Abstract
During surveillance of real environments, front-view gaits of people walking are more common than lateral-view gaits. The former is also more suitable for recognition and tracking with human eyes. The proposed front-view gait recognition method is based on the computation of the centroids of gait energy images and normalized conversion of perspectives. This method extracts and recognizes gait features under the same view angle after the transformation of view angles. Experiment results show that the front-view gaits of people walking can be identified even in the case of monocular surveillance cameras for which the parameters are unknown.