Stereo correspondence through feature grouping and maximal cliques

The authors propose a method for solving the stereo correspondence problem. The method consists of extracting local image structures and matching similar such structures between two images. Linear edge segments are extracted from both the left and right images. Each segment is characterized by its p...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 1989-11, Vol.11 (11), p.1168-1180
Main Authors: Horaud, R., Skordas, T.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Computer Science
Computer science
control theory
systems
Exact sciences and technology
Extraterrestrial measurements
Geometry
Graphics
Image segmentation
Image sensors
Layout
Pattern recognition. Digital image processing. Computational geometry
Stereo vision
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3
cites cdi_FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3
container_end_page 1180
container_issue 11
container_start_page 1168
container_title IEEE transactions on pattern analysis and machine intelligence
container_volume 11
creator Horaud, R.
Skordas, T.
description The authors propose a method for solving the stereo correspondence problem. The method consists of extracting local image structures and matching similar such structures between two images. Linear edge segments are extracted from both the left and right images. Each segment is characterized by its position and orientation in the image as well as its relationships with the nearby segments. A relational graph is thus built from each image. For each segment in one image as set of potential assignments is represented as a set of nodes in a correspondence graph. Arcs in the graph represent compatible assignments established on the basis of segment relationships. Stereo matching becomes equivalent to searching for sets of mutually compatible nodes in this graph. Sets are found by looking for maximal cliques. The maximal clique best suited to represent a stereo correspondence is selected using a benefit function. Numerous results obtained with this method are shown.< >
doi_str_mv 10.1109/34.42855
format article
fullrecord <record><control><sourceid>proquest_hal_p</sourceid><recordid>TN_cdi_proquest_miscellaneous_25476539</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>42855</ieee_id><sourcerecordid>28663481</sourcerecordid><originalsourceid>FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3</originalsourceid><addsrcrecordid>eNqNkMFLwzAYxYMoOKfg1VsPIoJ0Jk3SJkcd6oSBB_Uc0vTrFumamrSi_72ZHTt7-vh4P957PITOCZ4RguUtZTOWCc4P0IRIKlPKqTxEE0zyLBUiE8foJIQPjAnjmE7Q_WsPHlxinPcQOtdW0BpI-rV3w2qd1KD7wUOyim9n21Wi2yrZ6G-70U1iGvs5QDhFR7VuApzt7hS9Pz68zRfp8uXpeX63TA3DrE9LCabmHDCRjMii4MBZUZU8pwxMBaLKqaa6YFEpCZEZxRiKoqZGlzmVxtApuhl917pRnY8V_I9y2qrF3VLZ1lutMOZCSkm-SKSvRrrzbtuyVxsbDDSNbsENQWUij8niH2CsmccRI3g9gsa7EDzU-xIEq-32ijL1t31EL3eeOhjd1F63xoY9H5M54yxiFyNmAWCvjha_DSqKCg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>25476539</pqid></control><display><type>article</type><title>Stereo correspondence through feature grouping and maximal cliques</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Horaud, R. ; Skordas, T.</creator><creatorcontrib>Horaud, R. ; Skordas, T.</creatorcontrib><description>The authors propose a method for solving the stereo correspondence problem. The method consists of extracting local image structures and matching similar such structures between two images. Linear edge segments are extracted from both the left and right images. Each segment is characterized by its position and orientation in the image as well as its relationships with the nearby segments. A relational graph is thus built from each image. For each segment in one image as set of potential assignments is represented as a set of nodes in a correspondence graph. Arcs in the graph represent compatible assignments established on the basis of segment relationships. Stereo matching becomes equivalent to searching for sets of mutually compatible nodes in this graph. Sets are found by looking for maximal cliques. The maximal clique best suited to represent a stereo correspondence is selected using a benefit function. Numerous results obtained with this method are shown.&lt; &gt;</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>DOI: 10.1109/34.42855</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>Applied sciences ; Artificial intelligence ; Computer Science ; Computer science; control theory; systems ; Exact sciences and technology ; Extraterrestrial measurements ; Geometry ; Graphics ; Image segmentation ; Image sensors ; Layout ; Pattern recognition. Digital image processing. Computational geometry ; Stereo vision</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 1989-11, Vol.11 (11), p.1168-1180</ispartof><rights>1990 INIST-CNRS</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3</citedby><cites>FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3</cites><orcidid>0000-0001-5232-024X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/42855$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,314,776,780,881,27900,27901,54770</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=6635454$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://inria.hal.science/inria-00589991$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Horaud, R.</creatorcontrib><creatorcontrib>Skordas, T.</creatorcontrib><title>Stereo correspondence through feature grouping and maximal cliques</title><title>IEEE transactions on pattern analysis and machine intelligence</title><addtitle>TPAMI</addtitle><description>The authors propose a method for solving the stereo correspondence problem. The method consists of extracting local image structures and matching similar such structures between two images. Linear edge segments are extracted from both the left and right images. Each segment is characterized by its position and orientation in the image as well as its relationships with the nearby segments. A relational graph is thus built from each image. For each segment in one image as set of potential assignments is represented as a set of nodes in a correspondence graph. Arcs in the graph represent compatible assignments established on the basis of segment relationships. Stereo matching becomes equivalent to searching for sets of mutually compatible nodes in this graph. Sets are found by looking for maximal cliques. The maximal clique best suited to represent a stereo correspondence is selected using a benefit function. Numerous results obtained with this method are shown.&lt; &gt;</description><subject>Applied sciences</subject><subject>Artificial intelligence</subject><subject>Computer Science</subject><subject>Computer science; control theory; systems</subject><subject>Exact sciences and technology</subject><subject>Extraterrestrial measurements</subject><subject>Geometry</subject><subject>Graphics</subject><subject>Image segmentation</subject><subject>Image sensors</subject><subject>Layout</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Stereo vision</subject><issn>0162-8828</issn><issn>1939-3539</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>1989</creationdate><recordtype>article</recordtype><recordid>eNqNkMFLwzAYxYMoOKfg1VsPIoJ0Jk3SJkcd6oSBB_Uc0vTrFumamrSi_72ZHTt7-vh4P957PITOCZ4RguUtZTOWCc4P0IRIKlPKqTxEE0zyLBUiE8foJIQPjAnjmE7Q_WsPHlxinPcQOtdW0BpI-rV3w2qd1KD7wUOyim9n21Wi2yrZ6G-70U1iGvs5QDhFR7VuApzt7hS9Pz68zRfp8uXpeX63TA3DrE9LCabmHDCRjMii4MBZUZU8pwxMBaLKqaa6YFEpCZEZxRiKoqZGlzmVxtApuhl917pRnY8V_I9y2qrF3VLZ1lutMOZCSkm-SKSvRrrzbtuyVxsbDDSNbsENQWUij8niH2CsmccRI3g9gsa7EDzU-xIEq-32ijL1t31EL3eeOhjd1F63xoY9H5M54yxiFyNmAWCvjha_DSqKCg</recordid><startdate>19891101</startdate><enddate>19891101</enddate><creator>Horaud, R.</creator><creator>Skordas, T.</creator><general>IEEE</general><general>IEEE Computer Society</general><general>Institute of Electrical and Electronics Engineers</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0001-5232-024X</orcidid></search><sort><creationdate>19891101</creationdate><title>Stereo correspondence through feature grouping and maximal cliques</title><author>Horaud, R. ; Skordas, T.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>1989</creationdate><topic>Applied sciences</topic><topic>Artificial intelligence</topic><topic>Computer Science</topic><topic>Computer science; control theory; systems</topic><topic>Exact sciences and technology</topic><topic>Extraterrestrial measurements</topic><topic>Geometry</topic><topic>Graphics</topic><topic>Image segmentation</topic><topic>Image sensors</topic><topic>Layout</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Stereo vision</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Horaud, R.</creatorcontrib><creatorcontrib>Skordas, T.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Horaud, R.</au><au>Skordas, T.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Stereo correspondence through feature grouping and maximal cliques</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><stitle>TPAMI</stitle><date>1989-11-01</date><risdate>1989</risdate><volume>11</volume><issue>11</issue><spage>1168</spage><epage>1180</epage><pages>1168-1180</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><coden>ITPIDJ</coden><abstract>The authors propose a method for solving the stereo correspondence problem. The method consists of extracting local image structures and matching similar such structures between two images. Linear edge segments are extracted from both the left and right images. Each segment is characterized by its position and orientation in the image as well as its relationships with the nearby segments. A relational graph is thus built from each image. For each segment in one image as set of potential assignments is represented as a set of nodes in a correspondence graph. Arcs in the graph represent compatible assignments established on the basis of segment relationships. Stereo matching becomes equivalent to searching for sets of mutually compatible nodes in this graph. Sets are found by looking for maximal cliques. The maximal clique best suited to represent a stereo correspondence is selected using a benefit function. Numerous results obtained with this method are shown.&lt; &gt;</abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><doi>10.1109/34.42855</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0001-5232-024X</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 0162-8828
ispartof IEEE transactions on pattern analysis and machine intelligence, 1989-11, Vol.11 (11), p.1168-1180
issn 0162-8828
1939-3539
language eng
recordid cdi_proquest_miscellaneous_25476539
source IEEE Electronic Library (IEL) Journals
subjects Applied sciences
Artificial intelligence
Computer Science
Computer science
control theory
systems
Exact sciences and technology
Extraterrestrial measurements
Geometry
Graphics
Image segmentation
Image sensors
Layout
Pattern recognition. Digital image processing. Computational geometry
Stereo vision
title Stereo correspondence through feature grouping and maximal cliques
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-25T12%3A13%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_hal_p&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Stereo%20correspondence%20through%20feature%20grouping%20and%20maximal%20cliques&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=Horaud,%20R.&rft.date=1989-11-01&rft.volume=11&rft.issue=11&rft.spage=1168&rft.epage=1180&rft.pages=1168-1180&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/34.42855&rft_dat=%3Cproquest_hal_p%3E28663481%3C/proquest_hal_p%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c404t-b9ecf55e019419775e547db5634ecde8d63a3a74775b1192300e77f3cab639cc3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=25476539&rft_id=info:pmid/&rft_ieee_id=42855&rfr_iscdi=true