双目立体匹配的理论研究及算法优化-光学工程专业论文.docxVIP

AbstractBinocular Abstract Binocular stereo vision is an important rese2Lrch subj ect of computer Vision，which employs two di氐rent location c锄eras to shoot the same scene．Calculating the parallax of the corresponding points in two images of spatial point，3D coordinates of special point can be obtained by a series of inverse prQj ection transfomations．This is similar to the bi0109ical stereo vision．Binocular stereo matching is one of the most impoIrtant problem in stereo Vision． It afrects the results of the nnal stereo matching and the objects’3D infonIlation in real scene． There are several challenge problems in stereo matching，such as i11umination，occlusions and low textures．Stereo matching problems are aH、ected by each other to cause distonion of stereo vision in the complex background of natural environment，especially in real scene． In order to find a solution to solve the problems of stereo matching this paper focuses on three problems in Stereo matching，analyzes some kinds of stereo matching algorithms aIld proposes some reasonable and e丘宅ctiVe methods． (1)In order to solve the problem of illumination in binocular stereo matching，this paper proposes an algorithm which based on invariant moment to reduce the mismatching of disparity map． (2)The paper proposes an algorithm based on the occlusion．The algoritllIll is proposed which the tree stmctures of dynamic programming with self-adaptiVe parameters a11d a dispa“ty iterative refinement to improve stereo matching perfo唧ance．The algoritm model consists of an initialization model and a disparity iterative rennement．T6 obtain the initial disparity map with”clear”background and whole details，the tree stmcture of dyn锄ic programming with self-adaptiVe parameters is presented．A disparity iteratiVe refinement is proposed to estimate the disparity of unreliable pixels in the doubtml regions．The disparity iterative refinement consists of a doubtful regions growing method and a disparity filling based on color similarity．