Visual Place Recognition with Repetitive Structures

Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. They violate the feature independence assumed in the bag-of-visual...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 37; číslo 11; s. 2346 - 2359
Hlavní autoři:	Torii, Akihiko, Sivic, Josef, Okutomi, Masatoshi, Pajdla, Tomas
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.11.2015 Institute of Electrical and Electronics Engineers
Témata:	Bag of Visual Words Buildings Computer Science Computer Vision and Pattern Recognition Feature extraction Image recognition Image Retrieval Indexing Place Recognition Vectors Visual databases Visualization image retrieval Place recognition bag of visual words geometric verification Place Recognition Geometric Verification Image Retrieval Bag of Visual Words
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. They violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they form an important distinguishing feature for many places. We describe a representation of repeated structures suitable for scalable retrieval and geometric verification. The retrieval is based on robust detection of repeated image structures and a suitable modification of weights in the bag-of-visual-word model. We also demonstrate that the explicit detection of repeated patterns is beneficial for robust visual word matching for geometric verification. Place recognition results are shown on datasets of street-level imagery from Pittsburgh and San Francisco demonstrating significant gains in recognition performance compared to the standard bag-of-visual-words baseline as well as the more recently proposed burstiness weighting and Fisher vector encoding.
AbstractList	Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. They violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they form an important distinguishing feature for many places. We describe a representation of repeated structures suitable for scalable retrieval and geometric verification. The retrieval is based on robust detection of repeated image structures and a suitable modification of weights in the bag-of-visual-word model. We also demonstrate that the explicit detection of repeated patterns is beneficial for robust visual word matching for geometric verification. Place recognition results are shown on datasets of street-level imagery from Pittsburgh and San Francisco demonstrating significant gains in recognition performance compared to the standard bag-of-visual-words baseline as well as the more recently proposed burstiness weighting and Fisher vector encoding. Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. They violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they form an important distinguishing feature for many places. We describe a representation of repeated structures suitable for scalable retrieval and geometric verification. The retrieval is based on robust detection of repeated image structures and a suitable modification of weights in the bag-of-visual-word model. We also demonstrate that the explicit detection of repeated patterns is beneficial for robust visual word matching for geometric verification. Place recognition results are shown on datasets of street-level imagery from Pittsburgh and San Francisco demonstrating significant gains in recognition performance compared to the standard bag-of-visual-words baseline as well as the more recently proposed burstiness weighting and Fisher vector encoding.Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are notoriously hard for establishing correspondences using multi-view geometry. They violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance. In this work we show that repeated structures are not a nuisance but, when appropriately represented, they form an important distinguishing feature for many places. We describe a representation of repeated structures suitable for scalable retrieval and geometric verification. The retrieval is based on robust detection of repeated image structures and a suitable modification of weights in the bag-of-visual-word model. We also demonstrate that the explicit detection of repeated patterns is beneficial for robust visual word matching for geometric verification. Place recognition results are shown on datasets of street-level imagery from Pittsburgh and San Francisco demonstrating significant gains in recognition performance compared to the standard bag-of-visual-words baseline as well as the more recently proposed burstiness weighting and Fisher vector encoding.
Author	Torii, Akihiko Okutomi, Masatoshi Sivic, Josef Pajdla, Tomas
Author_xml	– sequence: 1 givenname: Akihiko surname: Torii fullname: Torii, Akihiko email: torii@ctrl.titech.ac.jp organization: Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan – sequence: 2 givenname: Josef surname: Sivic fullname: Sivic, Josef email: Josef.Sivic@ens.fr organization: Dept. d'Inf., Ecole Normale Super., Paris, France – sequence: 3 givenname: Masatoshi surname: Okutomi fullname: Okutomi, Masatoshi email: mxo@ctrl.titech.ac.jp organization: Dept. of Mech. & Control Eng., Tokyo Inst. of Technol., Tokyo, Japan – sequence: 4 givenname: Tomas surname: Pajdla fullname: Pajdla, Tomas email: pajdla@cmp.felk.cvut.cz organization: Dept. of Cybern., Czech Tech. Univ. in Prague, Prague, Czech Republic
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/26440272$$D View this record in MEDLINE/PubMed https://inria.hal.science/hal-01152483$$DView record in HAL
BookMark	eNp9kMlOwzAQhi1URMvyAiChHOGQMt4S51hVbFIRiO1qOe4EjNKkxA6ItyehpQcOXMaa0fePR98uGVR1hYQcUhhTCtnZ493k5nrMgMoxE5CpRG2REaMJxBnL2ICMgCYsVoqpIdn1_g2ACgl8hwxZIgSwlI0If3a-NWV0VxqL0T3a-qVywdVV9OnCazdYYuj6D4weQtPa0Dbo98l2YUqPB-t3jzxdnD9Or-LZ7eX1dDKLrRAyxEYUlkGeKpVILIRKzZwb3l1ppaAFz1KKc2YtQ8VVkee5FJAUuZTzTKKEHPkeOV3tfTWlXjZuYZovXRunryYz3c-AUsmE4h-0Y09W7LKp31v0QS-ct1iWpsK69ZqmDIToStqhx2u0zRc432z-ldIBbAXYpva-wWKDUNC9ef1jXvfm9dp8F1J_QtYF05sMjXHl_9GjVdQh4uavFGR_MP8GXtCO8Q
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1016_j_engappai_2022_105797 crossref_primary_10_1109_LRA_2022_3142901 crossref_primary_10_1109_JPROC_2017_2731600 crossref_primary_10_1109_ACCESS_2019_2910150 crossref_primary_10_1145_3284555 crossref_primary_10_3390_s24030855 crossref_primary_10_1016_j_patrec_2018_07_036 crossref_primary_10_1016_j_patcog_2019_107193 crossref_primary_10_3390_s24134130 crossref_primary_10_1016_j_cviu_2024_103929 crossref_primary_10_1016_j_patcog_2021_107926 crossref_primary_10_1109_LRA_2023_3235682 crossref_primary_10_1177_14780771241276935 crossref_primary_10_1109_TMM_2019_2935680 crossref_primary_10_1016_j_neucom_2018_05_102 crossref_primary_10_1049_iet_cvi_2016_0504 crossref_primary_10_3390_rs16050801 crossref_primary_10_1109_TIM_2022_3168892 crossref_primary_10_4218_etrij_17_0116_0034 crossref_primary_10_3390_s19224946 crossref_primary_10_1007_s11263_022_01615_7 crossref_primary_10_3390_s18010258 crossref_primary_10_1109_TIV_2024_3378716 crossref_primary_10_1016_j_patcog_2021_107952 crossref_primary_10_1109_ACCESS_2021_3054937 crossref_primary_10_1038_s41598_024_73853_3 crossref_primary_10_1109_LRA_2022_3142741 crossref_primary_10_1109_TIP_2019_2913509 crossref_primary_10_1002_rob_22088 crossref_primary_10_1109_LRA_2025_3592075 crossref_primary_10_1109_TPAMI_2020_3032010 crossref_primary_10_1007_s11390_021_1373_1 crossref_primary_10_1109_TPAMI_2019_2941876 crossref_primary_10_1117_1_JEI_32_6_063033 crossref_primary_10_1016_j_patcog_2017_09_013 crossref_primary_10_3233_IDA_173795 crossref_primary_10_1007_s10489_024_05539_2 crossref_primary_10_1016_j_patrec_2017_09_021 crossref_primary_10_1145_3707446 crossref_primary_10_1109_JSTSP_2024_3403247 crossref_primary_10_1109_TCSVT_2022_3212434 crossref_primary_10_1109_TPAMI_2017_2787132 crossref_primary_10_1007_s10489_024_06135_0 crossref_primary_10_1016_j_neucom_2017_07_040 crossref_primary_10_3390_rs12233978 crossref_primary_10_1109_TCYB_2023_3269756 crossref_primary_10_1016_j_jestch_2022_101098 crossref_primary_10_1007_s10055_023_00772_5 crossref_primary_10_3390_s20102870 crossref_primary_10_3390_s23239580 crossref_primary_10_1016_j_neucom_2018_03_059 crossref_primary_10_1007_s11263_020_01399_8 crossref_primary_10_1109_LSP_2017_2731426 crossref_primary_10_1109_TPAMI_2021_3094531
Cites_doi	10.1145/1873951.1874249 10.1145/1276377.1276484 10.1109/CVPR.2011.5995601 10.5244/C.12.2 10.1016/0306-4573(88)90021-0 10.5244/C.26.76 10.1017/S1351324996001246 10.1109/CVPR.2009.5206609 10.1109/34.589215 10.1109/ICCVW.2009.5457541 10.1109/CVPR.2005.221 10.1109/CVPR.2007.383150 10.1109/CVPR.2009.5206531 10.1109/ICCV.2003.1238663 10.1109/CVPR.2011.5995551 10.1109/ICCVW.2011.6130230 10.1109/CVPR.2007.383172 10.1109/CVPR.2007.382970 10.1145/1386352.1386363 10.1109/CVPR.2013.213 10.1109/CVPR.2008.4587461 10.1109/ICCV.2007.4408891 10.1109/CVPR.2009.5206587 10.1109/CVPR.2011.5995610 10.1109/CVPR.2010.5540068 10.1109/TPAMI.2011.235 10.1109/TPAMI.2009.132 10.1109/ICPR.2010.782 10.1109/TPAMI.2009.73 10.1109/CVPR.2011.5995528 10.1109/CVPR.2006.264 10.1109/CVPR.2008.4587635 10.1145/98267.98287 10.1109/TPAMI.2010.57 10.1145/1282280.1282359 10.1109/ICCV.2009.5459419 10.1017/CBO9780511811685 10.1007/s11263-010-0363-5 10.1109/CVPR.2013.119 10.1023/B:VISI.0000029664.99615.94 10.1109/CVPR.2012.6247677 10.1016/j.cviu.2003.06.008
ContentType	Journal Article
Copyright	Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	97E RIA RIE AAYXX CITATION NPM 7X8 1XC VOOES
DOI	10.1109/TPAMI.2015.2409868
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic PubMed
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Xplore url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	2359
ExternalDocumentID	oai:HAL:hal-01152483v1 26440272 10_1109_TPAMI_2015_2409868 7054472
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GrantInformation_xml	– fundername: TACR grantid: TA02011275 – fundername: JSPS KAKENHI grantid: 24700161 funderid: 10.13039/501100000646 – fundername: EIT-ICT labs funderid: 10.13039/501100000811 – fundername: CityLabs@Inria – fundername: ERC project LEAP funderid: 10.13039/501100000781 – fundername: PRoViDE – fundername: MSR-INRIA laboratory funderid: 10.13039/501100003007 – fundername: ANR project Semapolis funderid: 10.13039/501100001665
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AGSQL AHBIQ AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 5VS 9M8 ABFSI ADRHT AETEA AETIX AI. AIBXA AKJIK ALLEH FA8 H~9 IBMZZ ICLAB IFJZH NPM RIG RNI RZB VH1 XJT 7X8 1XC VOOES
ID	FETCH-LOGICAL-c445t-a4fc20b78865ef487ad3a3868c541f3971ed2cc2e838fbbb5406fb55d95e50be3
IEDL.DBID	RIE
ISICitedReferencesCount	98
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000362411000015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Tue Oct 28 06:36:55 EDT 2025 Thu Oct 02 11:22:09 EDT 2025 Mon Jul 21 05:51:27 EDT 2025 Tue Nov 18 21:39:53 EST 2025 Sat Nov 29 05:15:56 EST 2025 Wed Aug 27 02:47:50 EDT 2025
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	11
Keywords	image retrieval Place recognition bag of visual words geometric verification Place Recognition Geometric Verification Image Retrieval Bag of Visual Words
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c445t-a4fc20b78865ef487ad3a3868c541f3971ed2cc2e838fbbb5406fb55d95e50be3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
OpenAccessLink	https://inria.hal.science/hal-01152483
PMID	26440272
PQID	1720447207
PQPubID	23479
PageCount	14
ParticipantIDs	proquest_miscellaneous_1720447207 ieee_primary_7054472 pubmed_primary_26440272 hal_primary_oai_HAL_hal_01152483v1 crossref_primary_10_1109_TPAMI_2015_2409868 crossref_citationtrail_10_1109_TPAMI_2015_2409868
PublicationCentury	2000
PublicationDate	2015-11-01
PublicationDateYYYYMMDD	2015-11-01
PublicationDate_xml	– month: 11 year: 2015 text: 2015-11-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2015
Publisher	IEEE Institute of Electrical and Electronics Engineers
Publisher_xml	– name: IEEE – name: Institute of Electrical and Electronics Engineers
References	ref56 ref12 ref59 ref15 ref58 ref53 hays (ref30) 0 ref55 ref11 ref10 cummins (ref2) 2009 ref17 ref16 ref19 ref18 pritts (ref35) 0 li (ref20) 0 philbin (ref14) 0 ref51 (ref60) 0 ref46 zamir (ref24) 0 ref45 pylvanainen (ref50) 0 muja (ref52) 0 ref48 ref47 leung (ref31) 1996 ref42 ref44 ref43 ref49 arcas (ref1) 2010 ref8 ref7 ref9 ref3 arandjelovi? (ref54) 0 ref6 muller (ref38) 2007; 26 ref5 ref40 ref34 wu (ref37) 0 ref36 ref33 ref32 ref39 sattler (ref41) 0 ref23 ref25 ref22 ref21 ref28 knopp (ref4) 0 ref27 ref29 mikulik (ref13) 0 chum (ref57) 0 jegou (ref26) 0
References_xml	– start-page: 2911 year: 0 ident: ref54 article-title: Three things everyone should know to improve object retrieval publication-title: Proc IEEE Conf Comput Vis Pattern Recog – ident: ref53 doi: 10.1145/1873951.1874249 – volume: 26 start-page: 85 year: 2007 ident: ref38 article-title: Image-based procedural modeling of facades publication-title: ACM Trans Graph doi: 10.1145/1276377.1276484 – start-page: 546 year: 1996 ident: ref31 article-title: Detecting, localizing and grouping repeated scene elements from an image publication-title: Proc 4th Eur Conf Comput Vis – ident: ref18 doi: 10.1109/CVPR.2011.5995601 – ident: ref33 doi: 10.5244/C.12.2 – start-page: 304 year: 0 ident: ref26 article-title: Hamming embedding and weak geometric consistency for large-scale image search publication-title: Proc 10th Eur Conf Comput Vis – ident: ref44 doi: 10.1016/0306-4573(88)90021-0 – start-page: 142 year: 0 ident: ref37 article-title: Detecting large repetitive structures with salient boundaries publication-title: Proc 11th Eur Conf Comput Vis – ident: ref51 doi: 10.5244/C.26.76 – start-page: 791 year: 0 ident: ref20 article-title: Location recognition using prioritized feature matching publication-title: Proc 11th Eur Conf Comput Vis – ident: ref46 doi: 10.1017/S1351324996001246 – ident: ref8 doi: 10.1109/CVPR.2009.5206609 – ident: ref29 doi: 10.1109/34.589215 – ident: ref23 doi: 10.1109/ICCVW.2009.5457541 – start-page: 677 year: 0 ident: ref14 article-title: Descriptor learning for efficient retrieval publication-title: Proc 11th Eur Conf Comput Vis – ident: ref59 doi: 10.1109/CVPR.2005.221 – start-page: 1 year: 0 ident: ref13 article-title: Learning a fine vocabulary publication-title: Proc 11th Eur Conf Comput Vis – ident: ref6 doi: 10.1109/CVPR.2007.383150 – ident: ref25 doi: 10.1109/CVPR.2009.5206531 – start-page: 748 year: 0 ident: ref4 article-title: Avoiding confusing features in place recognition publication-title: Proc Eur Conf Comput Vis – ident: ref12 doi: 10.1109/ICCV.2003.1238663 – year: 2009 ident: ref2 article-title: Highly scalable appearance-only SLAM-FAB-MAP 2.0 – ident: ref40 doi: 10.1109/CVPR.2011.5995551 – ident: ref22 doi: 10.1109/ICCVW.2011.6130230 – ident: ref11 doi: 10.1109/CVPR.2007.383172 – ident: ref9 doi: 10.1109/CVPR.2007.382970 – ident: ref5 doi: 10.1145/1386352.1386363 – ident: ref45 doi: 10.1109/CVPR.2013.213 – start-page: 331 year: 0 ident: ref52 article-title: Fast approximate nearest neighbors with automatic algorithm configuration publication-title: Proc Int Conf Comput Vis Theory Appl – year: 0 ident: ref60 – ident: ref34 doi: 10.1109/CVPR.2008.4587461 – ident: ref7 doi: 10.1109/ICCV.2007.4408891 – ident: ref19 doi: 10.1109/CVPR.2009.5206587 – ident: ref3 doi: 10.1109/CVPR.2011.5995610 – start-page: 2973 year: 0 ident: ref35 article-title: Detection, rectification and segmentation of coplanar repeated patterns publication-title: Proc IEEE Conf Comput Vis Pattern Recog – ident: ref39 doi: 10.1109/CVPR.2010.5540068 – ident: ref55 doi: 10.1109/TPAMI.2011.235 – ident: ref17 doi: 10.1109/TPAMI.2009.132 – ident: ref42 doi: 10.1109/ICPR.2010.782 – year: 0 ident: ref50 article-title: Automatic alignment and multi-view segmentation of street view data using 3d shape prior – ident: ref32 doi: 10.1109/TPAMI.2009.73 – ident: ref27 doi: 10.1109/CVPR.2011.5995528 – ident: ref10 doi: 10.1109/CVPR.2006.264 – ident: ref16 doi: 10.1109/CVPR.2008.4587635 – ident: ref47 doi: 10.1145/98267.98287 – ident: ref15 doi: 10.1109/TPAMI.2010.57 – ident: ref49 doi: 10.1145/1282280.1282359 – start-page: 522 year: 0 ident: ref30 article-title: Discovering texture regularity as a higher-order correspondence problem publication-title: Proc Eur Conf Comput Vis – ident: ref56 doi: 10.1109/ICCV.2009.5459419 – start-page: 2090 year: 0 ident: ref41 article-title: SCRAMSAC: Improving RANSAC's efficiency with a spatial consistency filter publication-title: Proc IEEE 12th Int Conf Comput Vis – ident: ref58 doi: 10.1017/CBO9780511811685 – ident: ref21 doi: 10.1007/s11263-010-0363-5 – start-page: 255 year: 0 ident: ref24 article-title: Accurate image localization based on Google maps street view publication-title: Proc 11th Eur Conf Comput Vis – ident: ref43 doi: 10.1109/CVPR.2013.119 – ident: ref48 doi: 10.1023/B:VISI.0000029664.99615.94 – year: 2010 ident: ref1 – start-page: 812 year: 0 ident: ref57 article-title: Enhancing RANSAC by generalized model optimization publication-title: Proc Asian Conf Comput Vis – ident: ref36 doi: 10.1109/CVPR.2012.6247677 – ident: ref28 doi: 10.1016/j.cviu.2003.06.008
SSID	ssj0014503
Score	2.5510774
Snippet	Repeated structures such as building facades, fences or road markings often represent a significant challenge for place recognition. Repeated structures are...
SourceID	hal proquest pubmed crossref ieee
SourceType	Open Access Repository Aggregation Database Index Database Enrichment Source Publisher
StartPage	2346
SubjectTerms	Bag of Visual Words Buildings Computer Science Computer Vision and Pattern Recognition Feature extraction Image recognition Image Retrieval Indexing Place Recognition Vectors Visual databases Visualization
Title	Visual Place Recognition with Repetitive Structures
URI	https://ieeexplore.ieee.org/document/7054472 https://www.ncbi.nlm.nih.gov/pubmed/26440272 https://www.proquest.com/docview/1720447207 https://inria.hal.science/hal-01152483
Volume	37
WOSCitedRecordID	wos000362411000015&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Xplore customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB5UPOjB96O-qOJN67ZN0jbHRRQFlcUXeytNmqAgXXFdf78z6QMFFbyVMCkh3yTzTZKZAThEo5PKOCkDrXCRc8FEoDQrAxmjRmeGFbFVrthEenOTDYdyMAXHXSyMMcY9PjMn9Onu8suRntBRWS9FfsFT3HCn0zSpY7W6GwMuXBVkZDC4wtGNaANkQtm7H_SvL-kVlzhB-yWzhIr0ERFAlyz-Zo-mn-g1pCuz8jvjdJbnfPF_Y16ChYZh-v1aJZZhylQrsNhWb_CbxbwC819SEa4Ce3weT7DbgI7V_dv2WdGo8umkFhteKRwNt0b_zmWcnaCbvgYP52f3pxdBU1Ah0JyL96DgVsehQq83Ecaiq1KUrGA4H1rwyCIziUwZax2bjGVWKYVsLrFKiFIKI0Jl2DrMVKPKbIJvpUyNTmyEfIfL0BYU08pCXppECZmFHkTttOa6yTZORS9ecud1hDJ3qOSESt6g4sFR1-e1zrXxp_QBotUJUprsi_5VTm1Ec2OesY_Ig1WCpJNq0PBgvwU3x-VEdyRFZUaTcR5R0R6UCFMPNmrUu86tymz9_NNtmKPx1YGKOzCDaJhdmNUf78_jtz3U2WG253T2E76f4no
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VggQcKLQ8QnkExI2mdfxI4uMKUW3FdrWCBfVmxY4tKqFsxXb7-5lxHipSqcQpkTWOIn8ezze2ZwbgAxqdUvOiyZxFJZdKqMw60WSa44yuvKh5sLHYRDmfV2dnerEFB2MsjPc-Xj7zh_Qaz_KbldvQVtlRifxClrjg3sUnZ1201nhmIFWsg4wcBnUcHYkhRIbpo-VicnpC97jUIVowXRVUpo-oADpl_C-LdOcn3YeMhVb-zTmj7Tne-b-_fgyPeo6ZTrpJ8QS2fLsLO0P9hrRX5114eC0Z4R6IH-frDXZb0MZ6-nW4WLRqU9qrxYYLCkjDxTH9FnPObtBRfwrfjz8vP02zvqRC5qRUl1ktg-PMot9bKB_QWakbUQscD6dkHpCb5L7hznFfiSpYa5HPFcEq1WjlFbNePIPtdtX6F5AGrUvvipAj45GahZqiWgWTjS-s0hVLIB-G1bg-3ziVvfhlot_BtImoGELF9Kgk8HHsc9Fl27hV-j2iNQpSouzpZGaojYgul5W4yhPYI0hGqR6NBN4N4BpUKDolqVu_2qxNTmV7UIKVCTzvUB87D1Pm5c0ffQv3p8vTmZmdzL_swwP61y5s8RVsIzL-NdxzV5fn699v4sz9A1md5Nk
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Visual+Place+Recognition+with+Repetitive+Structures&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Torii%2C+Akihiko&rft.au=Sivic%2C+Josef&rft.au=Okutomi%2C+Masatoshi&rft.au=Pajdla%2C+Tomas&rft.date=2015-11-01&rft.pub=Institute+of+Electrical+and+Electronics+Engineers&rft.issn=0162-8828&rft.spage=1&rft.epage=14&rft_id=info:doi/10.1109%2FTPAMI.2015.2409868&rft.externalDBID=HAS_PDF_LINK&rft.externalDocID=oai%3AHAL%3Ahal-01152483v1
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon