DC Field | Value | Language |
---|---|---|
dc.contributor.author | Joo, Kyungdon | ko |
dc.contributor.author | Oh, Tae-Hyun | ko |
dc.contributor.author | Kim, Junsik | ko |
dc.contributor.author | Kweon, In-So | ko |
dc.date.accessioned | 2019-03-19T01:04:12Z | - |
dc.date.available | 2019-03-19T01:04:12Z | - |
dc.date.created | 2017-11-29 | - |
dc.date.issued | 2019-03 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, v.41, no.3, pp.682 - 696 | - |
dc.identifier.issn | 0162-8828 | - |
dc.identifier.uri | http://hdl.handle.net/10203/251481 | - |
dc.description.abstract | Most man-made environments, such as urban and indoor scenes, consist of a set of parallel and orthogonal planar structures. These structures are approximated by the Manhattan world assumption, of which notion can be represented as a Manhattan Frame (MF). Given a set of inputs such as surface normals or vanishing points, we pose an MF estimation problem as a consensus set maximization that maximizes the number of inliers over the rotation search space. Conventionally this problem can be solved by a branch-and-bound framework which mathematically guarantees global optimality. However, the computational time of the conventional branch-and-bound algorithms is rather far from real-time. In this paper, we propose a novel bound computation method on an efficient measurement domain for MF estimation, i.e., the extended Gaussian image (EGI). By relaxing the original problem, we can compute the bound with a constant complexity, while preserving global optimality. Furthermore, we quantitatively and qualitatively demonstrate the performance of the proposed method for various synthetic and real-world data. We also show the versatility of our approach through three different applications: extension to multiple MF estimation, 3D rotation based video stabilization and vanishing point estimation (line clustering). | - |
dc.language | English | - |
dc.publisher | IEEE COMPUTER SOC | - |
dc.title | Robust and Globally Optimal Manhattan Frame Estimation in Near Real Time | - |
dc.type | Article | - |
dc.identifier.wosid | 000458168800012 | - |
dc.identifier.scopusid | 2-s2.0-85041377941 | - |
dc.type.rims | ART | - |
dc.citation.volume | 41 | - |
dc.citation.issue | 3 | - |
dc.citation.beginningpage | 682 | - |
dc.citation.endingpage | 696 | - |
dc.citation.publicationname | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
dc.identifier.doi | 10.1109/TPAMI.2018.2799944 | - |
dc.contributor.localauthor | Kweon, In-So | - |
dc.description.isOpenAccess | N | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Manhattan frame | - |
dc.subject.keywordAuthor | rotation estimation | - |
dc.subject.keywordAuthor | branch-and-bound | - |
dc.subject.keywordAuthor | scene understanding | - |
dc.subject.keywordAuthor | video stabilization | - |
dc.subject.keywordAuthor | line clustering | - |
dc.subject.keywordAuthor | vanishing point estimation | - |
dc.subject.keywordPlus | CONSENSUS | - |
dc.subject.keywordPlus | MAXIMIZATION | - |
dc.subject.keywordPlus | SPACE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.