| The detection and tracking of the moving objects is one of the most important branches in the computer vision, which combines advanced technologies and research achievements in image processing, pattern recognition, artificial intelligence, automatic control and other relative fields. It has broadly applied in video surveillance, robots navigation, video transmission, video retrieval, medical image analysis, Meteorological analysis and other fields, so this subject has important theoretical significance and wide practical value.According to different video surveillance scene, the technique of the moving objects detection is different. In this paper, the detection of moving objects, the template correlation matching of the moving objects and the template matching algorithm based on Hausdorff distance have been studied and all the studies are onthe assumption that the background is stationary.The innovation and the major works of this paper include:1. Studying the detection of the moving objects. Since the background isstationary in most of video surveillance, this paper proposes the moving objects detecting algorithm combining the Background Subtraction and the Symmetrical difference in the moving region. In the proposed algorithm, the moving region is first detected according to the Symmetrical difference image, then the Symmetrical difference image does "or" operation with the Background Subtraction image in the detected moving region. Experiments show that this algorithm reduces the influence of the noise in the Background Subtraction image to the detection result of moving objects.2. Studying the pyramid template correlation matching algorithm. The calculation of the template correlation matching algorithm is too large, and can't satisfy the real-time tracking, so we apply the pyramidic structure to this algorithm. The pyramid template correlation matching algorithm has two processes: the coarse matching and the fine matching. In the coarse matching process, a lot of... |
PDF Full Text Request