基于立体视觉的双目匹配-物理电子学专业论文.docxVIP

优秀毕业论文 精品参考文献资料 研究生优秀毕业论文 竺竺坚! 竺竺坚!．_——————————————～一———————————————————一 堡主兰焦笙塞耿工=子化比义 Abstract B1nocu胁vision is all important branch of the computer vision field．is widelv used in many fields·This paper focus on the key of the binocular vision—Stereo Matching·The paper introduces some basic theoretical knowledge aS well as the basic modej of bmocular vision stereo matching，summarizes some of the existing common stereo matc}1ing algorithm，uses an improved local stereo matching algorithm and an global stereo matching algorithm based on graph cuts，and a global stereo matching algont№based on Bayesian theory．Meanwhile，do some expefiments on the Middlebury international standard platform， analysis the experimental results comp黜d with the results of existing matching algorithms，demons仃ating the effectiveness and accuracy of the algorithm． Local stereo matching algorithm in the paper use gradient di肫rence value as a matchmg cost，1mproving the smoothness of the disparity map，meanⅥ枉1e introduce ’I址ey’s Biweight function to matching cost，SO as to achieve the effect of suppressing noise,in the next step，optimize the disparity，obtaining a good matching results． In the global stereo matching algorithm based on graph cuts used in the paper， leature points and edge points are extracted firstly,then match featu鹏points觚d edge p0Ints to obtain the disparity of these points as the initial label of graph cuts algoritluIl； calculate DAISY descriptors of each pixel as data item of the energy function． calculate the sum of gradient difference between the horizontal direction．vertical dl咒ctlon and color change direction as the smooth item，finally obtain dense disparity map bY seeking the minimum energy function，achieving stereo matclling． In the global stereo matching algorithm based on Bayesian the theory used in paper， during the stereo matching process，Bayesian model is introduced．At firSt- use MSERD∞operator to extract support points，then match these supponpoints wlth plxeI gray va