Abstract: In view of the situation that the actual data of coal particle motion analysis is missing due to being blocked in the process of coal particle screening, the method of machine vision is used to detect and track the moving coal particle. In this paper, a simulation excitation experiment platform is set up to collect the sequence image of single coal particle under occlusion by high-speed camera. In the MATLAB, the guided filter is used to remove the noise from the sequential images, and the GMM is used to extract the potential masks of the target coal particles effectively. The target coal particles are tracked by the Kalman Filter. The experimental results show that the method used in this paper can effectively detect the moving coal particles, and still has good tracking robustness for the situation that the moving coal particles are blocked. In addition, we could obtain the centroid position information in the process of coal particle movement, which provides the experimental basis for theoretical analysis and numerical simulation of coal particle movement.