Abstract

Background: The effect of teaching and training in physical sports is improved by the sports demonstration system. The two-dimensional sports demonstration system is widely applied for the training of athletes. In accurate motion positioning, there exists a certain visual deficiency and the two-dimensional sports demonstration system is analyzed by kinematics.

Methodology: Aiming at the problems in the real-time tracking of fast-moving targets in sports images, an automatic tracking method of sports images based on the registration of landmark points of the passive optical motion capture system is proposed. Moreover, it aims to build a human model and divide the human model into several limb segments; find the corresponding relationship between the first frame of motion data and template data to complete the first frame of motion data registration; based on the smallest non-rigid deformation and point set matching error, find the corresponding relationship between the current frame of motion data and the previous frame of registered motion data; through the mark points, follow up to complete the registration process of the marker.

Results: Experiments show that the average processing accuracy of this algorithm can reach over 85% and the processing time of a single frame of motion data is t<1/60s, which can meet real-time requirements.

Conclusion: The multi-point set least-squares matching algorithm is used to rigidly correct the registered landmark data. No manual intervention is required for the entire mark registration process.

Keywords: Motion image, real-time tracking, first frame movement, landmark points, sports demonstration, processing accuracy.

Graphical Abstract