Image Matching For Trinocular Stereo Vision System

With the development of the computer vision, Binocular stereo vision is simple and reliable since the way in which human's eyes Process information is directly simulated. It is valuable in many fields such as the gesture detection and controlling of micro-operation system, robot navigation and aerial survey, three-dimension measurement and virtual reality. In stereo matching for depth recovery, trinocular stereo vision System matching algorithms are mainly studied after reviewing the issues of basic theory, camera calibration, difficulties, evaluation and methods for stereo matching. In this Paper the algorithms of image matching are lucubrated and the Computer system of binocular stereo vision is established to achieve the stereo matching of feature points of the object. An auto-adapted algorithm of the edge detection based on Canny operator is applied to extract the feature points so that the detected edge of the goal objects is more integrated and accurate. Moreover, the Precision and robustness of the algorithm was enhanced since the algorithm of image matching of feature Points based on SSDA algorithm, the epipolar restriction and the Parallax gradient restriction is applied. The method proposed in the paper is used to process the real stereo pairs. Experimental results have shown that the algorithm is accuracy and the complexity of matching is reduced, but need to improve.