View Item 

AdaBoost.MRF: Boosted Markov Random Forests and Application to Multilevel Activity Recognition

Access Status
Fulltext not available
Authors
Truyen, Tran
Phung, Dinh
Bui, H.
Venkatesh, Svetha
Date
2006
Type
Conference Paper

Metadata
Show full item record
Citation
Truyen, T. and Phung, D. and Bui, H. and Venkatesh, S. 2006. AdaBoost.MRF: Boosted Markov Random Forests and Application to Multilevel Activity Recognition, in Fitzgibbon, A. and Taylor, C. and LeCun, Y. (ed), IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Jun 17-26 2006, pp. 1686-1693. New York, USA: IEEE Computer Society Conference Publishing Services.
Source Title
2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Source Conference
IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2006
DOI
ISBN
School
Department of Computing
URI
Collection
Abstract

Activity recognition is an important issue in building intelligent monitoring systems. We address the recognition of multilevel activities in this paper via a conditional Markov random field (MRF), known as the dynamic conditional random field (DCRF). Parameter estimation in general MRFs using maximum likelihood is known to be computationally challenging (except for extreme cases), and thus we propose an efficient boosting-based algorithm AdaBoost.MRF for this task. Distinct from most existing work, our algorithm can handle hidden variables (missing labels) and is particularly attractive for smarthouse domains where reliable labels are often sparsely observed. Furthermore, our method works exclusively on trees and thus is guaranteed to converge. We apply the AdaBoost.MRF algorithmto a home video surveillance application and demonstrate its efficacy.