Automatic gait recognition from a distance

Gait recognition is an unique biometrics which can identify individuals from a distance where others are incapable. However, nearly all of the algorithms proposed are 2D methods based on studying image sequences captured by a mono-vision. This paper presents an original 3D approach for automatic gait recognition based on analyzing image sequences captured by stereo vision. Contour matching is done after binarized silhouette of a moving individual is firstly achieved in order to get 3D contour. Then, stereo gait feature (SGF) which is the norm of stereo silhouette vector (SSV) is extracted from 3D contour. In addition, Principal Component Analysis (PCA) is adopted for dimensionality reduction. Finally, NN and ENN is applied for classifying and distinguishing. A stereo gait database named PRLAB II was established as a training and probing sets for gait recognition based on stereo vision. Experimental result on PRLAB II proved the efficiency and robustness of the method.