Target positioning method and related equipment thereof

The invention discloses a target positioning method and related equipment thereof, and the method comprises the steps: obtaining a to-be-processed image and first text prompt information, the first text prompt information being description information of a target needing to be retrieved from the to-...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: WANG JIN, HUANG BO, CHI ZIQIU, LI YIFEI
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 WANG JIN
HUANG BO
CHI ZIQIU
LI YIFEI
description The invention discloses a target positioning method and related equipment thereof, and the method comprises the steps: obtaining a to-be-processed image and first text prompt information, the first text prompt information being description information of a target needing to be retrieved from the to-be-processed image; based on the to-be-processed image and the first text prompt information, positioning a bounding box of a target in the to-be-processed image through a preset multi-modal large model to obtain a positioning result; wherein the preset multi-modal large model is obtained by training a basic multi-modal large model on the basis of a preset bounding box positioning data set, each piece of data in the preset bounding box positioning data set comprises a first data set and a bounding box label corresponding to the first data set, the bounding box label and the first data set are in an N-to-1 relationship, N is greater than or equal to 0, and the first data set is a first data set; the first data set c
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN118568289A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN118568289A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN118568289A3</originalsourceid><addsrcrecordid>eNrjZDAPSSxKTy1RKMgvzizJzM_LzEtXyE0tychPUUjMS1EoSs1JLElNUUgtLM0syE3NK1EoyUgtSs1P42FgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoYWpmYWRhaWjsbEqAEABOcucg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Target positioning method and related equipment thereof</title><source>esp@cenet</source><creator>WANG JIN ; HUANG BO ; CHI ZIQIU ; LI YIFEI</creator><creatorcontrib>WANG JIN ; HUANG BO ; CHI ZIQIU ; LI YIFEI</creatorcontrib><description>The invention discloses a target positioning method and related equipment thereof, and the method comprises the steps: obtaining a to-be-processed image and first text prompt information, the first text prompt information being description information of a target needing to be retrieved from the to-be-processed image; based on the to-be-processed image and the first text prompt information, positioning a bounding box of a target in the to-be-processed image through a preset multi-modal large model to obtain a positioning result; wherein the preset multi-modal large model is obtained by training a basic multi-modal large model on the basis of a preset bounding box positioning data set, each piece of data in the preset bounding box positioning data set comprises a first data set and a bounding box label corresponding to the first data set, the bounding box label and the first data set are in an N-to-1 relationship, N is greater than or equal to 0, and the first data set is a first data set; the first data set c</description><language>chi ; eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</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=20240830&amp;DB=EPODOC&amp;CC=CN&amp;NR=118568289A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240830&amp;DB=EPODOC&amp;CC=CN&amp;NR=118568289A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG JIN</creatorcontrib><creatorcontrib>HUANG BO</creatorcontrib><creatorcontrib>CHI ZIQIU</creatorcontrib><creatorcontrib>LI YIFEI</creatorcontrib><title>Target positioning method and related equipment thereof</title><description>The invention discloses a target positioning method and related equipment thereof, and the method comprises the steps: obtaining a to-be-processed image and first text prompt information, the first text prompt information being description information of a target needing to be retrieved from the to-be-processed image; based on the to-be-processed image and the first text prompt information, positioning a bounding box of a target in the to-be-processed image through a preset multi-modal large model to obtain a positioning result; wherein the preset multi-modal large model is obtained by training a basic multi-modal large model on the basis of a preset bounding box positioning data set, each piece of data in the preset bounding box positioning data set comprises a first data set and a bounding box label corresponding to the first data set, the bounding box label and the first data set are in an N-to-1 relationship, N is greater than or equal to 0, and the first data set is a first data set; the first data set c</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDAPSSxKTy1RKMgvzizJzM_LzEtXyE0tychPUUjMS1EoSs1JLElNUUgtLM0syE3NK1EoyUgtSs1P42FgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoYWpmYWRhaWjsbEqAEABOcucg</recordid><startdate>20240830</startdate><enddate>20240830</enddate><creator>WANG JIN</creator><creator>HUANG BO</creator><creator>CHI ZIQIU</creator><creator>LI YIFEI</creator><scope>EVB</scope></search><sort><creationdate>20240830</creationdate><title>Target positioning method and related equipment thereof</title><author>WANG JIN ; HUANG BO ; CHI ZIQIU ; LI YIFEI</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN118568289A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG JIN</creatorcontrib><creatorcontrib>HUANG BO</creatorcontrib><creatorcontrib>CHI ZIQIU</creatorcontrib><creatorcontrib>LI YIFEI</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG JIN</au><au>HUANG BO</au><au>CHI ZIQIU</au><au>LI YIFEI</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Target positioning method and related equipment thereof</title><date>2024-08-30</date><risdate>2024</risdate><abstract>The invention discloses a target positioning method and related equipment thereof, and the method comprises the steps: obtaining a to-be-processed image and first text prompt information, the first text prompt information being description information of a target needing to be retrieved from the to-be-processed image; based on the to-be-processed image and the first text prompt information, positioning a bounding box of a target in the to-be-processed image through a preset multi-modal large model to obtain a positioning result; wherein the preset multi-modal large model is obtained by training a basic multi-modal large model on the basis of a preset bounding box positioning data set, each piece of data in the preset bounding box positioning data set comprises a first data set and a bounding box label corresponding to the first data set, the bounding box label and the first data set are in an N-to-1 relationship, N is greater than or equal to 0, and the first data set is a first data set; the first data set c</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN118568289A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title Target positioning method and related equipment thereof
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T00%3A12%3A30IST&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=WANG%20JIN&rft.date=2024-08-30&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN118568289A%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