Article(id=1149738768309076135, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738762382524507, articleNumber=1003-3033(2024)07-0146-07, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2024.07.0235, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1704988800000, receivedDateStr=2024-01-12, revisedDate=1712937600000, revisedDateStr=2024-04-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1752048683478, onlineDateStr=2025-07-09, pubDate=1722096000000, pubDateStr=2024-07-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752048683478, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752048683478, creator=13701087609, updateTime=1752048683478, updator=13701087609, issue=Issue{id=1149738762382524507, tenantId=1146029695717560320, journalId=1146031787341344770, year='2024', volume='34', issue='7', pageStart='1', pageEnd='252', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752048682065, creator=13701087609, updateTime=1757316437713, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1171833331021824745, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738762382524507, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1171833331021824746, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738762382524507, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=146, endPage=152, ext={EN=ArticleExt(id=1149738768468459689, articleId=1149738768309076135, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=DPIM algorithm for hoisting operation scene based on inspection robot, columnId=1149733269173878863, journalTitle=China Safety Science Journal, columnName=Safety engineering technology, runingTitle=null, highlight=null, articleAbstract=

In order to improve the high-precision detection and early warning of crane safety operation and enhance the safety management ability of enterprises,focusing on the needs of unmanned industrial safety incident analysis and monitoring and early warning,an inspection robot that combines ground and air flight in hoisting scene was customized to intelligentize hoisting safety monitoring,pop-up image recording and safety alarm.A lifting dataset Cranes-Dataset (CRN-Dataset) containing 3 120 images was made,and DPIM algorithm was proposed to enhance the rapid detection ability of multi-scale objects.Based on corner detection and density-based spatial clustering of applications with noise and considering the safety attributes of the space distance between cranes and workers,the process of triggering alarms based on safety rules was developed to record real-time illegal operation image and popup alarm.The results show that,after actual deployment and verification,the DPIM algorithm significantly improves target identification ability compared with other traditional algorithms,and it is suitable for real-time calculation and data transmission of embedded edge intelligent analysis nodes to complete field deployment.

, correspAuthors=Yuyin GUAN, 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=Shikang LIN, Qingwen HOU, Yuyin GUAN, Wencai WANG, Jialu LI, Xianzhong CHEN), CN=ArticleExt(id=1149738782074782516, articleId=1149738768309076135, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于巡检机器人的吊装作业场景DPIM算法, columnId=1149733269727526997, journalTitle=中国安全科学学报, columnName=安全工程技术, runingTitle=null, highlight=null, articleAbstract=

为提高吊车安全作业的高精度检测预警,增强企业安全管理能力,围绕工业安全事件分析与监测预警无人化的需求,定制吊装场景地面和空中飞行相结合的巡检机器人,智能化吊装过程安全规程监控、弹窗图像记录和安全告警。首先,制作包含3 120张图片的吊装数据集Cranes-Dataset (CRN-Dataset),提出一种动态视角智能监测 (DPIM) 算法,以增强人-车-物多尺度目标的快速检测能力;然后,依据多帧图像的角点检测和带噪声基于密度的聚类方法,以及吊车与作业工人空间距离的安全属性,制定安全规则触发告警的流程,实时记录违规操作图像并弹窗预警。结果表明:经过实际部署和验证,DPIM算法相较于其他传统算法,吊装作业目标识别能力有明显提高,且适用嵌入式边缘智能分析节点的实时计算与数据传输,完成危险区域人员拒止的现场部署。

, correspAuthors=关淯尹, authorNote=null, correspAuthorsNote=
** 关淯尹(1991—),女,宁夏盐池人,硕士,工程师(人工智能),主要从事智能制造与机器视觉方面的工作。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=FXWeQtOVN8JNekKbt6/0uQ==, magXml=DTYXqir35EC4+3uO5QZi7A==, pdfUrl=null, pdf=NZ5WIAXRIfBNFpAsqP7i4w==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=vT/wm6CEL4vWXZPv57k1nw==, mapNumber=null, authorCompany=null, fund=null, authors=

林世康 (2000—),男,福建福州人,硕士研究生,研究方向为人工智能和机器视觉。E-mail:

侯庆文 副教授;

陈先中 教授

, authorsList=林世康, 侯庆文, 关淯尹, 王文财, 李嘉禄, 陈先中)}, authors=[Author(id=1168186585972482836, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=2219101802@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1168186586102506263, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186585972482836, language=EN, stringName=Shikang LIN, firstName=Shikang, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China
2 Shunde Innovation School,University of Science and Technology Beijing,Foshan Guangdong 528399,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186586203169560, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186585972482836, language=CN, stringName=林世康, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 北京科技大学 自动化学院,北京 100083
2 北京科技大学 顺德创新学院,广东 佛山 528399, bio={"img":"3dcajRtb1owH1fQvE76dAQ==","content":"

林世康 (2000—),男,福建福州人,硕士研究生,研究方向为人工智能和机器视觉。E-mail:

"}, bioImg=3dcajRtb1owH1fQvE76dAQ==, bioContent=

林世康 (2000—),男,福建福州人,硕士研究生,研究方向为人工智能和机器视觉。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186585406251786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=1, ext=[AuthorCompanyExt(id=1168186585469166347, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China), AuthorCompanyExt(id=1168186585553052428, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京科技大学 自动化学院,北京 100083)]), AuthorCompany(id=1168186585712435981, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=2, ext=[AuthorCompanyExt(id=1168186585716630286, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585712435981, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Shunde Innovation School,University of Science and Technology Beijing,Foshan Guangdong 528399,China), AuthorCompanyExt(id=1168186585725018895, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585712435981, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 北京科技大学 顺德创新学院,广东 佛山 528399)])]), Author(id=1168186586261889818, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, 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=1168186586324804380, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586261889818, language=EN, stringName=Qingwen HOU, firstName=Qingwen, middleName=null, lastName=HOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186586383524637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586261889818, language=CN, stringName=侯庆文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北京科技大学 自动化学院,北京 100083, bio={"content":"

侯庆文 副教授;

"}, bioImg=null, bioContent=

侯庆文 副教授;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186585406251786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=1, ext=[AuthorCompanyExt(id=1168186585469166347, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China), AuthorCompanyExt(id=1168186585553052428, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京科技大学 自动化学院,北京 100083)])]), Author(id=1168186586438050591, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=guanyuyin@bbma.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1168186586538713889, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586438050591, language=EN, stringName=Yuyin GUAN, firstName=Yuyin, middleName=null, lastName=GUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=**, 3, address=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186586605822754, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586438050591, language=CN, stringName=关淯尹, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=**, 3, address=3 北京建筑材料科学研究总院有限公司,北京 100041, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186585771156240, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=3, ext=[AuthorCompanyExt(id=1168186585792127761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China), AuthorCompanyExt(id=1168186585808904978, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京建筑材料科学研究总院有限公司,北京 100041)])]), Author(id=1168186586677125924, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, 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=1168186586769400614, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586677125924, language=EN, stringName=Wencai WANG, firstName=Wencai, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186586823926567, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586677125924, language=CN, stringName=王文财, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 北京建筑材料科学研究总院有限公司,北京 100041, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186585771156240, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=3, ext=[AuthorCompanyExt(id=1168186585792127761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China), AuthorCompanyExt(id=1168186585808904978, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京建筑材料科学研究总院有限公司,北京 100041)])]), Author(id=1168186586878452521, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, 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=1168186586953949995, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586878452521, language=EN, stringName=Jialu LI, firstName=Jialu, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186587012670252, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186586878452521, language=CN, stringName=李嘉禄, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 北京建筑材料科学研究总院有限公司,北京 100041, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186585771156240, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=3, ext=[AuthorCompanyExt(id=1168186585792127761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China), AuthorCompanyExt(id=1168186585808904978, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京建筑材料科学研究总院有限公司,北京 100041)])]), Author(id=1168186587121722158, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, 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=1168186587180442417, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186587121722158, language=EN, stringName=Xianzhong CHEN, firstName=Xianzhong, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China
2 Shunde Innovation School,University of Science and Technology Beijing,Foshan Guangdong 528399,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1168186587264328498, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, authorId=1168186587121722158, language=CN, stringName=陈先中, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 北京科技大学 自动化学院,北京 100083
2 北京科技大学 顺德创新学院,广东 佛山 528399, bio={"content":"

陈先中 教授

"}, bioImg=null, bioContent=

陈先中 教授

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1168186585406251786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=1, ext=[AuthorCompanyExt(id=1168186585469166347, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China), AuthorCompanyExt(id=1168186585553052428, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京科技大学 自动化学院,北京 100083)]), AuthorCompany(id=1168186585712435981, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=2, ext=[AuthorCompanyExt(id=1168186585716630286, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585712435981, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Shunde Innovation School,University of Science and Technology Beijing,Foshan Guangdong 528399,China), AuthorCompanyExt(id=1168186585725018895, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585712435981, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 北京科技大学 顺德创新学院,广东 佛山 528399)])])], keywords=[Keyword(id=1168186587377574707, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, orderNo=1, keyword=inspection robot), Keyword(id=1168186587432100660, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, orderNo=2, keyword=hoisting scene), Keyword(id=1168186587478238005, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, orderNo=3, keyword=dynamic perspective intelligent monitoring (DPIM) algorithm), Keyword(id=1168186587532763958, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, orderNo=4, keyword=personnel denial), Keyword(id=1168186587583095607, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, orderNo=5, keyword=edge intelligent analysis), Keyword(id=1168186587637621560, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, orderNo=1, keyword=巡检机器人), Keyword(id=1168186587750867769, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, orderNo=2, keyword=吊装场景), Keyword(id=1168186587809588026, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, orderNo=3, keyword=动态视角智能监测(DPIM)算法), Keyword(id=1168186587880891195, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, orderNo=4, keyword=人员拒止), Keyword(id=1168186587952194364, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, orderNo=5, keyword=边缘智能分析)], refs=[Reference(id=1168186590447805297, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=669, pageEnd=674, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=GU Yuwan, XU Shoukun, WANG Yaru, journalName=International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), refType=null, unstructuredReference=GU Yuwan, XU Shoukun, WANG Yaru, et al. An advanced deep learning approach for safety helmet wearing detection[C]. International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2019: 669-674., articleTitle=An advanced deep learning approach for safety helmet wearing detection, refAbstract=null), Reference(id=1168186590502331251, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=93, pageEnd=96, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=DUAN Qipeng, PING Kuang, LI Fan, journalName=The 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), refType=null, unstructuredReference=DUAN Qipeng, PING Kuang, LI Fan, et al. Method of safety helmet wearing detection based on key-point estimation without anchor[C]. The 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 2020: 93-96., articleTitle=Method of safety helmet wearing detection based on key-point estimation without anchor, refAbstract=null), Reference(id=1168186590590411636, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=155, pageEnd=158, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=DENG Benyang, LEI Xiaochun, YE Miao, journalName=The 16th International Conference on Computational Intelligence and Security (CIS), refType=null, unstructuredReference=DENG Benyang, LEI Xiaochun, YE Miao. Safety helmet detection method based on YOLOv4[C]. The 16th International Conference on Computational Intelligence and Security (CIS), 2020: 155-158., articleTitle=Safety helmet detection method based on YOLOv4, refAbstract=null), Reference(id=1168186590657520502, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=391, pageEnd=395, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=GAO Guoqing, LIN Wenhua, LI Guohe, journalName=The 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), refType=null, unstructuredReference=GAO Guoqing, LIN Wenhua, LI Guohe, et al. Identification of risk behavior in power working scenarios based on deep learning[C]. The 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2022: 391-395., articleTitle=Identification of risk behavior in power working scenarios based on deep learning, refAbstract=null), Reference(id=1168186590724629368, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=12, pageStart=60, pageEnd=66, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=赵江平, 刘星星, 张想卓, journalName=中国安全科学学报, refType=null, unstructuredReference=赵江平, 刘星星, 张想卓. 基于改进YOLOv5s的外脚手架隐患图像识别技术[J]. 中国安全科学学报, 2023, 33(12): 60-66., articleTitle=基于改进YOLOv5s的外脚手架隐患图像识别技术, refAbstract=null), Reference(id=1168186590812709753, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=12, pageStart=60, pageEnd=66, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=ZHAO Jiangping, LIU Xingxing, ZHANG Xiangzhuo, journalName=China Safety Science Journal, refType=null, unstructuredReference=ZHAO Jiangping, LIU Xingxing, ZHANG Xiangzhuo. Research on image recognition technology for external scaffold hidden danger based on improved YOLOv5s[J]. China Safety Science Journal, 2023, 33(12): 60-66., articleTitle=Research on image recognition technology for external scaffold hidden danger based on improved YOLOv5s, refAbstract=null), Reference(id=1168186590925955963, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2022, volume=71, issue=null, pageStart=1, pageEnd=14, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=LI Zhishan, XIE Wenqing, ZHANG Lingzhi, journalName=IEEE Transactions on Instrumentation and Measurement, refType=null, unstructuredReference=LI Zhishan, XIE Wenqing, ZHANG Lingzhi, et al. Toward efficient safety helmet detection based on YOLOv5 with hierarchical positive sample selection and box density filtering[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14., articleTitle=Toward efficient safety helmet detection based on YOLOv5 with hierarchical positive sample selection and box density filtering, refAbstract=null), Reference(id=1168186591001453437, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=102, pageEnd=106, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=SUN Weichen, YANG Zhanhua, ZHAO Bo, journalName=The 7th International Conference on Machine Vision and Information Technology (CMVIT), refType=null, unstructuredReference=SUN Weichen, YANG Zhanhua, ZHAO Bo, et al. Research on target detection of regional monitoring with complex background using CNN and background modelling[C]. The 7th International Conference on Machine Vision and Information Technology (CMVIT), 2023:102-106., articleTitle=Research on target detection of regional monitoring with complex background using CNN and background modelling, refAbstract=null), Reference(id=1168186591081145215, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=604, pageEnd=609, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=FANG Lijin, HUANG Yongjie, ZHAO Qiankun, journalName=The 7th International Conference on Intelligent Computing and Signal Processing (ICSP), refType=null, unstructuredReference=FANG Lijin, HUANG Yongjie, ZHAO Qiankun, et al. Monocular 3D object detection based on occlusion optimization[C]. The 7th International Conference on Intelligent Computing and Signal Processing (ICSP), 2022:604-609., articleTitle=Monocular 3D object detection based on occlusion optimization, refAbstract=null), Reference(id=1168186591156642689, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=265, pageEnd=268, url=null, language=null, rfNumber=[9], rfOrder=9, authorNames=INTAWONG K, PROMPANTAKORN P, BOONCHIENG W, journalName=Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering, refType=null, unstructuredReference=INTAWONG K, PROMPANTAKORN P, BOONCHIENG W. An improved automatic zone detection algorithm based on mechanic flow for complex scene event[C]. Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering, 2021:265-268., articleTitle=An improved automatic zone detection algorithm based on mechanic flow for complex scene event, refAbstract=null), Reference(id=1168186591244723075, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1068, pageEnd=1072, url=null, language=null, rfNumber=[10], rfOrder=10, authorNames=HEO J, WANG Y, PARK J, journalName=The 20th International Conference on Control, Automation and Systems (ICCAS), refType=null, unstructuredReference=HEO J, WANG Y, PARK J. Occlusion data augmentation for object detectors based on random erasing and bounding box tailoring[C]. The 20th International Conference on Control, Automation and Systems (ICCAS), 2020: 1068-1072., articleTitle=Occlusion data augmentation for object detectors based on random erasing and bounding box tailoring, refAbstract=null), Reference(id=1168186591320220549, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=null, pageStart=862, pageEnd=110, url=null, language=null, rfNumber=[11], rfOrder=11, authorNames=GALLO G, FRANCESCO D R, GARZELLI F, journalName=IEEE Access, refType=null, unstructuredReference=GALLO G, FRANCESCO D R, GARZELLI F, et al. A smart system for personal protective equipment detection in industrial environments based on deep learning at the edge[J]. IEEE Access, 2022, 10: 110 862-110 878., articleTitle=A smart system for personal protective equipment detection in industrial environments based on deep learning at the edge, refAbstract=null), Reference(id=1168186591412495239, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=7, pageStart=82, pageEnd=89, url=null, language=null, rfNumber=[12], rfOrder=12, authorNames=张磊, 李熙尉, 燕倩如, journalName=中国安全科学学报, refType=null, unstructuredReference=张磊, 李熙尉, 燕倩如, 等. 基于改进YOLOv5s的综采工作面人员检测算法[J]. 中国安全科学学报, 2023, 33(7): 82-89., articleTitle=基于改进YOLOv5s的综采工作面人员检测算法, refAbstract=null), Reference(id=1168186591504769929, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2023, volume=33, issue=7, pageStart=82, pageEnd=89, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=ZHANG Lei, LI Xiwei, YAN Qianru, journalName=China Safety Science Journal, refType=null, unstructuredReference=ZHANG Lei, LI Xiwei, YAN Qianru, et al. Personnel detection algorithm in fully mechanized coal face based on improved YOLOv5s[J]. China Safety Science Journal, 2023, 33(7): 82-89., articleTitle=Personnel detection algorithm in fully mechanized coal face based on improved YOLOv5s, refAbstract=null), Reference(id=1168186591592850314, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=000, pageEnd=16, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=HE Kaiming, CHEN Xinlei, XIE Saining, journalName=The IEEE Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=HE Kaiming, CHEN Xinlei, XIE Saining, et al. Masked autoencoders are scalable vision learners[C]. The IEEE Conference on Computer Vision and Pattern Recognition, 2022:16000-16 009., articleTitle=Masked autoencoders are scalable vision learners, refAbstract=null), Reference(id=1168186591676736396, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1751, pageEnd=1759, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=KAT R, JEVNISEK R, AVIDAN S, journalName=The IEEE Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=KAT R, JEVNISEK R, AVIDAN S. Matching pixels using co-occurrence statistics[C]. The IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1751-1759., articleTitle=Matching pixels using co-occurrence statistics, refAbstract=null), Reference(id=1168186591752233870, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=581, pageEnd=17, url=null, language=null, rfNumber=[15], rfOrder=16, authorNames=LINDENBERGER P, SARLIN P, POLLEFEYS M, journalName=International Conference on Computer Vision (ICCV), refType=null, unstructuredReference=LINDENBERGER P, SARLIN P, POLLEFEYS M. LightGlue: local feature matching at light speed[C]. International Conference on Computer Vision (ICCV), 2023: 17 581-17 592., articleTitle=LightGlue: local feature matching at light speed, refAbstract=null)], funds=[Fund(id=1168186590212924268, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, awardId=2023YFB4706900, language=CN, fundingSource=国家重点研发计划项目(2023YFB4706900), fundOrder=null, country=null), Fund(id=1168186590296810350, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, awardId=BK22BE022, language=CN, fundingSource=广东佛山市科技创新项目(BK22BE022), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1168186585406251786, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=1, ext=[AuthorCompanyExt(id=1168186585469166347, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China), AuthorCompanyExt(id=1168186585553052428, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585406251786, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北京科技大学 自动化学院,北京 100083)]), AuthorCompany(id=1168186585712435981, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=2, ext=[AuthorCompanyExt(id=1168186585716630286, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585712435981, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Shunde Innovation School,University of Science and Technology Beijing,Foshan Guangdong 528399,China), AuthorCompanyExt(id=1168186585725018895, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585712435981, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 北京科技大学 顺德创新学院,广东 佛山 528399)]), AuthorCompany(id=1168186585771156240, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, xref=3, ext=[AuthorCompanyExt(id=1168186585792127761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Beijing Building Materials Academy of Science Research,Beijing 100041,China), AuthorCompanyExt(id=1168186585808904978, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, companyId=1168186585771156240, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 北京建筑材料科学研究总院有限公司,北京 100041)])], figs=[ArticleFig(id=1168186588237407039, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.1, caption=CRN-Dataset data set, figureFileSmall=VelUlsk67qFs+6PBhXoasg==, figureFileBig=EWjVAhbTd39wfN9RlK4Vug==, tableContent=null), ArticleFig(id=1168186588312904513, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图1, caption=CRN-Dataset数据集, figureFileSmall=VelUlsk67qFs+6PBhXoasg==, figureFileBig=EWjVAhbTd39wfN9RlK4Vug==, tableContent=null), ArticleFig(id=1168186588371624771, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.2, caption=ODM network model diagram, figureFileSmall=RCPNSFmgpfBKzCVuzU9WCQ==, figureFileBig=v/2sbqu2w7q5tBVg9YLVOA==, tableContent=null), ArticleFig(id=1168186588447122245, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图2, caption=ODM网络模型, figureFileSmall=RCPNSFmgpfBKzCVuzU9WCQ==, figureFileBig=v/2sbqu2w7q5tBVg9YLVOA==, tableContent=null), ArticleFig(id=1168186588514231110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.3, caption=Crane template library, figureFileSmall=ozzZ0hYO9chW8gytrzZ61Q==, figureFileBig=Fp56p4bxTRX/eHx4cDO28g==, tableContent=null), ArticleFig(id=1168186588606505799, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图3, caption=吊车模板库, figureFileSmall=ozzZ0hYO9chW8gytrzZ61Q==, figureFileBig=Fp56p4bxTRX/eHx4cDO28g==, tableContent=null), ArticleFig(id=1168186588669420360, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.4, caption=Flowchart of SDDM algorithm, figureFileSmall=0PSrgbNcXV0gT/9exeY+JA==, figureFileBig=pEGZXhpwviDQ7WkWW2JZ9g==, tableContent=null), ArticleFig(id=1168186588728140617, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图4, caption=SDDM算法流程, figureFileSmall=0PSrgbNcXV0gT/9exeY+JA==, figureFileBig=pEGZXhpwviDQ7WkWW2JZ9g==, tableContent=null), ArticleFig(id=1168186588795249482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.5, caption=Flowchart of DPIM, figureFileSmall=0m7QB/K8SPTMLRw6lFhjvQ==, figureFileBig=SeW4M6rEFFFISGuPPkG3xg==, tableContent=null), ArticleFig(id=1168186588870746958, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图5, caption=DPIM方法验证流程, figureFileSmall=0m7QB/K8SPTMLRw6lFhjvQ==, figureFileBig=SeW4M6rEFFFISGuPPkG3xg==, tableContent=null), ArticleFig(id=1168186588933661522, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.6, caption=DPIM recognition effect, figureFileSmall=L5tvoXGYqPPtmOdVwevjHw==, figureFileBig=WdgoAWLS5ai7QL5QNlExMA==, tableContent=null), ArticleFig(id=1168186589017547604, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图6, caption=DPIM识别效果, figureFileSmall=L5tvoXGYqPPtmOdVwevjHw==, figureFileBig=WdgoAWLS5ai7QL5QNlExMA==, tableContent=null), ArticleFig(id=1168186589114016597, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.7, caption=Comparison of video effect, figureFileSmall=DGA/QSwRNNke6MPUWp+VMA==, figureFileBig=OL8bOFSt4RzJOm0h+DJ8Bg==, tableContent=null), ArticleFig(id=1168186589185319767, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图7, caption=视频效果对比, figureFileSmall=DGA/QSwRNNke6MPUWp+VMA==, figureFileBig=OL8bOFSt4RzJOm0h+DJ8Bg==, tableContent=null), ArticleFig(id=1168186589424395097, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Fig.8, caption=Comparison of evaluation indexes in training process, figureFileSmall=PQSzjRq9mOWCDy9KzuOSgw==, figureFileBig=GAnAiBorLfza1vnCTwkHMQ==, tableContent=null), ArticleFig(id=1168186589487309658, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=图8, caption=训练过程评价指标对比, figureFileSmall=PQSzjRq9mOWCDy9KzuOSgw==, figureFileBig=GAnAiBorLfza1vnCTwkHMQ==, tableContent=null), ArticleFig(id=1168186589558612828, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Table 1, caption=

Images and annotations

, figureFileSmall=null, figureFileBig=null, tableContent=
CRN-Dataset 图像 吊车 工人
训练集 2 184 2 380 2 795
验证集 624 665 802
测试集 312 333 400
总和 3 120 3 378 3 997
), ArticleFig(id=1168186589617333088, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=表1, caption=

图像及标注

, figureFileSmall=null, figureFileBig=null, tableContent=
CRN-Dataset 图像 吊车 工人
训练集 2 184 2 380 2 795
验证集 624 665 802
测试集 312 333 400
总和 3 120 3 378 3 997
), ArticleFig(id=1168186589726384994, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Table 2, caption=

Comparative experiment

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R mAP@0.5 FPS/(帧·s-1)
YOLOv5l 0.862 0.771 0.778 47.6
Faster R-CNN 0.704 0.417 0.655 35.5
SSD 0.440 0.275 0.357 52.9
YOLOv8s 0.838 0.696 0.701 41.2
DPIM 0.894 0.809 0.831 39.4
), ArticleFig(id=1168186589818659684, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=表2, caption=

对比试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R mAP@0.5 FPS/(帧·s-1)
YOLOv5l 0.862 0.771 0.778 47.6
Faster R-CNN 0.704 0.417 0.655 35.5
SSD 0.440 0.275 0.357 52.9
YOLOv8s 0.838 0.696 0.701 41.2
DPIM 0.894 0.809 0.831 39.4
), ArticleFig(id=1168186589931905896, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=EN, label=Table 3, caption=

Ablation experiment

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R mAP@0.5 FPS/(帧·s-1)
YOLOv5l 0.862 0.771 0.778 47.6
YOLOv5l+C2f 0.870 0.777 0.791 50.3
YOLOv5l+CA 0.882 0.790 0.815 36.9
YOLOv5l+C2f+CA 0.892 0.807 0.820 39.8
), ArticleFig(id=1168186590032569194, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738768309076135, language=CN, label=表3, caption=

消融试验

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R mAP@0.5 FPS/(帧·s-1)
YOLOv5l 0.862 0.771 0.778 47.6
YOLOv5l+C2f 0.870 0.777 0.791 50.3
YOLOv5l+CA 0.882 0.790 0.815 36.9
YOLOv5l+C2f+CA 0.892 0.807 0.820 39.8
)], 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.issn1003-3033.2024.07.0235, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2024.07.0235, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2024.07.0235, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2024.07.0235, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于巡检机器人的吊装作业场景DPIM算法
收藏切换
PDF下载
林世康 1, 2 , 侯庆文 1 , 关淯尹 **, 3 , 王文财 3 , 李嘉禄 3 , 陈先中 1, 2
中国安全科学学报 | 安全工程技术 2024,34(7): 146-152
收起
收藏切换
中国安全科学学报 | 安全工程技术 2024, 34(7): 146-152
基于巡检机器人的吊装作业场景DPIM算法
全屏
林世康1, 2 , 侯庆文1, 关淯尹**, 3 , 王文财3, 李嘉禄3, 陈先中1, 2
作者信息
  • 1 北京科技大学 自动化学院,北京 100083
  • 2 北京科技大学 顺德创新学院,广东 佛山 528399
  • 3 北京建筑材料科学研究总院有限公司,北京 100041
  • 林世康 (2000—),男,福建福州人,硕士研究生,研究方向为人工智能和机器视觉。E-mail:

    侯庆文 副教授;

    陈先中 教授

通讯作者:

** 关淯尹(1991—),女,宁夏盐池人,硕士,工程师(人工智能),主要从事智能制造与机器视觉方面的工作。E-mail:
DPIM algorithm for hoisting operation scene based on inspection robot
Shikang LIN1, 2 , Qingwen HOU1, Yuyin GUAN**, 3 , Wencai WANG3, Jialu LI3, Xianzhong CHEN1, 2
Affiliations
  • 1 School of Automation and Electrical Engineering,University of Science and Technology Beijing,Beijing 100083,China
  • 2 Shunde Innovation School,University of Science and Technology Beijing,Foshan Guangdong 528399,China
  • 3 Beijing Building Materials Academy of Science Research,Beijing 100041,China
出版时间: 2024-07-28 doi: 10.16265/j.cnki.issn1003-3033.2024.07.0235
文章导航
收藏切换

为提高吊车安全作业的高精度检测预警,增强企业安全管理能力,围绕工业安全事件分析与监测预警无人化的需求,定制吊装场景地面和空中飞行相结合的巡检机器人,智能化吊装过程安全规程监控、弹窗图像记录和安全告警。首先,制作包含3 120张图片的吊装数据集Cranes-Dataset (CRN-Dataset),提出一种动态视角智能监测 (DPIM) 算法,以增强人-车-物多尺度目标的快速检测能力;然后,依据多帧图像的角点检测和带噪声基于密度的聚类方法,以及吊车与作业工人空间距离的安全属性,制定安全规则触发告警的流程,实时记录违规操作图像并弹窗预警。结果表明:经过实际部署和验证,DPIM算法相较于其他传统算法,吊装作业目标识别能力有明显提高,且适用嵌入式边缘智能分析节点的实时计算与数据传输,完成危险区域人员拒止的现场部署。

巡检机器人  /  吊装场景  /  动态视角智能监测(DPIM)算法  /  人员拒止  /  边缘智能分析

In order to improve the high-precision detection and early warning of crane safety operation and enhance the safety management ability of enterprises,focusing on the needs of unmanned industrial safety incident analysis and monitoring and early warning,an inspection robot that combines ground and air flight in hoisting scene was customized to intelligentize hoisting safety monitoring,pop-up image recording and safety alarm.A lifting dataset Cranes-Dataset (CRN-Dataset) containing 3 120 images was made,and DPIM algorithm was proposed to enhance the rapid detection ability of multi-scale objects.Based on corner detection and density-based spatial clustering of applications with noise and considering the safety attributes of the space distance between cranes and workers,the process of triggering alarms based on safety rules was developed to record real-time illegal operation image and popup alarm.The results show that,after actual deployment and verification,the DPIM algorithm significantly improves target identification ability compared with other traditional algorithms,and it is suitable for real-time calculation and data transmission of embedded edge intelligent analysis nodes to complete field deployment.

inspection robot  /  hoisting scene  /  dynamic perspective intelligent monitoring (DPIM) algorithm  /  personnel denial  /  edge intelligent analysis
林世康, 侯庆文, 关淯尹, 王文财, 李嘉禄, 陈先中. 基于巡检机器人的吊装作业场景DPIM算法. 中国安全科学学报, 2024 , 34 (7) : 146 -152 . DOI: 10.16265/j.cnki.issn1003-3033.2024.07.0235
Shikang LIN, Qingwen HOU, Yuyin GUAN, Wencai WANG, Jialu LI, Xianzhong CHEN. DPIM algorithm for hoisting operation scene based on inspection robot[J]. China Safety Science Journal, 2024 , 34 (7) : 146 -152 . DOI: 10.16265/j.cnki.issn1003-3033.2024.07.0235
随着工业自动化和智能化的发展,吊装作业作为一项涉及大型机械设备和现场人员交互的高风险任务,其安全问题日益受到重视。然而,现有安全管理方法往往难以满足对施工现场安全的准确监测和预警需求,特别是在复杂工业场景下,如何有效应用人工智能技术提高安全管理效果,已成为研究的热点。同时,随着机器人和计算机视觉技术的不断发展,机器人巡检代替人工巡检,在工业安全领域具有广阔的应用前景。
工业施工安全检测至关重要,传统方法难以满足监测预警需求,深度神经网络(Deep Neural Network,DNN)的应用是提升安全管理效果的研究热点。GU Yuwan[1]、DUAN Qipeng[2]、DENG Benyang[3]等通过引入多尺度关键点和多尺度训练,增强了DNN多尺度人员和设备检测的鲁棒性;GAO Guoqing[4]、赵江平[5]等结合YOLO系列算法和自注意力机制,提高了施工现场安全管理的质量和效率;LI Zhishan等[6]通过完善数据集,提高了YOLOv5的拟合能力。此外,采用构建前后文的时空关系、利用先验知识,可有效提高工业目标识别的正确率。SUN Weichen等[7]在YOLOv5中融合Vibe背景建模,实现了有限区域监控目标检测方法;FANG Lijin等[8]基于单目三维目标检测方法获取时空信息,实现了目标遮挡下的目标检测;INTAWONG等[9]根据现实物体运动特种提出一种鲁棒区域检测算法,实现了目标追踪;HEO等[10]基于二元标准正态分布的边界盒裁剪方法,使模型训练更接近真实情况。随着深度神经网络的发展,需要多元解决方案来解决巨大的算力需求。GALLO等[11]采用边缘计算模型提出一种实时高精度个人防护装备检测系统;张磊等[12]引入深度可分离卷积,降低参数量和计算量,实现了煤矿综采工作面安全情况监控。
综上,现有方法在工业场景安全管理方面具备可行性与有效性,但是,采用图像识别技术和边缘计算技术改进吊装施工现场人员安全管理的研究还较为鲜见,且吊装场景监督学习样本的稀缺。鉴于此,笔者拟提出一种融合先验知识、时空关联、适配边缘智能分析节点的吊装作业场景动态视角智能监测 (DPIM) 算法,以期提升吊装区域人员拒止的准确性和时效性。
创建CRN(Cranes)-Dataset数据集,数据来源于巡检机器人在工业园区的实景拍摄及后续扩增。扩增前共2 082张图片,分辨率为1 920×1 080。统一为jpg格式,RGB通道。分为Train和Val这2个子集,比例为9∶1。手动标注,使用最小外接矩形框住目标物体进行类别标注。数据扩增前,吊车标签2 255个,工人标签2 998个。
CRN-Dataset数据集如图1所示。具有以下特点:①频繁遮挡。巡检机器人在移动视角下,吊车在吊装作业过程中常处于被遮挡位置。②背景复杂。吊装场景环境往往十分复杂,背景中可能出现不同种类的视觉干扰物。③远近距离。巡检机器人摄像头与吊车的距离具有远近高低不同的情况,往往根据机器人行驶的路径和方位而变化。④移动视角。巡检机器人的移动工作方式决定了视角是移动的,且具有帧间联系。
现实的生产环境,往往存在大量的复杂情况,巡检机器人不一定能够实现标准的全景拍摄。为增加数据集的多样性和模拟复杂情况,通过以下技术手段扩增1 038张图像。
1) 图像合成。将多个不同的图像元素(如吊车、工人、厂房等)融合成一张新图像,设计人机元素在环境中的不同大小和景深,使得模型能够在更广泛的场景下得到训练。
2) 图像增强。对已有的图像进行旋转、改变图像大小、移动图像位置和调整图像亮度等,增加图片数量,使得模型能够提升多角度、多尺度、不同光照以及复杂环境下的目标识别能力[13]
图像及标注见表1
文中提出一种巡检机器人的吊装作业场景DPIM算法,包括目标检测模块(Object Detection Module,ODM)、移动视角处理模块(Moving View Processing Module,MVPM)和安全距离判定模块 (Security Distance Determination Module,SDDM)。
ODM的主干网络基于YOLOv5l Backbone,使用特征金字塔网络(Feature Pyramid Networks,FPN)增强特征提取,并设计3个不同尺度的检测头来适应不同大小目标的检测需求。其中,P3检测头用于捕捉细节目标,如远处的人;P4适用于近处的人;P5则针对中到大型目标,如吊车。
ODM通过引入C2f模块改进现有主干网络特征提取,利用残差连接学习特征间的关联信息,提高准确性。同时,C2f模块结构简单,降低了模型的计算量和复杂度,提升了运行效率。ODM还引入了协调注意力(Coordinate Attention,CA)机制,自适应地学习每个通道的权重,强化目标特征,抑制遮挡和背景信息,从而提高目标检测的准确性和鲁棒性。
此外,ODM通过调整主干网络卷积层的卷积核尺寸,有效扩大了针对吊车的感受野,兼顾了对大小目标的有效识别。ODM网络模型如图2所示。
ODM初步生成目标检测结果,包括定位及类别标识。由于环境背景复杂,移动视角下目标频繁遮挡等,需通过MVPM进行筛选和补漏。
对常见型号吊车全方位采集与拍摄,建立吊车模板库,提升方法泛化能力,如图3所示。
采用基于共现的模板匹配(Co-occurrence based Template Matching,CoTM),依靠先验知识完善吊装目标的识别[14]。通过吊车模板与当前待测图像匹配的方法,提升算法精度,具体处理如下:
S R = k l m R ( k l ) · m T ( k l ) R = I T
R = a r g R m a x ( S R )
式中:SR为某匹配区域下的相似度; m R ( k l )为原图匹配区域下PMI矩阵对应像素值(kl)的元素值; m T ( k l )为模板图像PMI矩阵对应像素值(kl)的元素值;R为匹配区域;T为模板图像;I为当前待测图像。
输入模板图像及当前待测图像,计算二者各自的共现矩阵C;共现矩阵经过计算转换为点互信息(Pointwise Mutual Information,PMI)矩阵M;通过式(1)、式(2)输出该模板图片在当前帧图片的匹配区域及其对应的SR值。选择SR值最大且达到最低相似度阈值的模板匹配结果,计算匹配区域与ODM识别结果的交并比,如果低于预设筛选阈值,则筛去该检测框,完成先验知识模板匹配方法。
通过对移动视角的上下多帧进行LightGlue轻量级特征匹配[15],得到多帧图像间的对应特征点,获取关联信息。假设特征点的平均移动速度和缩放速度与检测框的相应变化相等。基于此,根据特征点变化推理检测框变化,寻找漏检目标。具体计算方式如下:
s x = p - - a - = p c - a c s y = q - - b - = q c - b c
r x = σ p σ a = w 2 w 1 r y = σ q σ b = h 2 h 1
E ( s ) = s Δ t E ( r ) = ( r ) 1 / Δ t
式中:(ab)和(pq)分别为特征匹配前后2帧图像的任意一对特征点;wh分别为检测框的宽和高;(sxsy)为经过一帧特征点的平均位移;(rxry)为经过一帧横纵方向上特征点的平均密集度变化;(acbc)和(pcqc)分别为前后2帧检测框的中心点; Δ t为经过的间隔帧数。由式(3)、式(4)可以求得后一帧特征点对应的检测框,包括位置(pcqc)和大小(w2h2),由式(5)可得到图像位移和大小的运动估计E(s)和E(r),节约特征点匹配所需的计算资源,直接得到后续帧可能存在的漏检目标。
SDDM通过ODM和MVPM的逐帧识别结果,判断工人与吊车的安全关系,若工人处于吊车潜在坠物的拒止空间(以吊钩为顶点、底面半径覆盖有效作业范围的圆锥体),则发出告警并记录此次事件。SDDM算法流程如图4所示。
具体实现步骤如下:
步骤1:对每个吊车检测框,以其上边缘的中点和下边缘为边界,划定等腰三角形区域。在该区域内进行哈里斯角点检测,得到角点集合V。对每个工人检测框进行角点检测,得到角点集合U;
步骤2:对所有角点作带噪声基于密度的聚类方法分析,将所有角点分为不同的簇。计算V中与U元素划归同簇的元素的比例f,计算U中与V元素划归同簇的元素的比例g。综合比例Yfg的调和平均数,若Y超过预设的安全阈值Ymin,则判定工人与吊车间的安全关系为危险情况;
步骤3:若连续Z帧安全关系被判定为危险,则触发告警。Z为经验阈值,不断优化调整。
使用嵌入式边缘智能分析盒作为模型推理和安全分析的硬件载体,并通过无线网络传输告警信息。
使用CRN-Dataset数据集,训练DPIM模型。将训练得到的模型从pt格式经过onnx格式转化为rknn格式,集成到边缘计算平台,实现数据的实时收集和处理,减少延迟。获取评价指标,分析结果。DPIM算法方法验证流程如图5所示。
主观评估标准:准确识别吊车和工人;工人接近或身处吊车潜在坠物拒止空间时,发出告警,即目标顶部出现“Illegal Entry into the Hoisting Area!”(非法进入吊装区域!)字样;工人与吊车保持距离时,不发出告警。
DPIM算法验的识别效果如图6所示。图6a图6b中,由于安全裕量,工人靠近吊车即会触发告警。图6c中,位于危险区域的工人,其顶部除了标签还有告警。图6d中,吊臂向人群移动,更多工人顶部出现告警。通过试验可知:不论室外较远距离,还是室内复杂背景,新方法可有效识别工人和吊车,并通过SDDM判定并记录工人违规进入吊装区域事件,实现工业现场的实时安全隐患告警功能。
采用不同方法对比吊装场景目标识别的视频效果,如图7所示。由图7可知:随着视角的移动,障碍物遮挡愈发严重,传统方法无法识别所有目标,而DPIM能有效克服物体遮挡对目标识别的负面影响,且置信度高于传统方法。
为验证DPIM算法的实际识别效果,将其与其他方法比较,包括YOLOv5l、Faster R-CNN、SSD和YOLOv8s。采用4个评价指标:识别精确率P、识别召回率R、全类平均正确率(mean Average Precision,mAP)和每秒帧数(Frames Per Second,FPS)衡量识别质量和速度。训练过程指标变化如图8所示。对比试验结果见表2
图8可知:SSD和Faster R-CNN的PR、mAP曲线均在25代以内趋于平衡稳定,时间显著短于其他方法,两者的3种曲线稳定值均低于其他方法,5种算法的P曲线稳定值均高于R曲线稳定值。SSD和Faster R-CNN虽然收敛速度较快,但识别效果较差;5种算法其精确率P曲线的表现均优于其召回率R曲线的表现,由此可见:现有算法对工业场景目标的抗误检能力优于抗漏检能力。
表2可知:DPIM在PR和mAP这3个指标上的表现均优于其他4种算法,且表现最好的时候均超过0.8,分别比同指标其他最优表现提高3.2%、3.8%和5.3%。
为测试所引入模块对目标识别效果的影响,进行消融试验,以YOLOv5l为基准模型,结果见表3。+C2f表示引入C2f模块替换C3模块,+CA表示引入CA机制。
表3可知:对于表征抗误检能力的P,C2f提高0.8%,CA提高2%,C2f和CA均有效果,且CA影响更为显著;对于表征抗漏检能力的R,C2f提高0.6%,CA提高1.9%,C2f和CA均有效果,且CA影响更为显著;当两者共同作用时,mAP提高4.2%,效果显著。C2f不仅对检测精度有贡献,而且提高了FPS。CA的贡献重点体现在对抗复杂背景干扰和对抗遮挡物体的干扰。
1) CRN-Dataset数据集可为吊装场景下的巡检机器人安全检测提供丰富的视觉资源。DPIM方法融合移动视角识别技术和模板匹配算法,可有效提升复杂工业环境中对吊车与工人的实时检测精度。
2) 通过DPIM算法与边缘智能分析盒相结合,可以监控无人智能化吊装场景,并及时预警。
3) 文中尽管在提升吊装场景安全检测能力方面取得显著成果,但仍存在一些局限性:当前方法对于不同环境条件下的适应性和泛化能力尚需进一步验证和优化;随着工业环境的不断变化,未来研究需要考虑更广泛的样本多样性和更复杂的场景。无人机技术的引入将为工业安全监测带来新的视角,拓展监测范围,提高监测的全面性和准确性。
  • 国家重点研发计划项目(2023YFB4706900)
  • 广东佛山市科技创新项目(BK22BE022)
参考文献 引证文献
排序方式:
[1]
GU Yuwan, XU Shoukun, WANG Yaru, et al. An advanced deep learning approach for safety helmet wearing detection[C]. International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2019: 669-674.
[2]
DUAN Qipeng, PING Kuang, LI Fan, et al. Method of safety helmet wearing detection based on key-point estimation without anchor[C]. The 17th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 2020: 93-96.
[3]
DENG Benyang, LEI Xiaochun, YE Miao. Safety helmet detection method based on YOLOv4[C]. The 16th International Conference on Computational Intelligence and Security (CIS), 2020: 155-158.
[4]
GAO Guoqing, LIN Wenhua, LI Guohe, et al. Identification of risk behavior in power working scenarios based on deep learning[C]. The 10th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2022: 391-395.
[5]
赵江平, 刘星星, 张想卓. 基于改进YOLOv5s的外脚手架隐患图像识别技术[J]. 中国安全科学学报, 2023, 33(12): 60-66.
ZHAO Jiangping, LIU Xingxing, ZHANG Xiangzhuo. Research on image recognition technology for external scaffold hidden danger based on improved YOLOv5s[J]. China Safety Science Journal, 2023, 33(12): 60-66.
[6]
LI Zhishan, XIE Wenqing, ZHANG Lingzhi, et al. Toward efficient safety helmet detection based on YOLOv5 with hierarchical positive sample selection and box density filtering[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-14.
[7]
SUN Weichen, YANG Zhanhua, ZHAO Bo, et al. Research on target detection of regional monitoring with complex background using CNN and background modelling[C]. The 7th International Conference on Machine Vision and Information Technology (CMVIT), 2023:102-106.
[8]
FANG Lijin, HUANG Yongjie, ZHAO Qiankun, et al. Monocular 3D object detection based on occlusion optimization[C]. The 7th International Conference on Intelligent Computing and Signal Processing (ICSP), 2022:604-609.
[9]
INTAWONG K, PROMPANTAKORN P, BOONCHIENG W. An improved automatic zone detection algorithm based on mechanic flow for complex scene event[C]. Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering, 2021:265-268.
[10]
HEO J, WANG Y, PARK J. Occlusion data augmentation for object detectors based on random erasing and bounding box tailoring[C]. The 20th International Conference on Control, Automation and Systems (ICCAS), 2020: 1068-1072.
[11]
GALLO G, FRANCESCO D R, GARZELLI F, et al. A smart system for personal protective equipment detection in industrial environments based on deep learning at the edge[J]. IEEE Access, 2022, 10: 110 862-110 878.
[12]
张磊, 李熙尉, 燕倩如, 等. 基于改进YOLOv5s的综采工作面人员检测算法[J]. 中国安全科学学报, 2023, 33(7): 82-89.
ZHANG Lei, LI Xiwei, YAN Qianru, et al. Personnel detection algorithm in fully mechanized coal face based on improved YOLOv5s[J]. China Safety Science Journal, 2023, 33(7): 82-89.
[13]
HE Kaiming, CHEN Xinlei, XIE Saining, et al. Masked autoencoders are scalable vision learners[C]. The IEEE Conference on Computer Vision and Pattern Recognition, 2022:16000-16 009.
[14]
KAT R, JEVNISEK R, AVIDAN S. Matching pixels using co-occurrence statistics[C]. The IEEE Conference on Computer Vision and Pattern Recognition, 2018: 1751-1759.
[15]
LINDENBERGER P, SARLIN P, POLLEFEYS M. LightGlue: local feature matching at light speed[C]. International Conference on Computer Vision (ICCV), 2023: 17 581-17 592.
2024年第34卷第7期
PDF下载
308
116
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2024.07.0235
  • 接收时间:2024-01-12
  • 首发时间:2025-07-09
  • 出版时间:2024-07-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-12
  • 修回日期:2024-04-13
基金
国家重点研发计划项目(2023YFB4706900)
广东佛山市科技创新项目(BK22BE022)
作者信息
    1 北京科技大学 自动化学院,北京 100083
    2 北京科技大学 顺德创新学院,广东 佛山 528399
    3 北京建筑材料科学研究总院有限公司,北京 100041

通讯作者:

** 关淯尹(1991—),女,宁夏盐池人,硕士,工程师(人工智能),主要从事智能制造与机器视觉方面的工作。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.07.0235
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