Front view gait recognition using Spherical Space Model with Human Point Clouds

In this paper, we propose a novel gait recognition framework which is Spherical Space Model with Human Point Clouds (SSM-HPC). A new gait representation is also introduced, which is called Marching in Place (MIP) gait and preserves the spatiotemporal characteristics of individual gait manner. Various researches for gait recognition have used human silhouette images from moving picture. This research uses Three Dimensional (3D) point clouds data of human body obtained from stereo camera, which has the scale-invariant property. The framework is applied for frontal view gait recognition. This framework showed superior results for gait recognition rate than other gait recognition methods.