A Research of Motion Classification in Gait Recognition

Motion classification is the first step of gait recognition. The classification of motion is conducted, and behavior validity can be made under specific scenarios. In order to identify people movement in an intelligent security monitoring system, moving body is detected and the boundary is extracted. The paper proposes a complex number notation based on centroid in order to indicate a pedestrian´s movements. And according to the different sorts of movements, a set of standard image contours are made. A Procrustes shape analysis method is presented in order to get the degree to which two contours are resembled. Finally lying, bending, sitting, walking, side walking, jumping, crouching, uphill and downhill is given with a 72.2% recognition rate achieved.