High-resolution remote sensing image change detection method of multi-channel U-shaped deep network

A high-resolution remote sensing image change detection method of a multi-channel U-shaped deep network comprises the following steps that two-stage images are preprocessed and then input into a proposed model, features of the two-stage images are extracted through three down-sampling channels adopt...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: DU XINGQI, SHAO PAN
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 DU XINGQI
SHAO PAN
description A high-resolution remote sensing image change detection method of a multi-channel U-shaped deep network comprises the following steps that two-stage images are preprocessed and then input into a proposed model, features of the two-stage images are extracted through three down-sampling channels adopting different strategies, and difference features of all scale features in the down-sampling process of a channel 1 and a channel 2 are calculated; cascading the highest layer features obtained by the three channels through down-sampling and the highest layer difference features of the channel 1 and the channel 2 as up-sampling input, cascading the features of each scale of the three channels and the difference features of each scale of the channel 1 and the channel 2 to an up-sampling mirror image feature layer through short connection in the up-sampling process, and solving a change probability graph; and calculating loss based on the change probability graph and the real change graph, training a network model th
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115035403A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115035403A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115035403A3</originalsourceid><addsrcrecordid>eNqNyjEKwjAUBuAsDqLe4XmAQEvtAaQonZx0LiH9mwSTvNCkeH2reACnb_m2QvfOWDkjs1-K40gzAhdQRswuGnJBGZC2Kq6MKNDfFVAsj8QThcUXJz8hwtNDZqsSxrUiUUR58fzci82kfMbh504cr5d710skHpCT0ljn0N3quq2a9lQ15-af8waqaz5o</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>High-resolution remote sensing image change detection method of multi-channel U-shaped deep network</title><source>esp@cenet</source><creator>DU XINGQI ; SHAO PAN</creator><creatorcontrib>DU XINGQI ; SHAO PAN</creatorcontrib><description>A high-resolution remote sensing image change detection method of a multi-channel U-shaped deep network comprises the following steps that two-stage images are preprocessed and then input into a proposed model, features of the two-stage images are extracted through three down-sampling channels adopting different strategies, and difference features of all scale features in the down-sampling process of a channel 1 and a channel 2 are calculated; cascading the highest layer features obtained by the three channels through down-sampling and the highest layer difference features of the channel 1 and the channel 2 as up-sampling input, cascading the features of each scale of the three channels and the difference features of each scale of the channel 1 and the channel 2 to an up-sampling mirror image feature layer through short connection in the up-sampling process, and solving a change probability graph; and calculating loss based on the change probability graph and the real change graph, training a network model th</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; COUNTING ; PHYSICS</subject><creationdate>2022</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=20220909&amp;DB=EPODOC&amp;CC=CN&amp;NR=115035403A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20220909&amp;DB=EPODOC&amp;CC=CN&amp;NR=115035403A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>DU XINGQI</creatorcontrib><creatorcontrib>SHAO PAN</creatorcontrib><title>High-resolution remote sensing image change detection method of multi-channel U-shaped deep network</title><description>A high-resolution remote sensing image change detection method of a multi-channel U-shaped deep network comprises the following steps that two-stage images are preprocessed and then input into a proposed model, features of the two-stage images are extracted through three down-sampling channels adopting different strategies, and difference features of all scale features in the down-sampling process of a channel 1 and a channel 2 are calculated; cascading the highest layer features obtained by the three channels through down-sampling and the highest layer difference features of the channel 1 and the channel 2 as up-sampling input, cascading the features of each scale of the three channels and the difference features of each scale of the channel 1 and the channel 2 to an up-sampling mirror image feature layer through short connection in the up-sampling process, and solving a change probability graph; and calculating loss based on the change probability graph and the real change graph, training a network model th</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>2022</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNyjEKwjAUBuAsDqLe4XmAQEvtAaQonZx0LiH9mwSTvNCkeH2reACnb_m2QvfOWDkjs1-K40gzAhdQRswuGnJBGZC2Kq6MKNDfFVAsj8QThcUXJz8hwtNDZqsSxrUiUUR58fzci82kfMbh504cr5d710skHpCT0ljn0N3quq2a9lQ15-af8waqaz5o</recordid><startdate>20220909</startdate><enddate>20220909</enddate><creator>DU XINGQI</creator><creator>SHAO PAN</creator><scope>EVB</scope></search><sort><creationdate>20220909</creationdate><title>High-resolution remote sensing image change detection method of multi-channel U-shaped deep network</title><author>DU XINGQI ; SHAO PAN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115035403A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</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>DU XINGQI</creatorcontrib><creatorcontrib>SHAO PAN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>DU XINGQI</au><au>SHAO PAN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>High-resolution remote sensing image change detection method of multi-channel U-shaped deep network</title><date>2022-09-09</date><risdate>2022</risdate><abstract>A high-resolution remote sensing image change detection method of a multi-channel U-shaped deep network comprises the following steps that two-stage images are preprocessed and then input into a proposed model, features of the two-stage images are extracted through three down-sampling channels adopting different strategies, and difference features of all scale features in the down-sampling process of a channel 1 and a channel 2 are calculated; cascading the highest layer features obtained by the three channels through down-sampling and the highest layer difference features of the channel 1 and the channel 2 as up-sampling input, cascading the features of each scale of the three channels and the difference features of each scale of the channel 1 and the channel 2 to an up-sampling mirror image feature layer through short connection in the up-sampling process, and solving a change probability graph; and calculating loss based on the change probability graph and the real change graph, training a network model th</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115035403A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title High-resolution remote sensing image change detection method of multi-channel U-shaped deep network
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T04%3A23%3A37IST&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=DU%20XINGQI&rft.date=2022-09-09&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115035403A%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