A robust algorithm for feature point matching

Image matching is a key problem of computer vision and frequently used in 3D-model reconstruction, object recognition, image alignment, camera self-calibration and so on. Feature point matching is the most common one among all kinds of image matching. The result of feature point matching is affected...

Full description

Saved in:
Bibliographic Details
Published in:Computers & graphics 2002-06, Vol.26 (3), p.429-436
Main Authors: Zhou, Ji, Shi, Jiaoying
Format: Article
Language:English
Subjects:
Extended assignment problem
Feature point matching
Match strength
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-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93
cites cdi_FETCH-LOGICAL-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93
container_end_page 436
container_issue 3
container_start_page 429
container_title Computers & graphics
container_volume 26
creator Zhou, Ji
Shi, Jiaoying
description Image matching is a key problem of computer vision and frequently used in 3D-model reconstruction, object recognition, image alignment, camera self-calibration and so on. Feature point matching is the most common one among all kinds of image matching. The result of feature point matching is affected greatly by many factors, such as object occlusions, lighting conditions and noises, therefore it is important to find a robust algorithm of feature point matching. In this paper, we extend the method for standard assignment algorithm to solve extended assignment problem and propose a new feature point matching algorithm. It employs the condition that the depth of the scene is local continuous as extra constraint, and uses the method for extended assignment problem to do global optimization. Moreover, this algorithm only needs two optimizations and can be implemented with almost complete matrix computation, so its efficiency is higher than the existing algorithms. Experiments show that the results of the algorithm are satisfactory.
doi_str_mv 10.1016/S0097-8493(02)00086-9
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_27680289</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0097849302000869</els_id><sourcerecordid>27680289</sourcerecordid><originalsourceid>FETCH-LOGICAL-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93</originalsourceid><addsrcrecordid>eNqFkEtLAzEYRYMoWKs_QZiV6GI0j3kkKymlPqDgQl2HTPKljcxMapIR_PfOtOLW1d2ce-FchC4JviWYVHevGIs654Vg15jeYIx5lYsjNCO8Znld8eIYzf6QU3QW48cIUVoVM5QvsuCbIaZMtRsfXNp2mfUhs6DSECDbedenrFNJb12_OUcnVrURLn5zjt4fVm_Lp3z98vi8XKxzzRhPOTS0prwqhdCgy7JsSm6tMQqMEUw1xJoGDBPK0ga00Kqoba1AUEZqGCHB5ujqsLsL_nOAmGTnooa2VT34IUo6WmHKJ7A8gDr4GANYuQuuU-FbEiync-T-HDmZS0zl_hw59e4PPRgtvhwEGbWDXoNxAXSSxrt_Fn4Am2ltJg</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>27680289</pqid></control><display><type>article</type><title>A robust algorithm for feature point matching</title><source>ScienceDirect Journals</source><creator>Zhou, Ji ; Shi, Jiaoying</creator><creatorcontrib>Zhou, Ji ; Shi, Jiaoying</creatorcontrib><description>Image matching is a key problem of computer vision and frequently used in 3D-model reconstruction, object recognition, image alignment, camera self-calibration and so on. Feature point matching is the most common one among all kinds of image matching. The result of feature point matching is affected greatly by many factors, such as object occlusions, lighting conditions and noises, therefore it is important to find a robust algorithm of feature point matching. In this paper, we extend the method for standard assignment algorithm to solve extended assignment problem and propose a new feature point matching algorithm. It employs the condition that the depth of the scene is local continuous as extra constraint, and uses the method for extended assignment problem to do global optimization. Moreover, this algorithm only needs two optimizations and can be implemented with almost complete matrix computation, so its efficiency is higher than the existing algorithms. Experiments show that the results of the algorithm are satisfactory.</description><identifier>ISSN: 0097-8493</identifier><identifier>EISSN: 1873-7684</identifier><identifier>DOI: 10.1016/S0097-8493(02)00086-9</identifier><language>eng</language><publisher>Elsevier Ltd</publisher><subject>Extended assignment problem ; Feature point matching ; Match strength</subject><ispartof>Computers &amp; graphics, 2002-06, Vol.26 (3), p.429-436</ispartof><rights>2002 Elsevier Science Ltd</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93</citedby><cites>FETCH-LOGICAL-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27923,27924</link.rule.ids></links><search><creatorcontrib>Zhou, Ji</creatorcontrib><creatorcontrib>Shi, Jiaoying</creatorcontrib><title>A robust algorithm for feature point matching</title><title>Computers &amp; graphics</title><description>Image matching is a key problem of computer vision and frequently used in 3D-model reconstruction, object recognition, image alignment, camera self-calibration and so on. Feature point matching is the most common one among all kinds of image matching. The result of feature point matching is affected greatly by many factors, such as object occlusions, lighting conditions and noises, therefore it is important to find a robust algorithm of feature point matching. In this paper, we extend the method for standard assignment algorithm to solve extended assignment problem and propose a new feature point matching algorithm. It employs the condition that the depth of the scene is local continuous as extra constraint, and uses the method for extended assignment problem to do global optimization. Moreover, this algorithm only needs two optimizations and can be implemented with almost complete matrix computation, so its efficiency is higher than the existing algorithms. Experiments show that the results of the algorithm are satisfactory.</description><subject>Extended assignment problem</subject><subject>Feature point matching</subject><subject>Match strength</subject><issn>0097-8493</issn><issn>1873-7684</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2002</creationdate><recordtype>article</recordtype><recordid>eNqFkEtLAzEYRYMoWKs_QZiV6GI0j3kkKymlPqDgQl2HTPKljcxMapIR_PfOtOLW1d2ce-FchC4JviWYVHevGIs654Vg15jeYIx5lYsjNCO8Znld8eIYzf6QU3QW48cIUVoVM5QvsuCbIaZMtRsfXNp2mfUhs6DSECDbedenrFNJb12_OUcnVrURLn5zjt4fVm_Lp3z98vi8XKxzzRhPOTS0prwqhdCgy7JsSm6tMQqMEUw1xJoGDBPK0ga00Kqoba1AUEZqGCHB5ujqsLsL_nOAmGTnooa2VT34IUo6WmHKJ7A8gDr4GANYuQuuU-FbEiync-T-HDmZS0zl_hw59e4PPRgtvhwEGbWDXoNxAXSSxrt_Fn4Am2ltJg</recordid><startdate>20020601</startdate><enddate>20020601</enddate><creator>Zhou, Ji</creator><creator>Shi, Jiaoying</creator><general>Elsevier Ltd</general><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></search><sort><creationdate>20020601</creationdate><title>A robust algorithm for feature point matching</title><author>Zhou, Ji ; Shi, Jiaoying</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2002</creationdate><topic>Extended assignment problem</topic><topic>Feature point matching</topic><topic>Match strength</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zhou, Ji</creatorcontrib><creatorcontrib>Shi, Jiaoying</creatorcontrib><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><jtitle>Computers &amp; graphics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zhou, Ji</au><au>Shi, Jiaoying</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A robust algorithm for feature point matching</atitle><jtitle>Computers &amp; graphics</jtitle><date>2002-06-01</date><risdate>2002</risdate><volume>26</volume><issue>3</issue><spage>429</spage><epage>436</epage><pages>429-436</pages><issn>0097-8493</issn><eissn>1873-7684</eissn><abstract>Image matching is a key problem of computer vision and frequently used in 3D-model reconstruction, object recognition, image alignment, camera self-calibration and so on. Feature point matching is the most common one among all kinds of image matching. The result of feature point matching is affected greatly by many factors, such as object occlusions, lighting conditions and noises, therefore it is important to find a robust algorithm of feature point matching. In this paper, we extend the method for standard assignment algorithm to solve extended assignment problem and propose a new feature point matching algorithm. It employs the condition that the depth of the scene is local continuous as extra constraint, and uses the method for extended assignment problem to do global optimization. Moreover, this algorithm only needs two optimizations and can be implemented with almost complete matrix computation, so its efficiency is higher than the existing algorithms. Experiments show that the results of the algorithm are satisfactory.</abstract><pub>Elsevier Ltd</pub><doi>10.1016/S0097-8493(02)00086-9</doi><tpages>8</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0097-8493
ispartof Computers & graphics, 2002-06, Vol.26 (3), p.429-436
issn 0097-8493
1873-7684
language eng
recordid cdi_proquest_miscellaneous_27680289
source ScienceDirect Journals
subjects Extended assignment problem
Feature point matching
Match strength
title A robust algorithm for feature point matching
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-08T10%3A38%3A19IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20robust%20algorithm%20for%20feature%20point%20matching&rft.jtitle=Computers%20&%20graphics&rft.au=Zhou,%20Ji&rft.date=2002-06-01&rft.volume=26&rft.issue=3&rft.spage=429&rft.epage=436&rft.pages=429-436&rft.issn=0097-8493&rft.eissn=1873-7684&rft_id=info:doi/10.1016/S0097-8493(02)00086-9&rft_dat=%3Cproquest_cross%3E27680289%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c338t-eb27286599cec555b58ffddaedd93ab1fdbed39af2bec9ca47f7ae92317eaed93%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=27680289&rft_id=info:pmid/&rfr_iscdi=true