Abstract:Aiming at the problem of target tracking in sports video, a sports video target tracking algorithm based on optimized particle filter is proposed in order to improve the robustness and tracking accuracy of target. Firstly, the background subtraction is used to realize the initial detection of the target. Then, based on the RGB color histogram, the target movement model is achieved by combined with particle filter and color distribution. Finally, the update conditions of the target model are optimized to reduce the unnecessary observation model updating process. The video sequences of athletes are tested and verified. The experimental results show that this method can effectively track the athletes in the video of sports competitions. Compared with other methods, the proposed method has a lower average error and a higher operating efficiency.