{"title":"A new matching approach based on line moments in binocular stereovision","authors":"J. Brochard, M. Khoudeir, C. Eliot, T. Simon","doi":"10.1109/ICECS.1996.584455","DOIUrl":null,"url":null,"abstract":"This paper concern the matching phase needed in binocular stereovision, for object location in 3D scene. We present here a new matching approach exploiting line moments. We show that the relation between the line moments having (0+q) order of a segment of the image on the right and the same order moment of the image on the left keep a constant value if the two considered segments are well matched. This relation becomes variable in the case of a bad matching. This method have been tested on diverse real scenes with varied complexity levels and the results obtained are presented.","PeriodicalId":402369,"journal":{"name":"Proceedings of Third International Conference on Electronics, Circuits, and Systems","volume":"76 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1996-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of Third International Conference on Electronics, Circuits, and Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICECS.1996.584455","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
This paper concern the matching phase needed in binocular stereovision, for object location in 3D scene. We present here a new matching approach exploiting line moments. We show that the relation between the line moments having (0+q) order of a segment of the image on the right and the same order moment of the image on the left keep a constant value if the two considered segments are well matched. This relation becomes variable in the case of a bad matching. This method have been tested on diverse real scenes with varied complexity levels and the results obtained are presented.