Application of action recognition and tactical optimization methods for rope skipping competitions based on artificial intelligence

To solve the problems that action recognition methods in rope skipping competitions rely on manual annotation and are prone to misjudgment in complex movements, this study implemented an AI-based rope skipping action recognition and tactical optimization method, using artificial intelligence technology to achieve efficient and accurate action recognition and tactical adjustment. The feature extraction of video frames is performed through Convolutional Neural Network (CNN), and the processed feature sequence is sent to Long Short-Term Memory (LSTM) network for processing, so as to achieve accurate recognition of rope skipping actions. To optimize the competition strategy, the Deep Q Network (DQN) is used to optimize the tactical execution. Experimental results show that the proposed model can recognize common rope skipping movements such as single jump, double-leg jump and cross jump with an average accuracy of 98.4%; the tactical strategy optimized by reinforcement learning significantly improves the performance of athletes, the jumping frequency increases by 4.59% and the error rate decreases by 0.986%. This study not only provides an intelligent evaluation and optimization solution for rope skipping competitions, but also has certain reference significance for action recognition and tactical decision-making in other sports.