Action recognition with motion-appearance vocabulary forest

11 years 8 months ago
Action recognition with motion-appearance vocabulary forest
In this paper we propose an approach for action recognition based on a vocabulary forest of local motionappearance features. Large numbers of features with associated motion vectors are extracted from action data and are represented by many vocabulary trees. Features from a query sequence are matched to the trees and vote for action categories and their locations. Large number of trees make the process efficient and robust. The system is capable of simultaneous categorization and localization of actions using only a few frames per sequence. The approach obtains excellent performance on standard action recognition sequences. We perform large scale experiments on 17 challenging real action categories from olympic games1 . We demonstrate the robustness of our method to appearance variations, camera motion, scale change, asymmetric actions, background clutter and occlusion.
Krystian Mikolajczyk, Hirofumi Uemura
Added 29 May 2010
Updated 29 May 2010
Type Conference
Year 2008
Where CVPR
Authors Krystian Mikolajczyk, Hirofumi Uemura
Comments (0)