Authors:
Michalis Vrigkas
1
;
Vasileios Karavasilis
1
;
Christophoros Nikou
1
and
Ioannis Kakadiaris
2
Affiliations:
1
University of Ioannina, Greece
;
2
University of Houston, United States
Keyword(s):
Human Action Recognition, Optical Flow, Motion Curves, Gaussian Mixture Modeling (GMM), Clustering, Longest Common Subsequence.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Computer Vision, Visualization and Computer Graphics
;
Enterprise Information Systems
;
Human and Computer Interaction
;
Human-Computer Interaction
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Image Generation Pipeline: Algorithms and Techniques
;
Motion, Tracking and Stereo Vision
;
Optical Flow and Motion Analyses
;
Shape Representation and Matching
Abstract:
A framework for action representation and recognition based on the description of an action by time series of optical flow motion features is presented. In the learning step, the motion curves representing each action are clustered using Gaussian mixture modeling (GMM). In the recognition step, the optical flow curves of a probe sequence are also clustered using a GMM and the probe curves are matched to the learned curves using a non-metric similarity function based on the longest common subsequence which is robust to noise and provides an intuitive notion of similarity between trajectories. Finally, the probe sequence is categorized to the learned action with the maximum similarity using a nearest neighbor classification scheme. Experimental results on common action databases demonstrate the effectiveness of the proposed method.