Article(id=1148106720297082900, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, articleNumber=1003-3033(2025)03-0028-08, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2025.03.0749, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1726761600000, receivedDateStr=2024-09-20, revisedDate=1732291200000, revisedDateStr=2024-11-23, acceptedDate=null, acceptedDateStr=null, onlineDate=1751659572910, onlineDateStr=2025-07-05, pubDate=1743091200000, pubDateStr=2025-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751659572910, onlineIssueDateStr=2025-07-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1751659572910, creator=13701087609, updateTime=1751659572910, updator=13701087609, issue=Issue{id=1148106708670477182, tenantId=1146029695717560320, journalId=1146031787341344770, year='2025', volume='35', issue='3', pageStart='1', pageEnd='268', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1751659570138, creator=13701087609, updateTime=1757401518130, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1172190184155238915, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1172190184155238916, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=28, endPage=35, ext={EN=ArticleExt(id=1149767353124176265, articleId=1148106720297082900, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Recognition of personnel fatigue state and unsafe behavior based on computer vision, columnId=1149733271128420907, journalTitle=China Safety Science Journal, columnName=Safety social science and safety management, runingTitle=null, highlight=null, articleAbstract=

Taking improving the safety and efficiency of tower crane operation as an example,a method of integrated identification of fatigue state and unsafe behavior was proposed in order to detect the potential safety hazards of drivers in real time. A live video stream was captured via a camera,and the video was analyzed and pre-processed to extract critical information for identifying subsequent fatigue and unsafe behavior. In terms of fatigue state recognition,the analysis method based on the state of eyes and mouth was used to monitor the physiological indicators such as the state of eyes opening and closing,the blink frequency and yawn frequency. In terms of unsafe behavior identification,computer vision and deep learning technology were combined to detect the potential dangerous operations of drivers in real time,thus ensuring timely detection of safety risks. The results show that the performance of the optimized YOLOv5-ECA(Efficient Channel Attention) model is significantly improved in fatigue state and unsafe behavior recognition. The accuracy rate and recall rate of the model on the test set are more than 90%,showing good recognition ability.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Hua LI, Lizhou WU, Xingrun ZHONG, Liangwei GUO, Yuxin CUI), CN=ArticleExt(id=1148106725279916565, articleId=1148106720297082900, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于计算机视觉的人员疲劳状态与不安全行为识别, columnId=1149733271296193071, journalTitle=中国安全科学学报, columnName=安全社会科学与安全管理, runingTitle=null, highlight=null, articleAbstract=

以提高塔吊操作的安全性和效率为案例,提出一种综合识别疲劳状态和不安全行为的方法,以实时发现驾驶员可能存在的安全隐患。通过摄像头捕获实时视频流,并对视频进行分析和预处理,提取关键信息,用于识别后续的疲劳和不安全行为;在疲劳状态识别方面,采用基于眼睛和嘴部状态的分析方法,重点监测眼睛开闭状态、眨眼频率及哈欠次数等生理指标;在不安全行为识别方面,结合计算机视觉与深度学习技术,实时检测驾驶员的潜在危险操作,从而确保及时发现安全风险。结果表明:经过优化后的YOLOv5-高效通道关注(ECA)模型在疲劳状态和不安全行为识别中性能得到显著提升;模型在测试集上的精确率和召回率均超过90%,展现出良好的识别能力。

, correspAuthors=李华, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Vdd5Bjt7rYYHCKDcEoc9jg==, magXml=i5yuQw9wiCkD9i11xs15tQ==, pdfUrl=null, pdf=nR35n1JNpXNZoR9hb6EQ1g==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=dEhwpcv/k4TztyjJOIi0vQ==, mapNumber=null, authorCompany=null, fund=null, authors=

李 华 (1979—),女,陕西西安人,博士,副教授,硕士生导师,主要从事企业风险评估与安全管理、建筑安全监测与监控、公共安全与应急管理等方面的研究。E-mail:

钟兴润,讲师

, authorsList=李华, 吴立舟, 钟兴润, 郭粮玮, 崔煜馨)}, authors=[Author(id=1165678413823095388, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lihua@xauat.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678413881815646, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678413823095388, language=EN, stringName=Hua LI, firstName=Hua, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678413936341599, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678413823095388, language=CN, stringName=李华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安建筑科技大学 资源工程学院,陕西 西安 710055, bio={"content":"

李 华 (1979—),女,陕西西安人,博士,副教授,硕士生导师,主要从事企业风险评估与安全管理、建筑安全监测与监控、公共安全与应急管理等方面的研究。E-mail:

"}, bioImg=null, bioContent=

李 华 (1979—),女,陕西西安人,博士,副教授,硕士生导师,主要从事企业风险评估与安全管理、建筑安全监测与监控、公共安全与应急管理等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678413747597912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, xref=null, ext=[AuthorCompanyExt(id=1165678413751792217, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China), AuthorCompanyExt(id=1165678413760180826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安建筑科技大学 资源工程学院,陕西 西安 710055)])]), Author(id=1165678413990867553, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678414057976419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678413990867553, language=EN, stringName=Lizhou WU, firstName=Lizhou, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678414120890980, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678413990867553, language=CN, stringName=吴立舟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安建筑科技大学 资源工程学院,陕西 西安 710055, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678413747597912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, xref=null, ext=[AuthorCompanyExt(id=1165678413751792217, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China), AuthorCompanyExt(id=1165678413760180826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安建筑科技大学 资源工程学院,陕西 西安 710055)])]), Author(id=1165678414200582758, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678414288663144, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678414200582758, language=EN, stringName=Xingrun ZHONG, firstName=Xingrun, middleName=null, lastName=ZHONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678414347383401, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678414200582758, language=CN, stringName=钟兴润, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安建筑科技大学 资源工程学院,陕西 西安 710055, bio={"content":"

钟兴润,讲师

"}, bioImg=null, bioContent=

钟兴润,讲师

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678413747597912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, xref=null, ext=[AuthorCompanyExt(id=1165678413751792217, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China), AuthorCompanyExt(id=1165678413760180826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安建筑科技大学 资源工程学院,陕西 西安 710055)])]), Author(id=1165678414410297963, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678414473212525, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678414410297963, language=EN, stringName=Liangwei GUO, firstName=Liangwei, middleName=null, lastName=GUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678414523544174, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678414410297963, language=CN, stringName=郭粮玮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安建筑科技大学 资源工程学院,陕西 西安 710055, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678413747597912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, xref=null, ext=[AuthorCompanyExt(id=1165678413751792217, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China), AuthorCompanyExt(id=1165678413760180826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安建筑科技大学 资源工程学院,陕西 西安 710055)])]), Author(id=1165678414603235952, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678414657761906, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678414603235952, language=EN, stringName=Yuxin CUI, firstName=Yuxin, middleName=null, lastName=CUI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678414745842291, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, authorId=1165678414603235952, language=CN, stringName=崔煜馨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=西安建筑科技大学 资源工程学院,陕西 西安 710055, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678413747597912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, xref=null, ext=[AuthorCompanyExt(id=1165678413751792217, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China), AuthorCompanyExt(id=1165678413760180826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安建筑科技大学 资源工程学院,陕西 西安 710055)])])], keywords=[Keyword(id=1165678414871671412, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, orderNo=1, keyword=computer vision), Keyword(id=1165678415001694837, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, orderNo=2, keyword=fatigue state), Keyword(id=1165678415047832182, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, orderNo=3, keyword=unsafe behavior detection), Keyword(id=1165678415102358135, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, orderNo=4, keyword=tower crane driver), Keyword(id=1165678415161078392, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, orderNo=5, keyword=YOLOv5), Keyword(id=1165678415215604345, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, orderNo=1, keyword=计算机视觉), Keyword(id=1165678415270130298, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, orderNo=2, keyword=疲劳状态), Keyword(id=1165678415324656251, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, orderNo=3, keyword=不安全行为状态), Keyword(id=1165678415391765116, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, orderNo=4, keyword=塔吊驾驶员), Keyword(id=1165678415442096765, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, orderNo=5, keyword=YOLOv5)], refs=[Reference(id=1165678417140789909, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=SHAIK M, journalName=Transportation Research Interdisciplinary Perspectives, refType=null, unstructuredReference=SHAIK M. A systematic review on detection and prediction of driver drowsiness[J]. Transportation Research Interdisciplinary Perspectives, 2023, 21: DOI:10.1016/j.trip.2023.100864., articleTitle=A systematic review on detection and prediction of driver drowsiness, refAbstract=null), Reference(id=1165678417233064598, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2024, volume=89, issue=null, pageStart=234, pageEnd=250, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=MEHMOOD L, LI Heng, UMER W, journalName=Journal of Safety Research, refType=null, unstructuredReference=MEHMOOD L, LI Heng, UMER W, et al. Non-invasive detection of mental fatigue in construction equipment operators through geometric measurements of facial features[J]. Journal of Safety Research, 2024, 89: 234-250., articleTitle=Non-invasive detection of mental fatigue in construction equipment operators through geometric measurements of facial features, refAbstract=null), Reference(id=1165678417291784855, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2022, volume=2, issue=null, pageStart=50, pageEnd=59, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=KUWAHARA A, NISHIKAWA K, HIRAKAWA R, journalName=Cognitive Robotics, refType=null, unstructuredReference=KUWAHARA A, NISHIKAWA K, HIRAKAWA R, et al. Eye fatigue estimation using blink detection based on eye aspect ratio mapping(EARM)[J]. Cognitive Robotics, 2022, 2: 50-59., articleTitle=Eye fatigue estimation using blink detection based on eye aspect ratio mapping(EARM), refAbstract=null), Reference(id=1165678417367282328, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=LIU Pengkun, CHI Hunglin, LI Xiao, journalName=Automation in Construction, refType=null, unstructuredReference=LIU Pengkun, CHI Hunglin, LI Xiao, et al. Effects of dataset characteristics on the performance of fatigue detection for crane operators using hybrid deep neural networks[J]. Automation in Construction, 2021, 132: DOI:10.1016/j.autcon.2021.103901., articleTitle=Effects of dataset characteristics on the performance of fatigue detection for crane operators using hybrid deep neural networks, refAbstract=null), Reference(id=1165678417430196889, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=11, pageStart=30, pageEnd=37, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=孙世梅, 孙祖航, 冯子阳, journalName=中国安全科学学报, refType=null, unstructuredReference=孙世梅, 孙祖航, 冯子阳, 等. 基于行为安全“2-4”模型理论的建筑施工事故行为原因分析[J]. 中国安全科学学报, 2023, 33(11): 30-37., articleTitle=基于行为安全“2-4”模型理论的建筑施工事故行为原因分析, refAbstract=null), Reference(id=1165678417497305754, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=11, pageStart=30, pageEnd=37, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=SUN Shimei, SUN Zuhang, FENG Ziyang, journalName=China Safety Science Journal, refType=null, unstructuredReference=SUN Shimei, SUN Zuhang, FENG Ziyang, et al. Behavioral causes analysis of construction accidents based on behavior-based accident causation 24Model theory[J]. China Safety Science Journal, 2023, 33(11): 30-37., articleTitle=Behavioral causes analysis of construction accidents based on behavior-based accident causation 24Model theory, refAbstract=null), Reference(id=1165678417623134875, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=5, pageStart=52, pageEnd=57, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=蔡闯闯, 刘庆华, journalName=江苏科技大学学报:自然科学版, refType=null, unstructuredReference=蔡闯闯, 刘庆华. 基于多特征数据融合的疲劳驾驶检测研究[J]. 江苏科技大学学报:自然科学版, 2023, 37(5): 52-57., articleTitle=基于多特征数据融合的疲劳驾驶检测研究, refAbstract=null), Reference(id=1165678417686049436, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=37, issue=5, pageStart=52, pageEnd=57, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=CAI Chuangchuang, LIU Qinghua, journalName=Journal of Jiangsu Normal University: Natural Science Edition, refType=null, unstructuredReference=CAI Chuangchuang, LIU Qinghua. Research on fatigue driving detection based on multi-feature data fusion[J]. Journal of Jiangsu Normal University: Natural Science Edition, 2023, 37(5): 52-57., articleTitle=Research on fatigue driving detection based on multi-feature data fusion, refAbstract=null), Reference(id=1165678417740575389, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=1, pageStart=147, pageEnd=152, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=辛嵩, 宋明达, 王泽明, journalName=安全与环境学报, refType=null, unstructuredReference=辛嵩, 宋明达, 王泽明, 等. 针对特定驾驶员的疲劳驾驶检测方法[J]. 安全与环境学报, 2023, 23(1): 147-152., articleTitle=针对特定驾驶员的疲劳驾驶检测方法, refAbstract=null), Reference(id=1165678417858015902, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=1, pageStart=147, pageEnd=152, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=XIN Song, SONG Mingda, WANG Zeming, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=XIN Song, SONG Mingda, WANG Zeming, et al. Fatigue driving detection method for specific drivers[J]. Journal of Safety and Environment, 2023, 23(1): 147-152., articleTitle=Fatigue driving detection method for specific drivers, refAbstract=null), Reference(id=1165678417929319071, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=12, pageStart=4887, pageEnd=4894, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=王红君, 白浩, 赵辉, journalName=科学技术与工程, refType=null, unstructuredReference=王红君, 白浩, 赵辉, 等. 基于计算机视觉的驾驶员疲劳状态检测预警技术[J]. 科学技术与工程, 2022, 22(12): 4887-4894., articleTitle=基于计算机视觉的驾驶员疲劳状态检测预警技术, refAbstract=null), Reference(id=1165678417992233632, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=12, pageStart=4887, pageEnd=4894, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=WANG Hongjun, BAI Hao, ZHAO Hui, journalName=Science Technology and Engineering, refType=null, unstructuredReference=WANG Hongjun, BAI Hao, ZHAO Hui, et al. Driver fatigue state detection and early warning technology based on computer vision[J]. Science Technology and Engineering, 2022, 22(12): 4887-4894., articleTitle=Driver fatigue state detection and early warning technology based on computer vision, refAbstract=null), Reference(id=1165678418059342497, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=57, issue=7, pageStart=1287, pageEnd=1296, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=方浩杰, 董红召, 林少轩, journalName=浙江大学学报:工学版, refType=null, unstructuredReference=方浩杰, 董红召, 林少轩, 等. 多特征融合的驾驶员疲劳状态检测方法[J]. 浙江大学学报:工学版, 2023, 57(7): 1287-1296., articleTitle=多特征融合的驾驶员疲劳状态检测方法, refAbstract=null), Reference(id=1165678418105479842, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=57, issue=7, pageStart=1287, pageEnd=1296, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=FANG Haojie, DONG Hongzhao, LIN Shaoxuan, journalName=Journal of Zhejiang University: Engineering Science, refType=null, unstructuredReference=FANG Haojie, DONG Hongzhao, LIN Shaoxuan, et al. Driver fatigue state detection method based on multi-feature fusion[J]. Journal of Zhejiang University: Engineering Science, 2023, 57(7): 1287-1296., articleTitle=Driver fatigue state detection method based on multi-feature fusion, refAbstract=null), Reference(id=1165678418168394403, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=2, pageStart=373, pageEnd=379, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=田水承, 郭谦, 张江江, journalName=西安科技大学学报, refType=null, unstructuredReference=田水承, 郭谦, 张江江, 等. 基于蒙特卡罗法的建筑工人不安全行为风险评估[J]. 西安科技大学学报, 2023, 43(2): 373-379., articleTitle=基于蒙特卡罗法的建筑工人不安全行为风险评估, refAbstract=null), Reference(id=1165678418222920356, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=2, pageStart=373, pageEnd=379, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=TIAN Shuicheng, GUO Qian, ZHANG Jiangjiang, journalName=Journal of Xi'an University of Science and Technology, refType=null, unstructuredReference=TIAN Shuicheng, GUO Qian, ZHANG Jiangjiang, et al. Risk assessment of unsafe behaviors of construction workers based on Monte Carlo method[J]. Journal of Xi'an University of Science and Technology, 2023, 43(2): 373-379., articleTitle=Risk assessment of unsafe behaviors of construction workers based on Monte Carlo method, refAbstract=null), Reference(id=1165678418277446309, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=9, pageStart=69, pageEnd=75, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=李华, 吴立舟, 薛曦澄, journalName=中国安全科学学报, refType=null, unstructuredReference=李华, 吴立舟, 薛曦澄, 等. 基于计算机视觉的高处临边作业安全巡检[J]. 中国安全科学学报, 2023, 33(9): 69-75., articleTitle=基于计算机视觉的高处临边作业安全巡检, refAbstract=null), Reference(id=1165678418369720998, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=9, pageStart=69, pageEnd=75, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=LI Hua, WU Lizhou, XUE Xicheng, journalName=China Safety Science Journal, refType=null, unstructuredReference=LI Hua, WU Lizhou, XUE Xicheng, et al. Computer vision based safety detection of high abutting edges[J]. China Safety Science Journal, 2023, 33(9): 69-75., articleTitle=Computer vision based safety detection of high abutting edges, refAbstract=null), Reference(id=1165678418441024167, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=1, pageStart=122, pageEnd=127, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=叶贵, 王妍, 任梦雪, journalName=中国安全生产科学技术, refType=null, unstructuredReference=叶贵, 王妍, 任梦雪, 等. 体力疲劳对建筑工人不安全行为的影响效应研究[J]. 中国安全生产科学技术, 2023, 19(1): 122-127., articleTitle=体力疲劳对建筑工人不安全行为的影响效应研究, refAbstract=null), Reference(id=1165678418495550120, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2023, volume=19, issue=1, pageStart=122, pageEnd=127, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=YE Gui, WANG Yan, REN Mengxue, journalName=Journal of Safety Science and Technology, refType=null, unstructuredReference=YE Gui, WANG Yan, REN Mengxue, et al. Study on influence effect of physical fatigue on unsafe behavior of construction workers[J]. Journal of Safety Science and Technology, 2023, 19(1): 122-127., articleTitle=Study on influence effect of physical fatigue on unsafe behavior of construction workers, refAbstract=null), Reference(id=1165678418566853289, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=4, pageStart=712, pageEnd=719, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=史玉芳, 卢吉发, journalName=西安科技大学学报, refType=null, unstructuredReference=史玉芳, 卢吉发. 基于SEM的建筑工人疲劳对不安全行为影响机理[J]. 西安科技大学学报, 2020, 40(4): 712-719., articleTitle=基于SEM的建筑工人疲劳对不安全行为影响机理, refAbstract=null), Reference(id=1165678418654933674, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=4, pageStart=712, pageEnd=719, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=SHI Yufang, LU Jifa, journalName=Journal of Xi'an University of Science and Technology, refType=null, unstructuredReference=SHI Yufang, LU Jifa. Research on the impact of construction workers fatigue on unsafe behaviors based on SEM[J]. Journal of Xi'an University of Science and Technology, 2020, 40(4): 712-719., articleTitle=Research on the impact of construction workers fatigue on unsafe behaviors based on SEM, refAbstract=null)], funds=[Fund(id=1165678417002377876, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, awardId=X202410703391, language=CN, fundingSource=西安建筑科技大学创新创业训练计划项目(X202410703391), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1165678413747597912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, xref=null, ext=[AuthorCompanyExt(id=1165678413751792217, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China), AuthorCompanyExt(id=1165678413760180826, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, companyId=1165678413747597912, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=西安建筑科技大学 资源工程学院,陕西 西安 710055)])], figs=[ArticleFig(id=1165678415580508798, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.1, caption=Frame diagram of comprehensive identification of fatigue state and unsafe behavior, figureFileSmall=J90IL9/GFzZwmAUrRm9wjw==, figureFileBig=fSeCE/LmJ/i7VcxkNqexHA==, tableContent=null), ArticleFig(id=1165678415647617663, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图1, caption=疲劳状态与不安全行为综合识别框架, figureFileSmall=J90IL9/GFzZwmAUrRm9wjw==, figureFileBig=fSeCE/LmJ/i7VcxkNqexHA==, tableContent=null), ArticleFig(id=1165678415723115136, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.2, caption=Key point marks for left and right eyes, figureFileSmall=0bvyt3+DwnmigjxBMzvovA==, figureFileBig=VZPQP5tOcOHbzMF11eCW9g==, tableContent=null), ArticleFig(id=1165678415777641089, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图2, caption=左右眼关键点标记, figureFileSmall=0bvyt3+DwnmigjxBMzvovA==, figureFileBig=VZPQP5tOcOHbzMF11eCW9g==, tableContent=null), ArticleFig(id=1165678415827972738, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.3, caption=Key point marks on mouth, figureFileSmall=9vGhCYogRj59FrpuQhuyKg==, figureFileBig=C35K+hAHA/7jKkEa0pWrOQ==, tableContent=null), ArticleFig(id=1165678415890887299, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图3, caption=嘴部关键点标记, figureFileSmall=9vGhCYogRj59FrpuQhuyKg==, figureFileBig=C35K+hAHA/7jKkEa0pWrOQ==, tableContent=null), ArticleFig(id=1165678415949607556, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.4, caption=Code structure determined by fatigue state, figureFileSmall=XN1V+0Y2BW/JoxzAcIC1LQ==, figureFileBig=5ri046wMCEeEGoew9khZHQ==, tableContent=null), ArticleFig(id=1165678416012522117, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图4, caption=疲劳状态判定代码结构, figureFileSmall=XN1V+0Y2BW/JoxzAcIC1LQ==, figureFileBig=5ri046wMCEeEGoew9khZHQ==, tableContent=null), ArticleFig(id=1165678416071242374, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.5, caption=Example of unsafe behavior dataset, figureFileSmall=8GMjOJobNnMZ+ITjhUj4lw==, figureFileBig=p17hW6uFqdiKlGH+Z4Mklg==, tableContent=null), ArticleFig(id=1165678416134156935, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图5, caption=不安全行为数据集示例, figureFileSmall=8GMjOJobNnMZ+ITjhUj4lw==, figureFileBig=p17hW6uFqdiKlGH+Z4Mklg==, tableContent=null), ArticleFig(id=1165678416188682888, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.6, caption=Flowchart of unsafe behavior identification, figureFileSmall=f4MV3xz29974bVQqxKI1DQ==, figureFileBig=EUorSEXyq53vTIWXEzJhYg==, tableContent=null), ArticleFig(id=1165678416247403145, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图6, caption=不安全行为识别流程, figureFileSmall=f4MV3xz29974bVQqxKI1DQ==, figureFileBig=EUorSEXyq53vTIWXEzJhYg==, tableContent=null), ArticleFig(id=1165678416310317706, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.7, caption=Results of model training data, figureFileSmall=hJcOtk31efB/ca1L5y712A==, figureFileBig=9OiQrgBrqRoHiaWDQqVZUQ==, tableContent=null), ArticleFig(id=1165678416373232267, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图7, caption=模型训练数据结果, figureFileSmall=hJcOtk31efB/ca1L5y712A==, figureFileBig=9OiQrgBrqRoHiaWDQqVZUQ==, tableContent=null), ArticleFig(id=1165678416423563916, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.8, caption=YOLOv5-ECA identification effect diagram, figureFileSmall=YNqGhgtZEgnWMkCYym4hyw==, figureFileBig=q2R8NoDaRx6VlXqxgLxqJw==, tableContent=null), ArticleFig(id=1165678416499061389, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图8, caption=YOLOv5-ECA识别效果, figureFileSmall=YNqGhgtZEgnWMkCYym4hyw==, figureFileBig=q2R8NoDaRx6VlXqxgLxqJw==, tableContent=null), ArticleFig(id=1165678416553587342, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Fig.9, caption=Effect of recognition system for fatigue and unsafe behavior of crane drivers, figureFileSmall=NPKfUJ82cXgpQC2F5ms0Sg==, figureFileBig=X1AmKFA/ek71GGhyLa/5Mw==, tableContent=null), ArticleFig(id=1165678416603918991, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=图9, caption=塔吊驾驶员疲劳与不安全行为识别系统效果, figureFileSmall=NPKfUJ82cXgpQC2F5ms0Sg==, figureFileBig=X1AmKFA/ek71GGhyLa/5Mw==, tableContent=null), ArticleFig(id=1165678416658444944, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Table 1, caption=

Perclos value table of fatigue classification

, figureFileSmall=null, figureFileBig=null, tableContent=
Perclos取值 疲劳等级
[0,0.1) 清醒
[0.1,0.3) 临界状态
[0.3,0.4) 轻度疲劳
[0.4,0.5) 中度疲劳
[0.5,1.2) 严重疲劳
), ArticleFig(id=1165678416721359505, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=表1, caption=

疲劳分级Perclos取值[8]

, figureFileSmall=null, figureFileBig=null, tableContent=
Perclos取值 疲劳等级
[0,0.1) 清醒
[0.1,0.3) 临界状态
[0.3,0.4) 轻度疲劳
[0.4,0.5) 中度疲劳
[0.5,1.2) 严重疲劳
), ArticleFig(id=1165678416784274066, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=EN, label=Table 2, caption=

Fitting results of the 200th round of five model methods

, figureFileSmall=null, figureFileBig=null, tableContent=
训练方法 P R mAP@
0.5
mAP@
0.5:0.95
模型内
存/MB
YOLOv5 0.914 0.897 0.934 0.726 13.7
YOLOv5-CA 0.923 0.901 0.942 0.723 15.2
YOLOv5-CBAM 0.911 0.909 0.941 0.722 14.7
YOLOv5-ECA 0.923 0.905 0.940 0.723 13.7
YOLOv5-SE 0.904 0.904 0.934 0.715 14.7
), ArticleFig(id=1165678416872354451, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720297082900, language=CN, label=表2, caption=

5种模型方法第200轮拟合结果

, figureFileSmall=null, figureFileBig=null, tableContent=
训练方法 P R mAP@
0.5
mAP@
0.5:0.95
模型内
存/MB
YOLOv5 0.914 0.897 0.934 0.726 13.7
YOLOv5-CA 0.923 0.901 0.942 0.723 15.2
YOLOv5-CBAM 0.911 0.909 0.941 0.722 14.7
YOLOv5-ECA 0.923 0.905 0.940 0.723 13.7
YOLOv5-SE 0.904 0.904 0.934 0.715 14.7
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754269350027, createdBy=null, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1159052918994595848, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1754269350050, updatedTime=1754269350050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1159052919040733193, language=EN, name=China Safety Science Journal, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1754269350061, updatedTime=1754269350061, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.03.0749, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2025.03.0749, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2025.03.0749, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2025.03.0749, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于计算机视觉的人员疲劳状态与不安全行为识别
收藏切换
PDF下载
李华 , 吴立舟 , 钟兴润 , 郭粮玮 , 崔煜馨
中国安全科学学报 | 安全社会科学与安全管理 2025,35(3): 28-35
收起
收藏切换
中国安全科学学报 | 安全社会科学与安全管理 2025, 35(3): 28-35
基于计算机视觉的人员疲劳状态与不安全行为识别
全屏
李华 , 吴立舟, 钟兴润, 郭粮玮, 崔煜馨
作者信息
  • 西安建筑科技大学 资源工程学院,陕西 西安 710055
  • 李 华 (1979—),女,陕西西安人,博士,副教授,硕士生导师,主要从事企业风险评估与安全管理、建筑安全监测与监控、公共安全与应急管理等方面的研究。E-mail:

    钟兴润,讲师

Recognition of personnel fatigue state and unsafe behavior based on computer vision
Hua LI , Lizhou WU, Xingrun ZHONG, Liangwei GUO, Yuxin CUI
Affiliations
  • School of Resources Engineering,Xi'an University of Architecture and Technology,Xi'an Shaanxi 710055,China
出版时间: 2025-03-28 doi: 10.16265/j.cnki.issn1003-3033.2025.03.0749
文章导航
收藏切换

以提高塔吊操作的安全性和效率为案例,提出一种综合识别疲劳状态和不安全行为的方法,以实时发现驾驶员可能存在的安全隐患。通过摄像头捕获实时视频流,并对视频进行分析和预处理,提取关键信息,用于识别后续的疲劳和不安全行为;在疲劳状态识别方面,采用基于眼睛和嘴部状态的分析方法,重点监测眼睛开闭状态、眨眼频率及哈欠次数等生理指标;在不安全行为识别方面,结合计算机视觉与深度学习技术,实时检测驾驶员的潜在危险操作,从而确保及时发现安全风险。结果表明:经过优化后的YOLOv5-高效通道关注(ECA)模型在疲劳状态和不安全行为识别中性能得到显著提升;模型在测试集上的精确率和召回率均超过90%,展现出良好的识别能力。

计算机视觉  /  疲劳状态  /  不安全行为状态  /  塔吊驾驶员  /  YOLOv5

Taking improving the safety and efficiency of tower crane operation as an example,a method of integrated identification of fatigue state and unsafe behavior was proposed in order to detect the potential safety hazards of drivers in real time. A live video stream was captured via a camera,and the video was analyzed and pre-processed to extract critical information for identifying subsequent fatigue and unsafe behavior. In terms of fatigue state recognition,the analysis method based on the state of eyes and mouth was used to monitor the physiological indicators such as the state of eyes opening and closing,the blink frequency and yawn frequency. In terms of unsafe behavior identification,computer vision and deep learning technology were combined to detect the potential dangerous operations of drivers in real time,thus ensuring timely detection of safety risks. The results show that the performance of the optimized YOLOv5-ECA(Efficient Channel Attention) model is significantly improved in fatigue state and unsafe behavior recognition. The accuracy rate and recall rate of the model on the test set are more than 90%,showing good recognition ability.

computer vision  /  fatigue state  /  unsafe behavior detection  /  tower crane driver  /  YOLOv5
李华, 吴立舟, 钟兴润, 郭粮玮, 崔煜馨. 基于计算机视觉的人员疲劳状态与不安全行为识别. 中国安全科学学报, 2025 , 35 (3) : 28 -35 . DOI: 10.16265/j.cnki.issn1003-3033.2025.03.0749
Hua LI, Lizhou WU, Xingrun ZHONG, Liangwei GUO, Yuxin CUI. Recognition of personnel fatigue state and unsafe behavior based on computer vision[J]. China Safety Science Journal, 2025 , 35 (3) : 28 -35 . DOI: 10.16265/j.cnki.issn1003-3033.2025.03.0749
在建筑领域,塔吊作为常见的重型设备,承担着物料搬运和吊装的重要任务。然而,塔吊驾驶员的疲劳和不安全行为可能导致严重事故,威胁工人生命安全,造成财产损失和工程延误。因此,有效监测和预防塔吊安全具有重要实践意义。
近年来,驾驶员疲劳已成为导致塔吊事故的关键因素,尤其在长时间操作施工设备时,疲劳风险显著增加,对驾驶员健康和作业安全造成重大影响[1]。目前,基于面部特征的疲劳识别方法逐渐受到关注,特别是眼动监测和面部表情分析技术已成为非侵入性疲劳检测的重要手段。研究表明:融合多种生理信号能够显著提升疲劳识别的准确性,尤其是眼动指标在疲劳检测中的应用表现出良好效果[2-3]。基于面部视觉特征的疲劳识别方法,因其无接触性,具有较强的实施优势,能够通过早期警示疲劳有效预防起重机操作中的安全风险[4]。然而,现有研究大多集中于单一的疲劳识别,忽视了驾驶员行为与疲劳状态的交互影响,特别是在建筑项目中,工人的不安全行为往往是事故的主要诱因[5]
鉴于此,笔者拟设计一种基于计算机的塔吊驾驶员疲劳与不安全行为识别方法,通过计算机视觉技术和智能监控设备,捕获并分析实时视频流,提取关键特征以识别疲劳状态和不安全行为。重点比较不同模型性能,优化识别方案;探讨疲劳状态与不安全行为的关联,以期为更全面地评估和控制工地安全风险提供依据,为工地安全管理提供理论依据和技术支持,帮助提升现场作业的安全性和效率。
疲劳状态与不安全行为识别框架如图1所示。包括实时视频流的捕获与预处理、疲劳状态与不安全行为的独立识别与分析,以及综合识别结果的警报触发机制。将疲劳状态与不安全行为的检测有机结合,可有效提升塔吊驾驶员作业的安全性和工作效率。
在人脸识别和疲劳驾驶识别中,人脸识别与特征点定位至关重要,能够准确识别出人脸及关键特征点,如眼睛和嘴巴等。研究表明:疲劳状态下驾驶员的眨眼频率减少、眼睑开合幅度变小,口腔活动增加,因此,观察眼睛和嘴巴的状态是判断疲劳的有效方法[6]。此外,面部肌肉松弛和头部姿态变化也能反映疲劳,但实时监测面临技术挑战。因此,重点关注眼睛和嘴巴,以提高疲劳识别的准确性和效率。
眼睛闭合程度和嘴部状态的变化主要涉及几个关键特征:眼睑闭合程度的时间占比(Percentage of eyelid closure over time,Perclos)、眨眼频率、眼睛开合程度(Eye Aspect Ratio,EAR)和嘴巴开合程度(Mouth Aspect Ratio,MAR)。这些特征能够有效反映疲劳状态,人眼关键点标记如图2所示,图中,Di表示面部节点中各节点的位置。
通过图2分别获取左、右眼的EAR,见下式:
E A R L = D 1 - D 5 + D 2 - D 4 2 D 6 - D   3 E A R R = D 7 - D 11 + D 8 - D 10 2 D 12 - D 9
考虑到人眼睁开和闭合时,2只眼睛是同步进行的。为提高算法的准确性和鲁棒性,融合2只眼睛的EAR,综合评估驾驶员的疲劳状态。融合后的EAR见下式:
E A R = 1 2 ( E A R L + E A R R )
在驾驶员处于疲劳状态时,通常会出现打哈欠现象。此时嘴唇上下距离增大,而嘴角的左右宽度减小。因此,通过计算MAR来判断嘴巴的张开程度,从而判断驾驶员是否处于疲劳状态。嘴部的特征点标记如图3所示。
由于疲劳水平逐渐积累,不会在短时间内显著变化,因此,对判断速度的要求较低。然而,触发疲劳警报可能干扰驾驶,需提高识别准确性,尽量减少误报警[7]。为避免嘴唇厚度差异对判别造成误差,采用嘴部内轮廓计算MAR。其中,MAR计算见下式:
M A R = D 26 - D 32 + D 28 - D 30 2 D 13 - D 19
在塔吊司机的安全管理中,疲劳识别算法至关重要。2种常见方法分别为基于Dlib算法的人脸关键点提取和基于Perclos特征的疲劳评估。
Dlib是一个广泛应用的开源C++工具包,提供机器学习和计算机视觉算法。它在疲劳识别中用于人脸识别与关键点定位,能够准确捕捉驾驶员面部信息,如眼睛和嘴巴位置。提取的面部特征信息可嵌套于YOLO算法,进一步分析面部表情与姿态,以评估驾驶员的疲劳状态。
Perclos特征是一种常用的生物信号,用于评估驾驶员疲劳程度,通过分析Perclos间接推断疲劳状态。当Perclos值超过某个阈值时,驾驶员被视为疲劳。综合眼部和嘴部Perclos值并基于不同权重进行加权平均,生成最终的疲劳评分。该模型为工作场所的安全管理提供重要依据,疲劳状态判定的代码结构如图4所示。
由于眨眼频率、闭眼次数和打哈欠频率的单位不同,需标准化处理指标。王红君等[8]通过数学方法实时融合各指标,分级驾驶员的疲劳状态,验证模型的准确性,综合疲劳分级情况见表1
在眼部状态参数的计算中,模型利用眼部关键点的位置信息计算EAR,反映眨眼频率和眼睑闭合程度。为提高参数的准确性和稳定性,模型还考虑人脸面积的计算补偿。此外,模型分析嘴部状态,通过提取嘴部关键点的位置信息计算MAR,评估驾驶员的嘴部活动,尤其是频繁打哈欠的行为,这通常表明疲劳状态。
方浩杰等[9]结合人脸关键点算法提出参数补偿机制,以提高眨眼和打哈欠帧数的准确率,并将多种疲劳参数进行融合和归一化处理,以开展疲劳等级划分。基于眼部和嘴部状态参数的计算结果,综合考虑过去150帧的数据,形成Perclos模型得分。当得分超过预设阈值时,模型将触发疲劳警报,提醒驾驶员及时休息,以确保工程安全和驾驶员健康。Perclos模型得分的计算见下式[8]
P e r c l o s = R E R + R M R × 0.2
式中:(Rolleye,RE)为过去150帧中眼睛闭合帧数;(Rollmouth,RM)为嘴巴动作帧数;R为总帧数,取150帧。如果计算出的Perclos模型得分超过0.38,则判断驾驶员处于疲劳状态;当Perclos得分高于该阈值时,表示驾驶员的眼睛和嘴巴活动频率异常,可能处于疲劳状态。
YOLOv5作为高效目标识别算法,适用于塔吊司机不安全行为的实时识别,如使用手机和抽烟等,能够为行为分析提供准确结果。针对YOLOv5的性能优化,当前主要策略是引入多种注意力模型,包括协调注意力(Coordinate Attention,CA)模块、卷积注意力(Convolutional Block Attention Module,CBAM)模块、高效通道关注(Efficient Channel Attention,ECA)模块和挤压-激发(Squeeze-and-Excitation networks,SE)模块。这些注意力模型旨在增强模型对特定区域的感知能力,提升目标识别的准确性和鲁棒性。引入这些模型丰富了YOLOv5的特征表达能力,有助于提高目标识别的性能和精度,使其在复杂场景下的目标识别任务中表现更加出色。
在不安全行为分析与识别方面,建筑工地事故风险引起关注。研究表明:建筑工人行为风险差异明显,起重伤害风险最高[10]。文中重点关注手机使用、抽烟、喝水等行为,并探讨这些行为对工地安全的潜在影响。例如:手机使用可能导致驾驶员分心,增加操作失误和事故发生的风险,而抽烟行为则可能引发周围环境的火灾风险等不良后果。
1) 数据采集与预处理。针对塔吊驾驶员的不安全行为,构建一个包含7 507张有效照片的数据集,按8∶2比例划分为训练集和测试集,涵盖人脸、吸烟、喝水和使用手机4个方面。为聚焦于喝水和使用手机,调查工地常见饮料和畅销手机品牌。根据工人饮品偏好排名,选取代表性饮料构建数据集,同时参考近3年国内手机销量排行榜增加手机数据样本。
在数据预处理阶段,首先通过质量控制筛选图片,排除模糊或质量不佳的图像,仅保留清晰图像,筛选后的数据集示例如图5所示。然后利用LabelImg标注工具逐张标记,确保准确识别不安全行为并为每个区域添加标签。标注过程中,重点确保标记的准确性和一致性。最后审查和修正数据,确保数据集的高质量和可用性。
2) 不安全行为识别。不安全行为识别是系统的关键功能之一,旨在及时识别驾驶员的不安全行为,如使用手机、抽烟和饮水。该过程主要包括3个步骤:①图像处理。系统通过车载摄像头实时捕获驾驶员图像,并进行预处理,以突出关键信息。②特征提取。利用计算机视觉技术提取驾驶员的面部表情和手部动作等关键特征。③行为识别。通过深度学习模型分析提取的特征,判断是否存在不安全操作行为。
不安全行为识别的结果通过图像标记和文字提示呈现给驾驶员。系统标记不安全行为区域,并在界面上显示相应提示,如“正在用手机,请不要分心”或“正在抽烟,请注意安全”。不安全行为识别流程如图6所示。
通过以上方法和结果呈现方式,系统能够及时准确地识别驾驶员的不安全行为,有效提高驾驶员的安全意识和行为规范水平。为安全管理提供数据支持,进一步促进工地安全管理水平的提升。
3) 综合识别流程。在塔吊操作中,驾驶员的疲劳状态和不安全行为可能导致严重的安全事故。系统通过初始化摄像头并捕获视频流的方式获取塔吊驾驶员的实时图像数据,并预处理和分析视频流,以提取关键信息用于识别疲劳和不安全行为。针对塔吊驾驶员的疲劳状态,采用基于眼睛状态和嘴部状态的识别方法,通过分析眼睛的开闭状态、眨眼频率以及哈欠次数等指标来判断驾驶员是否处于疲劳状态。不安全行为识别技术主要包括识别驾驶员是否在驾驶过程中进行危险操作,如使用手机、吸烟等。利用计算机视觉和深度学习方法,实时检测和识别驾驶员的行为,以提高作业安全性。
1) 试验环境。模型训练平台选择国家超级计算西安中心提供的超算服务。训练系统配置为7285 32C处理器(16核心)、40 GB内存,搭载2块Z100SM(16 GB)图像处理器,运行TensorFlow和Python 3.7。测试平台为Windows 10,配备Intel Core i5-10400 F处理器、32GB内存和RTX-3060图像处理器(12 GB),运行TensorFlow和Python 3.8,使用CUDA 11.6。疲劳与不安全行为识别系统采用PySide2部署[11]。该系统为驾驶员疲劳识别系统的可视化界面,主要功能包括实时视频监控、疲劳识别指标显示、不安全行为识别指示及摄像头打开功能。
2) 模型评价标准。为评估模型性能,使用验证集测试模型的分类准确性和目标检测效果。验证集由模型的未知数据组成,其中,统计的分类目标仅有2类,分别标记为Positive和Negative。为计算精确率P和召回率R,将真阳性(True Positive,TP)、假阳性(False Positive,FP)和假阴性(False Negative,FN)分别定义为具有默认IoU≥0.6和<0.6的边界框,IoU(Intersection over Union)为交并比,是指预测框A和真实框B的交集除以它们的并集。
精确率P。精确率表示预测为正样本的实例中实际为正样本的比例,P越高,表示模型预测出的正例越准确,误检越少。
召回率R。召回率表示所有实际为正样本的实例中,被模型正确预测为正样本的比例,是衡量模型在识别图像中的对象或目标时,是否能找出全部真实存在的对象或目标的一种指标。R越高,模型漏检的情况就越少。
3) 训练量度。平均精度(Average Precision,AP),由每类目标P值的平均值得来,用于评估该类别的检测性能。均值平均精度(Mean Average Precision,mAP)是所有类别的平均精度求和除以所有类别。作为衡量识别精度的指标。
优化模型虽然能提高识别准确度,但也带来复杂性,具体体现在引入不同注意力模块后,执行时间有所增加。经过200轮的拟合训练,模型参数数量随之增加,模型权重文件的存储空间也略微增大。表2展示5种训练方法在第200轮拟合后的结果,包括精确率P、召回率R以及在不同IoU阈值下的平均精度(mAP@0.5、mAP@0.5∶0.95)。此外,还列出每种模型权重文件的内存占用情况。
图7为模型训练数据结果。如图7a所示,改进的YOLO模型提取的数据与人工标注的数据非常接近,每次测试的精度均超过90%,表明YOLO提取方法在识别训练数据集外的不安全行为时展现出强大性能和高准确性。YOLOv5-ECA模型的性能最佳,在第169步时P达到最大值(0.938 4)。后续推理过程中选择best.pt权重进行评估和推理。
图7b展示了经过200轮优化的YOLOv5-ECA模型训练测试结果雷达图,被分成代表不同类别的象限,使得评估所有类别的性能差异更为明显。值得注意的是,YOLOv5-ECA在多个类别中的表现优于原始模型,4类标签的识别结果稳定,ECA注意力模块的准确率较原始模型提高0.98%。因此,后续测试将基于ECA注意力模块进行。
图7c显示,YOLO模型在作业过程识别方面表现出色,特别是在优化后,YOLOv5模型的P增强显著,YOLOv5-ECA模型在没有增加模型内存情况下改进效果最为明显。
图7d所示的混淆矩阵,模型在识别人脸和喝水类别上表现良好,准确率分别达到94%和97%。然而,在吸烟和喝水类别上的准确率较低,分别为91%和92%,表明在这2个类别中可能存在较多的误分类。为提高模型在吸烟和喝水类别上的准确率,未来将考虑增加更多的训练样本并调整模型参数。
YOLOv5-ECA识别效果如图8所示,识别结果以图像和数据的形式呈现YOLOv5-ECA模型在不同类别(人脸、吸烟、喝水和玩手机)中的表现。在图8a中,人脸识别的精度为0.95;在图8b中,吸烟识别的精度为0.92;在图8c中,喝水识别精度超过0.94;在图8d中,玩手机识别精度为0.95。这种直观的可视化分析不仅提供具体的观察结果,还能系统评估模型在实际场景中的有效性。
在现实驾驶环境中,疲劳状态与不安全行为之间存在复杂而重要的关联。疲劳驾驶员常表现出反应速度下降、注意力不集中等不良行为,增加不安全行为的发生概率。例如:塔吊操作员在疲劳状态下可能出现分散注意力、忽略重要细节或作出冒险决策。同时,频繁的不安全行为也可能加剧驾驶员的疲劳程度,形成恶性循环。叶贵等[12]指出,疲劳直接正向影响建筑工人不安全行为,并通过工作倦怠作为中介因素间接影响建筑工人不安全行为。体力疲劳与建筑工人不安全行为显著正相关,且与工作倦怠也显著相关,因此,减少建筑工人的不安全行为可从降低体力疲劳程度入手。史玉芳等[13]将建筑工人疲劳分为体力疲劳、脑力疲劳和心理疲劳3个维度,开发疲劳量表并构建结构方程模型,通过实证分析验证建筑工人疲劳对不安全行为影响机制。
为有效管理疲劳和不安全行为,需采取综合应对策略。一是建立多层次的行为识别系统。该系统可利用先进的计算机视觉技术和智能监控设备,实时识别和分析驾驶员行为。二是通过及时发现疲劳状态和不安全行为并采取相应措施干预,可降低事故风险。三是构建融合疲劳与不安全行为识别的软件系统,实现全面的驾驶员状态监测和风险预警。
文中人脸关键点识别部分,采用Dlib库中的成熟模型,该库经过广泛测试和验证,具备较高的准确性和稳定性。作为开源项目,Dlib包含丰富的预训练模型和工具,在各种应用场景中表现出色,因此,直接应用Dlib检测人脸关键点是合理且高效的方法。图9展示了使用Dlib进行眼睛和嘴巴特征提取的结果,特征轮廓直观反映检测的实际效果,同时包含疲劳与不安全行为的关联分析示意图,包括人脸识别、吸烟、喝水、使用手机及多种不安全行为的同时识别,以及疲劳状态判定。当系统检测到疲劳或不安全行为时,会及时发出提醒。
1) 提出的综合识别系统有效提升了塔吊操作中驾驶员疲劳状态与不安全行为的实时监测能力。通过融合计算机视觉与深度学习技术,系统能够实时识别塔吊驾驶员眼部与嘴部状态,准确监控行为,显著增强驾驶员的安全意识,有效降低作业中的安全风险。
2) 系统在处理实时视频流时,能够维持高帧率与低延迟,表现出优异的实时检测能力。结合PySide2可视化界面,系统不仅操作简便,而且能够实时反馈驾驶员行为状态,为施工现场的安全管理提供可行的技术支持。
3) 综合识别系统不仅适用对塔吊操作人员疲劳状态的实时监控,还可推广到各行业人员疲劳状态的识别与监控。
4) 系统对操作人员出现疲劳提醒监控数据,还进入企业管理系统,可加强管理系统及时发现与提示安全风险,以及对操作人员进行综合评价。
5) 未来研究将进一步引入人体骨骼节点模型,提升识别精度,并拓展至树莓派平台,开发智能化疲劳与不安全行为识别机器人。
  • 西安建筑科技大学创新创业训练计划项目(X202410703391)
参考文献 引证文献
排序方式:
[1]
SHAIK M. A systematic review on detection and prediction of driver drowsiness[J]. Transportation Research Interdisciplinary Perspectives, 2023, 21: DOI:10.1016/j.trip.2023.100864.
[2]
MEHMOOD L, LI Heng, UMER W, et al. Non-invasive detection of mental fatigue in construction equipment operators through geometric measurements of facial features[J]. Journal of Safety Research, 2024, 89: 234-250.
[3]
KUWAHARA A, NISHIKAWA K, HIRAKAWA R, et al. Eye fatigue estimation using blink detection based on eye aspect ratio mapping(EARM)[J]. Cognitive Robotics, 2022, 2: 50-59.
[4]
LIU Pengkun, CHI Hunglin, LI Xiao, et al. Effects of dataset characteristics on the performance of fatigue detection for crane operators using hybrid deep neural networks[J]. Automation in Construction, 2021, 132: DOI:10.1016/j.autcon.2021.103901.
[5]
孙世梅, 孙祖航, 冯子阳, 等. 基于行为安全“2-4”模型理论的建筑施工事故行为原因分析[J]. 中国安全科学学报, 2023, 33(11): 30-37.
SUN Shimei, SUN Zuhang, FENG Ziyang, et al. Behavioral causes analysis of construction accidents based on behavior-based accident causation 24Model theory[J]. China Safety Science Journal, 2023, 33(11): 30-37.
[6]
蔡闯闯, 刘庆华. 基于多特征数据融合的疲劳驾驶检测研究[J]. 江苏科技大学学报:自然科学版, 2023, 37(5): 52-57.
CAI Chuangchuang, LIU Qinghua. Research on fatigue driving detection based on multi-feature data fusion[J]. Journal of Jiangsu Normal University: Natural Science Edition, 2023, 37(5): 52-57.
[7]
辛嵩, 宋明达, 王泽明, 等. 针对特定驾驶员的疲劳驾驶检测方法[J]. 安全与环境学报, 2023, 23(1): 147-152.
XIN Song, SONG Mingda, WANG Zeming, et al. Fatigue driving detection method for specific drivers[J]. Journal of Safety and Environment, 2023, 23(1): 147-152.
[8]
王红君, 白浩, 赵辉, 等. 基于计算机视觉的驾驶员疲劳状态检测预警技术[J]. 科学技术与工程, 2022, 22(12): 4887-4894.
WANG Hongjun, BAI Hao, ZHAO Hui, et al. Driver fatigue state detection and early warning technology based on computer vision[J]. Science Technology and Engineering, 2022, 22(12): 4887-4894.
[9]
方浩杰, 董红召, 林少轩, 等. 多特征融合的驾驶员疲劳状态检测方法[J]. 浙江大学学报:工学版, 2023, 57(7): 1287-1296.
FANG Haojie, DONG Hongzhao, LIN Shaoxuan, et al. Driver fatigue state detection method based on multi-feature fusion[J]. Journal of Zhejiang University: Engineering Science, 2023, 57(7): 1287-1296.
[10]
田水承, 郭谦, 张江江, 等. 基于蒙特卡罗法的建筑工人不安全行为风险评估[J]. 西安科技大学学报, 2023, 43(2): 373-379.
TIAN Shuicheng, GUO Qian, ZHANG Jiangjiang, et al. Risk assessment of unsafe behaviors of construction workers based on Monte Carlo method[J]. Journal of Xi'an University of Science and Technology, 2023, 43(2): 373-379.
[11]
李华, 吴立舟, 薛曦澄, 等. 基于计算机视觉的高处临边作业安全巡检[J]. 中国安全科学学报, 2023, 33(9): 69-75.
LI Hua, WU Lizhou, XUE Xicheng, et al. Computer vision based safety detection of high abutting edges[J]. China Safety Science Journal, 2023, 33(9): 69-75.
[12]
叶贵, 王妍, 任梦雪, 等. 体力疲劳对建筑工人不安全行为的影响效应研究[J]. 中国安全生产科学技术, 2023, 19(1): 122-127.
YE Gui, WANG Yan, REN Mengxue, et al. Study on influence effect of physical fatigue on unsafe behavior of construction workers[J]. Journal of Safety Science and Technology, 2023, 19(1): 122-127.
[13]
史玉芳, 卢吉发. 基于SEM的建筑工人疲劳对不安全行为影响机理[J]. 西安科技大学学报, 2020, 40(4): 712-719.
SHI Yufang, LU Jifa. Research on the impact of construction workers fatigue on unsafe behaviors based on SEM[J]. Journal of Xi'an University of Science and Technology, 2020, 40(4): 712-719.
2025年第35卷第3期
PDF下载
449
193
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2025.03.0749
  • 接收时间:2024-09-20
  • 首发时间:2025-07-05
  • 出版时间:2025-03-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-09-20
  • 修回日期:2024-11-23
基金
西安建筑科技大学创新创业训练计划项目(X202410703391)
作者信息
    西安建筑科技大学 资源工程学院,陕西 西安 710055
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.03.0749
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏