Welcome to the InfoSci Platform
Reference Hub1
Human Action Recognition with Expandable Graphical Models

Human Action Recognition with Expandable Graphical Models

Wanqing Li, Zhengyou Zhang, Zicheng Liu, Philip Ogunbona
Copyright: © 2010 |Pages: 26
ISBN13: 9781605669007|ISBN10: 1605669008|ISBN13 Softcover: 9781616922160|EISBN13: 9781605669014
DOI: 10.4018/978-1-60566-900-7.ch010
Cite Chapter Cite Chapter

MLA

Li, Wanqing, et al. "Human Action Recognition with Expandable Graphical Models." Machine Learning for Human Motion Analysis: Theory and Practice, edited by Liang Wang, et al., IGI Global, 2010, pp. 187-212. https://doi.org/10.4018/978-1-60566-900-7.ch010

APA

Li, W., Zhang, Z., Liu, Z., & Ogunbona, P. (2010). Human Action Recognition with Expandable Graphical Models. In L. Wang, L. Cheng, & G. Zhao (Eds.), Machine Learning for Human Motion Analysis: Theory and Practice (pp. 187-212). IGI Global. https://doi.org/10.4018/978-1-60566-900-7.ch010

Chicago

Li, Wanqing, et al. "Human Action Recognition with Expandable Graphical Models." In Machine Learning for Human Motion Analysis: Theory and Practice, edited by Liang Wang, Li Cheng, and Guoying Zhao, 187-212. Hershey, PA: IGI Global, 2010. https://doi.org/10.4018/978-1-60566-900-7.ch010

Export Reference

Mendeley
Favorite

Abstract

This chapter first presents a brief review of the recent development in human action recognition. In particular, the principle and shortcomings of the conventional Hidden Markov Model (HMM) and its variants are discussed. We then introduce an expandable graphical model that represents the dynamics of human actions using a weighted directed graph, referred to as action graph. Unlike the conventional HMM, the action graph is shared by all actions to be recognized with each action being encoded in one or multiple paths and, thus, can be effectively and efficiently trained from a small number of samples. Furthermore, the action graph is expandable to incorporate new actions without being retrained and compromised. To verify the performance of the proposed expandable graphic model, a system that learns and recognizes human actions from sequences of silhouettes is developed and promising results are obtained.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.