Journal
PATTERN RECOGNITION LETTERS
Volume 34, Issue 15, Pages 1799-1807Publisher
ELSEVIER
DOI: 10.1016/j.patrec.2013.01.021
Keywords
Human action recognition; Key pose; Key pose sequence; Weizmann dataset; MuHAVi dataset; IXMAS dataset
Categories
Funding
- Spanish Ministry of Science and Innovation [TIN2010-20510-C04-02]
- European Commission [PIEF-GA-2010-274649]
- Conselleria d'Educacio, Formacio i Ocupacio of the Generalitat Valenciana [ACIF/2011/160]
Ask authors/readers for more resources
In this paper, a human action recognition method is presented in which pose representation is based on the contour points of the human silhouette and actions are learned by making use of sequences of multiview key poses. Our contribution is twofold. Firstly, our approach achieves state-of-the-art success rates without compromising the speed of the recognition process and therefore showing suitability for online recognition and real-time scenarios. Secondly, dissimilarities among different actors performing the same action are handled by taking into account variations in shape (shifting the test data to the known domain of key poses) and speed (considering inconsistent time scales in the classification). Experimental results on the publicly available Weizmann, MuHAVi and IXMAS datasets return high and stable success rates, achieving, to the best of our knowledge, the best rate so far on the MuHAVi Novel Actor test. (C) 2013 Elsevier B.V. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available