Kinect-based gait recognition system design via deterministic learning

This paper proposes an effective and rapid human gait recognition system based on deterministic learning and Microsoft sensor. In order to deal with the difficulties of feature extraction in the gait recognition system, Kinect sensor is used for realtime skeleton detection and tracking. Dynamical deterministic learning algorithm implementation is achieved and a rapid gait recognition scheme is proposed. The graphical programming language of C# and MATLAB GUI controls are combined for building user-friendly and simple interfaces to display the gait training and recognition process. The recognition results and detailed parameters can be displayed on the system panels, which is also helpful for further data analysis and algorithm improvement. The effectiveness of the gait recognition system under multi-pattern is verified on the self-constructed gait database.