Study On Computer Three-Dimension Reconstruction Technique Based On Binocular Stereoscopic Vision

Firstly, this paper introduce research content and development of computer vision. Analyzing stereo distance detection technique ,the paper point out the superiority of binocular stereoscopic vision and select it as the basic theory. Then, introduce basic principle of binocular stereoscopic vision and three-dimension reconstruction system. In succession, this paper focus on computer three-dimension reconstruction technique based on binocular stereoscopic vision. The key technique is composed of six parts, which are image acquisition, camera calibration, image pre-processing, feature extraction, stereo matching and three-dimension reconstruction.Image acquisition is realized through CCD camera and a image acquisition card. Using VC++, a image acquisition system accessing to buffer directly is designed. Simultaneously, the calibration techniques of two cameras are studied. By using RAC(radial alignment constraint)of imaging process to decompose camera parameters and organizing the solving sequence of the parameters rationally, all parameters can be obtained through solving linear equations that avoid non-linear optimization. The pre-processing of image includes the smoothing and filtering, contrast enhancement and edge detection. This paper use histogram equalization method to enhance contrast. Studying and comparing some kinds of methods, we select tow-dimension median filter and Canny edge detection method. The arithmetic is implemented with VC++ and Matlab. A stereo matching approach based on edge feature is proposed. The procedure of the correspondence is fulfilled through the edge-detection, the similarity check and the consistence check. Rebuild three-dimension image for disperse data and achieve depth information. In the last part, we display three-dimension information through OpenGL on computer.