Silhouette-based gesture and action recognition via modeling trajectories on Riemannian shape manifolds.
Mohamed F. AbdelkaderWael Abd-AlmageedAnuj SrivastavaRama ChellappaPublished in: Comput. Vis. Image Underst. (2011)
Keyphrases
- action recognition
- view invariant
- human actions
- shape analysis
- activity recognition
- bag of words
- action classification
- manifold learning
- human detection
- body parts
- computer vision
- tangent space
- recognition of human actions
- shape descriptors
- recognizing human actions
- motion history images
- euclidean space
- shape space
- geodesic paths
- gesture recognition
- visual hull
- riemannian manifolds
- human object interactions
- bag of features
- static images
- machine learning
- recognizing actions
- feature extraction
- video sequences
- hidden markov models
- lie group
- image representation
- geodesic distance