DocumentCode :
2312540
Title :
A robust Bayesian network for articulated motion classification
Author :
Imennov, Nikita S. ; Dockstader, Shiloh L. ; Tekalp, A. Murat
Author_Institution :
Dept. of Comp. Sci. & Biomedical Eng., Rochester Univ., NY, USA
Volume :
3
fYear :
2003
fDate :
14-17 Sept. 2003
Abstract :
We introduce a new approach to motion-based recognition that combines the temporally descriptive abilities of a hidden Markov model (HMM) with the inferential power of a Bayesian belief network. We define activities using a collection of multiple Markov models, each associated with a unique set of body model parameters or gait variables. A single Bayesian network integrates the models by operating on virtual evidence derived from the HMM conditional output probabilities. We introduce both fundamental and auxiliary models for characterizing events and tracking failures, respectively. We demonstrate the system using multi-view video sequences corrupted by occlusion, noise, and entirely missing observations.
Keywords :
belief networks; hidden Markov models; image classification; image motion analysis; image sequences; video signal processing; Bayesian belief network; articulated motion classification; characterizing events; hidden Markov model; motion-based recognition; multi-view video sequences; noise; occlusion; tracking failures; Bayesian methods; Biological system modeling; Biomedical engineering; Hidden Markov models; Humans; Motion analysis; Power system modeling; Robustness; Video sequences; Working environment noise;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on
ISSN :
1522-4880
Print_ISBN :
0-7803-7750-8
Type :
conf
DOI :
10.1109/ICIP.2003.1247242
Filename :
1247242
Link To Document :
بازگشت