Target identification method and device, electronic equipment and storage medium

The invention relates to the technical field of image recognition, in particular to a target recognition method and device, electronic equipment and a storage medium. According to the invention, multiple affine transformations are carried out on the first feature map of the first frame image to obta...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: TIAN CHANGJIA, BAI SHIJIE
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 TIAN CHANGJIA
BAI SHIJIE
description The invention relates to the technical field of image recognition, in particular to a target recognition method and device, electronic equipment and a storage medium. According to the invention, multiple affine transformations are carried out on the first feature map of the first frame image to obtain multiple transformed feature maps, and the target rotation angle is determined through the rotation invariance score between each transformed feature map and the second feature map. And inputting the transformation feature map corresponding to the target rotation angle into a trained target rotation equivalent encoder to obtain a template feature vector, and further, based on a rotation invariance score between a query feature vector of the second frame image and the template feature vector, determining whether a candidate object in the second frame image is a target object. In this way, continuous recognition of the three-dimensionally rotating target object in the target video can be realized, and the recognit
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115424180A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115424180A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115424180A3</originalsourceid><addsrcrecordid>eNqNy70KwjAUhuEsDqLew3FXMFrBVYriJA7dS0i-1gPNj8mp128RL8DpXZ53rh6NyT2E2CEId2yNcAzkIc_oyARHDm-22BAGWMkxsCW8Rk5-Gr6gSMymx_Q4Hv1SzTozFKx-Xaj19dLUty1SbFGSsQiQtr5rfaz2lT7tzod_zAexCzd1</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Target identification method and device, electronic equipment and storage medium</title><source>esp@cenet</source><creator>TIAN CHANGJIA ; BAI SHIJIE</creator><creatorcontrib>TIAN CHANGJIA ; BAI SHIJIE</creatorcontrib><description>The invention relates to the technical field of image recognition, in particular to a target recognition method and device, electronic equipment and a storage medium. According to the invention, multiple affine transformations are carried out on the first feature map of the first frame image to obtain multiple transformed feature maps, and the target rotation angle is determined through the rotation invariance score between each transformed feature map and the second feature map. And inputting the transformation feature map corresponding to the target rotation angle into a trained target rotation equivalent encoder to obtain a template feature vector, and further, based on a rotation invariance score between a query feature vector of the second frame image and the template feature vector, determining whether a candidate object in the second frame image is a target object. In this way, continuous recognition of the three-dimensionally rotating target object in the target video can be realized, and the recognit</description><language>chi ; eng</language><subject>CALCULATING ; 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=20221202&amp;DB=EPODOC&amp;CC=CN&amp;NR=115424180A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25544,76292</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20221202&amp;DB=EPODOC&amp;CC=CN&amp;NR=115424180A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>TIAN CHANGJIA</creatorcontrib><creatorcontrib>BAI SHIJIE</creatorcontrib><title>Target identification method and device, electronic equipment and storage medium</title><description>The invention relates to the technical field of image recognition, in particular to a target recognition method and device, electronic equipment and a storage medium. According to the invention, multiple affine transformations are carried out on the first feature map of the first frame image to obtain multiple transformed feature maps, and the target rotation angle is determined through the rotation invariance score between each transformed feature map and the second feature map. And inputting the transformation feature map corresponding to the target rotation angle into a trained target rotation equivalent encoder to obtain a template feature vector, and further, based on a rotation invariance score between a query feature vector of the second frame image and the template feature vector, determining whether a candidate object in the second frame image is a target object. In this way, continuous recognition of the three-dimensionally rotating target object in the target video can be realized, and the recognit</description><subject>CALCULATING</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>eNqNy70KwjAUhuEsDqLew3FXMFrBVYriJA7dS0i-1gPNj8mp128RL8DpXZ53rh6NyT2E2CEId2yNcAzkIc_oyARHDm-22BAGWMkxsCW8Rk5-Gr6gSMymx_Q4Hv1SzTozFKx-Xaj19dLUty1SbFGSsQiQtr5rfaz2lT7tzod_zAexCzd1</recordid><startdate>20221202</startdate><enddate>20221202</enddate><creator>TIAN CHANGJIA</creator><creator>BAI SHIJIE</creator><scope>EVB</scope></search><sort><creationdate>20221202</creationdate><title>Target identification method and device, electronic equipment and storage medium</title><author>TIAN CHANGJIA ; BAI SHIJIE</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115424180A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2022</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>TIAN CHANGJIA</creatorcontrib><creatorcontrib>BAI SHIJIE</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>TIAN CHANGJIA</au><au>BAI SHIJIE</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Target identification method and device, electronic equipment and storage medium</title><date>2022-12-02</date><risdate>2022</risdate><abstract>The invention relates to the technical field of image recognition, in particular to a target recognition method and device, electronic equipment and a storage medium. According to the invention, multiple affine transformations are carried out on the first feature map of the first frame image to obtain multiple transformed feature maps, and the target rotation angle is determined through the rotation invariance score between each transformed feature map and the second feature map. And inputting the transformation feature map corresponding to the target rotation angle into a trained target rotation equivalent encoder to obtain a template feature vector, and further, based on a rotation invariance score between a query feature vector of the second frame image and the template feature vector, determining whether a candidate object in the second frame image is a target object. In this way, continuous recognition of the three-dimensionally rotating target object in the target video can be realized, and the recognit</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115424180A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title Target identification method and device, electronic equipment and storage medium
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T09%3A04%3A27IST&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=TIAN%20CHANGJIA&rft.date=2022-12-02&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115424180A%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