Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Haoang Li | - |
dc.contributor.author | 김표진 | - |
dc.contributor.author | Ji Zhao | - |
dc.contributor.author | 주경돈 | - |
dc.contributor.author | Zhipeng Cai | - |
dc.contributor.author | Zhe Liu | - |
dc.contributor.author | Yun-Hui Liu | - |
dc.date.accessioned | 2022-05-23T05:40:17Z | - |
dc.date.available | 2022-05-23T05:40:17Z | - |
dc.date.issued | 2020-11 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.uri | https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/151348 | - |
dc.description.abstract | Atlanta world holds for the scenes composed of a vertical dominant direction and several horizontal dominant directions. Vanishing point (VP) is the intersection of the image lines projected from parallel 3D lines. In Atlanta world, given a set of image lines, we aim to cluster them by the unknown-but-sought VPs whose number is unknown. Existing approaches are prone to missing partial inliers, rely on prior knowledge of the number of VPs, and/or lead to low efficiency. To overcome these limitations, we propose the novel mine-and-stab (MnS) algorithm and embed it in the branch-and-bound (BnB) algorithm. Different from BnB that iteratively branches the full parameter intervals, our MnS directly mines the narrow sub-intervals and then stabs them by probes. We simultaneously search for the vertical VP by BnB and horizontal VPs by MnS. The proposed collaboration between BnB and MnS guarantees global optimality in terms of maximizing the number of inliers. It can also automatically determine the number of VPs. Moreover, its efficiency is suitable for practical applications. Experiments on synthetic and real-world datasets showed that our method outperforms state-of-the-art approaches in terms of accuracy and/or efficiency. © 2020, Springer Nature Switzerland AG. | - |
dc.format.extent | 17 | - |
dc.language | 영어 | - |
dc.language.iso | ENG | - |
dc.publisher | Springer Science | - |
dc.title | Globally Optimal and Efficient Vanishing Point Estimation in Atlanta World | - |
dc.type | Article | - |
dc.publisher.location | 영국 | - |
dc.identifier.doi | 10.1007/978-3-030-58542-6_10 | - |
dc.identifier.scopusid | 2-s2.0-85097305280 | - |
dc.identifier.bibliographicCitation | Lecture Notes in Computer Science (European Conference on Computer Vision), v.12367, pp 153 - 169 | - |
dc.citation.title | Lecture Notes in Computer Science (European Conference on Computer Vision) | - |
dc.citation.volume | 12367 | - |
dc.citation.startPage | 153 | - |
dc.citation.endPage | 169 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.identifier.url | https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123670154.pdf | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
Sookmyung Women's University. Cheongpa-ro 47-gil 100 (Cheongpa-dong 2ga), Yongsan-gu, Seoul, 04310, Korea02-710-9127
Copyright©Sookmyung Women's 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.