摘要：Race walking is one of the key events in the Tokyo Olympic Games, and also one of the strengths of China in athletics events. In recent years, China has made remarkable achievements in various race-walking competitions. However, with the improvement of the performance of race walkers, more and more technical problems have emerged, and the number of fouls due to nonstandard movements has increased significantly. It is a pity that athletes are disqualified for technical fouls in long-distance race-walking competitions. Therefore, it is necessary to introduce scientific training methods to help coaches strictly monitor the training process of athletes and accurately detect their standard degree of action in real-time. This paper mainly proposes a novel mechanism for foul recognition in race walking based on deep learning. Firstly, the image frames in the video are preprocessed by the Yolo algorithm to obtain the athletes' separated images. The U-Net network mixed with the attention mechanism is used to detect the athletes’ actions to identify fouls and nonstandard actions, so as to assist the coach to identify the athletes’ nonstandard actions in training and adjust them in time. Experiments show that the above method can identify the foul actions and nonstandard actions of multiple athletes in training at the same time quickly, and the recognition accuracy is higher than human eyes. It is more conducive to assist the coach to monitor and standardize the athletes’ actions in the long-term training process, so as to reduce the error rate and improve the performance.
