Human action recognition under Log-Euclidean Riemannian metric
Yuan, C. and Hu, W. and Li, X. and Maybank, Stephen J. and Luo, G. (2010) Human action recognition under Log-Euclidean Riemannian metric. In: Zha, H. and Taniguchi, R.-i. and Maybank, Stephen J. (eds.) Computer Vision – ACCV 2009. Lecture Notes in Computer Science 5994. Berlin, Germany: Springer, pp. 343-353. ISBN 9783642123061.
This paper presents a new action recognition approach based on local spatio-temporal features. The main contributions of our approach are twofold. First, a new local spatio-temporal feature is proposed to represent the cuboids detected in video sequences. Specifically, the descriptor utilizes the covariance matrix to capture the self-correlation information of the low-level features within each cuboid. Since covariance matrices do not lie on Euclidean space, the Log-Euclidean Riemannian metric is used for distance measure between covariance matrices. Second, the Earth Mover’s Distance (EMD) is used for matching any pair of video sequences. In contrast to the widely used Euclidean distance, EMD achieves more robust performances in matching histograms/distributions with different sizes. Experimental results on two datasets demonstrate the effectiveness of the proposed approach.
|Item Type:||Book Section|
|Additional Information:||9th Asian Conference on Computer Vision, Xi’an, September 23-27, 2009, Revised Selected Papers, Part I|
|Keyword(s) / Subject(s):||Action recognition, Spatio-temporal descriptor, Log-Euclidean Riemannian metric, EMD|
|School:||Birkbeck Schools and Departments > School of Business, Economics & Informatics > Computer Science and Information Systems|
|Date Deposited:||06 Nov 2012 10:52|
|Last Modified:||14 May 2013 07:18|
Additional statistics are available via IRStats2.