Research On Technology Of Motion Detecting & Tracking In Moving Background

Moving target detecting and tracking technology is a key technology of Computer Vision System. Now, the research on motion detecting and tracking in immobile background has already been maturity. The technology has been widely applied to military affairs, traffic and industry. Compared with immobile background, the moving background is the relative motion between moving target and image background because of the motion of camera platform. In moving background, the moving target detecting and tracking has been getting more complex. Especially, the real-time speed and reliability of motion detecting and tracking can not be fully satisfied in practice. How to exactly distinguish moving target and background is the chiefly task of the technology of motion detecting and tracking in moving background.The problem of motion detecting and tracking in moving background can be analyzed to be described as background motion compensation, moving target detecting and moving target tracking. In this thesis, our study and discuss all focused on the above three sub-problems.The research on background motion compensation is a key problem. A new feature point detect method was proposed called Improved MIC Algorithm. Using the feature points extracted by our new method, combining effective ARPS search method and robust RANSAC estimate algorithm, the transform parameters of background motion model can be calculated, and the impact of background motion can be effectively reduced. Based on the background motion compensation, using frame difference method which is a traditional and effective method, and combining morphological operation, moving target can be detected.The researched on moving target tracking is deeply discussed. After studying the motion estimation method based on Kalman Filter and the Mean Shift algorithm, a quick Mean Shift algorithm based on difference image and gray level histogram was proposed. Compared with Kalman Filter tracking algorithm, our method has obtained a better tracking experiment results quickly and exactly.