

[21]  Jamie S. Evans,et al.  Finite-Dimensional Filters for Passive Tracking of Markov Jump Linear Systems , 1998, Autom..

[22]  Vladimir Pavlovic,et al.  Time-series classification using mixed-state dynamic Bayesian networks , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[23]  James M. Rehg,et al.  A multiple hypothesis approach to figure tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[24]  Matthew Brand,et al.  Pattern discovery via entropy minimization , 1999, AISTATS.