Vehicle re-identification method and device, storage medium and electronic equipment

The invention provides a vehicle re-identification method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The vehicle re-identification method comprises the following steps: acquiring an image of a to-be-identified vehicle; acquiring sub...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: LIU YUAN, CHEN YING, ZHAO JIZHUANG, JIA GUANYI, CHENG SHUAI
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 YUAN
CHEN YING
ZHAO JIZHUANG
JIA GUANYI
CHENG SHUAI
description The invention provides a vehicle re-identification method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The vehicle re-identification method comprises the following steps: acquiring an image of a to-be-identified vehicle; acquiring sub-images and key point features of the to-be-identified vehicle based on a first neural network, and forming an image feature group; inputting the image feature group into a second neural network, wherein the second neural network extracts global features of the to-be-identified vehicle; splicing and fusing the global features and the corresponding key point features to obtain a fused feature map; and based on the matching operation of the fused feature map and a feature warehouse, determining an identified vehicle. The key point features obtained based on the original image are richer and more fidelity in information, feature loss caused by zooming is reduced, the key point features and global features are fused, a
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116434178A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116434178A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116434178A3</originalsourceid><addsrcrecordid>eNqNjL0KwjAURrM4iPoO190OoUW7SlGcnIprCclXeyF_JqnPbxEfwOkM53DWon9gYm1BCRUb-MIja1U4eHIoUzCkvCGDN2scKJeQ1BOLMjy7r4KFLil41oTXzNEtj61Yjcpm7H7ciP310ne3CjEMyFFpeJShu0t5bOpGntpz_U_zAZovOOg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Vehicle re-identification method and device, storage medium and electronic equipment</title><source>esp@cenet</source><creator>LIU YUAN ; CHEN YING ; ZHAO JIZHUANG ; JIA GUANYI ; CHENG SHUAI</creator><creatorcontrib>LIU YUAN ; CHEN YING ; ZHAO JIZHUANG ; JIA GUANYI ; CHENG SHUAI</creatorcontrib><description>The invention provides a vehicle re-identification method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The vehicle re-identification method comprises the following steps: acquiring an image of a to-be-identified vehicle; acquiring sub-images and key point features of the to-be-identified vehicle based on a first neural network, and forming an image feature group; inputting the image feature group into a second neural network, wherein the second neural network extracts global features of the to-be-identified vehicle; splicing and fusing the global features and the corresponding key point features to obtain a fused feature map; and based on the matching operation of the fused feature map and a feature warehouse, determining an identified vehicle. The key point features obtained based on the original image are richer and more fidelity in information, feature loss caused by zooming is reduced, the key point features and global features are fused, a</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&amp;date=20230714&amp;DB=EPODOC&amp;CC=CN&amp;NR=116434178A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25543,76293</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230714&amp;DB=EPODOC&amp;CC=CN&amp;NR=116434178A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>LIU YUAN</creatorcontrib><creatorcontrib>CHEN YING</creatorcontrib><creatorcontrib>ZHAO JIZHUANG</creatorcontrib><creatorcontrib>JIA GUANYI</creatorcontrib><creatorcontrib>CHENG SHUAI</creatorcontrib><title>Vehicle re-identification method and device, storage medium and electronic equipment</title><description>The invention provides a vehicle re-identification method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The vehicle re-identification method comprises the following steps: acquiring an image of a to-be-identified vehicle; acquiring sub-images and key point features of the to-be-identified vehicle based on a first neural network, and forming an image feature group; inputting the image feature group into a second neural network, wherein the second neural network extracts global features of the to-be-identified vehicle; splicing and fusing the global features and the corresponding key point features to obtain a fused feature map; and based on the matching operation of the fused feature map and a feature warehouse, determining an identified vehicle. The key point features obtained based on the original image are richer and more fidelity in information, feature loss caused by zooming is reduced, the key point features and global features are fused, a</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>eNqNjL0KwjAURrM4iPoO190OoUW7SlGcnIprCclXeyF_JqnPbxEfwOkM53DWon9gYm1BCRUb-MIja1U4eHIoUzCkvCGDN2scKJeQ1BOLMjy7r4KFLil41oTXzNEtj61Yjcpm7H7ciP310ne3CjEMyFFpeJShu0t5bOpGntpz_U_zAZovOOg</recordid><startdate>20230714</startdate><enddate>20230714</enddate><creator>LIU YUAN</creator><creator>CHEN YING</creator><creator>ZHAO JIZHUANG</creator><creator>JIA GUANYI</creator><creator>CHENG SHUAI</creator><scope>EVB</scope></search><sort><creationdate>20230714</creationdate><title>Vehicle re-identification method and device, storage medium and electronic equipment</title><author>LIU YUAN ; CHEN YING ; ZHAO JIZHUANG ; JIA GUANYI ; CHENG SHUAI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116434178A3</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>LIU YUAN</creatorcontrib><creatorcontrib>CHEN YING</creatorcontrib><creatorcontrib>ZHAO JIZHUANG</creatorcontrib><creatorcontrib>JIA GUANYI</creatorcontrib><creatorcontrib>CHENG SHUAI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>LIU YUAN</au><au>CHEN YING</au><au>ZHAO JIZHUANG</au><au>JIA GUANYI</au><au>CHENG SHUAI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Vehicle re-identification method and device, storage medium and electronic equipment</title><date>2023-07-14</date><risdate>2023</risdate><abstract>The invention provides a vehicle re-identification method and device, a storage medium and electronic equipment, and relates to the technical field of image processing. The vehicle re-identification method comprises the following steps: acquiring an image of a to-be-identified vehicle; acquiring sub-images and key point features of the to-be-identified vehicle based on a first neural network, and forming an image feature group; inputting the image feature group into a second neural network, wherein the second neural network extracts global features of the to-be-identified vehicle; splicing and fusing the global features and the corresponding key point features to obtain a fused feature map; and based on the matching operation of the fused feature map and a feature warehouse, determining an identified vehicle. The key point features obtained based on the original image are richer and more fidelity in information, feature loss caused by zooming is reduced, the key point features and global features are fused, a</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116434178A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Vehicle re-identification method and device, storage medium and electronic equipment
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-24T05%3A55%3A12IST&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%20YUAN&rft.date=2023-07-14&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116434178A%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