{"title":"A Linear and Aspect Ratio Invariant Rectification Method for Stereo Vision","authors":"Jiang Ze-tao, Wu Min, Zheng Bi Na","doi":"10.1109/CSSE.2008.508","DOIUrl":null,"url":null,"abstract":"In 3d reconstruction, to search the corresponding points only in horizontal line rapidly and accurately, it is used to make the epipolar lines of stereo images be parallel to the horizontal direction and to remove the parallax in vertical direction, then we can complete the density match better. In the foundation traditional projective transform, a novel liner and aspect ratio invariant rectification method is proposed. This method selects corresponding points in the pairs of images to define a reference plane. Through the relation of epipolar geometry, construct a linear equation set and calculate the projective transformation matrix. Then eliminate distortion by using shearing transform. Thus the algorithm accomplishes the rectification of stereo vision greatly. Experiments with real images show that the method an effective method which can eliminate the distortion in stereo rectification.","PeriodicalId":6460,"journal":{"name":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","volume":"22 1","pages":"903-906"},"PeriodicalIF":0.0000,"publicationDate":"2008-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 14th International Joint Conference on Computer Science and Software Engineering (JCSSE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CSSE.2008.508","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
In 3d reconstruction, to search the corresponding points only in horizontal line rapidly and accurately, it is used to make the epipolar lines of stereo images be parallel to the horizontal direction and to remove the parallax in vertical direction, then we can complete the density match better. In the foundation traditional projective transform, a novel liner and aspect ratio invariant rectification method is proposed. This method selects corresponding points in the pairs of images to define a reference plane. Through the relation of epipolar geometry, construct a linear equation set and calculate the projective transformation matrix. Then eliminate distortion by using shearing transform. Thus the algorithm accomplishes the rectification of stereo vision greatly. Experiments with real images show that the method an effective method which can eliminate the distortion in stereo rectification.