Model-based human gait recognition using leg and arm movements

We have presented a model-based approach for human gait recognition, which is based on analyzing the leg and arm movements. An initial model is created based on anatomical proportions, and a posterior model is constructed upon the movements of the articulated parts of the body, using active contour models and the Hough transform. Fourier analysis is used to describe the motion patterns of the moving parts. The k-nearest neighbor rule applied to the phase-weighted Fourier magnitude of each segment’s spectrum is used for classification. In contrast to the existing approaches, the main focus of this paper is on increasing the discrimination capability of the model through extra features produced from the motion of the arms. Experimental results indicate good performance of the proposed method. The technique has also proved to be able to reduce the adverse effects of self-occlusion, which is a common incident in human walking.