A Branch and Bound Approach to Correspondence and Grouping Problems
Identifieur interne : 000009 ( Hal/Curation ); précédent : 000008; suivant : 000010A Branch and Bound Approach to Correspondence and Grouping Problems
Auteurs : Jean-Charles Bazin [Japon] ; Hongdong Li [Australie] ; Inso Kweon [Corée du Sud] ; Cédric Demonceaux [France] ; Pascal Vasseur [France] ; Katsushi Ikeuchi [Japon]Source :
- IEEE Transactions on Pattern Analysis and Machine Intelligence [ 0162-8828 ] ; 2013.
Descripteurs français
- Wicri :
- topic : Courrier électronique.
English descriptors
- mix :
Abstract
Data correspondence/grouping is a fundamental topic in computer vision. Finding feature correspondences is probably the most popular application of this topic and constitutes our main motivation. It is a key ingredient for various tasks including 3D reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity, or global geometric consistency, or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially with repetitive image textures or mis-matches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods, and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features as input, and outputs the largest set of feature correspondences verifying both the appearance and geometric constraints. We formulate the problem as a mixed integer program, and solve it efficiently by a series of linear programs via branch-and-bound. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images.
Url:
DOI: 10.1109/TPAMI.2012.264
Links toward previous steps (curation, corpus...)
- to stream Hal, to step Corpus: Pour aller vers cette notice dans l'étape Curation :000009
Links to Exploration step
Hal:hal-00829611Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">A Branch and Bound Approach to Correspondence and Grouping Problems</title><author><name sortKey="Bazin, Jean Charles" sort="Bazin, Jean Charles" uniqKey="Bazin J" first="Jean-Charles" last="Bazin">Jean-Charles Bazin</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-179740" status="INCOMING"><orgName>Ikeuchi Laboratory, Institute of Industrial Science</orgName><desc><address><addrLine>The University of Tokyo</addrLine><country key="JP"></country></address></desc><listRelation><relation active="#struct-254193" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-254193" type="direct"><org type="institution" xml:id="struct-254193" status="VALID"><orgName>University of Tokyo [Tokyo]</orgName><desc><address><addrLine>7-3-1 Hongo, Bunkyo, Tokyo 113-8654</addrLine><country key="JP"></country></address><ref type="url">http://www.u-tokyo.ac.jp/en/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>Japon</country></affiliation></author><author><name sortKey="Li, Hongdong" sort="Li, Hongdong" uniqKey="Li H" first="Hongdong" last="Li">Hongdong Li</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-103314" status="VALID"><orgName>Networks Research Group</orgName><orgName type="acronym">NICTA</orgName><desc><address><addrLine>Locked Bag 9013, Alexandria NSW 1435</addrLine><country key="AU"></country></address><ref type="url">http://www.nicta.com.au/research/networks</ref></desc><listRelation><relation active="#struct-302164" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-302164" type="direct"><org type="institution" xml:id="struct-302164" status="VALID"><orgName>National ICT Australia Ltd</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>Australie</country></affiliation></author><author><name sortKey="Kweon, Inso" sort="Kweon, Inso" uniqKey="Kweon I" first="Inso" last="Kweon">Inso Kweon</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-153498" status="VALID"><orgName>Robotics and Computer Vision Laboratory [KAIST]</orgName><orgName type="acronym">RCV</orgName><desc><address><addrLine>#3215 Electrical Engineering Building (E3) KAIST Guseong-dong Yuseong-gu Daejeon KOREA</addrLine><country key="KR"></country></address><ref type="url">http://rcv.kaist.ac.kr/v2/</ref></desc><listRelation><relation active="#struct-301570" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-301570" type="direct"><org type="institution" xml:id="struct-301570" status="VALID"><orgName>Korea Advanced Institute of Science and Technology</orgName><orgName type="acronym">KAIST</orgName><date type="start">2016-10-19</date><desc><address><country key="KR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>Corée du Sud</country></affiliation></author><author><name sortKey="Demonceaux, Cedric" sort="Demonceaux, Cedric" uniqKey="Demonceaux C" first="Cédric" last="Demonceaux">Cédric Demonceaux</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-22594" status="VALID"><orgName>Laboratoire Electronique, Informatique et Image</orgName><orgName type="acronym">Le2i</orgName><desc><address><addrLine>Université de Bourgogne - Laboratoire Le2i - UFR Sciences et Techniques - BP 47870 - 21078 DIJON CEDEX</addrLine><country key="FR"></country></address><ref type="url">http://le2i.cnrs.fr</ref></desc><listRelation><relation active="#struct-300062" type="direct"></relation><relation active="#struct-300270" type="direct"></relation><relation name="UMR6306" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-300062" type="direct"><org type="institution" xml:id="struct-300062" status="VALID"><orgName>Arts et Métiers ParisTech</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle active="#struct-300270" type="direct"><org type="institution" xml:id="struct-300270" status="VALID"><orgName>Université de Bourgogne</orgName><orgName type="acronym">UB</orgName><desc><address><addrLine>Maison de l'université - Esplanade Érasme - BP 27877 - 21078 Dijon cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bourgogne.fr/</ref></desc></org></tutelle><tutelle name="UMR6306" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno><idno type="IdRef">02636817X</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Dijon</settlement><region type="region" nuts="2">Région Bourgogne</region></placeName><orgName type="university">Université de Bourgogne</orgName><orgName type="institution" wicri:auto="newGroup">Université de Bourgogne Franche-Comté</orgName></affiliation></author><author><name sortKey="Vasseur, Pascal" sort="Vasseur, Pascal" uniqKey="Vasseur P" first="Pascal" last="Vasseur">Pascal Vasseur</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-23832" status="VALID"><orgName>Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</orgName><orgName type="acronym">LITIS</orgName><desc><address><addrLine>Avenue de l'Université UFR des Sciences et Techniques 76800 Saint-Etienne du Rouvray</addrLine><country key="FR"></country></address><ref type="url">http://www.litislab.eu</ref></desc><listRelation><relation active="#struct-300317" type="direct"></relation><relation name="EA4108" active="#struct-300318" type="direct"></relation><relation active="#struct-301288" type="direct"></relation><relation active="#struct-301232" type="indirect"></relation></listRelation><tutelles><tutelle active="#struct-300317" type="direct"><org type="institution" xml:id="struct-300317" status="VALID"><orgName>Université du Havre</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="EA4108" active="#struct-300318" type="direct"><org type="institution" xml:id="struct-300318" status="VALID"><orgName>Université de Rouen</orgName><desc><address><addrLine> 1 rue Thomas Becket - 76821 Mont-Saint-Aignan</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-rouen.fr/</ref></desc></org></tutelle><tutelle active="#struct-301288" type="direct"><org type="department" xml:id="struct-301288" status="VALID"><orgName>Institut National des Sciences Appliquées - Rouen</orgName><orgName type="acronym">INSA Rouen</orgName><desc><address><country key="FR"></country></address></desc><listRelation><relation active="#struct-301232" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-301232" type="indirect"><org type="institution" xml:id="struct-301232" status="VALID"><orgName>Institut National des Sciences Appliquées</orgName><orgName type="acronym">INSA</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Le Havre</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université du Havre</orgName><placeName><settlement type="city">Rouen</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université de Rouen</orgName></affiliation></author><author><name sortKey="Ikeuchi, Katsushi" sort="Ikeuchi, Katsushi" uniqKey="Ikeuchi K" first="Katsushi" last="Ikeuchi">Katsushi Ikeuchi</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-50647" status="VALID"><orgName>Institute of Industrial Science</orgName><desc><address><addrLine>4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Japan</addrLine><country key="JP"></country></address><ref type="url">http://dfs.iis.u-tokyo.ac.jp/</ref></desc><listRelation><relation active="#struct-254193" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-254193" type="direct"><org type="institution" xml:id="struct-254193" status="VALID"><orgName>University of Tokyo [Tokyo]</orgName><desc><address><addrLine>7-3-1 Hongo, Bunkyo, Tokyo 113-8654</addrLine><country key="JP"></country></address><ref type="url">http://www.u-tokyo.ac.jp/en/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>Japon</country></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">HAL</idno><idno type="RBID">Hal:hal-00829611</idno><idno type="halId">hal-00829611</idno><idno type="halUri">https://hal.archives-ouvertes.fr/hal-00829611</idno><idno type="url">https://hal.archives-ouvertes.fr/hal-00829611</idno><idno type="doi">10.1109/TPAMI.2012.264</idno><date when="2013">2013</date><idno type="wicri:Area/Hal/Corpus">000009</idno><idno type="wicri:Area/Hal/Curation">000009</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">A Branch and Bound Approach to Correspondence and Grouping Problems</title><author><name sortKey="Bazin, Jean Charles" sort="Bazin, Jean Charles" uniqKey="Bazin J" first="Jean-Charles" last="Bazin">Jean-Charles Bazin</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-179740" status="INCOMING"><orgName>Ikeuchi Laboratory, Institute of Industrial Science</orgName><desc><address><addrLine>The University of Tokyo</addrLine><country key="JP"></country></address></desc><listRelation><relation active="#struct-254193" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-254193" type="direct"><org type="institution" xml:id="struct-254193" status="VALID"><orgName>University of Tokyo [Tokyo]</orgName><desc><address><addrLine>7-3-1 Hongo, Bunkyo, Tokyo 113-8654</addrLine><country key="JP"></country></address><ref type="url">http://www.u-tokyo.ac.jp/en/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>Japon</country></affiliation></author><author><name sortKey="Li, Hongdong" sort="Li, Hongdong" uniqKey="Li H" first="Hongdong" last="Li">Hongdong Li</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-103314" status="VALID"><orgName>Networks Research Group</orgName><orgName type="acronym">NICTA</orgName><desc><address><addrLine>Locked Bag 9013, Alexandria NSW 1435</addrLine><country key="AU"></country></address><ref type="url">http://www.nicta.com.au/research/networks</ref></desc><listRelation><relation active="#struct-302164" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-302164" type="direct"><org type="institution" xml:id="struct-302164" status="VALID"><orgName>National ICT Australia Ltd</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>Australie</country></affiliation></author><author><name sortKey="Kweon, Inso" sort="Kweon, Inso" uniqKey="Kweon I" first="Inso" last="Kweon">Inso Kweon</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-153498" status="VALID"><orgName>Robotics and Computer Vision Laboratory [KAIST]</orgName><orgName type="acronym">RCV</orgName><desc><address><addrLine>#3215 Electrical Engineering Building (E3) KAIST Guseong-dong Yuseong-gu Daejeon KOREA</addrLine><country key="KR"></country></address><ref type="url">http://rcv.kaist.ac.kr/v2/</ref></desc><listRelation><relation active="#struct-301570" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-301570" type="direct"><org type="institution" xml:id="struct-301570" status="VALID"><orgName>Korea Advanced Institute of Science and Technology</orgName><orgName type="acronym">KAIST</orgName><date type="start">2016-10-19</date><desc><address><country key="KR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>Corée du Sud</country></affiliation></author><author><name sortKey="Demonceaux, Cedric" sort="Demonceaux, Cedric" uniqKey="Demonceaux C" first="Cédric" last="Demonceaux">Cédric Demonceaux</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-22594" status="VALID"><orgName>Laboratoire Electronique, Informatique et Image</orgName><orgName type="acronym">Le2i</orgName><desc><address><addrLine>Université de Bourgogne - Laboratoire Le2i - UFR Sciences et Techniques - BP 47870 - 21078 DIJON CEDEX</addrLine><country key="FR"></country></address><ref type="url">http://le2i.cnrs.fr</ref></desc><listRelation><relation active="#struct-300062" type="direct"></relation><relation active="#struct-300270" type="direct"></relation><relation name="UMR6306" active="#struct-441569" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-300062" type="direct"><org type="institution" xml:id="struct-300062" status="VALID"><orgName>Arts et Métiers ParisTech</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle active="#struct-300270" type="direct"><org type="institution" xml:id="struct-300270" status="VALID"><orgName>Université de Bourgogne</orgName><orgName type="acronym">UB</orgName><desc><address><addrLine>Maison de l'université - Esplanade Érasme - BP 27877 - 21078 Dijon cedex</addrLine><country key="FR"></country></address><ref type="url">http://www.u-bourgogne.fr/</ref></desc></org></tutelle><tutelle name="UMR6306" active="#struct-441569" type="direct"><org type="institution" xml:id="struct-441569" status="VALID"><idno type="ISNI">0000000122597504</idno><idno type="IdRef">02636817X</idno><orgName>Centre National de la Recherche Scientifique</orgName><orgName type="acronym">CNRS</orgName><date type="start">1939-10-19</date><desc><address><country key="FR"></country></address><ref type="url">http://www.cnrs.fr/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Dijon</settlement><region type="region" nuts="2">Région Bourgogne</region></placeName><orgName type="university">Université de Bourgogne</orgName><orgName type="institution" wicri:auto="newGroup">Université de Bourgogne Franche-Comté</orgName></affiliation></author><author><name sortKey="Vasseur, Pascal" sort="Vasseur, Pascal" uniqKey="Vasseur P" first="Pascal" last="Vasseur">Pascal Vasseur</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-23832" status="VALID"><orgName>Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</orgName><orgName type="acronym">LITIS</orgName><desc><address><addrLine>Avenue de l'Université UFR des Sciences et Techniques 76800 Saint-Etienne du Rouvray</addrLine><country key="FR"></country></address><ref type="url">http://www.litislab.eu</ref></desc><listRelation><relation active="#struct-300317" type="direct"></relation><relation name="EA4108" active="#struct-300318" type="direct"></relation><relation active="#struct-301288" type="direct"></relation><relation active="#struct-301232" type="indirect"></relation></listRelation><tutelles><tutelle active="#struct-300317" type="direct"><org type="institution" xml:id="struct-300317" status="VALID"><orgName>Université du Havre</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle><tutelle name="EA4108" active="#struct-300318" type="direct"><org type="institution" xml:id="struct-300318" status="VALID"><orgName>Université de Rouen</orgName><desc><address><addrLine> 1 rue Thomas Becket - 76821 Mont-Saint-Aignan</addrLine><country key="FR"></country></address><ref type="url">http://www.univ-rouen.fr/</ref></desc></org></tutelle><tutelle active="#struct-301288" type="direct"><org type="department" xml:id="struct-301288" status="VALID"><orgName>Institut National des Sciences Appliquées - Rouen</orgName><orgName type="acronym">INSA Rouen</orgName><desc><address><country key="FR"></country></address></desc><listRelation><relation active="#struct-301232" type="direct"></relation></listRelation></org></tutelle><tutelle active="#struct-301232" type="indirect"><org type="institution" xml:id="struct-301232" status="VALID"><orgName>Institut National des Sciences Appliquées</orgName><orgName type="acronym">INSA</orgName><desc><address><country key="FR"></country></address></desc></org></tutelle></tutelles></hal:affiliation><country>France</country><placeName><settlement type="city">Le Havre</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université du Havre</orgName><placeName><settlement type="city">Rouen</settlement><region type="region" nuts="2">Région Normandie</region><region type="old region" nuts="2">Haute-Normandie</region></placeName><orgName type="university">Université de Rouen</orgName></affiliation></author><author><name sortKey="Ikeuchi, Katsushi" sort="Ikeuchi, Katsushi" uniqKey="Ikeuchi K" first="Katsushi" last="Ikeuchi">Katsushi Ikeuchi</name><affiliation wicri:level="1"><hal:affiliation type="laboratory" xml:id="struct-50647" status="VALID"><orgName>Institute of Industrial Science</orgName><desc><address><addrLine>4-6-1 Komaba, Meguro-ku, Tokyo 153-8505, Japan</addrLine><country key="JP"></country></address><ref type="url">http://dfs.iis.u-tokyo.ac.jp/</ref></desc><listRelation><relation active="#struct-254193" type="direct"></relation></listRelation><tutelles><tutelle active="#struct-254193" type="direct"><org type="institution" xml:id="struct-254193" status="VALID"><orgName>University of Tokyo [Tokyo]</orgName><desc><address><addrLine>7-3-1 Hongo, Bunkyo, Tokyo 113-8654</addrLine><country key="JP"></country></address><ref type="url">http://www.u-tokyo.ac.jp/en/</ref></desc></org></tutelle></tutelles></hal:affiliation><country>Japon</country></affiliation></author></analytic><idno type="DOI">10.1109/TPAMI.2012.264</idno><series><title level="j">IEEE Transactions on Pattern Analysis and Machine Intelligence</title><idno type="ISSN">0162-8828</idno><imprint><date type="datePub">2013</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="mix" xml:lang="en"><term>Computer vision</term><term>Educational institutions</term><term>Electronic mail</term><term>Feature extraction</term><term>Geometry</term><term>Mixed integer programming</term><term>Optimization</term><term>Pattern matching</term><term>bilinearities</term><term>branch-and-bound</term><term>global optimization</term><term>quadratic constraint</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Courrier électronique</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Data correspondence/grouping is a fundamental topic in computer vision. Finding feature correspondences is probably the most popular application of this topic and constitutes our main motivation. It is a key ingredient for various tasks including 3D reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity, or global geometric consistency, or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially with repetitive image textures or mis-matches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods, and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features as input, and outputs the largest set of feature correspondences verifying both the appearance and geometric constraints. We formulate the problem as a mixed integer program, and solve it efficiently by a series of linear programs via branch-and-bound. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images.</div></front></TEI><hal api="V3"><titleStmt><title xml:lang="en">A Branch and Bound Approach to Correspondence and Grouping Problems</title><author role="crp"><persName><forename type="first">Jean-Charles</forename><surname>Bazin</surname></persName><email>jcbazin@cvl.iis.u-tokyo.ac.jp</email><idno type="halauthor">681481</idno><affiliation ref="#struct-179740"></affiliation></author><author role="aut"><persName><forename type="first">Hongdong</forename><surname>Li</surname></persName><email></email><idno type="halauthor">856624</idno><affiliation ref="#struct-103314"></affiliation></author><author role="aut"><persName><forename type="first">Inso</forename><surname>Kweon</surname></persName><email></email><idno type="halauthor">355691</idno><affiliation ref="#struct-153498"></affiliation></author><author role="aut"><persName><forename type="first">Cédric</forename><surname>Demonceaux</surname></persName><email>cedric.demonceaux@u-bourgogne.fr</email><idno type="idhal">cedric-demonceaux</idno><idno type="halauthor">655037</idno><affiliation ref="#struct-22594"></affiliation></author><author role="aut"><persName><forename type="first">Pascal</forename><surname>Vasseur</surname></persName><email>pascal.vasseur@univ-rouen.fr</email><idno type="halauthor">665359</idno><affiliation ref="#struct-23832"></affiliation></author><author role="aut"><persName><forename type="first">Katsushi</forename><surname>Ikeuchi</surname></persName><email>ki@iis.u-tokyo.ac.jp</email><idno type="halauthor">723686</idno><affiliation ref="#struct-50647"></affiliation></author><editor role="depositor"><persName><forename>Cédric</forename><surname>Demonceaux</surname></persName><email>cedric.demonceaux@u-bourgogne.fr</email></editor></titleStmt><editionStmt><edition n="v1" type="current"><date type="whenSubmitted">2013-06-03 15:28:06</date><date type="whenWritten">2013</date><date type="whenModified">2016-03-09 01:06:06</date><date type="whenReleased">2013-06-03 15:28:06</date><date type="whenProduced">2013</date></edition><respStmt><resp>contributor</resp><name key="160834"><persName><forename>Cédric</forename><surname>Demonceaux</surname></persName><email>cedric.demonceaux@u-bourgogne.fr</email></name></respStmt></editionStmt><publicationStmt><distributor>CCSD</distributor><idno type="halId">hal-00829611</idno><idno type="halUri">https://hal.archives-ouvertes.fr/hal-00829611</idno><idno type="halBibtex">bazin:hal-00829611</idno><idno type="halRefHtml">IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2013, 35 (7), pp.1565-1576. <10.1109/TPAMI.2012.264></idno><idno type="halRef">IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2013, 35 (7), pp.1565-1576. <10.1109/TPAMI.2012.264></idno></publicationStmt><seriesStmt><idno type="stamp" n="CNRS">CNRS - Centre national de la recherche scientifique</idno><idno type="stamp" n="UNIV-LEHAVRE">Université du Havre</idno><idno type="stamp" n="UNIV-ROUEN">Université de Rouen</idno><idno type="stamp" n="LITIS">Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes</idno><idno type="stamp" n="ENSAM">Ecole Nationale Supérieure d'Arts et Métiers</idno><idno type="stamp" n="UNIV-BOURGOGNE">Université de Bourgogne</idno><idno type="stamp" n="LE2I" p="UNIV-BOURGOGNE">Laboratoire Electronique, Informatique et Image</idno><idno type="stamp" n="COMUE-NORMANDIE">Normandie Université</idno></seriesStmt><notesStmt><note type="audience" n="2">International</note><note type="popular" n="0">No</note><note type="peer" n="1">Yes</note></notesStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">A Branch and Bound Approach to Correspondence and Grouping Problems</title><author role="crp"><persName><forename type="first">Jean-Charles</forename><surname>Bazin</surname></persName><email>jcbazin@cvl.iis.u-tokyo.ac.jp</email><idno type="halAuthorId">681481</idno><affiliation ref="#struct-179740"></affiliation></author><author role="aut"><persName><forename type="first">Hongdong</forename><surname>Li</surname></persName><idno type="halAuthorId">856624</idno><affiliation ref="#struct-103314"></affiliation></author><author role="aut"><persName><forename type="first">Inso</forename><surname>Kweon</surname></persName><idno type="halAuthorId">355691</idno><affiliation ref="#struct-153498"></affiliation></author><author role="aut"><persName><forename type="first">Cédric</forename><surname>Demonceaux</surname></persName><email>cedric.demonceaux@u-bourgogne.fr</email><idno type="idHal">cedric-demonceaux</idno><idno type="halAuthorId">655037</idno><affiliation ref="#struct-22594"></affiliation></author><author role="aut"><persName><forename type="first">Pascal</forename><surname>Vasseur</surname></persName><email>pascal.vasseur@univ-rouen.fr</email><idno type="halAuthorId">665359</idno><affiliation ref="#struct-23832"></affiliation></author><author role="aut"><persName><forename type="first">Katsushi</forename><surname>Ikeuchi</surname></persName><email>ki@iis.u-tokyo.ac.jp</email><idno type="halAuthorId">723686</idno><affiliation ref="#struct-50647"></affiliation></author></analytic><monogr><idno type="halJournalId" status="VALID">5390</idno><idno type="issn">0162-8828</idno><title level="j">IEEE Transactions on Pattern Analysis and Machine Intelligence</title><imprint><publisher>Institute of Electrical and Electronics Engineers</publisher><biblScope unit="volume">35</biblScope><biblScope unit="issue">7</biblScope><biblScope unit="pp">1565-1576</biblScope><date type="datePub">2013</date></imprint></monogr><idno type="doi">10.1109/TPAMI.2012.264</idno></biblStruct></sourceDesc><profileDesc><langUsage><language ident="en">English</language></langUsage><textClass><keywords scheme="author"><term xml:lang="en">Optimization</term><term xml:lang="en">Feature extraction</term><term xml:lang="en">Geometry</term><term xml:lang="en">Computer vision</term><term xml:lang="en">Electronic mail</term><term xml:lang="en">Pattern matching</term><term xml:lang="en">Educational institutions</term><term xml:lang="en">branch-and-bound</term><term xml:lang="en">Mixed integer programming</term><term xml:lang="en">quadratic constraint</term><term xml:lang="en">bilinearities</term><term xml:lang="en">global optimization</term></keywords><classCode scheme="halDomain" n="info.info-cv">Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]</classCode><classCode scheme="halTypology" n="ART">Journal articles</classCode></textClass><abstract xml:lang="en">Data correspondence/grouping is a fundamental topic in computer vision. Finding feature correspondences is probably the most popular application of this topic and constitutes our main motivation. It is a key ingredient for various tasks including 3D reconstruction and object recognition. Existing feature correspondence methods are based on either local appearance similarity, or global geometric consistency, or a combination of both in some heuristic manner. None of these methods is fully satisfactory, especially with repetitive image textures or mis-matches. In this paper, we present a new algorithm that combines the benefits of both appearance-based and geometry-based methods, and mathematically guarantees a global optimization. Our algorithm accepts the two sets of features as input, and outputs the largest set of feature correspondences verifying both the appearance and geometric constraints. We formulate the problem as a mixed integer program, and solve it efficiently by a series of linear programs via branch-and-bound. We subsequently generalize our framework in the context of data correspondence/grouping under an unknown parametric model and show it can be applied to certain classes of computer vision problems. Our algorithm has been validated successfully on synthesized data and challenging real images.</abstract></profileDesc></hal></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/France/explor/LeHavreV1/Data/Hal/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000009 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Hal/Curation/biblio.hfd -nk 000009 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/France
|area= LeHavreV1
|flux= Hal
|étape= Curation
|type= RBID
|clé= Hal:hal-00829611
|texte= A Branch and Bound Approach to Correspondence and Grouping Problems
}}
| This area was generated with Dilib version V0.6.25. |  |