A new gait recognition method using kinect via deterministic learning

Gait as biometric information obtained by one's walking, is used to identify individuals widely because it can be done unobtrusively. This paper presents a new side-view gait recognition method based on joint angle data captured by Microsoft Kinect via deterministic learning. These skeletal kinematic features describe the motion trajectories of human gait and contain rich information for human identification. The gait recognition approach consists of two phases: a training phase and a recognition phase. In the training phase, gait dynamics underlying different individuals' gaits are represented by the shoulder, elbow, hip and knee joint angles features, and are locally accurately approximated by radial basis function (RBF) neural networks. The obtained knowledge of approximated gait dynamics is stored in constant RBF networks. In the recognition phase, a bank of dynamical estimators is constructed for all the training gait patterns. Prior knowledge of human gait dynamics represented by the constant RBF networks are embedded in the estimators. By comparing the set of estimators with a test gait pattern, a set of recognition errors are generated. The average L\ norms of the errors are taken as the similarity measure between the dynamics of the training gait patterns and the dynamics of the test gait pattern. The test gait pattern similar to one of the training gait patterns can be recognized according to the smallest error principle. Finally, comprehensive experiments are carried out on the self-constructed Kinect-based gait database, which includes at most 42 subjects, to demonstrate the recognition performance of the proposed algorithm.