Abstract
With the popularity of sports competitions, the traditional manual scoring method cannot meet the requirements of fairness and real time due to its subjectivity and efficiency. In this study, an automated scoring system based on artificial intelligence is constructed. Convolution neural network and long- and short-term memory network are combined to identify complex movements in competition, collect athletes’ hitting data, and ensure the accuracy and consistency of scoring. The results show that the accuracy of the model in the recognition of common movements is more than 85%, which improves the efficiency and fairness of the scoring, and provides a reliable technical support for Wushu Sanda competition.
Get full access to this article
View all access options for this article.
