3D depth camera based human posture detection and recognition using PCNN circuits and learning-based hierarchical classifier

Abstract

A new scheme for human posture recognition is proposed based on analysis of key body parts. Utilizing a time-of-flight depth camera, a pulse coupled neural network (PCNN) is employed to detect a moving human in cluttered background. In the posture recognition phase, a hierarchical decision tree is designed for classification of body parts so that the 3D coordinate of the key points of the detected human body can be determined. The features described in each individual layer of the tree can be chained as hierarchical searching indices for retrieval procedure to drastically improve the efficiency of template matching in contrast to conventional shape-context method. Experimental results show that the proposed scheme gives competitive performance as compared with the state-of-the-art counterparts.