Silhouette-based human action recognition using sequences of key poses

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 multi-view key poses. Our contribution is two-fold. 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 ∗Corresponding author: Alexandros Andre Chaaraoui, Department of Computing Technology, University of Alicante, P.O. Box 99, E-03080, Alicante, Spain. Phone: +34 965903681, Fax: +34 965909643 Email addresses: [email protected] (Alexandros Andre Chaaraoui), [email protected] (Pau Climent-Pérez), [email protected] (Francisco Flórez-Revuelta) URL: http://www.dtic.ua.es (Alexandros Andre Chaaraoui) Preprint submitted to Pattern Recognition Letters January 3, 2013 Paper Click here to download Manuscript [Word or (La)TeX]: Paper.tex Click here to view linked References