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

DMCA

A dynamic Bayesian network approach to figure tracking using learned dynamic models (1999)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Vladimir Pavlović , James M. Rehg , Tat-jen Cham , Kevin P. Murphy

Citations:

125 - 6 self

BibTeX

@INPROCEEDINGS{Pavlović99adynamic,
    author = {Vladimir Pavlović 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 = {},
    year = {1999},
    pages = {94--101}
}

OpenURL

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. 1

Keyphrases

dynamic bayesian network approach learned dynamic model rich dynamic behavior approximate viterbi inference technique human figure broad class learning figure dynamic figure motion key feature linear dynamic system specific hand-tailored one present experimental result dynamic bayesian network mixed-state dbns motion analysis exact inference promising initial result video data inference algorithm generic dynamic model learned model time-series model

DMCA