Research Of Feature Matching In Binocular Stereo Vision

Binocular stereovision 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, 3D measurement and virtual reality.The matching of feature points is not only the difficulty, but also the key in binocular. In this paper the algorithms of image matching are lucubrated and the computer system of binocular stereovision is established to achieve the stereo matching of feature points of the object after studying the relative subjects.The camera model and different calibration techniques are studied in image acquisition. The camera calibration model of the binocular is constructed by combining the linear and non-linear model. It improves the calibration precision while avoided the errors caused by imperfect math model.The median filtering technique is adopted to perform smooth filtering on image. Then image enhancement and edge detection are adopted. An auto-adapted algorithm of the edge detection based on Canny operator is applied to extract the feature points so that the image segmentation threshold is auto-adaptive.The detected edge of the goal objects is more integrated and accurate since the character of partial image was taken into account. 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 3D coordinates of the feature points were calculated after the matching process had finished. And the 3D reconstruction technique is talked about at last.The research on matching of feature points and related techniques illustrated in here are good elicitations for further study.