Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/12340
Full metadata record
DC FieldValueLanguage
dc.contributor.authorOrhan, Semih-
dc.contributor.authorBaştanlar, Yalın-
dc.date.accessioned2022-08-15T18:23:28Z-
dc.date.available2022-08-15T18:23:28Z-
dc.date.issued2021-
dc.identifier.isbn978-1-6654-0191-3-
dc.identifier.issn2473-9936-
dc.identifier.urihttps://doi.org/10.1109/ICCVW54120.2021.00198-
dc.identifier.urihttps://hdl.handle.net/11147/12340-
dc.description18th IEEE/CVF International Conference on Computer Vision (ICCV) -- OCT 11-17, 2021en_US
dc.description.abstractIn this work, we focus on a localization technique that is based on image retrieval. In this technique, database images are kept with GPS coordinates and the geographic location of the retrieved database image serves as an approximate position of the query image. In our scenario, database consists of panoramic images (e.g. Google Street View) and query images are collected with a standard field-of-view camera in a different time. While searching the match of a perspective query image in a panoramic image database, unlike previous studies, we do not generate a number of perspective images from the panoramic image. Instead, taking advantage of CNNs, we slide a search window in the last convolutional layer belonging to the panoramic image and compute the similarity with the descriptor extracted from the query image. In this way, more locations are visited in less amount of time. We conducted experiments with state-of-the-art descriptors and results reveal that the proposed sliding window approach reaches higher accuracy than generating 4 or 8 perspective images.en_US
dc.description.sponsorshipThis work was supported by the Scientific and Technological Research Council of Turkey (TUBI.TAK), Grant No: 120E500en_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartof18th IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2021en_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectImage retrievalen_US
dc.subjectDatabase imagesen_US
dc.titleEfficient search in a panoramic image database for long-term visual localizationen_US
dc.typeConference Objecten_US
dc.authorid0000-0002-3774-6872-
dc.departmentİzmir Institute of Technology. Computer Engineeringen_US
dc.identifier.startpage1727en_US
dc.identifier.endpage1734en_US
dc.identifier.wosWOS:000739651101091en_US
dc.identifier.scopus2-s2.0-85123055290en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı ve Öğrencien_US
dc.identifier.doi10.1109/ICCVW54120.2021.00198-
item.grantfulltextopen-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.fulltextWith Fulltext-
item.languageiso639-1en-
item.openairetypeConference Object-
item.cerifentitytypePublications-
crisitem.author.dept01.01. Units Affiliated to the Rectorate-
crisitem.author.dept03.04. Department of Computer Engineering-
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Files in This Item:
File SizeFormat 
Efficient_Search_in_a_Panoramic.pdf5.83 MBAdobe PDFView/Open
Show simple item record



CORE Recommender

SCOPUSTM   
Citations

2
checked on Feb 17, 2024

WEB OF SCIENCETM
Citations

1
checked on Feb 17, 2024

Page view(s)

962
checked on Feb 19, 2024

Download(s)

68
checked on Feb 19, 2024

Google ScholarTM

Check




Altmetric


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