End-to-end SAR-visible light image template matching method based on deep learning

The invention relates to an end-to-end SAR-visible light image template matching method based on deep learning, and belongs to the technical field of image processing. The method comprises the steps of firstly establishing a visible light-SAR heterogeneous image data set, then performing denoising p...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	LI YIQIANG, CAO XIAOHE, OH JONG-GUN, CHENG CHEN, WANG SHENGZHE, ZHENG JIE, LUO ZHENBAO, KANG PENGXIN, LIAO DAN, HUO YIHUA, HUO JIANLIANG, GUAN WEI
Format:	Patent
Sprache:	chi ; eng
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
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	LI YIQIANG CAO XIAOHE OH JONG-GUN CHENG CHEN WANG SHENGZHE ZHENG JIE LUO ZHENBAO KANG PENGXIN LIAO DAN HUO YIHUA HUO JIANLIANG GUAN WEI
description	The invention relates to an end-to-end SAR-visible light image template matching method based on deep learning, and belongs to the technical field of image processing. The method comprises the steps of firstly establishing a visible light-SAR heterogeneous image data set, then performing denoising processing on an SAR image, then performing edge extraction on a visible light image and the SAR image by using a Sobel edge detection algorithm, highlighting the edge features of the visible light image and the SAR image to obtain an edge extraction image, and finally obtaining a visible light-SAR heterogeneous image. And finally, establishing a heterogeneous image template matching algorithm based on a dense connection type twin network and a region regression network, and inputting the processed heterogeneous image groups into a matching network at the same time to realize a matching task. 本发明涉及一种基于深度学习的端到端SAR-可见光图像模板匹配方法，属于图像处理技术领域。该方法首先建立可见光-SAR异源图像数据集，然后对SAR图像进行去噪处理，之后，使用Sobel边缘检测算法对可见光图像和SAR图像进行边缘提取，突出二者边缘特征，
format	Patent
fullrecord	<record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116310430A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116310430A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116310430A3</originalsourceid><addsrcrecordid>eNqNyr0KwjAUhuEsDqLew_ECAi0R91IqTg7VvZw2n00gf5iD16-DF-D0Ds-7VeOQrJaskSzdu1G_ffVzAAW_OiEfeQUJYgksoMiyOJ9WihCXLc1cYSknskChAH6lr-7V5smh4vDrTh0vw6O_apQ8oRZekCBTf2vbs2mbk2k688_zAYL0Nvg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>End-to-end SAR-visible light image template matching method based on deep learning</title><source>esp@cenet</source><creator>LI YIQIANG ; CAO XIAOHE ; OH JONG-GUN ; CHENG CHEN ; WANG SHENGZHE ; ZHENG JIE ; LUO ZHENBAO ; KANG PENGXIN ; LIAO DAN ; HUO YIHUA ; HUO JIANLIANG ; GUAN WEI</creator><creatorcontrib>LI YIQIANG ; CAO XIAOHE ; OH JONG-GUN ; CHENG CHEN ; WANG SHENGZHE ; ZHENG JIE ; LUO ZHENBAO ; KANG PENGXIN ; LIAO DAN ; HUO YIHUA ; HUO JIANLIANG ; GUAN WEI</creatorcontrib><description>The invention relates to an end-to-end SAR-visible light image template matching method based on deep learning, and belongs to the technical field of image processing. The method comprises the steps of firstly establishing a visible light-SAR heterogeneous image data set, then performing denoising processing on an SAR image, then performing edge extraction on a visible light image and the SAR image by using a Sobel edge detection algorithm, highlighting the edge features of the visible light image and the SAR image to obtain an edge extraction image, and finally obtaining a visible light-SAR heterogeneous image. And finally, establishing a heterogeneous image template matching algorithm based on a dense connection type twin network and a region regression network, and inputting the processed heterogeneous image groups into a matching network at the same time to realize a matching task. 本发明涉及一种基于深度学习的端到端SAR-可见光图像模板匹配方法，属于图像处理技术领域。该方法首先建立可见光-SAR异源图像数据集，然后对SAR图像进行去噪处理，之后，使用Sobel边缘检测算法对可见光图像和SAR图像进行边缘提取，突出二者边缘特征，</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; 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&date=20230623&DB=EPODOC&CC=CN&NR=116310430A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230623&DB=EPODOC&CC=CN&NR=116310430A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LI YIQIANG</creatorcontrib><creatorcontrib>CAO XIAOHE</creatorcontrib><creatorcontrib>OH JONG-GUN</creatorcontrib><creatorcontrib>CHENG CHEN</creatorcontrib><creatorcontrib>WANG SHENGZHE</creatorcontrib><creatorcontrib>ZHENG JIE</creatorcontrib><creatorcontrib>LUO ZHENBAO</creatorcontrib><creatorcontrib>KANG PENGXIN</creatorcontrib><creatorcontrib>LIAO DAN</creatorcontrib><creatorcontrib>HUO YIHUA</creatorcontrib><creatorcontrib>HUO JIANLIANG</creatorcontrib><creatorcontrib>GUAN WEI</creatorcontrib><title>End-to-end SAR-visible light image template matching method based on deep learning</title><description>The invention relates to an end-to-end SAR-visible light image template matching method based on deep learning, and belongs to the technical field of image processing. The method comprises the steps of firstly establishing a visible light-SAR heterogeneous image data set, then performing denoising processing on an SAR image, then performing edge extraction on a visible light image and the SAR image by using a Sobel edge detection algorithm, highlighting the edge features of the visible light image and the SAR image to obtain an edge extraction image, and finally obtaining a visible light-SAR heterogeneous image. And finally, establishing a heterogeneous image template matching algorithm based on a dense connection type twin network and a region regression network, and inputting the processed heterogeneous image groups into a matching network at the same time to realize a matching task. 本发明涉及一种基于深度学习的端到端SAR-可见光图像模板匹配方法，属于图像处理技术领域。该方法首先建立可见光-SAR异源图像数据集，然后对SAR图像进行去噪处理，之后，使用Sobel边缘检测算法对可见光图像和SAR图像进行边缘提取，突出二者边缘特征，</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyr0KwjAUhuEsDqLew_ECAi0R91IqTg7VvZw2n00gf5iD16-DF-D0Ds-7VeOQrJaskSzdu1G_ffVzAAW_OiEfeQUJYgksoMiyOJ9WihCXLc1cYSknskChAH6lr-7V5smh4vDrTh0vw6O_apQ8oRZekCBTf2vbs2mbk2k688_zAYL0Nvg</recordid><startdate>20230623</startdate><enddate>20230623</enddate><creator>LI YIQIANG</creator><creator>CAO XIAOHE</creator><creator>OH JONG-GUN</creator><creator>CHENG CHEN</creator><creator>WANG SHENGZHE</creator><creator>ZHENG JIE</creator><creator>LUO ZHENBAO</creator><creator>KANG PENGXIN</creator><creator>LIAO DAN</creator><creator>HUO YIHUA</creator><creator>HUO JIANLIANG</creator><creator>GUAN WEI</creator><scope>EVB</scope></search><sort><creationdate>20230623</creationdate><title>End-to-end SAR-visible light image template matching method based on deep learning</title><author>LI YIQIANG ; CAO XIAOHE ; OH JONG-GUN ; CHENG CHEN ; WANG SHENGZHE ; ZHENG JIE ; LUO ZHENBAO ; KANG PENGXIN ; LIAO DAN ; HUO YIHUA ; HUO JIANLIANG ; GUAN WEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116310430A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>LI YIQIANG</creatorcontrib><creatorcontrib>CAO XIAOHE</creatorcontrib><creatorcontrib>OH JONG-GUN</creatorcontrib><creatorcontrib>CHENG CHEN</creatorcontrib><creatorcontrib>WANG SHENGZHE</creatorcontrib><creatorcontrib>ZHENG JIE</creatorcontrib><creatorcontrib>LUO ZHENBAO</creatorcontrib><creatorcontrib>KANG PENGXIN</creatorcontrib><creatorcontrib>LIAO DAN</creatorcontrib><creatorcontrib>HUO YIHUA</creatorcontrib><creatorcontrib>HUO JIANLIANG</creatorcontrib><creatorcontrib>GUAN WEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LI YIQIANG</au><au>CAO XIAOHE</au><au>OH JONG-GUN</au><au>CHENG CHEN</au><au>WANG SHENGZHE</au><au>ZHENG JIE</au><au>LUO ZHENBAO</au><au>KANG PENGXIN</au><au>LIAO DAN</au><au>HUO YIHUA</au><au>HUO JIANLIANG</au><au>GUAN WEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>End-to-end SAR-visible light image template matching method based on deep learning</title><date>2023-06-23</date><risdate>2023</risdate><abstract>The invention relates to an end-to-end SAR-visible light image template matching method based on deep learning, and belongs to the technical field of image processing. The method comprises the steps of firstly establishing a visible light-SAR heterogeneous image data set, then performing denoising processing on an SAR image, then performing edge extraction on a visible light image and the SAR image by using a Sobel edge detection algorithm, highlighting the edge features of the visible light image and the SAR image to obtain an edge extraction image, and finally obtaining a visible light-SAR heterogeneous image. And finally, establishing a heterogeneous image template matching algorithm based on a dense connection type twin network and a region regression network, and inputting the processed heterogeneous image groups into a matching network at the same time to realize a matching task. 本发明涉及一种基于深度学习的端到端SAR-可见光图像模板匹配方法，属于图像处理技术领域。该方法首先建立可见光-SAR异源图像数据集，然后对SAR图像进行去噪处理，之后，使用Sobel边缘检测算法对可见光图像和SAR图像进行边缘提取，突出二者边缘特征，</abstract><oa>free_for_read</oa></addata></record>
fulltext	fulltext_linktorsrc
identifier
ispartof
issn
language	chi ; eng
recordid	cdi_epo_espacenet_CN116310430A
source	esp@cenet
subjects	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING PHYSICS
title	End-to-end SAR-visible light image template matching method based on deep learning
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-11T20%3A58%3A16IST&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=LI%20YIQIANG&rft.date=2023-06-23&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116310430A%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