No abstract

Abstract

Though motion posture correction technology based on the computer vision technology has been developed to decrease the loss from sports injury, there still exists some weakness. The joint movement of the same athlete varies in different sports program. Under high movement speed, the angle changes of joints are relevant to the motion effects, but it is difficult to measure the subtle changes with constraint models or methods. The traditional identification methods include the Factorization method and skeletal model method, both of which use the stable constraints model to analyze the motion parameters, so they cannot analyze motion parameters in the small-scale areas or effectively measure the subtle movement of the athlete motion posture parameters. To address these issues, this paper presents a new method to measure the 3D motion posture of the athletes. Through the simulation experiments, it has been proved that this method is able to measure the 3D motion parameters of athletes accurately and has a high application value.