Automatic Gait Recognition Using Weighted Binary Pattern on Video
AVSS '09 Proceedings of the 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance
Hi-index | 0.00 |
This paper presents a method of human gait tracking, which determines the parameters -joint angles of human motion by linear model fitting. First a 3D model of human body is designed then the joint angles are computed according to the contour corresponding to the model components. This method combines the 3D model of human body and contour information in images to get the joint angles of human body. It is more accurate and faster than the other methods of same kind. This paper gives the experimental results and the solutions to the problems met in the application.