Human pose recognition by memory-based hierarchical feature matching

A human posture recognition system based on a memory-based approach is studied. Human body images extracted by depth data are labeled and stored in a database together with compressed feature values consist of higher-order local correlation values and outline diameters. The compressed features are used to speed up the database search in a hierarchical manner. The system can classify human body postures into 6 categories in the experiment. The system was robust against change of humans and light condition.

[1]  Satoru Hayamizu,et al.  Gesture recognition using HLAC features of PARCOR images and HMM based recognizer , 1998, Proceedings Third IEEE International Conference on Automatic Face and Gesture Recognition.

[2]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Katsuhiko Sakaue,et al.  Utilization of stereo disparity and optical flow information for the computer analysis of human interactions , 2003, Machine Vision and Applications.

[4]  Hideo Saito,et al.  3-D drawing system via hand motion recognition from two cameras , 2000, Smc 2000 conference proceedings. 2000 ieee international conference on systems, man and cybernetics. 'cybernetics evolving to systems, humans, organizations, and their complex interactions' (cat. no.0.

[5]  Rahul Sukthankar,et al.  Memory-based face recognition for visitor identification , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).