Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm
The construction industry is one of the most dangerous industries in the world due to workers being vulnerable to accidents, injuries and even death. Therefore, how to effectively manage the appropriate usage of personal protective equipment (PPE) is an important research issue. In this study, deep...
Gespeichert in:
| Veröffentlicht in: | Sustainability 2023-01, Vol.15 (1), p.391 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 1 |
| container_start_page | 391 |
| container_title | Sustainability |
| container_volume | 15 |
| creator | Lo, Jye-Hwang Lin, Lee-Kuo Hung, Chu-Chun |
| description | The construction industry is one of the most dangerous industries in the world due to workers being vulnerable to accidents, injuries and even death. Therefore, how to effectively manage the appropriate usage of personal protective equipment (PPE) is an important research issue. In this study, deep learning is applied to the PPE inspection model to verify whether construction workers are equipped in accordance with the regulations, and this is expected to reduce the probability of related occupational disasters caused by the inappropriate use of PPE. The method is based on the YOLOv3, YOLOv4 and YOLOv7 algorithms to detect worker’s helmets and high-visibility vests from images or videos in real time. The model was trained on a new PPE dataset collected and organized by this study; the dataset contains 11,000 images and 88,725 labels. According to the test results, can achieve a 97% mean average precision (mAP) and 25 frames per second (FPS). The research result shows that the detection and counting data in this method have performed well and can be applied to the real-time PPE detection of workers at the construction job site. |
| doi_str_mv | 10.3390/su15010391 |
| format | Article |
| fullrecord | <record><control><sourceid>gale_proqu</sourceid><recordid>TN_cdi_proquest_journals_2761217570</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A747199152</galeid><sourcerecordid>A747199152</sourcerecordid><originalsourceid>FETCH-LOGICAL-c368t-f493b4540f267de1078ce10305e544fcbf197127b4b7994649d68b52760979ec3</originalsourceid><addsrcrecordid>eNpVkVFLwzAQx4soOOZe_AQBnxQ6kyZtlse5TR0MHHM-Skmz68xomy5JRb-90Qm6O7g77n7_g-Oi6JLgIaUC37qOpJhgKshJ1EswJzHBKT79V59HA-d2OBilRJCsF72uQFbxWteAlmCdaWSFltZ4UF6_A5rtO93W0Hg0MXVbadkoQFP4GZsG3UkHGxSKKUCLFiBto5stGldbY7V_qy-is1JWDga_uR-93M_Wk8d48fQwn4wXsaLZyMclE7RgKcNlkvENEMxHKkSKU0gZK1VREsFJwgtWcCFYxsQmGxVpwjMsuABF-9HVYW9rzb4D5_Od6Wy4xeUBIgnhKceBGh6orawg101pvJUq-AZqrUwDpQ79MWecCEHSJAiujwSB8fDht7JzLp8_r47ZmwOrrHHOQpm3VtfSfuYE59_vyf_eQ78A35N_RA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2761217570</pqid></control><display><type>article</type><title>Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm</title><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Lo, Jye-Hwang ; Lin, Lee-Kuo ; Hung, Chu-Chun</creator><creatorcontrib>Lo, Jye-Hwang ; Lin, Lee-Kuo ; Hung, Chu-Chun</creatorcontrib><description>The construction industry is one of the most dangerous industries in the world due to workers being vulnerable to accidents, injuries and even death. Therefore, how to effectively manage the appropriate usage of personal protective equipment (PPE) is an important research issue. In this study, deep learning is applied to the PPE inspection model to verify whether construction workers are equipped in accordance with the regulations, and this is expected to reduce the probability of related occupational disasters caused by the inappropriate use of PPE. The method is based on the YOLOv3, YOLOv4 and YOLOv7 algorithms to detect worker’s helmets and high-visibility vests from images or videos in real time. The model was trained on a new PPE dataset collected and organized by this study; the dataset contains 11,000 images and 88,725 labels. According to the test results, can achieve a 97% mean average precision (mAP) and 25 frames per second (FPS). The research result shows that the detection and counting data in this method have performed well and can be applied to the real-time PPE detection of workers at the construction job site.</description><identifier>ISSN: 2071-1050</identifier><identifier>EISSN: 2071-1050</identifier><identifier>DOI: 10.3390/su15010391</identifier><language>eng</language><publisher>Basel: MDPI AG</publisher><subject>Accidents ; Algorithms ; Compliance ; Construction industry ; Construction workers ; Data entry ; Data mining ; Datasets ; Deep learning ; Engineering research ; Frames per second ; Headgear ; Heavy construction ; Helmets ; Injuries ; Inspection ; International economic relations ; Internet of Things ; Machine learning ; Methods ; Neural networks ; Occupational accidents ; Personal protective equipment ; Protective clothing ; Protective equipment ; Radio frequency identification ; Real time ; Regulatory compliance ; Sensors ; Technology application ; Visibility ; Workers</subject><ispartof>Sustainability, 2023-01, Vol.15 (1), p.391</ispartof><rights>COPYRIGHT 2022 MDPI AG</rights><rights>2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c368t-f493b4540f267de1078ce10305e544fcbf197127b4b7994649d68b52760979ec3</citedby><cites>FETCH-LOGICAL-c368t-f493b4540f267de1078ce10305e544fcbf197127b4b7994649d68b52760979ec3</cites><orcidid>0000-0001-8106-269X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,776,780,27901,27902</link.rule.ids></links><search><creatorcontrib>Lo, Jye-Hwang</creatorcontrib><creatorcontrib>Lin, Lee-Kuo</creatorcontrib><creatorcontrib>Hung, Chu-Chun</creatorcontrib><title>Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm</title><title>Sustainability</title><description>The construction industry is one of the most dangerous industries in the world due to workers being vulnerable to accidents, injuries and even death. Therefore, how to effectively manage the appropriate usage of personal protective equipment (PPE) is an important research issue. In this study, deep learning is applied to the PPE inspection model to verify whether construction workers are equipped in accordance with the regulations, and this is expected to reduce the probability of related occupational disasters caused by the inappropriate use of PPE. The method is based on the YOLOv3, YOLOv4 and YOLOv7 algorithms to detect worker’s helmets and high-visibility vests from images or videos in real time. The model was trained on a new PPE dataset collected and organized by this study; the dataset contains 11,000 images and 88,725 labels. According to the test results, can achieve a 97% mean average precision (mAP) and 25 frames per second (FPS). The research result shows that the detection and counting data in this method have performed well and can be applied to the real-time PPE detection of workers at the construction job site.</description><subject>Accidents</subject><subject>Algorithms</subject><subject>Compliance</subject><subject>Construction industry</subject><subject>Construction workers</subject><subject>Data entry</subject><subject>Data mining</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>Engineering research</subject><subject>Frames per second</subject><subject>Headgear</subject><subject>Heavy construction</subject><subject>Helmets</subject><subject>Injuries</subject><subject>Inspection</subject><subject>International economic relations</subject><subject>Internet of Things</subject><subject>Machine learning</subject><subject>Methods</subject><subject>Neural networks</subject><subject>Occupational accidents</subject><subject>Personal protective equipment</subject><subject>Protective clothing</subject><subject>Protective equipment</subject><subject>Radio frequency identification</subject><subject>Real time</subject><subject>Regulatory compliance</subject><subject>Sensors</subject><subject>Technology application</subject><subject>Visibility</subject><subject>Workers</subject><issn>2071-1050</issn><issn>2071-1050</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpVkVFLwzAQx4soOOZe_AQBnxQ6kyZtlse5TR0MHHM-Skmz68xomy5JRb-90Qm6O7g77n7_g-Oi6JLgIaUC37qOpJhgKshJ1EswJzHBKT79V59HA-d2OBilRJCsF72uQFbxWteAlmCdaWSFltZ4UF6_A5rtO93W0Hg0MXVbadkoQFP4GZsG3UkHGxSKKUCLFiBto5stGldbY7V_qy-is1JWDga_uR-93M_Wk8d48fQwn4wXsaLZyMclE7RgKcNlkvENEMxHKkSKU0gZK1VREsFJwgtWcCFYxsQmGxVpwjMsuABF-9HVYW9rzb4D5_Od6Wy4xeUBIgnhKceBGh6orawg101pvJUq-AZqrUwDpQ79MWecCEHSJAiujwSB8fDht7JzLp8_r47ZmwOrrHHOQpm3VtfSfuYE59_vyf_eQ78A35N_RA</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Lo, Jye-Hwang</creator><creator>Lin, Lee-Kuo</creator><creator>Hung, Chu-Chun</creator><general>MDPI AG</general><scope>AAYXX</scope><scope>CITATION</scope><scope>ISR</scope><scope>4U-</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><orcidid>https://orcid.org/0000-0001-8106-269X</orcidid></search><sort><creationdate>20230101</creationdate><title>Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm</title><author>Lo, Jye-Hwang ; Lin, Lee-Kuo ; Hung, Chu-Chun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c368t-f493b4540f267de1078ce10305e544fcbf197127b4b7994649d68b52760979ec3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Accidents</topic><topic>Algorithms</topic><topic>Compliance</topic><topic>Construction industry</topic><topic>Construction workers</topic><topic>Data entry</topic><topic>Data mining</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>Engineering research</topic><topic>Frames per second</topic><topic>Headgear</topic><topic>Heavy construction</topic><topic>Helmets</topic><topic>Injuries</topic><topic>Inspection</topic><topic>International economic relations</topic><topic>Internet of Things</topic><topic>Machine learning</topic><topic>Methods</topic><topic>Neural networks</topic><topic>Occupational accidents</topic><topic>Personal protective equipment</topic><topic>Protective clothing</topic><topic>Protective equipment</topic><topic>Radio frequency identification</topic><topic>Real time</topic><topic>Regulatory compliance</topic><topic>Sensors</topic><topic>Technology application</topic><topic>Visibility</topic><topic>Workers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Lo, Jye-Hwang</creatorcontrib><creatorcontrib>Lin, Lee-Kuo</creatorcontrib><creatorcontrib>Hung, Chu-Chun</creatorcontrib><collection>CrossRef</collection><collection>Gale In Context: Science</collection><collection>University Readers</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><jtitle>Sustainability</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Lo, Jye-Hwang</au><au>Lin, Lee-Kuo</au><au>Hung, Chu-Chun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm</atitle><jtitle>Sustainability</jtitle><date>2023-01-01</date><risdate>2023</risdate><volume>15</volume><issue>1</issue><spage>391</spage><pages>391-</pages><issn>2071-1050</issn><eissn>2071-1050</eissn><abstract>The construction industry is one of the most dangerous industries in the world due to workers being vulnerable to accidents, injuries and even death. Therefore, how to effectively manage the appropriate usage of personal protective equipment (PPE) is an important research issue. In this study, deep learning is applied to the PPE inspection model to verify whether construction workers are equipped in accordance with the regulations, and this is expected to reduce the probability of related occupational disasters caused by the inappropriate use of PPE. The method is based on the YOLOv3, YOLOv4 and YOLOv7 algorithms to detect worker’s helmets and high-visibility vests from images or videos in real time. The model was trained on a new PPE dataset collected and organized by this study; the dataset contains 11,000 images and 88,725 labels. According to the test results, can achieve a 97% mean average precision (mAP) and 25 frames per second (FPS). The research result shows that the detection and counting data in this method have performed well and can be applied to the real-time PPE detection of workers at the construction job site.</abstract><cop>Basel</cop><pub>MDPI AG</pub><doi>10.3390/su15010391</doi><orcidid>https://orcid.org/0000-0001-8106-269X</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 2071-1050 |
| ispartof | Sustainability, 2023-01, Vol.15 (1), p.391 |
| issn | 2071-1050 2071-1050 |
| language | eng |
| recordid | cdi_proquest_journals_2761217570 |
| source | MDPI - Multidisciplinary Digital Publishing Institute; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals |
| subjects | Accidents Algorithms Compliance Construction industry Construction workers Data entry Data mining Datasets Deep learning Engineering research Frames per second Headgear Heavy construction Helmets Injuries Inspection International economic relations Internet of Things Machine learning Methods Neural networks Occupational accidents Personal protective equipment Protective clothing Protective equipment Radio frequency identification Real time Regulatory compliance Sensors Technology application Visibility Workers |
| title | Real-Time Personal Protective Equipment Compliance Detection Based on Deep Learning Algorithm |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T16%3A00%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale_proqu&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Real-Time%20Personal%20Protective%20Equipment%20Compliance%20Detection%20Based%20on%20Deep%20Learning%20Algorithm&rft.jtitle=Sustainability&rft.au=Lo,%20Jye-Hwang&rft.date=2023-01-01&rft.volume=15&rft.issue=1&rft.spage=391&rft.pages=391-&rft.issn=2071-1050&rft.eissn=2071-1050&rft_id=info:doi/10.3390/su15010391&rft_dat=%3Cgale_proqu%3EA747199152%3C/gale_proqu%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2761217570&rft_id=info:pmid/&rft_galeid=A747199152&rfr_iscdi=true |