96 0

Full metadata record

DC FieldValueLanguage
dc.contributor.author임종우-
dc.date.accessioned2021-11-15T06:39:34Z-
dc.date.available2021-11-15T06:39:34Z-
dc.date.issued2020-05-
dc.identifier.citationIEEE TRANSACTIONS ON IMAGE PROCESSING, v. 29, page. 6992-7005en_US
dc.identifier.issn1057-7149-
dc.identifier.issn1941-0042-
dc.identifier.urihttps://ieeexplore.ieee.org/document/9102429-
dc.identifier.urihttps://repository.hanyang.ac.kr/handle/20.500.11754/166241-
dc.description.abstractWe present a novel feature matching algorithm that systematically utilizes the geometric properties of image features such as position, scale, and orientation, in addition to the conventional descriptor vectors. In challenging scenes, in which repetitive structures and large view changes are present, it is difficult to find correct correspondences using conventional approaches that only use descriptors, as the descriptor distances of correct matches may not be the least among the candidates. The feature matching problem is formulated as a Markov random field (MRF) that uses descriptor distances and relative geometric similarities together. Assuming that the layout of the nearby features does not considerably change, we propose the bidirectional transfer measure to gauge the geometric consistency between the pairs of feature correspondences. The unmatched features are explicitly modeled in the MRF to minimize their negative impact. Instead of solving the MRF on the entire features at once, we start with a small set of confident feature matches, and then progressively expand the MRF with the remaining candidate matches. The proposed progressive approach yields better feature matching performance and faster processing time. Experimental results show that the proposed algorithm provides better feature correspondences in many challenging scenes, i.e., more matches with higher inlier ratio and lower computational cost than those of the state-of-the-art algorithms. The source code of our implementation is open to the public.en_US
dc.description.sponsorshipThis work was supported in part by the CREST from JST under Grant JPMJCR1652, in part by the Next-Generation Information Computing Development Program through the National Research Foundation of Korea (NRF) under Grant NRF-2017M3C4A7069369, and in part by the NRF Grant funded by the Ministry of Science, ICT (MSIT), under Grant NRF-2019R1A4A1029800.en_US
dc.language.isoenen_US
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INCen_US
dc.subjectFeature matchingen_US
dc.subjectcorrespondencesen_US
dc.subjectlocal featuresen_US
dc.subjectMarkov random field (MRF)en_US
dc.subjectprogressive optimizationen_US
dc.titleProgressive Feature Matching: Incremental Graph Construction and Optimizationen_US
dc.typeArticleen_US
dc.relation.volume29-
dc.identifier.doi10.1109/TIP.2020.2996092-
dc.relation.page6992-7005-
dc.relation.journalIEEE TRANSACTIONS ON IMAGE PROCESSING-
dc.contributor.googleauthorLee, Sehyung-
dc.contributor.googleauthorLim, Jongwoo-
dc.contributor.googleauthorSuh, Il Hong-
dc.relation.code2020047912-
dc.sector.campusS-
dc.sector.daehakCOLLEGE OF ENGINEERING[S]-
dc.sector.departmentSCHOOL OF COMPUTER SCIENCE-
dc.identifier.pidjlim-
dc.identifier.orcidhttps://orcid.org/0000-0002-2814-4765-
Appears in Collections:
COLLEGE OF ENGINEERING[S](공과대학) > COMPUTER SCIENCE(컴퓨터소프트웨어학부) > Articles
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE