Construction site safety helmet identification method and device based on independent training framework

The invention discloses a construction site safety helmet identification method and device based on an independent training framework, and the method comprises the steps: enabling a photographed construction site worker picture to serve as the input of a complementary feature learning framework, and...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: YATAMACHI SHIGESHI, LIANG WEISEN, LIN ZUNHU, XIE MENG, LIU KE, WANG ZEGUO, HUANG LICHUN, WANG MINSHUAI, YANG WEI, ZHOU CHEN, YANG YANBIN, YIN XINGLONG, CHEN YUBO
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 YATAMACHI SHIGESHI
LIANG WEISEN
LIN ZUNHU
XIE MENG
LIU KE
WANG ZEGUO
HUANG LICHUN
WANG MINSHUAI
YANG WEI
ZHOU CHEN
YANG YANBIN
YIN XINGLONG
CHEN YUBO
description The invention discloses a construction site safety helmet identification method and device based on an independent training framework, and the method comprises the steps: enabling a photographed construction site worker picture to serve as the input of a complementary feature learning framework, and carrying out the convolution operation of the inputted picture, and obtaining the abstract representation information conv of the picture; respectively sending the conv into a feature extraction channel Attention CNN model and an Attention LSTM model which are parallel to each other for feature learning; the Attention CNN model outputs color information F1 about the safety helmet, the Attention LSTM model outputs contour information F2 about the safety helmet, outputs of the Attention CNN model and the Attention LSTM model are combined into F, F = [F1, F2], and F is input into a full connection layer; and inputting the output of the full connection layer into a support vector machine to judge the wearing condition
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_CN116168430A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>CN116168430A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_CN116168430A3</originalsourceid><addsrcrecordid>eNqNyjEKwkAQheE0FqLeYTyAYIgEWwmKlZV9GLNvzWAyG3ZHxdsbxQNYPfjfN83aKmiyeG9MglISAyX2sBe16HoYiYOaeGn4K8bUBkesjhwe0oAunOBovEQdBujHk0UWFb2Sj9zjGeJtnk08dwmL386y5WF_ro4rDKFGGriBwurqlOdlXm43xXpX_GPedddBGA</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>Construction site safety helmet identification method and device based on independent training framework</title><source>esp@cenet</source><creator>YATAMACHI SHIGESHI ; LIANG WEISEN ; LIN ZUNHU ; XIE MENG ; LIU KE ; WANG ZEGUO ; HUANG LICHUN ; WANG MINSHUAI ; YANG WEI ; ZHOU CHEN ; YANG YANBIN ; YIN XINGLONG ; CHEN YUBO</creator><creatorcontrib>YATAMACHI SHIGESHI ; LIANG WEISEN ; LIN ZUNHU ; XIE MENG ; LIU KE ; WANG ZEGUO ; HUANG LICHUN ; WANG MINSHUAI ; YANG WEI ; ZHOU CHEN ; YANG YANBIN ; YIN XINGLONG ; CHEN YUBO</creatorcontrib><description>The invention discloses a construction site safety helmet identification method and device based on an independent training framework, and the method comprises the steps: enabling a photographed construction site worker picture to serve as the input of a complementary feature learning framework, and carrying out the convolution operation of the inputted picture, and obtaining the abstract representation information conv of the picture; respectively sending the conv into a feature extraction channel Attention CNN model and an Attention LSTM model which are parallel to each other for feature learning; the Attention CNN model outputs color information F1 about the safety helmet, the Attention LSTM model outputs contour information F2 about the safety helmet, outputs of the Attention CNN model and the Attention LSTM model are combined into F, F = [F1, F2], and F is input into a full connection layer; and inputting the output of the full connection layer into a support vector machine to judge the wearing condition</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=20230526&amp;DB=EPODOC&amp;CC=CN&amp;NR=116168430A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20230526&amp;DB=EPODOC&amp;CC=CN&amp;NR=116168430A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>YATAMACHI SHIGESHI</creatorcontrib><creatorcontrib>LIANG WEISEN</creatorcontrib><creatorcontrib>LIN ZUNHU</creatorcontrib><creatorcontrib>XIE MENG</creatorcontrib><creatorcontrib>LIU KE</creatorcontrib><creatorcontrib>WANG ZEGUO</creatorcontrib><creatorcontrib>HUANG LICHUN</creatorcontrib><creatorcontrib>WANG MINSHUAI</creatorcontrib><creatorcontrib>YANG WEI</creatorcontrib><creatorcontrib>ZHOU CHEN</creatorcontrib><creatorcontrib>YANG YANBIN</creatorcontrib><creatorcontrib>YIN XINGLONG</creatorcontrib><creatorcontrib>CHEN YUBO</creatorcontrib><title>Construction site safety helmet identification method and device based on independent training framework</title><description>The invention discloses a construction site safety helmet identification method and device based on an independent training framework, and the method comprises the steps: enabling a photographed construction site worker picture to serve as the input of a complementary feature learning framework, and carrying out the convolution operation of the inputted picture, and obtaining the abstract representation information conv of the picture; respectively sending the conv into a feature extraction channel Attention CNN model and an Attention LSTM model which are parallel to each other for feature learning; the Attention CNN model outputs color information F1 about the safety helmet, the Attention LSTM model outputs contour information F2 about the safety helmet, outputs of the Attention CNN model and the Attention LSTM model are combined into F, F = [F1, F2], and F is input into a full connection layer; and inputting the output of the full connection layer into a support vector machine to judge the wearing condition</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>eNqNyjEKwkAQheE0FqLeYTyAYIgEWwmKlZV9GLNvzWAyG3ZHxdsbxQNYPfjfN83aKmiyeG9MglISAyX2sBe16HoYiYOaeGn4K8bUBkesjhwe0oAunOBovEQdBujHk0UWFb2Sj9zjGeJtnk08dwmL386y5WF_ro4rDKFGGriBwurqlOdlXm43xXpX_GPedddBGA</recordid><startdate>20230526</startdate><enddate>20230526</enddate><creator>YATAMACHI SHIGESHI</creator><creator>LIANG WEISEN</creator><creator>LIN ZUNHU</creator><creator>XIE MENG</creator><creator>LIU KE</creator><creator>WANG ZEGUO</creator><creator>HUANG LICHUN</creator><creator>WANG MINSHUAI</creator><creator>YANG WEI</creator><creator>ZHOU CHEN</creator><creator>YANG YANBIN</creator><creator>YIN XINGLONG</creator><creator>CHEN YUBO</creator><scope>EVB</scope></search><sort><creationdate>20230526</creationdate><title>Construction site safety helmet identification method and device based on independent training framework</title><author>YATAMACHI SHIGESHI ; LIANG WEISEN ; LIN ZUNHU ; XIE MENG ; LIU KE ; WANG ZEGUO ; HUANG LICHUN ; WANG MINSHUAI ; YANG WEI ; ZHOU CHEN ; YANG YANBIN ; YIN XINGLONG ; CHEN YUBO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_CN116168430A3</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>YATAMACHI SHIGESHI</creatorcontrib><creatorcontrib>LIANG WEISEN</creatorcontrib><creatorcontrib>LIN ZUNHU</creatorcontrib><creatorcontrib>XIE MENG</creatorcontrib><creatorcontrib>LIU KE</creatorcontrib><creatorcontrib>WANG ZEGUO</creatorcontrib><creatorcontrib>HUANG LICHUN</creatorcontrib><creatorcontrib>WANG MINSHUAI</creatorcontrib><creatorcontrib>YANG WEI</creatorcontrib><creatorcontrib>ZHOU CHEN</creatorcontrib><creatorcontrib>YANG YANBIN</creatorcontrib><creatorcontrib>YIN XINGLONG</creatorcontrib><creatorcontrib>CHEN YUBO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>YATAMACHI SHIGESHI</au><au>LIANG WEISEN</au><au>LIN ZUNHU</au><au>XIE MENG</au><au>LIU KE</au><au>WANG ZEGUO</au><au>HUANG LICHUN</au><au>WANG MINSHUAI</au><au>YANG WEI</au><au>ZHOU CHEN</au><au>YANG YANBIN</au><au>YIN XINGLONG</au><au>CHEN YUBO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>Construction site safety helmet identification method and device based on independent training framework</title><date>2023-05-26</date><risdate>2023</risdate><abstract>The invention discloses a construction site safety helmet identification method and device based on an independent training framework, and the method comprises the steps: enabling a photographed construction site worker picture to serve as the input of a complementary feature learning framework, and carrying out the convolution operation of the inputted picture, and obtaining the abstract representation information conv of the picture; respectively sending the conv into a feature extraction channel Attention CNN model and an Attention LSTM model which are parallel to each other for feature learning; the Attention CNN model outputs color information F1 about the safety helmet, the Attention LSTM model outputs contour information F2 about the safety helmet, outputs of the Attention CNN model and the Attention LSTM model are combined into F, F = [F1, F2], and F is input into a full connection layer; and inputting the output of the full connection layer into a support vector machine to judge the wearing condition</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language chi ; eng
recordid cdi_epo_espacenet_CN116168430A
source esp@cenet
subjects CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
title Construction site safety helmet identification method and device based on independent training framework
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T10%3A13%3A47IST&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=YATAMACHI%20SHIGESHI&rft.date=2023-05-26&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3ECN116168430A%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