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

Authors:
Tran The Truyen;Dinh Q. Phung;Svetha Venkatesh;Hung H. Bui
Affiliations:
Curtin University of Technology;Curtin University of Technology;Curtin University of Technology;Artificial Intelligence Center, SRI International, Menlo Park, CA
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Year:
2006

Citing 0
Cited 4

Fast online action recognition with efficient structured boosting

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Boosted multiple deformable trees for parsing human poses

Proceedings of the 2nd conference on Human motion: understanding, modeling, capture and animation
Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models

International Journal of Computer Vision
Survey on classifying human actions through visual sensors

Artificial Intelligence Review

Quantified Score

Hi-index	0.00

Visualization

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.