Pedestrian re-identification method and system

Pedestrian re-identification method and system

The invention relates to the field of intelligent decision, and discloses a pedestrian re-identification method, which comprises the following steps: preprocessing pedestrian image data to obtain a preprocessed image; performing local feature extraction on the preprocessed image to obtain pedestrian...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: CHEN SHANGLIANG, LI YUEZHONG, LIU GUOQUAN, LUO XIANXI, ZHOU WUHAO
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
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 CHEN SHANGLIANG
LI YUEZHONG
LIU GUOQUAN
LUO XIANXI
ZHOU WUHAO
description The invention relates to the field of intelligent decision, and discloses a pedestrian re-identification method, which comprises the following steps: preprocessing pedestrian image data to obtain a preprocessed image; performing local feature extraction on the preprocessed image to obtain pedestrian local features; performing global feature extraction on the preprocessed image; self-adaptive noise matching processing is carried out on the pedestrian local features and the pedestrian global features, and the pedestrian local features and the pedestrian global features are converted into self-adaptive local vectors and self-adaptive global vectors; detecting human body key points, constructing a connecting edge between any human body key points, constructing a posture node matrix, and constructing a posture edge matrix according to the connecting edges; carrying out updating aggregation processing on the node feature matrix and the edge feature matrix, and carrying out dimension reduction and splicing processin
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116012878A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116012878A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116012878A3</originalsourceid><addsrcrecordid>eNrjZNALSE1JLS4pykzMUyhK1c1MSc0ryUzLTE4syczPU8hNLcnIT1FIzEtRKK4sLknN5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoZmBoZGFuYWjsbEqAEAF1gqzw</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Pedestrian re-identification method and system</title><source>esp@cenet</source><creator>CHEN SHANGLIANG ; LI YUEZHONG ; LIU GUOQUAN ; LUO XIANXI ; ZHOU WUHAO</creator><creatorcontrib>CHEN SHANGLIANG ; LI YUEZHONG ; LIU GUOQUAN ; LUO XIANXI ; ZHOU WUHAO</creatorcontrib><description>The invention relates to the field of intelligent decision, and discloses a pedestrian re-identification method, which comprises the following steps: preprocessing pedestrian image data to obtain a preprocessed image; performing local feature extraction on the preprocessed image to obtain pedestrian local features; performing global feature extraction on the preprocessed image; self-adaptive noise matching processing is carried out on the pedestrian local features and the pedestrian global features, and the pedestrian local features and the pedestrian global features are converted into self-adaptive local vectors and self-adaptive global vectors; detecting human body key points, constructing a connecting edge between any human body key points, constructing a posture node matrix, and constructing a posture edge matrix according to the connecting edges; carrying out updating aggregation processing on the node feature matrix and the edge feature matrix, and carrying out dimension reduction and splicing processin</description><language>chi ; eng</language><subject>CALCULATING ; 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=20230425&amp;DB=EPODOC&amp;CC=CN&amp;NR=116012878A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230425&amp;DB=EPODOC&amp;CC=CN&amp;NR=116012878A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>CHEN SHANGLIANG</creatorcontrib><creatorcontrib>LI YUEZHONG</creatorcontrib><creatorcontrib>LIU GUOQUAN</creatorcontrib><creatorcontrib>LUO XIANXI</creatorcontrib><creatorcontrib>ZHOU WUHAO</creatorcontrib><title>Pedestrian re-identification method and system</title><description>The invention relates to the field of intelligent decision, and discloses a pedestrian re-identification method, which comprises the following steps: preprocessing pedestrian image data to obtain a preprocessed image; performing local feature extraction on the preprocessed image to obtain pedestrian local features; performing global feature extraction on the preprocessed image; self-adaptive noise matching processing is carried out on the pedestrian local features and the pedestrian global features, and the pedestrian local features and the pedestrian global features are converted into self-adaptive local vectors and self-adaptive global vectors; detecting human body key points, constructing a connecting edge between any human body key points, constructing a posture node matrix, and constructing a posture edge matrix according to the connecting edges; carrying out updating aggregation processing on the node feature matrix and the edge feature matrix, and carrying out dimension reduction and splicing processin</description><subject>CALCULATING</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>eNrjZNALSE1JLS4pykzMUyhK1c1MSc0ryUzLTE4syczPU8hNLcnIT1FIzEtRKK4sLknN5WFgTUvMKU7lhdLcDIpuriHOHrqpBfnxqcUFicmpeakl8c5-hoZmBoZGFuYWjsbEqAEAF1gqzw</recordid><startdate>20230425</startdate><enddate>20230425</enddate><creator>CHEN SHANGLIANG</creator><creator>LI YUEZHONG</creator><creator>LIU GUOQUAN</creator><creator>LUO XIANXI</creator><creator>ZHOU WUHAO</creator><scope>EVB</scope></search><sort><creationdate>20230425</creationdate><title>Pedestrian re-identification method and system</title><author>CHEN SHANGLIANG ; LI YUEZHONG ; LIU GUOQUAN ; LUO XIANXI ; ZHOU WUHAO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116012878A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>CHEN SHANGLIANG</creatorcontrib><creatorcontrib>LI YUEZHONG</creatorcontrib><creatorcontrib>LIU GUOQUAN</creatorcontrib><creatorcontrib>LUO XIANXI</creatorcontrib><creatorcontrib>ZHOU WUHAO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>CHEN SHANGLIANG</au><au>LI YUEZHONG</au><au>LIU GUOQUAN</au><au>LUO XIANXI</au><au>ZHOU WUHAO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Pedestrian re-identification method and system</title><date>2023-04-25</date><risdate>2023</risdate><abstract>The invention relates to the field of intelligent decision, and discloses a pedestrian re-identification method, which comprises the following steps: preprocessing pedestrian image data to obtain a preprocessed image; performing local feature extraction on the preprocessed image to obtain pedestrian local features; performing global feature extraction on the preprocessed image; self-adaptive noise matching processing is carried out on the pedestrian local features and the pedestrian global features, and the pedestrian local features and the pedestrian global features are converted into self-adaptive local vectors and self-adaptive global vectors; detecting human body key points, constructing a connecting edge between any human body key points, constructing a posture node matrix, and constructing a posture edge matrix according to the connecting edges; carrying out updating aggregation processing on the node feature matrix and the edge feature matrix, and carrying out dimension reduction and splicing processin</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116012878A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
PHYSICS
title Pedestrian re-identification method and system
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T20%3A13%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=CHEN%20SHANGLIANG&rft.date=2023-04-25&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116012878A%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