A dynamic Bayesian network approach to figure tracking using learned dynamic models
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 94-101 vol.1
- https://doi.org/10.1109/iccv.1999.791203
Abstract
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.Keywords
This publication has 15 references indexed in Scilit:
- Time-series classification using mixed-state dynamic Bayesian networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A mixed-state condensation tracker with automatic model-switchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Singularity analysis for articulated object trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Finite-Dimensional Filters for Passive Tracking of Markov Jump Linear SystemsAutomatica, 1998
- A View of the Em Algorithm that Justifies Incremental, Sparse, and other VariantsPublished by Springer Nature ,1998
- Proceedings of the 1998 workshop on New security paradigmsPublished by Association for Computing Machinery (ACM) ,1998
- Model-based estimation of 3D human motion with occlusion based on active multi-viewpoint selectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1996
- Dynamic linear models with Markov-switchingJournal of Econometrics, 1994
- Connectionist learning of belief networksArtificial Intelligence, 1992
- New Results in Linear Filtering and Prediction TheoryJournal of Basic Engineering, 1961