Human gait recognition based on deterministic learning and Kinect sensor

Model construction, fitting and feature extraction remain the main difficult tasks in model-based gait recognition methods. To develop an easy practical model-based gait recognition system, this paper investigate the combined use of deterministic learning and Microsoft Kinect sensor for human gait recognition. First, real-time data stream of human joints position are acquired by using Microsoft Kinect and MATLAB toolbox. Second, four different time-varying gait feature are selected to represent human walking. Third, gait variability underlying different individuals' time-varying gait features is effectively modeled by using deterministic learning algorithm. This kind of variability reflects the change of the walking information while preserving temporal dynamics information. Gait patterns are represented as the gait variability underlying time-varying gait features and a rapid recognition scheme is presented. Experimental results show that the combination of deterministic learning and Microsoft Kinect sensor can provide an encouraging recognition accuracy.