Action recognition with motion-appearance vocabulary forest
Authors:
- 1 June 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 1-8
Abstract
In this paper we propose an approach for action recognition based on a vocabulary forest of local motion-appearance 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.Keywords
This publication has 16 references indexed in Scilit:
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- Object retrieval with large vocabularies and fast spatial matching2007
- A Hierarchical Model of Shape and Appearance for Human Action Classification2007
- Discriminative Subsequence Mining for Action Classification2007
- Improving Descriptors for Fast Tree Matching by Optimal Linear Projection2007
- Scalable Recognition with a Vocabulary Tree2006
- Multiple Object Class Detection with a Generative Model2006
- Efficient Clustering and Matching for Object Class Recognition2006
- Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words2006
- Robust wide-baseline stereo from maximally stable extremal regionsImage and Vision Computing, 2004