Article(id=1148106720443887644, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1148106708670477182, articleNumber=1003-3033(2025)03-0036-09, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2025.03.1598, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1728835200000, receivedDateStr=2024-10-14, revisedDate=1734969600000, revisedDateStr=2024-12-24, acceptedDate=null, acceptedDateStr=null, onlineDate=1751659572945, onlineDateStr=2025-07-05, pubDate=1743091200000, pubDateStr=2025-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751659572945, onlineIssueDateStr=2025-07-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1751659572945, creator=13701087609, updateTime=1751659572945, 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=36, endPage=44, ext={EN=ArticleExt(id=1149767556057182791, articleId=1148106720443887644, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Classification and recognition of unsafe behaviors of tobacco warehouse personnel based on improved YOLOv11, columnId=1149733271128420907, journalTitle=China Safety Science Journal, columnName=Safety social science and safety management, runingTitle=null, highlight=null, articleAbstract=

To ensure the safety of personnel and property within the storage environment,the traditional YOLOv11 object detection algorithm was improved,and a method and model to identify unsafe behaviors of personnel in the complex environment of tobacco warehouses were proposed. First,a statistical analysis of common unsafe behavior types in tobacco storage was conducted,and the classification of unsafe behaviors of warehouse personnel was explored,including item-related,action-related,and area-related unsafe behaviors. Second,based on the characteristics of unsafe behaviors of warehouse personnel,a dataset augmentation and denoising preprocessing approach was proposed to enhance fine-grained feature extraction,and introduced to improve the saliency mapping of personnel behaviors. Then,the YOLOv11 algorithm was improved through functional enhancement modules and K-means++ anchor box optimization,and a fast detection method for unsafe behaviors of tobacco warehouse personnel was proposed. Finally,the proposed method's effectiveness was validated by comparing with self-built datasets and the open Microsoft COCO dataset. The results show that the method can quickly and effectively identify unsafe behaviors of warehouse personnel,with a significant improvement in recognition accuracy compared to traditional methods(accuracy rate is 94.91% and 88.69% respectively).

, correspAuthors=Quanjie ZHU, 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=Wei KE, Quanjie ZHU, Changmao CHEN, Chengyi WU, Yan LIU, Yanlin ZHANG), CN=ArticleExt(id=1148106724210373031, articleId=1148106720443887644, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于改进YOLOV11的卷烟仓储人员不安全行为分类及识别, 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=

为确保仓储环境内的人员与财产安全,改进传统的YOLOv11目标检测算法,提出一种适用于卷烟仓储复杂环境的人员不安全行为识别方法和模型。首先,统计分析卷烟仓储中常见的不安全行为类型,探讨仓储人员不安全行为的分类,包括物品类、动作类和区域类的不安全行为;其次,基于仓储人员不安全行为的特征,提出数据集增广和去噪预处理的思路,强化细粒度特征提取,进而改进人员行为的显著性映射;然后,通过功能增强模块和K-means++锚框优化改进YOLOv11算法,提出一种卷烟仓储人员不安全行为快速检测方法;最后,利用自建数据集和微软公开数据集(COCO)对比验证方法的有效性。结果表明:该方法能够快速、有效地识别仓储人员的不安全行为,相较于传统方法,识别准确率得到显著提升,2个数据集上的精度分别达到94.91%和88.69%,综合表现更加均衡。

, correspAuthors=朱权洁, authorNote=null, correspAuthorsNote=
** 朱权洁(1984—),男,湖北孝感人,博士,教授,主要从事数字化矿山、矿山安全、灾害监测预警等方面的研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=H8zhhcPe0be1uksBCG3z+w==, magXml=Gb+XgXunKI1CfX0dALY+gA==, pdfUrl=null, pdf=AV2igpJiAWgb56NZ192aIw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=/gZGOKXMVGitk12D3ldUZQ==, mapNumber=null, authorCompany=null, fund=null, authors=

柯 巍 (1992—),男,湖北十堰人,博士,工程师,主要从事安全生产信息化、企业安全管理、锂离子电池安全防控等方面的工作。E-mail:

陈长茂,政工师;

吴成毅,政工师;

刘 衍,工程师;

张艳林,工程师

, authorsList=柯巍, 朱权洁, 陈长茂, 吴成毅, 刘衍, 张艳林)}, authors=[Author(id=1165678502679421338, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=onlykw@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1165678502746530204, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678502679421338, language=EN, stringName=Wei KE, firstName=Wei, middleName=null, lastName=KE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678502809444765, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678502679421338, language=CN, stringName=柯巍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099, bio={"img":"y885Jiu830REodtq5Gmnwg==","content":"

柯 巍 (1992—),男,湖北十堰人,博士,工程师,主要从事安全生产信息化、企业安全管理、锂离子电池安全防控等方面的工作。E-mail:

"}, bioImg=y885Jiu830REodtq5Gmnwg==, bioContent=

柯 巍 (1992—),男,湖北十堰人,博士,工程师,主要从事安全生产信息化、企业安全管理、锂离子电池安全防控等方面的工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678502473900432, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=1, ext=[AuthorCompanyExt(id=1165678502482289041, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China), AuthorCompanyExt(id=1165678502486483346, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099)])]), Author(id=1165678502872359327, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhqj2016@ncist.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1165678502947856801, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678502872359327, language=EN, stringName=Quanjie ZHU, firstName=Quanjie, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, **, address=2 School of Safety Emergency Technology and Management,North China Institute of Science and Technology,Langfang Hebei 065201,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678503006577058, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678502872359327, language=CN, stringName=朱权洁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, **, address=2 华北科技学院 应急技术与管理学院,河北 廊坊 065201, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678502549397907, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=2, ext=[AuthorCompanyExt(id=1165678502553592212, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502549397907, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Emergency Technology and Management,North China Institute of Science and Technology,Langfang Hebei 065201,China), AuthorCompanyExt(id=1165678502561980821, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502549397907, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 华北科技学院 应急技术与管理学院,河北 廊坊 065201)])]), Author(id=1165678503065297316, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, 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=1165678503136600486, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503065297316, language=EN, stringName=Changmao CHEN, firstName=Changmao, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678503191126439, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503065297316, language=CN, stringName=陈长茂, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099, bio={"content":"

陈长茂,政工师;

"}, bioImg=null, bioContent=

陈长茂,政工师;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678502473900432, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=1, ext=[AuthorCompanyExt(id=1165678502482289041, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China), AuthorCompanyExt(id=1165678502486483346, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099)])]), Author(id=1165678503262429609, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, 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=1165678503329538475, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503262429609, language=EN, stringName=Chengyi WU, firstName=Chengyi, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678503396647340, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503262429609, language=CN, stringName=吴成毅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099, bio={"content":"

吴成毅,政工师;

"}, bioImg=null, bioContent=

吴成毅,政工师;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678502473900432, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=1, ext=[AuthorCompanyExt(id=1165678502482289041, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China), AuthorCompanyExt(id=1165678502486483346, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099)])]), Author(id=1165678503459561902, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, 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=1165678503526670768, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503459561902, language=EN, stringName=Yan LIU, firstName=Yan, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678503589585329, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503459561902, language=CN, stringName=刘衍, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099, bio={"content":"

刘 衍,工程师;

"}, bioImg=null, bioContent=

刘 衍,工程师;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678502473900432, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=1, ext=[AuthorCompanyExt(id=1165678502482289041, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China), AuthorCompanyExt(id=1165678502486483346, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099)])]), Author(id=1165678503648305587, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, orderNo=5, 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=1165678503715414453, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503648305587, language=EN, stringName=Yanlin ZHANG, firstName=Yanlin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Hubei Branch,China National Tobacco Corporation,Wuhan Hubei 430033,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1165678503790911926, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, authorId=1165678503648305587, language=CN, stringName=张艳林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 中国烟草总公司 湖北省公司,湖北 武汉 430033, bio={"content":"

张艳林,工程师

"}, bioImg=null, bioContent=

张艳林,工程师

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1165678502608118166, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=3, ext=[AuthorCompanyExt(id=1165678502616506775, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502608118166, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Hubei Branch,China National Tobacco Corporation,Wuhan Hubei 430033,China), AuthorCompanyExt(id=1165678502624895384, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502608118166, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国烟草总公司 湖北省公司,湖北 武汉 430033)])])], keywords=[Keyword(id=1165678503925129655, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, orderNo=1, keyword=improved YOLOv11), Keyword(id=1165678503988044216, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, orderNo=2, keyword=tobacco warehouse personnel), Keyword(id=1165678504046764473, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, orderNo=3, keyword=unsafe behaviors), Keyword(id=1165678504105484730, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, orderNo=4, keyword=denoising), Keyword(id=1165678504164204987, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, orderNo=5, keyword=object detection), Keyword(id=1165678504222925244, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, orderNo=1, keyword=改进YOLOv11), Keyword(id=1165678504285839805, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, orderNo=2, keyword=卷烟仓储人员), Keyword(id=1165678504348754366, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, orderNo=3, keyword=不安全行为), Keyword(id=1165678504399086015, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, orderNo=4, keyword=去噪), Keyword(id=1165678504449417664, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, orderNo=5, keyword=目标检测)], refs=[Reference(id=1165678505766429139, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2019, volume=6, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=SREENU G, journalName=Journal of Big Data, refType=null, unstructuredReference=SREENU G, SALEEM DURAI M A. Intelligent video surveillance: a review through deep learning techniques for crowd analysis[J]. Journal of Big Data, 2019, 6 (1): DOI: 10.1186/s40537-019-0212-5., articleTitle=Intelligent video surveillance: a review through deep learning techniques for crowd analysis, refAbstract=null), Reference(id=1165678505820955092, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2018, volume=81, issue=null, pageStart=307, pageEnd=313, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=HASSAN M M, UDDIN M D, MOHAMED A, journalName=Future Generation Computer Systems, refType=null, unstructuredReference=HASSAN M M, UDDIN M D, MOHAMED A, et al. A robust human activity recognition system using smartphone sensors and deep learning[J]. Future Generation Computer Systems, 2018, 81: 307-313., articleTitle=A robust human activity recognition system using smartphone sensors and deep learning, refAbstract=null), Reference(id=1165678505879675349, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2018, volume=2, issue=4, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=冯仕民, 刘忠育, 俞啸, journalName=物联网学报, refType=null, unstructuredReference=冯仕民, 刘忠育, 俞啸, 等. 矿山物联网人员情境描述与不安全行为识别[J]. 物联网学报, 2018, 2(4): 93-98., articleTitle=矿山物联网人员情境描述与不安全行为识别, refAbstract=null), Reference(id=1165678505959367126, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2018, volume=2, issue=4, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=FENG Shimin, LIU Zhongyu, YU Xiao, journalName=Chinese Journal on Internet of Things, refType=null, unstructuredReference=FENG Shimin, LIU Zhongyu, YU Xiao, et al. Workers' context description and unsafe behavior recognition in internet of things for mines[J]. Chinese Journal on Internet of Things, 2018, 2(4): 93-98., articleTitle=Workers' context description and unsafe behavior recognition in internet of things for mines, refAbstract=null), Reference(id=1165678506018087383, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=10, pageStart=46, pageEnd=51, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=谢逸, 张竞文, 李韬, journalName=华中科技大学学报:自然科学版, refType=null, unstructuredReference=谢逸, 张竞文, 李韬, 等. 基于视频监控的地铁施工不安全行为检测预警[J]. 华中科技大学学报:自然科学版, 2019, 47(10): 46-51., articleTitle=基于视频监控的地铁施工不安全行为检测预警, refAbstract=null), Reference(id=1165678506081001944, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2019, volume=47, issue=10, pageStart=46, pageEnd=51, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=XIE Yi, ZHANG Jingwen, LI Tao, journalName=Journal Huazhong University of Science and Technology: Natural Science Edition, refType=null, unstructuredReference=XIE Yi, ZHANG Jingwen, LI Tao, et al. Research on detection and early warning of unsafe behavior in metro construction based on video monitoring[J]. Journal Huazhong University of Science and Technology: Natural Science Edition, 2019, 47(10): 46-51., articleTitle=Research on detection and early warning of unsafe behavior in metro construction based on video monitoring, refAbstract=null), Reference(id=1165678506148110809, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2021, volume=17, issue=5, pageStart=1660, pageEnd=1670, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=RAHMANI M, OSKOUEI A N, PETRUDI A M, journalName=Defence Technology, refType=null, unstructuredReference=RAHMANI M, OSKOUEI A N, PETRUDI A M. Experimental and numerical study of the blast wave decrease using sandwich panel by granular materials core[J]. Defence Technology, 2021, 17(5): 1660-1670., articleTitle=Experimental and numerical study of the blast wave decrease using sandwich panel by granular materials core, refAbstract=null), Reference(id=1165678506223608282, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2021, volume=43, issue=1, pageStart=172, pageEnd=186, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=CAO Zhe, HIDALGO M G, SIMON T, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=CAO Zhe, HIDALGO M G, SIMON T, et al. OpenPose: realtime multi-person 2D pose estimation using part affinity fields[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 172-186., articleTitle=OpenPose: realtime multi-person 2D pose estimation using part affinity fields, refAbstract=null), Reference(id=1165678506282328539, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=4, pageStart=1495, pageEnd=1502, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=王松, 党建武, 王阳萍, journalName=吉林大学学报:工学版, refType=null, unstructuredReference=王松, 党建武, 王阳萍, 等. 基于3D运动历史图像和多任务学习的动作识别[J]. 吉林大学学报:工学版, 2020, 50(4): 1495-1502., articleTitle=基于3D运动历史图像和多任务学习的动作识别, refAbstract=null), Reference(id=1165678506341048796, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=4, pageStart=1495, pageEnd=1502, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=WANG Song, DANG Jianwu, WANG Yangping, journalName=Journal of Jilin University: Engineering and Technology Edition, refType=null, unstructuredReference=WANG Song, DANG Jianwu, WANG Yangping, et al. Action recognition based on 3D motion history image and multi-task learning[J]. Journal of Jilin University: Engineering and Technology Edition, 2020, 50(4): 1495-1502., articleTitle=Action recognition based on 3D motion history image and multi-task learning, refAbstract=null), Reference(id=1165678506399769053, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2020, volume=31, issue=null, pageStart=593, pageEnd=607, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=PATEL V, SINGH R, journalName=Journal of Intelligent Manufacturing, refType=null, unstructuredReference=PATEL V, SINGH R. Real-time detection of unsafe behaviors using LSTM[J]. Journal of Intelligent Manufacturing, 2020, 31: 593-607., articleTitle=Real-time detection of unsafe behaviors using LSTM, refAbstract=null), Reference(id=1165678506454295006, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2020, volume=57, issue=24, pageStart=346, pageEnd=350, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=郭如意, 金杰, 刘高华, journalName=激光与光电子学进展, refType=null, unstructuredReference=郭如意, 金杰, 刘高华, 等. 基于双流快速区域卷积神经网络改进的人体动作识别算法[J]. 激光与光电子学进展, 2020, 57(24): 346-350., articleTitle=基于双流快速区域卷积神经网络改进的人体动作识别算法, refAbstract=null), Reference(id=1165678506521403871, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2020, volume=57, issue=24, pageStart=346, pageEnd=350, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=GUO Ruyi, JIN Jie, LIU Gaohua, journalName=Laser & Optoelectronics Progress, refType=null, unstructuredReference=GUO Ruyi, JIN Jie, LIU Gaohua, et al. Improved human action recognition algorithm based on two-stream faster region convolutional neural network[J]. Laser & Optoelectronics Progress, 2020, 57(24): 346-350., articleTitle=Improved human action recognition algorithm based on two-stream faster region convolutional neural network, refAbstract=null), Reference(id=1165678506575929824, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=13, pageStart=168, pageEnd=175, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=刘锁兰, 顾嘉晖, 王洪元, journalName=计算机工程与应用, refType=null, unstructuredReference=刘锁兰, 顾嘉晖, 王洪元, 等. 基于关联分区和ST-GCN的人体行为识别[J]. 计算机工程与应用, 2021, 57(13): 168-175., articleTitle=基于关联分区和ST-GCN的人体行为识别, refAbstract=null), Reference(id=1165678506630455777, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=13, pageStart=168, pageEnd=175, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=LIU Suolan, GU Jiahui, WANG Hongyuan, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=LIU Suolan, GU Jiahui, WANG Hongyuan, et al. Human behavior recognition based on associative partition and ST-GCN[J]. Computer Engineering and Applications, 2021, 57(13): 168-175., articleTitle=Human behavior recognition based on associative partition and ST-GCN, refAbstract=null)], funds=[Fund(id=1165678505581879761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, awardId=SYK2023-09, language=CN, fundingSource=湖北省烟草公司十堰市公司科技项目(SYK2023-09), fundOrder=null, country=null), Fund(id=1165678505632211410, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, awardId=3142021002, language=CN, fundingSource=中央高校科研业务费项目(3142021002), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1165678502473900432, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=1, ext=[AuthorCompanyExt(id=1165678502482289041, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China), AuthorCompanyExt(id=1165678502486483346, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502473900432, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北省烟草公司 十堰市公司,湖北 十堰 442099)]), AuthorCompany(id=1165678502549397907, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=2, ext=[AuthorCompanyExt(id=1165678502553592212, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502549397907, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 School of Safety Emergency Technology and Management,North China Institute of Science and Technology,Langfang Hebei 065201,China), AuthorCompanyExt(id=1165678502561980821, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502549397907, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 华北科技学院 应急技术与管理学院,河北 廊坊 065201)]), AuthorCompany(id=1165678502608118166, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, xref=3, ext=[AuthorCompanyExt(id=1165678502616506775, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502608118166, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Hubei Branch,China National Tobacco Corporation,Wuhan Hubei 430033,China), AuthorCompanyExt(id=1165678502624895384, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, companyId=1165678502608118166, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国烟草总公司 湖北省公司,湖北 武汉 430033)])], figs=[ArticleFig(id=1165678504600412609, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Fig.1, caption=Tobacoo warehouse site photo preprocessing, figureFileSmall=d7A9HLfWbiJM10yk/gZ2iQ==, figureFileBig=8KgzBgsjjAbfUmCNPi+Qzw==, tableContent=null), ArticleFig(id=1165678504650744258, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=图1, caption=卷烟仓储现场图片预处理, figureFileSmall=d7A9HLfWbiJM10yk/gZ2iQ==, figureFileBig=8KgzBgsjjAbfUmCNPi+Qzw==, tableContent=null), ArticleFig(id=1165678504705270211, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Fig.2, caption=Schematic diagram of recognition model for unsafe behaviors of tobacco storage personnel, figureFileSmall=cE10EuCz1VzRZXa3vKlFeQ==, figureFileBig=mDg99ubgXFtvwiSf5p3w3A==, tableContent=null), ArticleFig(id=1165678504755601860, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=图2, caption=卷烟仓储人员不安全行为识别模型流程, figureFileSmall=cE10EuCz1VzRZXa3vKlFeQ==, figureFileBig=mDg99ubgXFtvwiSf5p3w3A==, tableContent=null), ArticleFig(id=1165678504801739205, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Fig.3, caption=Evaluation metric curves for YOLOv11 model, figureFileSmall=U1mVYoADdugXavTnAM9dqA==, figureFileBig=QhskiVlm3wqHcRDHbSRTjA==, tableContent=null), ArticleFig(id=1165678504856265158, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=图3, caption=YOLOv11模型评价指标曲线, figureFileSmall=U1mVYoADdugXavTnAM9dqA==, figureFileBig=QhskiVlm3wqHcRDHbSRTjA==, tableContent=null), ArticleFig(id=1165678504910791111, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Fig.4, caption=Effectiveness of wearing safety helmets, figureFileSmall=rgs2C6tF4Be27qYbCqbmMg==, figureFileBig=VWKZn+s1ddCir/zFU/fCXw==, tableContent=null), ArticleFig(id=1165678504969511368, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=图4, caption=安全帽佩戴检测效果, figureFileSmall=rgs2C6tF4Be27qYbCqbmMg==, figureFileBig=VWKZn+s1ddCir/zFU/fCXw==, tableContent=null), ArticleFig(id=1165678505024037321, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Fig.5, caption=Skeletal recognition of workers' walking and working conditions, figureFileSmall=M3d6rEVN0xiwIfWKEeMLlA==, figureFileBig=HXZD8dZFTzw5q+EZNf/KDQ==, tableContent=null), ArticleFig(id=1165678505078563274, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=图5, caption=工人行走、工作状态下的骨骼识别结果, figureFileSmall=M3d6rEVN0xiwIfWKEeMLlA==, figureFileBig=HXZD8dZFTzw5q+EZNf/KDQ==, tableContent=null), ArticleFig(id=1165678505133089227, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Fig.6, caption=Comparison of recognition effect of different methods, figureFileSmall=qRCckuB7j4V/VwGWHeppXg==, figureFileBig=8+C5+ilmDBXLaQ5VaXYhqg==, tableContent=null), ArticleFig(id=1165678505187615180, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=图6, caption=不同方法的识别效果对比, figureFileSmall=qRCckuB7j4V/VwGWHeppXg==, figureFileBig=8+C5+ilmDBXLaQ5VaXYhqg==, tableContent=null), ArticleFig(id=1165678505263112653, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Table 1, caption=

Comparative analysis of recognition effects of multiple methods

, figureFileSmall=null, figureFileBig=null, tableContent=
类型 识别结果 类型 识别结果 类型 识别结果 类型 识别结果
未戴
安全
区域
入侵
跨越
传送
叉车
操作
消防
区域
攀爬
笼车
搬运
车操
攀爬
货架
), ArticleFig(id=1165678505334415822, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=表1, caption=

多种行为识别效果对比分析

, figureFileSmall=null, figureFileBig=null, tableContent=
类型 识别结果 类型 识别结果 类型 识别结果 类型 识别结果
未戴
安全
区域
入侵
跨越
传送
叉车
操作
消防
区域
攀爬
笼车
搬运
车操
攀爬
货架
), ArticleFig(id=1165678505393136079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=EN, label=Table 2, caption=

Comparison of detection results of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 数据集 P/% R/% RP/% F1/% 检测时间/ms
单次多框目标检测算法(Single
Shot multibox Detector,SSD)
COCO数据集 81.78 91.49 74.82 86.36 42
自建数据集 83.66 97.61 81.66 90.10 43
YOLOv8s COCO数据集 90.33 95.35 86.13 92.77 25
自建数据集 81.18 97.82 79.41 88.73 28
OpenPose-MobileNetV1 COCO数据集 77.48 84.96 65.83 81.05 91
自建数据集 80.01 97.47 77.99 87.88 95
Faster RCNN COCO数据集 90.39 90.2 81.53 90.29 126
自建数据集 82.88 99.36 82.35 90.37 117
YOLOv11x COCO数据集 90.48 89.51 80.99 89.99 50
自建数据集 88.51 87.76 77.68 88.13 48
改进YOLOv11 COCO数据集 88.69 98.32 87.20 93.26 52
自建数据集 94.91 95.55 90.69 95.23 56
), ArticleFig(id=1165678505460244944, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1148106720443887644, language=CN, label=表2, caption=

不同模型检测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 数据集 P/% R/% RP/% F1/% 检测时间/ms
单次多框目标检测算法(Single
Shot multibox Detector,SSD)
COCO数据集 81.78 91.49 74.82 86.36 42
自建数据集 83.66 97.61 81.66 90.10 43
YOLOv8s COCO数据集 90.33 95.35 86.13 92.77 25
自建数据集 81.18 97.82 79.41 88.73 28
OpenPose-MobileNetV1 COCO数据集 77.48 84.96 65.83 81.05 91
自建数据集 80.01 97.47 77.99 87.88 95
Faster RCNN COCO数据集 90.39 90.2 81.53 90.29 126
自建数据集 82.88 99.36 82.35 90.37 117
YOLOv11x COCO数据集 90.48 89.51 80.99 89.99 50
自建数据集 88.51 87.76 77.68 88.13 48
改进YOLOv11 COCO数据集 88.69 98.32 87.20 93.26 52
自建数据集 94.91 95.55 90.69 95.23 56
)], 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.issn1003-3033.2025.03.1598, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2025.03.1598, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2025.03.1598, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2025.03.1598, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进YOLOV11的卷烟仓储人员不安全行为分类及识别
收藏切换
PDF下载
柯巍 1 , 朱权洁 2, ** , 陈长茂 1 , 吴成毅 1 , 刘衍 1 , 张艳林 3
中国安全科学学报 | 安全社会科学与安全管理 2025,35(3): 36-44
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): 36-44
基于改进YOLOV11的卷烟仓储人员不安全行为分类及识别
全屏
柯巍1 , 朱权洁2, ** , 陈长茂1, 吴成毅1, 刘衍1, 张艳林3
作者信息
  • 1 湖北省烟草公司 十堰市公司,湖北 十堰 442099
  • 2 华北科技学院 应急技术与管理学院,河北 廊坊 065201
  • 3 中国烟草总公司 湖北省公司,湖北 武汉 430033
  • 柯 巍 (1992—),男,湖北十堰人,博士,工程师,主要从事安全生产信息化、企业安全管理、锂离子电池安全防控等方面的工作。E-mail:

    陈长茂,政工师;

    吴成毅,政工师;

    刘 衍,工程师;

    张艳林,工程师

通讯作者:

** 朱权洁(1984—),男,湖北孝感人,博士,教授,主要从事数字化矿山、矿山安全、灾害监测预警等方面的研究。E-mail:
Classification and recognition of unsafe behaviors of tobacco warehouse personnel based on improved YOLOv11
Wei KE1 , Quanjie ZHU2, ** , Changmao CHEN1, Chengyi WU1, Yan LIU1, Yanlin ZHANG3
Affiliations
  • 1 Shiyan Tobacco Company,Hubei Province,Shiyan Hubei 442099,China
  • 2 School of Safety Emergency Technology and Management,North China Institute of Science and Technology,Langfang Hebei 065201,China
  • 3 Hubei Branch,China National Tobacco Corporation,Wuhan Hubei 430033,China
出版时间: 2025-03-28 doi: 10.16265/j.cnki.issn1003-3033.2025.03.1598
文章导航
收藏切换

为确保仓储环境内的人员与财产安全,改进传统的YOLOv11目标检测算法,提出一种适用于卷烟仓储复杂环境的人员不安全行为识别方法和模型。首先,统计分析卷烟仓储中常见的不安全行为类型,探讨仓储人员不安全行为的分类,包括物品类、动作类和区域类的不安全行为;其次,基于仓储人员不安全行为的特征,提出数据集增广和去噪预处理的思路,强化细粒度特征提取,进而改进人员行为的显著性映射;然后,通过功能增强模块和K-means++锚框优化改进YOLOv11算法,提出一种卷烟仓储人员不安全行为快速检测方法;最后,利用自建数据集和微软公开数据集(COCO)对比验证方法的有效性。结果表明:该方法能够快速、有效地识别仓储人员的不安全行为,相较于传统方法,识别准确率得到显著提升,2个数据集上的精度分别达到94.91%和88.69%,综合表现更加均衡。

改进YOLOv11  /  卷烟仓储人员  /  不安全行为  /  去噪  /  目标检测

To ensure the safety of personnel and property within the storage environment,the traditional YOLOv11 object detection algorithm was improved,and a method and model to identify unsafe behaviors of personnel in the complex environment of tobacco warehouses were proposed. First,a statistical analysis of common unsafe behavior types in tobacco storage was conducted,and the classification of unsafe behaviors of warehouse personnel was explored,including item-related,action-related,and area-related unsafe behaviors. Second,based on the characteristics of unsafe behaviors of warehouse personnel,a dataset augmentation and denoising preprocessing approach was proposed to enhance fine-grained feature extraction,and introduced to improve the saliency mapping of personnel behaviors. Then,the YOLOv11 algorithm was improved through functional enhancement modules and K-means++ anchor box optimization,and a fast detection method for unsafe behaviors of tobacco warehouse personnel was proposed. Finally,the proposed method's effectiveness was validated by comparing with self-built datasets and the open Microsoft COCO dataset. The results show that the method can quickly and effectively identify unsafe behaviors of warehouse personnel,with a significant improvement in recognition accuracy compared to traditional methods(accuracy rate is 94.91% and 88.69% respectively).

improved YOLOv11  /  tobacco warehouse personnel  /  unsafe behaviors  /  denoising  /  object detection
柯巍, 朱权洁, 陈长茂, 吴成毅, 刘衍, 张艳林. 基于改进YOLOV11的卷烟仓储人员不安全行为分类及识别. 中国安全科学学报, 2025 , 35 (3) : 36 -44 . DOI: 10.16265/j.cnki.issn1003-3033.2025.03.1598
Wei KE, Quanjie ZHU, Changmao CHEN, Chengyi WU, Yan LIU, Yanlin ZHANG. Classification and recognition of unsafe behaviors of tobacco warehouse personnel based on improved YOLOv11[J]. China Safety Science Journal, 2025 , 35 (3) : 36 -44 . DOI: 10.16265/j.cnki.issn1003-3033.2025.03.1598
随着人工智能(Artificial Intelligence,AI)、大数据等技术的快速发展,各行各业正从信息化向智能化转型。在安全生产领域,基于AI的人员行为识别技术已在地铁防坠落、危化品操作监管、建筑施工安全等高风险场景取得显著成效,有效预防了人为安全事故。然而,当前研究多集中于矿业、化工、航空等政策驱动强、安全风险高的行业,烟草储配领域的安全行为智能识别研究仍较为薄弱。随着视频监控与AI技术的深度融合,智能行为预警系统已成为提升企业安全管理效能、降低事故损失的重要技术手段[1-2],为烟草储备安全带来了机遇。
目前,已有学者使用深度学习和计算机视觉算法识别人的不安全行为,从而预防人为事故的发生,并取得较好的成效。冯仕民等[3]提出一种基于语义本体的人员转态信息感知描述方法,以及一种数据和知识驱动相结合的矿山人员不安全行为识别框架;谢逸等[4]基于方向梯度直方图+支持向量机方法,识别了地铁中常见的不安全行为;RAHMANI等[5]将不安全动作信息转化到一个更高维度的特征空间,提出递归神经键点轨迹模型算法获取人物姿态的三维信息。在姿态识别方面,以OpenPose[6]为代表的姿态识别模型能够高效地识别视频中人的姿态以及人的头、手、肘等关键部位。在动作识别方面,以3D卷积神经网络(Convolutional Neural Network,CNN)[7]、长短期记忆网络(Long Short-Term Memory,LSTM)[8]、双流快速区域CNN(Faster Region-based CNN,RCNN)[9]、时空图CNN[10]等为代表的动态识别模型用于人的动作有效识别。卷烟储配仓库不安全、违规操作等不安全行为问题不同于物的不安全问题,其本身是潜在的、难以衡量的,因此,如何借助现有先进技术手段,实现对卷烟储配人员不规范/安全行为的准确识别与预警,是当前烟草企业应考虑的一个前沿课题和发展趋势。
鉴于此,笔者将定义和分类卷烟储配人员不规范/安全行为,收集不规范/安全行为数据并建立典型样本库,构建基于YOLOv11算法的不规范/安全行为分类识别模型,以期快速、准确识别卷烟储配人员不规范/安全行为,并及时预警。
目前,不安全行为的边界问题尚无定论。通常倾向于将危险行为等同于不安全行为,但危险或不安全本身就是一种潜在的、难以统一衡量的状态,因此,不安全行为包括违章行为、人因失误、人的可靠性等方面的研究。由于各个行业特点及研究侧重点不同,具体概念上没有统一,因此,在不安全行为的分类上也存在差异。一般来说,不安全行为是指在生产过程中发生的、可能导致事故的人的失误行为。主要由组织中人的原因、人行为的偏离、造成事故的主要原因3个要素组成。
基于上述分析,将卷烟储配作业人员的不安全行为定义为:由卷烟储配作业人员引发,其行为偏离常规操作,导致储配区安全事故的发生,或虽然未造成事故,但已对安全构成威胁或可能产生影响的事件。卷烟储配作业人员的不安全行为是由多重因素交织引发的复杂现象,涉及个体因素、组织管理、环境条件以及行为心理等多个层面。为更准确地识别和处理仓储人员的不安全行为,结合仓储人员的工作习惯以及卷烟仓储工作中的特殊性和多样性,将不安全行为划分为物品类、动作类和区域类,每类不安全行为又包含更具体的行为类型。物品类不安全行为是指卷烟储配作业人员未按照规定穿戴个人防护装备,或在工作区域内未正确存放或摆放卷烟及其他物品等不当行为,包括未佩戴安全帽、堆垛倾斜、物品存放不当等;动作类不安全行为是指卷烟储配工作人员由于安全意识薄弱,忽视仓库操作规程,擅自操作或执行一系列严重危害自身和他人安全的不负责任行为,包括跨越输送带、攀爬护栏、违规操作叉车等;区域类不安全行为指卷烟储配作业人员因心存侥幸心理、缺乏责任感,忽视警告标识,在未授权或未采取适当安全措施的情况下,进入或在危险区域内作业,包括擅入危险区域、堵塞消防区域等,这些行为将人员暴露于高风险环境中,增加事故发生的概率,可能导致更严重的伤害后果。
选择湖北省某烟草分公司,利用该仓储布置的监控摄像头进行初始样本的采集。现场作业的数据种类众多,可提高模型的泛化能力和检测性能。在视频格式转换工具方面,采用OpenCV软件进行视频的读取、写入和格式转换。利用OpenCV转换部分收集到的监控视频格式时,主要修改视频的分辨率和帧率。同时结合现场监控的环境,设置OpenCV在视频处理时调整视频图像的参数。
现场监控视频可能以多种格式存在,如AVI、MP4或MPEG等,这些格式在存储和压缩方法上各有差异。为有效处理这些视频,需要将它们转换成统一的格式,从而确保处理过程的一致性和效率。此外,视频格式转换还有助于减少数据大小和提高处理速度。现场监控视频往往具有大文件尺寸的特点,直接处理这些大文件可能导致计算资源的大量消耗和处理速度的降低。通过转换视频格式,可优化存储和处理过程。利用OpenCV技术深度处理监控视频,将视频转化成一系列按帧顺序排列的图像集合。这一转换过程不仅允许计算机以帧为单位细致地分析视频内容,而且还明显降低了图像的分辨率和帧率。
在进行人员不安全行为识别之前,需要去噪处理视频图像,提高图像的清晰度和对比度,增强模型的识别能力。采用基于深度学习的CNN(Denoising CNN,DnCNN)降噪算法进行图像去噪,实现对图像的有效识别和噪声的去除。
DnCNN的结构由多个卷积层、批量标准化层和激活函数层级联构成。卷积层负责提取图像特征,批量标准化层解决内部协变量偏移问题,并加快训练过程,而ReLU激活函数引入非线性,使网络能够捕获更复杂的数据模式。DnCNN网络共包含17层,其中,第1层由64个尺寸大小为3×3的卷积核构成的卷积层和ReLU激活函数组成;第2~16层比第1层多了批量标准化层,提升了模型训练的速度和稳定性;最后一层由一个卷积层构成,负责输出图像的残差图像。
为提高模型在真实仓储环境下的适应性和准确性,对仓储数据集和实验室模拟的数据集进行一系列预处理操作,如图1所示。图1b中,通过黑白处理原始图像(图1a),改变了光照强度,反映出现场光线条件从彩色到黑白的变化,有效增强模型在不同照明环境下的识别能力。图1c使用数据翻转技术对图像进行180°旋转,从不同视角训练模型,进而提升模型不同角度的识别能力。数据增广技术不仅能提高数据集的多样性,还能增强模型对现实复杂情况的适应性,为模型提供更全面的训练基础。在数据增广之后,严格筛选数据集,排除质量不高或与研究目的不符的数据,确保数据集的质量和可靠性,同时,也有利于后续图像去噪和数据集标注。现场实测与实验室样本数量总计31 000张图片,其中,物品类9 700张、动作类15 800张、区域类6 500张。
为验证DnCNN图像去噪算法对监控图像的去噪效果,训练自建的不安全行为数据集,通过多轮迭代预测过程中,模型的权重不断调整和优化,使得最终输出的图像质量越来越接近原始的无噪声图像。图1a图1d分别展示了未经处理过的图像与经过DnCNN算法处理过的图像。通过对比可以发现,经过DnCNN算法处理过的图像在清晰度和细节上有了显著提升。由于卷烟仓储特殊环境条件造成的噪声,如模糊不清的轮廓、颗粒感强烈的背景和由光照不均造成的阴影,使得未经处理图像的细节和重要特征难以辨认;而DnCNN处理后的图像则展现出更加清晰的边缘、平滑的纹理以及更均匀的光照条件,使得图像中不安全行为,如未佩戴安全帽的人员、非法操作等,变得更加易于识别。
卷烟仓储人员不安全行为识别模型的构建主要包括2部分,分别是YOLOv11目标检测模型和YOLOv11-pose行为检测模型。在构建过程中,模型采用新的激活函数、特征金字塔网络(Feature Pyramid Network,FPN)以及锚点盒的优化策略,以增强检测精度和速度。卷烟仓储人员不安全行为识别模型流程如图2所示。在YOLOv11模型构建过程中,网络架构的设计至关重要。YOLOv11采用改进的CNN结构,模型的基础架构通常由多个卷积层、批归一化层和激活函数(如Leaky ReLU)构成。此外,YOLOv11通过将检测和分类过程整合为一个单一的回归问题来实现高效的对象识别,该模型通过改进网络结构、引入注意力机制和轻量化设计等方式,提高检测精度和推理速度。相比于之前的版本,YOLOv11更适合小目标和复杂场景的检测,可在边缘设备上实现实时目标检测,是快速、高效、资源友好的目标检测解决方案。
模型参数设置方面,YOLOv11配置多个超参数,包括学习率、批量大小和锚框尺寸。学习率通常采用动态调整策略,批量大小的选择平衡了内存消耗和训练速度,通常设置为32或64。在锚框尺寸方面,通过K-means聚类算法分析训练数据,确定适合目标检测的最优锚框尺寸。此外,模型还包含多种数据增强策略,如随机裁剪、旋转和颜色变换,以增强模型的鲁棒性和泛化能力,确保在各种环境下都能实现高效的目标检测。其中,网络架构方面的参数设置为:①输入层,输入图像尺寸为640×640像素,采用标准化预处理。②主干网络,采用跨阶段部分连接结构(Cross Stage Partial Darknet,CSPDarknet)作为特征提取网络。③FPN,使用FPN结构,并结合不同层次特征。④检测头,输出包括类别预测和边界框回归的检测头,设置3个锚框以适应不同尺寸目标。模型参数设置方面为:①设置3个锚框,尺寸分别为(10,13),(16,30),(33,23)。②采用YOLO损失函数。③使用Adam优化器,初始学习率设定为0.001。
姿态估计模块是模型的核心部分,通过特征提取网络提取原始特征图,获取新的特征图,再将骨骼关键点信息处理获得人体骨骼图。YOLOv11-pose 模型的检测流程可概述为:首先,在初始化阶段设定一系列关键参数,这些参数为整个检测流程奠定基础。其次,采用模型处理输入的图像或视频数据,提取其中人体骨骼图的关键信息,着重计算各关节点之间的距离以及角度变化情况等特征量。然后,将其与预先通过大量样本训练得到的模型所设定的阈值进行细致的比较与深入的分析。最后,借助这种比较分析机制,模型能够有效区分不同类型的行为模式,从而准确判断与识别行走、奔跑、跳跃、坐下、站立等行为。
由于卷烟仓储环境复杂多变,除光照条件、粉尘等简单干扰因素可通过数据集预处理进行解决,但在遮挡或远距离目标等复杂的背景干扰方面仍存在挑战。为此,在YOLOv11模型中引入功能增强模块,借以提升对重要区域或复杂背景中的识别能力。在卷烟仓储环境中,因其复杂且多变的条件,除了像光照变化、粉尘等简单的干扰因素可以通过数据集的预处理来解决外,遮挡物或远距离目标等复杂背景依然是难以克服的挑战。为此,YOLOv11模型引入功能增强模块,以提升在复杂背景中对目标的识别能力:①通道激活模块:去除包含大量无效信息的通道,通过减少冗余信息,间接地提高有效信息的比例。②空间注意力模块:通过max-pooling和average-pooling操作处理特征图,再通过卷积和非线性激活来计算权重系数,将权重系数应用于输入特征图像,得到缩放后的新特征图。
该功能增强模块由通道激活模块和空间注意力模块组成。通道激活模块去除无效的通道,从而提高有效信息的比例;空间注意力模块则通过专注于局部最相关特征,进一步优化模型的识别效果。通过这种方式,模型能够更有效地处理复杂背景下的目标识别任务。
使用YOLOv11算法检测与识别卷烟仓储人员不安全行为的研究中,优化锚框是提升模型检测精度的关键环节。在卷烟仓储环境中,人员姿态、与摄像机的距离和角度等因素可能会影响检测效果。因此,为更好地适应这种特殊环境,需针对性地优化锚框,以符合目标特征的变化。
K-means++算法是一种改进的K-means聚类方法,它在选择初始质心时进行优化,增加初始化的多样性,从而降低陷入局部最优解的风险。该方法能够更好地适应数据集中对象的形状和大小分布,从而提高检测算法的效率与准确性。通过使用K-means++算法优化目标锚框,不仅增强模型在卷烟仓储不安全行为检测中的适应性和精度,还提高训练与推理的效率。
试验引入精确度P和检测速率作为衡量标准定量表征模型的有效性。其中,P的计算如下式:
P = T P T P + F P
式中:TP为正样本(目标样本)中被正确识别为正样本的数量;FP为负样本(非目标样本)中被错误地识别为正样本的数量。
召回率R的计算如下式:
R = T P T P + F N
式中FN为正样本中被错误地识别为负样本的数量。
RP是召回率R和精确度P的乘积,用来评估分类器在正类样本识别上的平衡表现。RP可表述为:
R P = P × R
F1分数通过以下方式计算:
F 1 = 2 × P × R P + R
模型训练基于Windows10操作系统,中央处理器为i7-10750H,显卡为RTX(Ray Tracing Texel eXtreme)3060。YOLOv11网络的训练轮数为100轮,训练批量大小设为16,即每次训练16张图片。限于篇幅,重点介绍穿戴类、动作类识别。
为验证模型的有效性,训练和测试模型。训练数据集准备包括数据集划分和数据增强2部分,其中,数据集划分为:训练集占70%,验证集占20%,测试集占10%。训练过程采用Adam优化器,逐步调整学习率,训练结果如图3所示。从图3a可以看出,大部分类别的精确度P随置信度增加而提高,说明模型在更高置信度下的预测更加准确,但凉鞋和拖鞋等类别的精确度提升不明显。从图3b可以看出,召回率R随置信度增加而下降,尤其是在高置信度时大幅下降,表明模型在高置信度下漏检较多,特别是对某些物体类别(如高跟鞋和托盘)。图3c显示,模型在不同类别的表现差异较大,安全帽等类型的曲线表现出较好的精确度和召回率平衡,而其他类别表现不理想。图3d显示,F1分数在中等置信度时达到最高,表明该置信度范围内模型的综合性能最好,但不同类别之间的差异仍然较为显著。
通过调取卷烟仓储各区域的监控视频,以及卷烟仓储工作人员的帮助和配合,使用防爆手机拍摄卷烟仓储人员不安全行为。通过融合网络公开数据集,构建卷烟仓储安全帽集。在试验过程中,改进YOLOv11网络的训练轮数为200轮,训练批量大小设为50,即每次训练50张图片;交并比设置为0.6,即预测框与真实框的重叠比率达到0.6,则表示任务目标被检测出来。
经过实测数据集与公共数据集的预处理和训练,以安全帽佩戴检测为例,将安全帽经过标注工具“labelimg”定义标签“helmt”和“no-helmt”,即佩戴安全帽为“helmt”,未佩戴安全帽为“no-helmt”,检测结果如图4所示。检测结果表明:无论是在光照过强、过弱,还是在较为复杂的背景下,以及距离较远和人体型较小的情况下,改进后的YOLOv11x模型均较好地检测出安全帽的佩戴效果,同时,改进后的模型也可满足多人检测的需求,并得到准确的结果。
人体骨骼关键点估计是一个核心组成部分,它涉及到从图像中准确识别人体的结构性特征,如手臂、腿部、头部等部位的关键点。这一过程不仅需要定位这些关键点,还要正确地将它们连接起来形成人体的骨骼结构。动作类识别算法难度稍大,姿态估计模块是YOLOv11-pose模型的核心部分,其主要思路是通过YOLOv11特征提取网络提取原始特征图,获取骨骼关键点的相关信息,经信息处理后即可获得人体骨骼图。再设定相应的判断准则,通过计算人体骨骼图关节点之间的指标信息(包括骨骼点之间的距离、高度、角度等),与训练好的模型设定阈值进行比较分析,最终判断得出不安全行为的类别。使用YOLOv11-pose检测识别仓储员工骨骼关键点,如图5a所示。关键点包括鼻子、眼睛、肩膀、手肘、手掌、膝盖和脚等。通过实时捕捉分析的员工姿势,快速判断人员是否存在违规/不安全行为。
YOLOv11对人员骨骼姿势的识别结果如图5b图5c所示。人体关键部位识别提供了丰富的行为数据支持。通过分析逐帧视频,YOLOv11能够精准识别并标注员工的各个身体关键点,如鼻子、肩膀、手掌、膝盖等,使得能够实时捕捉人员的姿势变化,从而形成连续的运动轨迹。这些姿势变化信息有助于实现多视角的时序分析,通过分析各关键点的时序变化,识别员工的行为模式,判断是否存在不安全行为及可能导致的安全隐患。此外,姿势变化为后续的行为特征提取奠定了基础。
为评估所提出方法的效果,从测试数据集中选取8张原始图像进行分析,包括未佩戴安全帽、不戴头盔、非法骑行、穿越设备和区域入侵等,检测识别结果见表1。从表1中可以看出,不同类型行为的识别结果在精确度、检测框定位以及背景复杂度处理方面均有良好的表现。
为验证改进YOLOv11的效果,在相同配置条件下使用相同数量的安全帽测试集,并使用目前比较流行的不安全行为识别模型进行对比检验,结果见表2,其中,数据集增加了COCO(Common Objects in Context)数据集。由表2可知:相较于其他训练方法,改进YOLOv11在不同的数据集上都保持较高的准确率,主要原因是改进算法在数据集预处理、识别模型等方面性能更优,且提取目标的特征更具适应性。
具体而言,相较于其他几种识别方法,改进YOLOv11算法能够有效提高对卷烟仓储人员不安全行为的检测精度,在公共COCO数据集和自建数据集上分别能达到88.69%和94.91%,远高于SSD和YOLOv8s等几种方法。同时,与另外几种方法相比,改进YOLOv11算法在检测时间和帧率上均有一定提升。由此说明:改进YOLOv11算法在安全帽佩戴检测准确性方面表现优秀,能够满足现在卷烟仓储复杂环境下是否佩戴安全帽检测的准确率要求。不同方法的识别效果对比如图6所示。
图6可以看出,从识别精度和识别效率2方面综合考虑时,改进YOLOv11模型的准确率相比于其他几种模型更具有优势。对比表2可知:改进的YOLOv11模型在自建数据集上的表现相对较为均衡,尤其在PRF1得分方面表现良好。与其他模型相比,YOLOv11x虽然在COCO数据集上的性能较好,具有较高的F1和mAP指标,但在自建数据集上的精度有所下降。相比之下,YOLOv8s在自建数据集上显示出不错的平衡性,推理时间较短,适合需要实时性场景的应用。SSD和Faster RCNN在自建数据集上表现略逊一筹,其中,Faster RCNN推理时间最长,不适用于需要较高实时性的场景。改进YOLOv11模型相较于其他模型,在PF1得分方面有所提升,推理时间中等,具有一定的优越性。总体而言,各模型在COCO和自建数据集之间表现有所差异,改进YOLOv11在自建数据集上的性能略优,且在各类数据集下都表现出较好的性能。
1) 根据卷烟仓储人员不安全行为的行为特点,并结合目前卷烟仓储人员工作的习惯与诱导因素,将卷烟仓储人员不安全行为分为3大类,即物品类不安全行为、动作类不安全行为、区域类不安全行为,有利于快速分析和处理卷烟仓储人员不安全行为。
2) 在数据集增广、DnCNN去噪预处理的基础上,引入功能增强模块、K-means++算法目标锚框优化方法等,优化改进传统YOLOv11目标检测算法,有效提高该方法对3类卷烟仓储人员不安全行为的检测效率和准确率。
3) 基于改进YOLOv11目标检测算法构建了一种卷烟仓储作业人员不安全行为识别系统。通过多种数据的对比验证,证明改进YOLOv11方法相较于传统方法在识别精度和准确性方面表现更为稳定。
  • 湖北省烟草公司十堰市公司科技项目(SYK2023-09)
  • 中央高校科研业务费项目(3142021002)
参考文献 引证文献
排序方式:
[1]
SREENU G, SALEEM DURAI M A. Intelligent video surveillance: a review through deep learning techniques for crowd analysis[J]. Journal of Big Data, 2019, 6 (1): DOI: 10.1186/s40537-019-0212-5.
[2]
HASSAN M M, UDDIN M D, MOHAMED A, et al. A robust human activity recognition system using smartphone sensors and deep learning[J]. Future Generation Computer Systems, 2018, 81: 307-313.
[3]
冯仕民, 刘忠育, 俞啸, 等. 矿山物联网人员情境描述与不安全行为识别[J]. 物联网学报, 2018, 2(4): 93-98.
FENG Shimin, LIU Zhongyu, YU Xiao, et al. Workers' context description and unsafe behavior recognition in internet of things for mines[J]. Chinese Journal on Internet of Things, 2018, 2(4): 93-98.
[4]
谢逸, 张竞文, 李韬, 等. 基于视频监控的地铁施工不安全行为检测预警[J]. 华中科技大学学报:自然科学版, 2019, 47(10): 46-51.
XIE Yi, ZHANG Jingwen, LI Tao, et al. Research on detection and early warning of unsafe behavior in metro construction based on video monitoring[J]. Journal Huazhong University of Science and Technology: Natural Science Edition, 2019, 47(10): 46-51.
[5]
RAHMANI M, OSKOUEI A N, PETRUDI A M. Experimental and numerical study of the blast wave decrease using sandwich panel by granular materials core[J]. Defence Technology, 2021, 17(5): 1660-1670.
[6]
CAO Zhe, HIDALGO M G, SIMON T, et al. OpenPose: realtime multi-person 2D pose estimation using part affinity fields[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(1): 172-186.
[7]
王松, 党建武, 王阳萍, 等. 基于3D运动历史图像和多任务学习的动作识别[J]. 吉林大学学报:工学版, 2020, 50(4): 1495-1502.
WANG Song, DANG Jianwu, WANG Yangping, et al. Action recognition based on 3D motion history image and multi-task learning[J]. Journal of Jilin University: Engineering and Technology Edition, 2020, 50(4): 1495-1502.
[8]
PATEL V, SINGH R. Real-time detection of unsafe behaviors using LSTM[J]. Journal of Intelligent Manufacturing, 2020, 31: 593-607.
[9]
郭如意, 金杰, 刘高华, 等. 基于双流快速区域卷积神经网络改进的人体动作识别算法[J]. 激光与光电子学进展, 2020, 57(24): 346-350.
GUO Ruyi, JIN Jie, LIU Gaohua, et al. Improved human action recognition algorithm based on two-stream faster region convolutional neural network[J]. Laser & Optoelectronics Progress, 2020, 57(24): 346-350.
[10]
刘锁兰, 顾嘉晖, 王洪元, 等. 基于关联分区和ST-GCN的人体行为识别[J]. 计算机工程与应用, 2021, 57(13): 168-175.
LIU Suolan, GU Jiahui, WANG Hongyuan, et al. Human behavior recognition based on associative partition and ST-GCN[J]. Computer Engineering and Applications, 2021, 57(13): 168-175.
2025年第35卷第3期
PDF下载
274
99
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2025.03.1598
  • 接收时间:2024-10-14
  • 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:2024-10-14
  • 修回日期:2024-12-24
基金
湖北省烟草公司十堰市公司科技项目(SYK2023-09)
中央高校科研业务费项目(3142021002)
作者信息
    1 湖北省烟草公司 十堰市公司,湖北 十堰 442099
    2 华北科技学院 应急技术与管理学院,河北 廊坊 065201
    3 中国烟草总公司 湖北省公司,湖北 武汉 430033

通讯作者:

** 朱权洁(1984—),男,湖北孝感人,博士,教授,主要从事数字化矿山、矿山安全、灾害监测预警等方面的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2025.03.1598
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