The Recognition of Human Movement Using Temporal Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Incremental Nonlinear Dimensionality Reduction by Manifold Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Human Action Recognition Using Multi-View Image Sequences Features
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
Comparison of Silhouette Shape Descriptors for Example-based Human Pose Recovery
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
HMM-based Human Action Recognition Using Multiview Image Sequences
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
A general method for human activity recognition in video
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Free viewpoint action recognition using motion history volumes
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Nonlinear manifold learning for dynamic shape and dynamic appearance
Computer Vision and Image Understanding
3D Skeleton-Based Body Pose Recovery
3DPVT '06 Proceedings of the Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT'06)
| Hi-index | 0.00 |
Though recognizing human action from video is important to applications like visual surveillance, some hurdles still slower the progress of action recognition. One of the main difficulties is view dependency, and this causes the degeneration of many recognition algorithms. In this paper, we propose a template-based view-independent human action recognition approach. The action template comprises a series of "action hyperspheres" in a nonlinear subspace and encodes multi-view information of several typical human actions to facilitate the view-independent recognition. Given an input action from video, we first compute the Motion History Image (MHI) and corresponding polar feature according to the extracted human silhouettes; recognition is achieved by evaluating the distances between the embedding of the polar feature and the virtual centers of the hyperspheres. Experiments show that our approach maintains high recognition accuracy in free viewpoints, and is more computationally efficient compared with classical kNN approach.