A Dynamic Bayesian Network Approach to Figure Tracking using Learned Dynamic Models

Vladimir Pavlovic, James M. Rehg, Tat-Jen Cham, Kevin P. Murphy

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.
BibTeX
@inproceedings{pavlovic1999dynamic,
  author = {Vladimir Pavlovic and James M. Rehg and Tat-Jen Cham and Kevin P. Murphy},
  title = {{A Dynamic Bayesian Network Approach to Figure Tracking using Learned Dynamic Models}},
  booktitle = {IEEE/CVF International Conference on Computer Vision},
  year = {1999},
  doi = {10.1109/iccv.1999.791203},
}

Loading related content...

Figure