Abstract
Gait is a very important biometric technology for human recognition. Gait feature can be divided into two categories: static and dynamic. Many previous works argue that, although motion reflects the essential nature of gait, the recognition performance based purely on the motion feature is limited. The root cause of the limited performance is however not yet to understand. In this paper, we study the gait recognition with motion feature by Kinect and show that, with a novel representation, the motion feature is still effective to distinguish the gaits from different human beings. In particular, relative distance-based motion features are proposed, which are extracted without calculating the gait cycle. Experimental results show that the accuracy of recognition with relative motion features is up to 85 %, which is comparable to that of static features. By combining the relative motion features and the static ones, the accuracy is above 95 %.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
