Alíz Nagy, Istvan Szakats, T. Mariţa, S. Nedevschi
{"title":"Development of an omnidirectional stereo vision system","authors":"Alíz Nagy, Istvan Szakats, T. Mariţa, S. Nedevschi","doi":"10.1109/ICCP.2013.6646114","DOIUrl":null,"url":null,"abstract":"Although stereo systems built up of omnidirectional cameras offer the possibility of providing information for a 360 grade field of view, the research in the field is still in an early stage compared to perspective systems. We provide in this study an extensive overview on existing techniques for camera calibration, stereo rectification, stereo matching methods and 3D depth reconstruction on omnidirectional images. A comparison of methods, together with a few ideas of improvement is presented, establishing an equivalency, and transformation between an omnidirectional and a perspective vision system.","PeriodicalId":380109,"journal":{"name":"2013 IEEE 9th International Conference on Intelligent Computer Communication and Processing (ICCP)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"15","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE 9th International Conference on Intelligent Computer Communication and Processing (ICCP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCP.2013.6646114","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 15
Abstract
Although stereo systems built up of omnidirectional cameras offer the possibility of providing information for a 360 grade field of view, the research in the field is still in an early stage compared to perspective systems. We provide in this study an extensive overview on existing techniques for camera calibration, stereo rectification, stereo matching methods and 3D depth reconstruction on omnidirectional images. A comparison of methods, together with a few ideas of improvement is presented, establishing an equivalency, and transformation between an omnidirectional and a perspective vision system.