A Dynamic Bayesian Network Approach to Figure Tracking Using Learned Dynamic Models
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.
Cite
Text
Pavlovic et al. "A Dynamic Bayesian Network Approach to Figure Tracking Using Learned Dynamic Models." IEEE/CVF International Conference on Computer Vision, 1999. doi:10.1109/ICCV.1999.791203Markdown
[Pavlovic et al. "A Dynamic Bayesian Network Approach to Figure Tracking Using Learned Dynamic Models." IEEE/CVF International Conference on Computer Vision, 1999.](https://mlanthology.org/iccv/1999/pavlovic1999iccv-dynamic/) doi:10.1109/ICCV.1999.791203BibTeX
@inproceedings{pavlovic1999iccv-dynamic,
title = {{A Dynamic Bayesian Network Approach to Figure Tracking Using Learned Dynamic Models}},
author = {Pavlovic, Vladimir and Rehg, James M. and Cham, Tat-Jen and Murphy, Kevin P.},
booktitle = {IEEE/CVF International Conference on Computer Vision},
year = {1999},
pages = {94-101},
doi = {10.1109/ICCV.1999.791203},
url = {https://mlanthology.org/iccv/1999/pavlovic1999iccv-dynamic/}
}