Impact of dynamic model learning on classification of human motion

The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. However, most work on tracking and analysis of figure motion has employed either generic or highly specific hand-tailored dynamic models superficially coupled with hidden Markov models (HMMs) of motion regimes. Recently, an alternative class of learned dynamic models known as switching linear dynamic systems (SLDSs) has been cast in the framework of dynamic Bayesian networks (DBNs) and applied to analysis and tracking of the human figure. In this paper we further study the impact of learned SLDS models on analysis and tracking of human motion and contrast them to the more common HMM models. We develop a novel approximate structured variational inference algorithm for SLDS, a globally convergent DBN inference scheme, and compare it with standard SLDS inference techniques. Experimental results on learning and analysis of figure dynamics from video data indicate the significant potential of the SLDS approach.

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

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

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

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

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

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

[7]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  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).

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

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

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

[12]  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).

[13]  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.

[14]  William T. Freeman,et al.  Bayesian Reconstruction of 3D Human Motion from Single-Camera Video , 1999, NIPS.

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

[16]  Xavier Boyen,et al.  Discovering the Hidden Structure of Complex Dynamic Systems , 1999, UAI.