In this paper, gait and race is analyzed in various velocities. Biomechanical ingredients as position, velocity, acceleration, torque, force and power are measured using a novel approach in human motion tracking. Six velocity are considered in this study include 1.5, 3.5,6, 8, 10, and 12 Km/h. The proposed method is developed to capture markers positions associated with human motion obtained from video data. A data-driven predictor is used for tracking of wearing reflective markers. The uncertainty and occlusion of detected markers increase the noise in captured positions. For solving these problems, we proposed a suitable approach which includes a memory based data-driven System. The result of tracking algorithm is tested over 12 sport men in 6 velocities over more than 30000 captured frames. Simulation results validate the analysis and ensuing method.
© Copyright 2008 The Engineering of sport 7, Volume 1. Published by Springer. All rights reserved.