Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion

Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion

The invention discloses a behavior recognition method driven by co-time and cross-domain asynchronous fusion. The behavior recognition method comprises the following steps: acquiring multi-person body color images as an image sequence; estimating a two-dimensional human body posture from the interce...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG GEGE, SONG WEI, MENG SENSEN, GUO FANGTAI, QIAN JINJU, MU ZONGHAO, ZHU SHIQIANG
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
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 ZHANG GEGE
SONG WEI
MENG SENSEN
GUO FANGTAI
QIAN JINJU
MU ZONGHAO
ZHU SHIQIANG
description The invention discloses a behavior recognition method driven by co-time and cross-domain asynchronous fusion. The behavior recognition method comprises the following steps: acquiring multi-person body color images as an image sequence; estimating a two-dimensional human body posture from the intercepted image, and calculating a key point heat map of the two-dimensional human body posture as a posture sequence; establishing an apparent network, taking the image sequence as input, and extracting image features; meanwhile, establishing an attitude network, taking the attitude sequence as input, and extracting attitude features; taking the image features and the attitude features as input, and zooming, aligning and fusing the image features and the attitude features; normalizing the fused image features and attitude features, splicing the normalized double-flow features to obtain global features, and inputting the global features into a classifier to solve a behavior category with the maximum probability; a multi
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN115761885A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN115761885A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN115761885A3</originalsourceid><addsrcrecordid>eNqNzDEOgkAQQFEaC6PeYTwABTEoLRKNlZWJJRl3B3YSmSE7Cwm318IDWP3m5a-z55kCzqwRIjnthROrwEApqAcfeSaB1wKJB8otYGTpAcWDi2qWex2QBdAWcSGq6GTQTfZdbLNVh2-j3a-bbH-9PJpbTqO2ZCM6Ekptcy-K8nQsqqqsD_-YD7DfOrE</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion</title><source>esp@cenet</source><creator>ZHANG GEGE ; SONG WEI ; MENG SENSEN ; GUO FANGTAI ; QIAN JINJU ; MU ZONGHAO ; ZHU SHIQIANG</creator><creatorcontrib>ZHANG GEGE ; SONG WEI ; MENG SENSEN ; GUO FANGTAI ; QIAN JINJU ; MU ZONGHAO ; ZHU SHIQIANG</creatorcontrib><description>The invention discloses a behavior recognition method driven by co-time and cross-domain asynchronous fusion. The behavior recognition method comprises the following steps: acquiring multi-person body color images as an image sequence; estimating a two-dimensional human body posture from the intercepted image, and calculating a key point heat map of the two-dimensional human body posture as a posture sequence; establishing an apparent network, taking the image sequence as input, and extracting image features; meanwhile, establishing an attitude network, taking the attitude sequence as input, and extracting attitude features; taking the image features and the attitude features as input, and zooming, aligning and fusing the image features and the attitude features; normalizing the fused image features and attitude features, splicing the normalized double-flow features to obtain global features, and inputting the global features into a classifier to solve a behavior category with the maximum probability; a multi</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=20230307&amp;DB=EPODOC&amp;CC=CN&amp;NR=115761885A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230307&amp;DB=EPODOC&amp;CC=CN&amp;NR=115761885A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>ZHANG GEGE</creatorcontrib><creatorcontrib>SONG WEI</creatorcontrib><creatorcontrib>MENG SENSEN</creatorcontrib><creatorcontrib>GUO FANGTAI</creatorcontrib><creatorcontrib>QIAN JINJU</creatorcontrib><creatorcontrib>MU ZONGHAO</creatorcontrib><creatorcontrib>ZHU SHIQIANG</creatorcontrib><title>Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion</title><description>The invention discloses a behavior recognition method driven by co-time and cross-domain asynchronous fusion. The behavior recognition method comprises the following steps: acquiring multi-person body color images as an image sequence; estimating a two-dimensional human body posture from the intercepted image, and calculating a key point heat map of the two-dimensional human body posture as a posture sequence; establishing an apparent network, taking the image sequence as input, and extracting image features; meanwhile, establishing an attitude network, taking the attitude sequence as input, and extracting attitude features; taking the image features and the attitude features as input, and zooming, aligning and fusing the image features and the attitude features; normalizing the fused image features and attitude features, splicing the normalized double-flow features to obtain global features, and inputting the global features into a classifier to solve a behavior category with the maximum probability; a multi</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>eNqNzDEOgkAQQFEaC6PeYTwABTEoLRKNlZWJJRl3B3YSmSE7Cwm318IDWP3m5a-z55kCzqwRIjnthROrwEApqAcfeSaB1wKJB8otYGTpAcWDi2qWex2QBdAWcSGq6GTQTfZdbLNVh2-j3a-bbH-9PJpbTqO2ZCM6Ekptcy-K8nQsqqqsD_-YD7DfOrE</recordid><startdate>20230307</startdate><enddate>20230307</enddate><creator>ZHANG GEGE</creator><creator>SONG WEI</creator><creator>MENG SENSEN</creator><creator>GUO FANGTAI</creator><creator>QIAN JINJU</creator><creator>MU ZONGHAO</creator><creator>ZHU SHIQIANG</creator><scope>EVB</scope></search><sort><creationdate>20230307</creationdate><title>Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion</title><author>ZHANG GEGE ; SONG WEI ; MENG SENSEN ; GUO FANGTAI ; QIAN JINJU ; MU ZONGHAO ; ZHU SHIQIANG</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN115761885A3</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>ZHANG GEGE</creatorcontrib><creatorcontrib>SONG WEI</creatorcontrib><creatorcontrib>MENG SENSEN</creatorcontrib><creatorcontrib>GUO FANGTAI</creatorcontrib><creatorcontrib>QIAN JINJU</creatorcontrib><creatorcontrib>MU ZONGHAO</creatorcontrib><creatorcontrib>ZHU SHIQIANG</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>ZHANG GEGE</au><au>SONG WEI</au><au>MENG SENSEN</au><au>GUO FANGTAI</au><au>QIAN JINJU</au><au>MU ZONGHAO</au><au>ZHU SHIQIANG</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion</title><date>2023-03-07</date><risdate>2023</risdate><abstract>The invention discloses a behavior recognition method driven by co-time and cross-domain asynchronous fusion. The behavior recognition method comprises the following steps: acquiring multi-person body color images as an image sequence; estimating a two-dimensional human body posture from the intercepted image, and calculating a key point heat map of the two-dimensional human body posture as a posture sequence; establishing an apparent network, taking the image sequence as input, and extracting image features; meanwhile, establishing an attitude network, taking the attitude sequence as input, and extracting attitude features; taking the image features and the attitude features as input, and zooming, aligning and fusing the image features and the attitude features; normalizing the fused image features and attitude features, splicing the normalized double-flow features to obtain global features, and inputting the global features into a classifier to solve a behavior category with the maximum probability; a multi</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN115761885A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Behavior recognition method driven by time-sharing and cross-domain asynchronous fusion
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T13%3A39%3A05IST&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=ZHANG%20GEGE&rft.date=2023-03-07&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN115761885A%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