The position extraction of lower limb joint points is important for gait recognition because the feature data is always based on the position of lower limb joint points. Since the detection of motion information of human body can affect the gait recognition directly, we propose a position extraction method of lower limb joint points in this paper. Through the study on the human body centroid tracking, and positioning of human lower limb joint point, we can obtain the step cycle information. It has been demonstrated via plenty experiments that the proposed method is feasible and easy for implement, since it can achieve real-time tracking and improve positioning accuracy of the human body joints, and can provide feature data for human gait recognition.
A Method of Lower Limb Joint Points Extraction Based on Pendulum Model under Arbitrary Gesture Walk
Applied Mechanics and Materials ; 556-562 ; 4347-4351
2014-05-23
5 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Trans Tech Publications | 2016
|SAE Technical Papers | 1986
|