Sciweavers

Share
BMVC
2010

Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests

9 years 5 months ago
Real-time Action Recognition by Spatiotemporal Semantic and Structural Forests
Whereas most existing action recognition methods require computationally demanding feature extraction and/or classification, this paper presents a novel real-time solution that utilises local appearance and structural information. Semantic texton forests (STFs) are applied to local space-time volumes as a powerful discriminative codebook. Since STFs act directly on video pixels without using expensive descriptors, visual codeword generation by STFs is extremely fast. To capture the structural information of actions, so called pyramidal spatiotemporal relationship match (PSRM) is introduced. Leveraging the hierarchical structure of STFs, the pyramid match kernel is applied to obtain robust structural matching, avoiding quantisation effects. We propose the kernel k-means forest classifier using PSRM to perform classification. In the experiments using KTH and the latest UT-interaction data sets, we demonstrate real-time performance as well as state-ofthe-art accuracy by the proposed meth...
Tsz-Ho Yu, Tae-Kyun Kim, Roberto Cipolla
Added 10 Feb 2011
Updated 10 Feb 2011
Type Journal
Year 2010
Where BMVC
Authors Tsz-Ho Yu, Tae-Kyun Kim, Roberto Cipolla
Comments (0)
books