Recognizing human gait in video sequences

The recognition of humans and their activities from video sequences is currently a very active area of research because of its applications in video surveillance, design of realistic entertainment systems, multimedia communications, and medical diagnosis. This paper presents an automatic gait recognition system that recognizes a person by the way he/she walks. The gait signature is obtained based on three values of angles: angle between front thigh and back thigh , the angle between the back foot and back thigh , the angle between the front foot and front thigh. Next, we applied the principal component analysis (PCA) to reduce the dimensionality of the data set. This paper uses the dynamic time warping to distinguish the different gaits of human. The performance of the proposed method is tested using CASIA database B. The proposed algorithm has a promising performance because the identification rate is 92,3% .