Action Recognition by Matching Clustered Trajectories of Motion Vectors

Abstract

A framework for action representation and recognition base d 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 c urves 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 traject ories. Finally, the probe sequence is categorized to the learned action with the maximum similarity using a neare st n ighbor classification scheme. Experimental results on common action databases demonstrate the effecti veness of the proposed method.