Human Action Recognition Algorithm Based on Key Posture

Abstract

A novel human action recognition algorithm based on key posture is proposed in this paper. In the method, the mesh features of each image in human action sequences are firstly calculated; then the key postures of the human mesh features are generated through k-medoids clustering algorithm; and the motion sequences are thus represented as vectors of key postures. The component of the vector is the occurrence number of the corresponding posture included in the action. For human action recognition, the observed action is firstly changed into key posture vector; then the correlevant coefficients to the training samples are calculated and the action which best matches the observed sequence is chosen as the final category. The experiments on Weizmann dataset demonstrate that our method is effective for human action recognition. The average recognition accuracy can exceed 90%.

Action Recognition of Human’s Lower Limbs Based on a Human Joint

“…An important reason is action characteristics are difficult to represent. Many scholars proposed many methods, such as key frames [5,6], spatiotemporal attitude model [7], etc. But their expression manners are always complicated and used in specific action processes.…”