A gait recognition method based on positioning human body joints

Gait recognition is to identify individuals by analysis of gait pattern. Here a simple and efficient gait recognition method based on positioning body joints is presented. At first key frame is extracted based on cyclic gait analysis. For each key frame image, background subtraction is performed to extract moving body silhouettes from the background. Then the coordinates of joints are computed according to the geometrical characteristics shown while walking. The limbs angles are computed based on the coordinates of joints and then made discrete Fourier transform. The amplitude-frequency and phase-frequency of angles are chosen as gait feature. At last the nearest neighbor classifier is used to classify subjects. Evaluation about the proposed gait recognition method is given according to experiment on the Soton gait database, and the experimental results demonstrate the encouraging performance.