Multi-sensor image registration using edge-enhanced maximally stable extremal region

Image registration is an important topic in computer vision and many techniques have been developed. But when it comes to the multi-sensor images, intensity-based global methods often achieve poor results. In this paper, we propose an edge-enhanced maximally stable extremal region method (E-MSER) to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li Liu, Hongya Tuo, Tao Xu, Zhongliang Jing
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 905
container_issue
container_start_page 901
container_title
container_volume
creator Li Liu
Hongya Tuo
Tao Xu
Zhongliang Jing
description Image registration is an important topic in computer vision and many techniques have been developed. But when it comes to the multi-sensor images, intensity-based global methods often achieve poor results. In this paper, we propose an edge-enhanced maximally stable extremal region method (E-MSER) to improve the registration performance of multi-sensor images. It is obtained by combining edge enhancement with maximally stable extremal region (MSER) detector. Thus the region features can maintain stability through the changing image intensities. Criteria including matching score, repeatability, recall, precision and root-mean-square error (RMSE) are used for evaluation. Experiment results show that E-MSER outperforms other detectors with its registration accuracy reaching pixel-level.
doi_str_mv 10.1109/CISP.2012.6469944
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6469944</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6469944</ieee_id><sourcerecordid>6469944</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-bf1b3ad7c0386cada736cf365db4c62d557288d9418c443f85cd0d6538cadf123</originalsourceid><addsrcrecordid>eNpVkN1KAzEQhSMiKHUfQLzJC-yabP4vZfGnUFGwXpdsMrtGtqkkW2jf3qC98eowh_MNMwehG0oaSom565bvb01LaNtILo3h_AxVRmnKpWLESGbO_82CXaIq5y9CSMFlK_kVWr_spznUGWLeJRy2dgScYAx5TnYOu4j3OcQRgx-hhvhpowOPt_ZQktN0xHm2_QQYDnOC4vyiu3iNLgY7ZahOukAfjw_r7rlevT4tu_tVHagSc90PtGfWK0eYls56q5h0A5PC99zJ1guhWq294VQ7ztmghfPElzd0CQ-0ZQt0-7c3AMDmO5Wj0nFz6oL9AHVoU8c</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Multi-sensor image registration using edge-enhanced maximally stable extremal region</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Li Liu ; Hongya Tuo ; Tao Xu ; Zhongliang Jing</creator><creatorcontrib>Li Liu ; Hongya Tuo ; Tao Xu ; Zhongliang Jing</creatorcontrib><description>Image registration is an important topic in computer vision and many techniques have been developed. But when it comes to the multi-sensor images, intensity-based global methods often achieve poor results. In this paper, we propose an edge-enhanced maximally stable extremal region method (E-MSER) to improve the registration performance of multi-sensor images. It is obtained by combining edge enhancement with maximally stable extremal region (MSER) detector. Thus the region features can maintain stability through the changing image intensities. Criteria including matching score, repeatability, recall, precision and root-mean-square error (RMSE) are used for evaluation. Experiment results show that E-MSER outperforms other detectors with its registration accuracy reaching pixel-level.</description><identifier>ISBN: 9781467309653</identifier><identifier>ISBN: 1467309656</identifier><identifier>EISBN: 9781467309639</identifier><identifier>EISBN: 146730963X</identifier><identifier>EISBN: 1467309648</identifier><identifier>EISBN: 9781467309646</identifier><identifier>DOI: 10.1109/CISP.2012.6469944</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; Detectors ; E-MSER ; Feature extraction ; Image edge detection ; Image registration ; MSER ; Multi-sensor ; Performance evaluation ; Robustness ; Vectors</subject><ispartof>2012 5th International Congress on Image and Signal Processing, 2012, p.901-905</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6469944$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6469944$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Li Liu</creatorcontrib><creatorcontrib>Hongya Tuo</creatorcontrib><creatorcontrib>Tao Xu</creatorcontrib><creatorcontrib>Zhongliang Jing</creatorcontrib><title>Multi-sensor image registration using edge-enhanced maximally stable extremal region</title><title>2012 5th International Congress on Image and Signal Processing</title><addtitle>CISP</addtitle><description>Image registration is an important topic in computer vision and many techniques have been developed. But when it comes to the multi-sensor images, intensity-based global methods often achieve poor results. In this paper, we propose an edge-enhanced maximally stable extremal region method (E-MSER) to improve the registration performance of multi-sensor images. It is obtained by combining edge enhancement with maximally stable extremal region (MSER) detector. Thus the region features can maintain stability through the changing image intensities. Criteria including matching score, repeatability, recall, precision and root-mean-square error (RMSE) are used for evaluation. Experiment results show that E-MSER outperforms other detectors with its registration accuracy reaching pixel-level.</description><subject>Accuracy</subject><subject>Detectors</subject><subject>E-MSER</subject><subject>Feature extraction</subject><subject>Image edge detection</subject><subject>Image registration</subject><subject>MSER</subject><subject>Multi-sensor</subject><subject>Performance evaluation</subject><subject>Robustness</subject><subject>Vectors</subject><isbn>9781467309653</isbn><isbn>1467309656</isbn><isbn>9781467309639</isbn><isbn>146730963X</isbn><isbn>1467309648</isbn><isbn>9781467309646</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVkN1KAzEQhSMiKHUfQLzJC-yabP4vZfGnUFGwXpdsMrtGtqkkW2jf3qC98eowh_MNMwehG0oaSom565bvb01LaNtILo3h_AxVRmnKpWLESGbO_82CXaIq5y9CSMFlK_kVWr_spznUGWLeJRy2dgScYAx5TnYOu4j3OcQRgx-hhvhpowOPt_ZQktN0xHm2_QQYDnOC4vyiu3iNLgY7ZahOukAfjw_r7rlevT4tu_tVHagSc90PtGfWK0eYls56q5h0A5PC99zJ1guhWq294VQ7ztmghfPElzd0CQ-0ZQt0-7c3AMDmO5Wj0nFz6oL9AHVoU8c</recordid><startdate>201210</startdate><enddate>201210</enddate><creator>Li Liu</creator><creator>Hongya Tuo</creator><creator>Tao Xu</creator><creator>Zhongliang Jing</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201210</creationdate><title>Multi-sensor image registration using edge-enhanced maximally stable extremal region</title><author>Li Liu ; Hongya Tuo ; Tao Xu ; Zhongliang Jing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-bf1b3ad7c0386cada736cf365db4c62d557288d9418c443f85cd0d6538cadf123</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Accuracy</topic><topic>Detectors</topic><topic>E-MSER</topic><topic>Feature extraction</topic><topic>Image edge detection</topic><topic>Image registration</topic><topic>MSER</topic><topic>Multi-sensor</topic><topic>Performance evaluation</topic><topic>Robustness</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Li Liu</creatorcontrib><creatorcontrib>Hongya Tuo</creatorcontrib><creatorcontrib>Tao Xu</creatorcontrib><creatorcontrib>Zhongliang Jing</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Li Liu</au><au>Hongya Tuo</au><au>Tao Xu</au><au>Zhongliang Jing</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Multi-sensor image registration using edge-enhanced maximally stable extremal region</atitle><btitle>2012 5th International Congress on Image and Signal Processing</btitle><stitle>CISP</stitle><date>2012-10</date><risdate>2012</risdate><spage>901</spage><epage>905</epage><pages>901-905</pages><isbn>9781467309653</isbn><isbn>1467309656</isbn><eisbn>9781467309639</eisbn><eisbn>146730963X</eisbn><eisbn>1467309648</eisbn><eisbn>9781467309646</eisbn><abstract>Image registration is an important topic in computer vision and many techniques have been developed. But when it comes to the multi-sensor images, intensity-based global methods often achieve poor results. In this paper, we propose an edge-enhanced maximally stable extremal region method (E-MSER) to improve the registration performance of multi-sensor images. It is obtained by combining edge enhancement with maximally stable extremal region (MSER) detector. Thus the region features can maintain stability through the changing image intensities. Criteria including matching score, repeatability, recall, precision and root-mean-square error (RMSE) are used for evaluation. Experiment results show that E-MSER outperforms other detectors with its registration accuracy reaching pixel-level.</abstract><pub>IEEE</pub><doi>10.1109/CISP.2012.6469944</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISBN: 9781467309653
ispartof 2012 5th International Congress on Image and Signal Processing, 2012, p.901-905
issn
language eng
recordid cdi_ieee_primary_6469944
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Accuracy
Detectors
E-MSER
Feature extraction
Image edge detection
Image registration
MSER
Multi-sensor
Performance evaluation
Robustness
Vectors
title Multi-sensor image registration using edge-enhanced maximally stable extremal region
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-24T20%3A14%3A17IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Multi-sensor%20image%20registration%20using%20edge-enhanced%20maximally%20stable%20extremal%20region&rft.btitle=2012%205th%20International%20Congress%20on%20Image%20and%20Signal%20Processing&rft.au=Li%20Liu&rft.date=2012-10&rft.spage=901&rft.epage=905&rft.pages=901-905&rft.isbn=9781467309653&rft.isbn_list=1467309656&rft_id=info:doi/10.1109/CISP.2012.6469944&rft_dat=%3Cieee_6IE%3E6469944%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467309639&rft.eisbn_list=146730963X&rft.eisbn_list=1467309648&rft.eisbn_list=9781467309646&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6469944&rfr_iscdi=true