A Caltech Library Service

Learning probabilistic structure for human motion detection

Song, Yang and Goncalves, Luis and Perona, Pietro (2001) Learning probabilistic structure for human motion detection. In: 2001 IEEE computer society conference on computer vision and pattern recognition. IEEE Computer Society , Los Alamitos, CA, pp. 771-777. ISBN 0-7695-1272-0.

PDF - Published Version
See Usage Policy.


Use this Persistent URL to link to this item:


Decomposable triangulated graphs have been shown to be efficient and effective for modeling the probabilistic spatio-temporal structure of brief stretches of human motion. In previous work such model structure was handcrafted by expert human observers and labeled data were needed for parameter learning. We present a method to build automatically the structure of the decomposable triangulated graph from unlabeled data. It is based on maximum-likelihood. Taking the labeling of the data as hidden variables, a variant of the EM algorithm can be applied. A greedy algorithm is developed to search for the optimal structure of the decomposable model based on the (conditional) differential entropy of variables. Our algorithm is demonstrated by learning models of human motion completely automatically from unlabeled real image sequences with clutter and occlusion. Experiments on both motion captured data and grayscale image sequences show that the resulting models perform better than the hand-constructed models.

Item Type:Book Section
Related URLs:
URLURL TypeDescription DOIArticle
Perona, Pietro0000-0002-7583-5809
Additional Information:© 2001 IEEE. Date of Current Version: 15 April 2003. Funded by the NSF Engineering Research Center for Neuromorphic Systems Engineering (CNSE) at Caltech (NSF9402726), and by an NSF National Young Investigator Award to PP (NSF9457618).
Funding AgencyGrant Number
Center for Neuromorphic Systems Engineering, CaltechUNSPECIFIED
Record Number:CaltechAUTHORS:20111109-104004085
Persistent URL:
Official Citation:Song, Y.; Goncalves, L.; Perona, P.; , "Learning probabilistic structure for human motion detection," Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on , vol.2, no., pp. II-771- II-777 vol.2, 2001 doi: 10.1109/CVPR.2001.991043 URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:27704
Deposited By: Tony Diaz
Deposited On:11 Nov 2011 19:21
Last Modified:09 Nov 2021 16:50

Repository Staff Only: item control page