ENHANCING MOTION CAPTURE TECHNOLOGY FOR YOUTH SPORTS TRAINING THROUGH DECISION TREE ALGORITHMS

Abstract

With the popularization and specialization of youth sports training, how to accurately capture and evaluate the quality of trainers' movements has become an important topic in sports science research. This study aims to improve the youth sports training motion capture technology, using decision tree algorithm to classify and analyze the movement data in order to improve the training effect of athletes. The traditional motion capture technique has problems such as high subjectivity, low efficiency, and error-prone, while the decision tree algorithm has the advantages of simplicity, fast training speed, and adaptability to small sample data. In this study, the action data of youth athletes were collected and the decision tree algorithm was used to train and predict the athletes' action classification results. The experimental results show that the decision tree algorithm can effectively classify and analyze the action data of adolescent athletes, accurately judge the strengths and weaknesses of athletes' actions, and provide targeted training suggestions and improvement directions. Compared with the traditional manual observation method, the motion capture technology based on the decision tree algorithm has obvious advantages in terms of accuracy and efficiency. Therefore, this technical improvement method provides a new way and method for youth sports training, which is expected to provide important support for improving the training effect and assessment accuracy.