Different-source image registration method and system based on spatio-temporal joint information

The invention provides a different-source image registration method and system based on spatio-temporal joint information, and solves the problem of low registration precision caused by large gray difference and inaccurate feature information positioning of infrared and visible light different-sourc...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LIU SIQI, YANG BEIER, LI FANG, TANG SHANJUN, ZHAO BINGQING
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator LIU SIQI
YANG BEIER
LI FANG
TANG SHANJUN
ZHAO BINGQING
description The invention provides a different-source image registration method and system based on spatio-temporal joint information, and solves the problem of low registration precision caused by large gray difference and inaccurate feature information positioning of infrared and visible light different-source images. According to the method, a step-by-step registration frame is adopted, and a motion foreground in a scene is extracted in a foreground extraction and preprocessing process and used for calculation of a subsequent motion vector field; in the coarse registration process, foreground contour registration is completed, and targets in a scene are roughly aligned; in the precise registration process, precise matching of intra-frame feature points is completed, and spatial transformation matrix parameters are obtained through a matching library updated frame by frame. Test results of real acquisition of infrared and visible light sequence images show that accurate positioning of feature information of the differe
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116823899A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116823899A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116823899A3</originalsourceid><addsrcrecordid>eNqNizEOwjAQBNNQIOAPxwNShEgoKVEAUVHRB5Osg1Hss3xHwe8JiAdQrTQ7M8-ue2ctEoLmws_UgZw3AyhhcKLJqONAHnrnnkzoSV6i8HQzgp6mS-JHyScWOZmRHuyCkguWk__Gy2xmzShY_XaRrY-HS3PKEbnFlHcI0LY5F8W22pRVXe_Kf5w3K8Y-OA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Different-source image registration method and system based on spatio-temporal joint information</title><source>esp@cenet</source><creator>LIU SIQI ; YANG BEIER ; LI FANG ; TANG SHANJUN ; ZHAO BINGQING</creator><creatorcontrib>LIU SIQI ; YANG BEIER ; LI FANG ; TANG SHANJUN ; ZHAO BINGQING</creatorcontrib><description>The invention provides a different-source image registration method and system based on spatio-temporal joint information, and solves the problem of low registration precision caused by large gray difference and inaccurate feature information positioning of infrared and visible light different-source images. According to the method, a step-by-step registration frame is adopted, and a motion foreground in a scene is extracted in a foreground extraction and preprocessing process and used for calculation of a subsequent motion vector field; in the coarse registration process, foreground contour registration is completed, and targets in a scene are roughly aligned; in the precise registration process, precise matching of intra-frame feature points is completed, and spatial transformation matrix parameters are obtained through a matching library updated frame by frame. Test results of real acquisition of infrared and visible light sequence images show that accurate positioning of feature information of the differe</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ; PHYSICS</subject><creationdate>2023</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230929&amp;DB=EPODOC&amp;CC=CN&amp;NR=116823899A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230929&amp;DB=EPODOC&amp;CC=CN&amp;NR=116823899A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LIU SIQI</creatorcontrib><creatorcontrib>YANG BEIER</creatorcontrib><creatorcontrib>LI FANG</creatorcontrib><creatorcontrib>TANG SHANJUN</creatorcontrib><creatorcontrib>ZHAO BINGQING</creatorcontrib><title>Different-source image registration method and system based on spatio-temporal joint information</title><description>The invention provides a different-source image registration method and system based on spatio-temporal joint information, and solves the problem of low registration precision caused by large gray difference and inaccurate feature information positioning of infrared and visible light different-source images. According to the method, a step-by-step registration frame is adopted, and a motion foreground in a scene is extracted in a foreground extraction and preprocessing process and used for calculation of a subsequent motion vector field; in the coarse registration process, foreground contour registration is completed, and targets in a scene are roughly aligned; in the precise registration process, precise matching of intra-frame feature points is completed, and spatial transformation matrix parameters are obtained through a matching library updated frame by frame. Test results of real acquisition of infrared and visible light sequence images show that accurate positioning of feature information of the differe</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNizEOwjAQBNNQIOAPxwNShEgoKVEAUVHRB5Osg1Hss3xHwe8JiAdQrTQ7M8-ue2ctEoLmws_UgZw3AyhhcKLJqONAHnrnnkzoSV6i8HQzgp6mS-JHyScWOZmRHuyCkguWk__Gy2xmzShY_XaRrY-HS3PKEbnFlHcI0LY5F8W22pRVXe_Kf5w3K8Y-OA</recordid><startdate>20230929</startdate><enddate>20230929</enddate><creator>LIU SIQI</creator><creator>YANG BEIER</creator><creator>LI FANG</creator><creator>TANG SHANJUN</creator><creator>ZHAO BINGQING</creator><scope>EVB</scope></search><sort><creationdate>20230929</creationdate><title>Different-source image registration method and system based on spatio-temporal joint information</title><author>LIU SIQI ; YANG BEIER ; LI FANG ; TANG SHANJUN ; ZHAO BINGQING</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116823899A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>IMAGE DATA PROCESSING OR GENERATION, IN GENERAL</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LIU SIQI</creatorcontrib><creatorcontrib>YANG BEIER</creatorcontrib><creatorcontrib>LI FANG</creatorcontrib><creatorcontrib>TANG SHANJUN</creatorcontrib><creatorcontrib>ZHAO BINGQING</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LIU SIQI</au><au>YANG BEIER</au><au>LI FANG</au><au>TANG SHANJUN</au><au>ZHAO BINGQING</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Different-source image registration method and system based on spatio-temporal joint information</title><date>2023-09-29</date><risdate>2023</risdate><abstract>The invention provides a different-source image registration method and system based on spatio-temporal joint information, and solves the problem of low registration precision caused by large gray difference and inaccurate feature information positioning of infrared and visible light different-source images. According to the method, a step-by-step registration frame is adopted, and a motion foreground in a scene is extracted in a foreground extraction and preprocessing process and used for calculation of a subsequent motion vector field; in the coarse registration process, foreground contour registration is completed, and targets in a scene are roughly aligned; in the precise registration process, precise matching of intra-frame feature points is completed, and spatial transformation matrix parameters are obtained through a matching library updated frame by frame. Test results of real acquisition of infrared and visible light sequence images show that accurate positioning of feature information of the differe</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116823899A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
title Different-source image registration method and system based on spatio-temporal joint information
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T00%3A47%3A04IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=LIU%20SIQI&rft.date=2023-09-29&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116823899A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true