Sciweavers

Share
ACCV
2009
Springer

Human Action Recognition under Log-Euclidean Riemannian Metric

8 years 9 months ago
Human Action Recognition under Log-Euclidean Riemannian Metric
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.
Chunfeng Yuan, Weiming Hu, Xi Li, Stephen J. Mayba
Added 16 Feb 2011
Updated 16 Feb 2011
Type Journal
Year 2009
Where ACCV
Authors Chunfeng Yuan, Weiming Hu, Xi Li, Stephen J. Maybank, Guan Luo
Comments (0)
books