Research Of Target Tracking Algorithm Under Occlusion Based On Feature Correlation Matching

Moving target tracking is a crucial subject in computer vision, and it has very important practical value and wide developmental prosperity in science and technology, national defense building, medical diagnosing, and all areas of the national economy. Target tracking is a challenging subject because of the variety of the target feature and the complexity of the background, especially the occlusion problem in the course of tracking is the crucial restrictive factor to the robustness of tracking algorithm. In this paper, moving object tracking is investigated and special attention is paid to occlusion handling.In this article, we firstly analysis the traditional target tracking algorithms, and then discuss the use of background updating and shadow removal method to accurately detect moving targets ,and the use of Kalman filter to track moving targets. Finally, contrary to target tracking problem of occlusion, a method is proposed based on Kalman filter prediction and area of moving region ,and it is effective to solve the target tracking problem of occlusion.We have carried out a computer simulation algorithm, the test moving target tracking and block the removal of performance , our results show that the method is simple and effective, suitable for use in the real scene.