Abstract

In this paper, we propose a novel temporal template, called Chrono-Gait Image (CGI), to describe the spatio-temporal walking pat- tern for human identification by gait. The CGI temporal template en- codes the temporal information among gait frames via color mapping to improve the recognition performance. Our method starts with the ex- traction of the contour in each gait image, followed by utilizing a color mapping function to encode each of gait contour images in the same gait sequence and compositing them to a single CGI. We also obtain the CGI-based real templates by generating CGI for each period of one gait se- quence and utilize contour distortion to generate the CGI-based synthetic templates. In addition to independent recognition using either of individ- ual templates, we combine the real and synthetic temporal templates for refining the performance of human recognition. Extensive experiments on the USF HumanID database indicate that compared with the recently published gait recognition approaches, our CGI-based approach attains better performance in gait recognition with considerable robustness to gait period detection.