.With the vigorous development of contemporary information technology, the field of computer technology is constantly innovating and progressing. Among them, the field of computer vision has achieved more prominent development. Computer vision is a discipline that uses cameras and computers to imitate the structure of human organs, processes and analyzes the collected video sequences, and then makes corresponding behavior judgments. Moving object detection and tracking is an important branch of computer vision. Moving target detection and tracking has broad application space and development scenarios. Here, we aim to study the detection and tracking method of moving targets in a martial arts arena video based on non-scene target features. Based on this research theme, we combine the particle filter moving target tracking algorithm based on non-scene target features to carry out the moving target detection and tracking experiments in the video of the martial arts arena. The experiment concluded: compared with the conventional methods, the particle filter moving target tracking algorithm based on the non-scene target features can perform the following tasks without affecting the detection accuracy. It reduces the time for detecting and tracking the same moving target in the video of the martial arts arena by 1.5 min. It shows that the algorithm can improve the efficiency of non-scene moving target detection and tracking.