Transfer learning model for the motion detection of sports players

Abstract

Recognizing and analyzing moving targets is an important research subject since computer vision is employed in so many facets of our daily lives, including intelligent robotics, video surveillance, medical education, sporting events, and the maintenance of our national defense. This is because it may be difficult to properly analyse and keep up with moving materials. The various training postures of an athlete are explored in this study through the examination of a weightlifting video. This article was written to assist coaches in their efforts to improve the performance of their athletes in their respective sports. A technique for extracting essential poses from sports films has been proposed. The classification of different subjects of interest serves as the foundation for this technique. Because of its inadequate edge detection method, the current motion identification system does a bad job of detecting athletes, which is one of the reasons why it does a poor job of identifying motion in general. This flaw is one of the reasons why the system isn’t very strong at detecting athletes. The following was one of the factors that contributed to this outcome: in truth, the situation is currently in this state. The result of the newly developed system outperforms the prior system in terms of tracking recognition accuracy and convergence speed. The system was put to the test. The findings of the system’s study served as the foundation for this decision. Finally, the findings of the categorization reveal that the selection approach tries to separate fundamental postures.