A robust technique for correspondence using the epipolar geometry
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yun, Y.-I. | - |
dc.contributor.author | Kang, K.-H. | - |
dc.contributor.author | Park, Y.-S. | - |
dc.contributor.author | Choi, J.-S. | - |
dc.contributor.author | Song, H.-K. | - |
dc.contributor.author | Kim, Y.-M. | - |
dc.date.accessioned | 2021-06-18T13:42:02Z | - |
dc.date.available | 2021-06-18T13:42:02Z | - |
dc.date.issued | 2007-10 | - |
dc.identifier.issn | 1790-0832 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/47006 | - |
dc.description.abstract | The accurate matching problem is an important issue in computer vision. This paper proposes a robust techniques to find correspondence by using a classical method (correlation technique) based on the epipolar constraints and motion flows from uncalibrated stereo images. If we detect matching for only the epipolar geometry, the problem is very difficult. We first use a classical method to accurately find an initial set of matches and then exploit motion vectors in order to remove mismatches among matching candidates. The epipolar geometry can therefore be estimated accurately using well adapted criterion and computing the fundamental matrix. We also adapt to a bucketing technique to optimize the fundamental matrix. More matches are eventually founded by the F-guided matching method underlying the epipolar geometry. The experimental results show the proposed algorithm has been widely tested and works remarkably well in various circumstances with many repetitive patterns. The results also represent that the performance of the proposed algorithm is better than that of conventional methods. | - |
dc.format.extent | 7 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.title | A robust technique for correspondence using the epipolar geometry | - |
dc.type | Article | - |
dc.identifier.bibliographicCitation | WSEAS Transactions on Information Science and Applications, v.4, no.10, pp 1386 - 1392 | - |
dc.description.isOpenAccess | N | - |
dc.identifier.scopusid | 2-s2.0-38349085356 | - |
dc.citation.endPage | 1392 | - |
dc.citation.number | 10 | - |
dc.citation.startPage | 1386 | - |
dc.citation.title | WSEAS Transactions on Information Science and Applications | - |
dc.citation.volume | 4 | - |
dc.type.docType | Article | - |
dc.publisher.location | 그리이스 | - |
dc.subject.keywordAuthor | Correlation | - |
dc.subject.keywordAuthor | Correspondence | - |
dc.subject.keywordAuthor | Epipolar geometry | - |
dc.subject.keywordAuthor | F-guided matching | - |
dc.subject.keywordAuthor | Fundamental matrix | - |
dc.subject.keywordAuthor | Motion vectors | - |
dc.subject.keywordPlus | Geometry | - |
dc.subject.keywordPlus | Image matching | - |
dc.subject.keywordPlus | Motion pictures | - |
dc.subject.keywordPlus | Optical correlation | - |
dc.subject.keywordPlus | Robust control | - |
dc.subject.keywordPlus | Stereo vision | - |
dc.subject.keywordPlus | Epipolar geometry | - |
dc.subject.keywordPlus | F-guided matching | - |
dc.subject.keywordPlus | Fundamental matrix | - |
dc.subject.keywordPlus | Motion vectors | - |
dc.subject.keywordPlus | Computer vision | - |
dc.description.journalRegisteredClass | scopus | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
84, Heukseok-ro, Dongjak-gu, Seoul, Republic of Korea (06974)02-820-6194
COPYRIGHT 2019 Chung-Ang University All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.