Article(id=1149789679798678163, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404733, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1719244800000, receivedDateStr=2024-06-25, revisedDate=1741276800000, revisedDateStr=2025-03-07, acceptedDate=null, acceptedDateStr=null, onlineDate=1752060821722, onlineDateStr=2025-07-09, pubDate=1749312000000, pubDateStr=2025-06-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752060821722, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752060821722, creator=13701087609, updateTime=1752060821722, updator=13701087609, issue=Issue{id=1149768563956826506, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='16', pageStart='6587', pageEnd='7021', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752055787314, creator=13701087609, updateTime=1768456850262, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559607937618069, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559607937618070, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768563956826506, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=6812, endPage=6820, ext={EN=ArticleExt(id=1149789680012587670, articleId=1149789679798678163, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Tunnel Lining Defects Precision Detection Method Based on Improved YOLOv5, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

Tunnel lining detection is an important element of quality management in tunnel construction and maintenance. Due to the variety of internal lining defects and unclear boundaries makes it challenging to identify these problems and train models effectively. Relying on manual detection or existing models, it is not possible to achieve fast and accurate defect detection. To address the above problems, A dataset consisted of 1 922 liner radar samples collected from Yunnan Tunnel B-scan was developed for training the model. A tunnel lining defect detection model YOLO-Tunnel based on YOLOv5 was proposed, which improved the model feature extraction ability, increased the receptive field, and improved the model localization ability by upgraded the Backbone and Neck. And further improved the model detection ability by selected the appropriate model size and balanced weight based on the dataset's scale and target size proportions. The results show that YOLO-Tunnel has better defect detection accuracy compared to YOLOv5s and also meets the real-time detection requirements, in which the precision, recall, and mAP are increased by 2.5, 9.0, and 8.1 percentage points, respectively, with the inference time increases by 2.7 ms to 21.8 ms. The research results provide a reference for further improving the performance of the detection of tunnel lining detection and the direction of optimization of the model reference.

, correspAuthors=Qing-wen ZHANG, 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=Li-han FANG, Qing-wen ZHANG, Wei-guo LI, Da-qing ZOU, Jiu-fei LU), CN=ArticleExt(id=1149789694919144422, articleId=1149789679798678163, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于改进YOLOv5的隧道衬砌病害精确检测方法, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

隧道衬砌检测是隧道建造与维护的一项重要质量管理内容。因衬砌内部病害种类多样、边界模糊,导致病害识别不准、模型训练困难。而依靠人工识别或现有模型无法实现快速、准确得检测病害。针对上述问题,以云南隧道B-scan取得的1 922个衬砌雷达样本创建数据集,用于训练模型,并提出一种基于YOLOv5的隧道衬砌病害检测模型YOLO-Tunnel。通过改进Backbone与Neck,提升了模型特征提取能力、增加感受野、提升模型定位能力;根据数据集规模和目标尺寸比例,选择合适的模型尺寸和平衡权重,进一步提高模型识别能力。结果表明:YOLO-Tunnel相比YOLOv5s有更好的病害检测精度同时也满足实时检测需求,其中准确率、召回率、均值平均精度(mAP)分别提高了2.5、9.0、8.1个百分点,推理时间增加了2.7 ms,为21.8 ms。研究成果为进一步提高隧道衬砌病害识别性能及模型优化方向提供参考。

, correspAuthors=张庆文, authorNote=null, correspAuthorsNote=
* 张庆文(1966—),男,汉族,云南鹤庆人,博士,教授。研究方向:隧道工程。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=ihBakAXh+0ECscczAPIcCQ==, magXml=zrnpfBF85NgqtcNt4+Dk9g==, pdfUrl=null, pdf=HaZO+7AQxhjCdl/ibixeHQ==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=gcfovnEHERfHnHUK1KvD7A==, mapNumber=null, authorCompany=null, fund=null, authors=

方力涵(1994—),男,汉族,湖北黄石人,硕士。研究方向:计算机视觉。E-mail:

, authorsList=方力涵, 张庆文, 李卫国, 邹大晴, 陆久飞)}, authors=[Author(id=1178019431939719658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=flh1994@live.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1178019432011022828, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019431939719658, language=EN, stringName=Li-han FANG, firstName=Li-han, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering, Southwest Forestry University, Kunming 650224, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1178019432069743085, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019431939719658, language=CN, stringName=方力涵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西南林业大学土木工程学院, 昆明 650224, bio={"content":"

方力涵(1994—),男,汉族,湖北黄石人,硕士。研究方向:计算机视觉。E-mail:

"}, bioImg=null, bioContent=

方力涵(1994—),男,汉族,湖北黄石人,硕士。研究方向:计算机视觉。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1178019431688061408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=1, ext=[AuthorCompanyExt(id=1178019431696450017, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431688061408, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering, Southwest Forestry University, Kunming 650224, China), AuthorCompanyExt(id=1178019431700644322, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431688061408, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南林业大学土木工程学院, 昆明 650224)])]), Author(id=1178019432124269039, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=99tmzqw@swfu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1178019432187183601, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432124269039, language=EN, stringName=Qing-wen ZHANG, firstName=Qing-wen, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Civil Engineering, Southwest Forestry University, Kunming 650224, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1178019432241709554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432124269039, language=CN, stringName=张庆文, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 西南林业大学土木工程学院, 昆明 650224, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1178019431688061408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=1, ext=[AuthorCompanyExt(id=1178019431696450017, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431688061408, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering, Southwest Forestry University, Kunming 650224, China), AuthorCompanyExt(id=1178019431700644322, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431688061408, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南林业大学土木工程学院, 昆明 650224)])]), Author(id=1178019432317207028, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, 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=1178019432371732982, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432317207028, language=EN, stringName=Wei-guo LI, firstName=Wei-guo, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Baoshan Longying Expressway Co. , Ltd. , Baoshan 678000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1178019432430453239, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432317207028, language=CN, stringName=李卫国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 保山隆营高速公路有限公司, 保山 678000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1178019431767753187, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=2, ext=[AuthorCompanyExt(id=1178019431776141796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431767753187, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Baoshan Longying Expressway Co. , Ltd. , Baoshan 678000, China), AuthorCompanyExt(id=1178019431780336101, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431767753187, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 保山隆营高速公路有限公司, 保山 678000)])]), Author(id=1178019432489173497, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, 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=1178019432556282363, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432489173497, language=EN, stringName=Da-qing ZOU, firstName=Da-qing, middleName=null, lastName=ZOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Baoshan Longying Expressway Co. , Ltd. , Baoshan 678000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1178019432602419708, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432489173497, language=CN, stringName=邹大晴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 保山隆营高速公路有限公司, 保山 678000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1178019431767753187, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=2, ext=[AuthorCompanyExt(id=1178019431776141796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431767753187, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Baoshan Longying Expressway Co. , Ltd. , Baoshan 678000, China), AuthorCompanyExt(id=1178019431780336101, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431767753187, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 保山隆营高速公路有限公司, 保山 678000)])]), Author(id=1178019432652751358, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, 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=1178019432724054528, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432652751358, language=EN, stringName=Jiu-fei LU, firstName=Jiu-fei, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Broadvision Engineering Consultants Co. , Ltd. , Kunming 650220, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1178019432791163393, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, authorId=1178019432652751358, language=CN, stringName=陆久飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 云南省交通规划设计研究院有限公司, 昆明 650220, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1178019431855833574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=3, ext=[AuthorCompanyExt(id=1178019431864222183, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431855833574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Broadvision Engineering Consultants Co. , Ltd. , Kunming 650220, China), AuthorCompanyExt(id=1178019431872610792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431855833574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 云南省交通规划设计研究院有限公司, 昆明 650220)])])], keywords=[Keyword(id=1178019432908603906, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, orderNo=1, keyword=ground penetrating radar), Keyword(id=1178019432967324163, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, orderNo=2, keyword=lining inspection), Keyword(id=1178019433026044420, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, orderNo=3, keyword=deep learning), Keyword(id=1178019433084764677, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, orderNo=4, keyword=objection detection), Keyword(id=1178019433168650758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, orderNo=1, keyword=探地雷达), Keyword(id=1178019433256731143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, orderNo=2, keyword=衬砌检测), Keyword(id=1178019433336422920, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, orderNo=3, keyword=深度学习), Keyword(id=1178019433390948873, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, orderNo=4, keyword=目标检测)], refs=[Reference(id=1178019435290968611, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=7, pageStart=29, pageEnd=33, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=中华人民共和国交通运输部, journalName=中国水运, refType=null, unstructuredReference=中华人民共和国交通运输部. 2022年交通运输行业发展统计公报[J]. 中国水运, 2023(7): 29-33., articleTitle=2022年交通运输行业发展统计公报, refAbstract=null), Reference(id=1178019435358077476, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=7, pageStart=29, pageEnd=33, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Ministry of Transport of the People's Republic of China, journalName=China Water Transport, refType=null, unstructuredReference=Ministry of Transport of the People's Republic of China. Statistical bulletin on the development of the transportation industry in 2022[J]. China Water Transport, 2023(7): 29-33., articleTitle=Statistical bulletin on the development of the transportation industry in 2022, refAbstract=null), Reference(id=1178019435420992037, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=721, pageEnd=738, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=巩江峰, 王伟, 黎旭, journalName=隧道建设, refType=null, unstructuredReference=巩江峰, 王伟, 黎旭, 等. 截至2022年底中国铁路隧道情况统计及2022年新开通项目重点隧道概况[J]. 隧道建设, 2023, 43(4): 721-738., articleTitle=截至2022年底中国铁路隧道情况统计及2022年新开通项目重点隧道概况, refAbstract=null), Reference(id=1178019435471323686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=4, pageStart=721, pageEnd=738, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Gong Jiangfeng, Wang Wei, Li Xu, journalName=Tunnel Construction, refType=null, unstructuredReference=Gong Jiangfeng, Wang Wei, Li Xu, et al. Statistics of railway tunnels in China by the end of 2022 and overview of key tunnels of projects newly put into operation in 2022[J]. Tunnel Construction, 2023, 43(4): 721-738., articleTitle=Statistics of railway tunnels in China by the end of 2022 and overview of key tunnels of projects newly put into operation in 2022, refAbstract=null), Reference(id=1178019435530043943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2021, volume=34, issue=11, pageStart=178, pageEnd=199, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=刘德军, 仲飞, 黄宏伟, journalName=中国公路学报, refType=null, unstructuredReference=刘德军, 仲飞, 黄宏伟, 等. 运营隧道衬砌病害诊治的现状与发展[J]. 中国公路学报, 2021, 34(11): 178-199., articleTitle=运营隧道衬砌病害诊治的现状与发展, refAbstract=null), Reference(id=1178019435605541416, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2021, volume=34, issue=11, pageStart=178, pageEnd=199, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Liu Dejun, Zhong Fei, Huang Hongwei, journalName=China Journal of Highway and Transport, refType=null, unstructuredReference=Liu Dejun, Zhong Fei, Huang Hongwei, et al. Present status and development trend of diagnosis and treatment of tunnel lining diseases[J]. China Journal of Highway and Transport, 2021, 34(11): 178-199., articleTitle=Present status and development trend of diagnosis and treatment of tunnel lining diseases, refAbstract=null), Reference(id=1178019435685233193, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=张隽, journalName=探地雷达检测技术与管理, refType=null, unstructuredReference=张隽. 探地雷达检测技术与管理[M]. 长春: 吉林大学出版社, 2021., articleTitle=null, refAbstract=null), Reference(id=1178019435748147754, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Zhang Juan, journalName=Ground penetrating radar detection technology and management, refType=null, unstructuredReference=Zhang Juan. Ground penetrating radar detection technology and management[M]. Changchun: Jilin University Press, 2021., articleTitle=null, refAbstract=null), Reference(id=1178019435806868011, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=董亚楠, journalName=基于深度学习的隧道衬砌结构多病害智能识别, refType=null, unstructuredReference=董亚楠. 基于深度学习的隧道衬砌结构多病害智能识别[D]. 济南: 山东大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1178019435886559788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Dong Yanan, journalName=Intelligent detection of multiple defect in tunnel lining structure based on deep learning, refType=null, unstructuredReference=Dong Yanan. Intelligent detection of multiple defect in tunnel lining structure based on deep learning[D]. Jinan: Shandong University, 2020., articleTitle=null, refAbstract=null), Reference(id=1178019435949474349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=1986, volume=null, issue=null, pageStart=8, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Canny J, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8: DOI: 10.1109/TPAMI.1986.4767851., articleTitle=A computational approach to edge detection, refAbstract=null), Reference(id=1178019436008194606, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2003, volume=20, issue=null, pageStart=91, pageEnd=110, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Lowe D, journalName=International Journal of Computer Vision, refType=null, unstructuredReference=Lowe D. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2003, 20: 91-110., articleTitle=Distinctive image features from scale-invariant key points, refAbstract=null), Reference(id=1178019436092080687, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=Bay H, Tuytelaars T, Gool L V, journalName=SURF: speeded up robust features, refType=null, unstructuredReference=Bay H, Tuytelaars T, Gool L V. SURF: speeded up robust features[M]. Berlin: Springer, 2006., articleTitle=null, refAbstract=null), Reference(id=1178019436175966768, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2018, volume=40, issue=3, pageStart=293, pageEnd=301, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=高永涛, 徐俊, 吴顺川, journalName=工程科学学报, refType=null, unstructuredReference=高永涛, 徐俊, 吴顺川, 等. 基于GPR反射波信号多维分析的隧道病害智能辨识[J]. 工程科学学报, 2018, 40(3): 293-301., articleTitle=基于GPR反射波信号多维分析的隧道病害智能辨识, refAbstract=null), Reference(id=1178019436238881329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2018, volume=40, issue=3, pageStart=293, pageEnd=301, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=Gao Yongtao, Xu Jun, Wu Shunchuan, journalName=Chines Journal of Engineering, refType=null, unstructuredReference=Gao Yongtao, Xu Jun, Wu Shunchuan, et al. An intelligent identification method to detect tunnel defects based on the multidimensional analysis of GPR reflections[J]. Chines Journal of Engineering, 2018, 40(3): 293-301., articleTitle=An intelligent identification method to detect tunnel defects based on the multidimensional analysis of GPR reflections, refAbstract=null), Reference(id=1178019436301795890, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=29, pageStart=13075, pageEnd=13082, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=王平让, 黄宏伟, 薛亚东, journalName=科学技术与工程, refType=null, unstructuredReference=王平让, 黄宏伟, 薛亚东. 基于图像结构信息的隧道衬砌裂缝实时快速识别[J]. 科学技术与工程, 2022, 22(29): 13075-13082., articleTitle=基于图像结构信息的隧道衬砌裂缝实时快速识别, refAbstract=null), Reference(id=1178019436381487667, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=29, pageStart=13075, pageEnd=13082, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=Wang Pingrang, Huang Hongwei, Xue Yadong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wang Pingrang, Huang Hongwei, Xue Yadong. Real-time fast recognition of tunnel lining cracks based on image structure information[J]. Science Technology and Engineering, 2022, 22(29): 13075-13082., articleTitle=Real-time fast recognition of tunnel lining cracks based on image structure information, refAbstract=null), Reference(id=1178019436444402228, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=Girshick R, Donahue J, Darrell T, journalName=IEEE Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation tech report(v5)[C]// IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH: IEEE, 2014: DOI: 10.1109/cvpr.2014.81., articleTitle=Rich feature hierarchies for accurate object detection and semantic segmentation tech report(v5), refAbstract=null), Reference(id=1178019436515705397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=Redmon J, Divvala S, Girshick R, journalName=Computer Vision & Pattern Recognition. Las Vegas, refType=null, unstructuredReference=Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]// Computer Vision & Pattern Recognition. Las Vegas, NV: IEEE, 2016: DOI: 10.1109/CVPR.2016.91., articleTitle=You only look once: unified, real-time object detection, refAbstract=null), Reference(id=1178019436587008566, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=5, pageStart=19, pageEnd=29, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=王建锋, 刘文豪, 潘清云, journalName=北京交通大学学报, refType=null, unstructuredReference=王建锋, 刘文豪, 潘清云. 基于图像处理与深度学习的隧道衬砌裂缝检测[J]. 北京交通大学学报, 2022, 46(5): 19-29., articleTitle=基于图像处理与深度学习的隧道衬砌裂缝检测, refAbstract=null), Reference(id=1178019436641534519, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2022, volume=46, issue=5, pageStart=19, pageEnd=29, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=Wang Jianfeng, Liu Wenhao, Pan Qingyun, journalName=Journal of Beijing Jiaotong University, refType=null, unstructuredReference=Wang Jianfeng, Liu Wenhao, Pan Qingyun. Crack detection for tunnel lining based on image processing and deep learning[J]. Journal of Beijing Jiaotong University, 2022, 46(5): 19-29., articleTitle=Crack detection for tunnel lining based on image processing and deep learning, refAbstract=null), Reference(id=1178019436696060472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=7, pageStart=137, pageEnd=146, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=薛亚东, 高健, 李宜城, journalName=湖南大学学报(自然科学版), refType=null, unstructuredReference=薛亚东, 高健, 李宜城, 等. 基于深度学习的地铁隧道衬砌病害检测模型优化[J]. 湖南大学学报(自然科学版), 2020, 47(7): 137-146., articleTitle=基于深度学习的地铁隧道衬砌病害检测模型优化, refAbstract=null), Reference(id=1178019436771557945, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=7, pageStart=137, pageEnd=146, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=Xue Yadong, Gao Jian, Li Yicheng, journalName=Journal of Hunan University(Natural Sciences), refType=null, unstructuredReference=Xue Yadong, Gao Jian, Li Yicheng, et al. Optimization of shield tunnel lining defect detection model based on deep learning[J]. Journal of Hunan University(Natural Sciences), 2020, 47(7): 137-146., articleTitle=Optimization of shield tunnel lining defect detection model based on deep learning, refAbstract=null), Reference(id=1178019436838666810, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=3, pageStart=1008, pageEnd=1019, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=朱家松, 郑澳, 雷占占, journalName=铁道科学与工程学报, refType=null, unstructuredReference=朱家松, 郑澳, 雷占占, 等. 基于改进YOLOv5的地铁隧道附属设施与衬砌表观病害检测方法[J]. 铁道科学与工程学报, 2023, 20(3): 1008-1019., articleTitle=基于改进YOLOv5的地铁隧道附属设施与衬砌表观病害检测方法, refAbstract=null), Reference(id=1178019436893192763, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=20, issue=3, pageStart=1008, pageEnd=1019, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=Zhu Jiasong, Zheng Ao, Lei Zhanzhan, journalName=Journal of Railway Science and Engineering, refType=null, unstructuredReference=Zhu Jiasong, Zheng Ao, Lei Zhanzhan, et al. Metro tunnel accessorial facilities and lining diseases detection method based on improved YOLOv5[J]. Journal of Railway Science and Engineering, 2023, 20(3): 1008-1019., articleTitle=Metro tunnel accessorial facilities and lining diseases detection method based on improved YOLOv5, refAbstract=null), Reference(id=1178019436943524412, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=60, issue=4, pageStart=67, pageEnd=75, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=吴刚, 罗炜, 王小龙, journalName=现代隧道技术, refType=null, unstructuredReference=吴刚, 罗炜, 王小龙, 等. 基于深度学习的盾构隧道衬砌表观病害检测模型研究[J]. 现代隧道技术, 2023, 60(4): 67-75., articleTitle=基于深度学习的盾构隧道衬砌表观病害检测模型研究, refAbstract=null), Reference(id=1178019437006438973, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=60, issue=4, pageStart=67, pageEnd=75, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=Wu Gang, Luo Wei, Wang Xiaolong, journalName=Modern Tunnelling Technology, refType=null, unstructuredReference=Wu Gang, Luo Wei, Wang Xiaolong, et al. Study on a deep learning-based model for detecting apparent defects inshield tunnel lining[J]. Modern Tunnelling Technology, 2023, 60(4): 67-75., articleTitle=Study on a deep learning-based model for detecting apparent defects inshield tunnel lining, refAbstract=null), Reference(id=1178019437060964926, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=4, pageStart=1018, pageEnd=1032, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=彭雨诺, 刘敏, 万智, journalName=自动化学报, refType=null, unstructuredReference=彭雨诺, 刘敏, 万智, 等. 基于改进YOLO的双网络桥梁表观病害快速检测算法[J]. 自动化学报, 2022, 48(4): 1018-1032., articleTitle=基于改进YOLO的双网络桥梁表观病害快速检测算法, refAbstract=null), Reference(id=1178019437132268095, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=4, pageStart=1018, pageEnd=1032, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=Peng Yunuo, Liu Min, Wan Zhi, journalName=Acta Automatica Sinica, refType=null, unstructuredReference=Peng Yunuo, Liu Min, Wan Zhi, et al. A dual deep network based on the improved YOLO for fast bridge surface defect detection[J]. Acta Automatica Sinica, 2022, 48(4): 1018-1032., articleTitle=A dual deep network based on the improved YOLO for fast bridge surface defect detection, refAbstract=null), Reference(id=1178019437182599744, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=4, pageStart=1552, pageEnd=1556, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=冯德山, 杨子龙, journalName=地球物理学进展, refType=null, unstructuredReference=冯德山, 杨子龙. 基于深度学习的隧道衬砌结构物探地雷达图像自动识别[J]. 地球物理学进展, 2020, 35(4): 1552-1556., articleTitle=基于深度学习的隧道衬砌结构物探地雷达图像自动识别, refAbstract=null), Reference(id=1178019437241320001, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2020, volume=35, issue=4, pageStart=1552, pageEnd=1556, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=Feng Deshan, Yang Zilong, journalName=Progress in Geophysics, refType=null, unstructuredReference=Feng Deshan, Yang Zilong. Automatic recognition of ground penetrating radar image of tunnel lining structure based on deep learning[J]. Progress in Geophysics, 2020, 35(4): 1552-1556., articleTitle=Automatic recognition of ground penetrating radar image of tunnel lining structure based on deep learning, refAbstract=null), Reference(id=1178019437300040258, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=4, pageStart=45, pageEnd=54, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=杜义康, 罗建利, 郭瑜, journalName=昆明理工大学学报(自然科学版), refType=null, unstructuredReference=杜义康, 罗建利, 郭瑜. 基于深度迁移学习的铁路隧道衬砌结构病害检测研究[J]. 昆明理工大学学报(自然科学版), 2023, 48(4): 45-54., articleTitle=基于深度迁移学习的铁路隧道衬砌结构病害检测研究, refAbstract=null), Reference(id=1178019437388120643, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=4, pageStart=45, pageEnd=54, url=null, language=null, rfNumber=[19], rfOrder=32, authorNames=Du Yikang, Luo Jianli, Guo Yu, journalName=Journal of Kunming University of Science and Technology(Natural Science), refType=null, unstructuredReference=Du Yikang, Luo Jianli, Guo Yu. Detection of railway tunnel lining structure defects basedon deep transfer learning[J]. Journal of Kunming University of Science and Technology(Natural Science), 2023, 48(4): 45-54., articleTitle=Detection of railway tunnel lining structure defects basedon deep transfer learning, refAbstract=null), Reference(id=1178019437455229508, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=2, pageStart=171, pageEnd=180, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=崔广炎, 王艳辉, 徐杰, journalName=铁道学报, refType=null, unstructuredReference=崔广炎, 王艳辉, 徐杰, 等. 基于改进Faster R-CNN的隧道衬砌中离散实体目标自动检测研究[J]. 铁道学报, 2024, 46(2): 171-180., articleTitle=基于改进Faster R-CNN的隧道衬砌中离散实体目标自动检测研究, refAbstract=null), Reference(id=1178019437513949765, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=2, pageStart=171, pageEnd=180, url=null, language=null, rfNumber=[20], rfOrder=34, authorNames=Cui Guangyan, Wang Yanhui, Xu Jie, journalName=Journal of The China Railway Society, refType=null, unstructuredReference=Cui Guangyan, Wang Yanhui, Xu Jie, et al. Automatic detection of discrete entity objects in tunnel lining based on improved Faster R-CNN[J]. Journal of The China Railway Society, 2024, 46(2): 171-180., articleTitle=Automatic detection of discrete entity objects in tunnel lining based on improved Faster R-CNN, refAbstract=null), Reference(id=1178019437572670022, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://github.com/ultralytics/yolov5, language=null, rfNumber=[21], rfOrder=35, authorNames=Glenn J, journalName=null, refType=null, unstructuredReference=Glenn J. Ultralytics YOLOv5[EB/OL]. (2020-05-10)[2023-10-24]. https://github.com/ultralytics/yolov5., articleTitle=Ultralytics YOLOv5, refAbstract=null), Reference(id=1178019437627195975, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=Lin T Y, Dollar P, Girshick R, journalName=2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), refType=null, unstructuredReference=Lin T Y, Dollar P, Girshick R, et al. Feature pyramid networks for object detection[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). New York: IEEE, 2017: DOI: 10.1109/CVPR.2017.106., articleTitle=Feature pyramid networks for object detection, refAbstract=null), Reference(id=1178019437698499144, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=Liu S, Qi L, Qin H, journalName=IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, refType=null, unstructuredReference=Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE, 2018: DOI: 10.1109/CVPR.2018.00913., articleTitle=Path aggregation network for instance segmentation, refAbstract=null), Reference(id=1178019437765608009, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://hub.fgit.cf/ultralytics/yolov5/issues/6998, language=null, rfNumber=[24], rfOrder=38, authorNames=Glenn J, journalName=null, refType=null, unstructuredReference=Glenn J. YOLOv5(6.0/6.1) brief summary #6998[EB/OL]. (2022-05-30)[2023-10-15]. https://hub.fgit.cf/ultralytics/yolov5/issues/6998., articleTitle=YOLOv5(6.0/6.1) brief summary #6998, refAbstract=null), Reference(id=1178019437828522570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[25], rfOrder=39, authorNames=Ren S, He K, Girshick R, journalName=IEEE Transactions on Pattern Analysis & Machine Intelligence, refType=null, unstructuredReference=Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149., articleTitle=Faster R-CNN: towards real-time object detection with region proposal networks, refAbstract=null), Reference(id=1178019437887242827, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=40, authorNames=Redmon J, Farhadi A, journalName=arXiv E-prints, refType=null, unstructuredReference=Redmon J, Farhadi A. YOLOv3: an incremental improvement[J]. arXiv E-prints, 2018: DOI: 10.48550/arXiv.1804.02767., articleTitle=YOLOv3: an incremental improvement, refAbstract=null)], funds=[Fund(id=1178019435165139490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, awardId=YCIC-YF-2023-16, language=CN, fundingSource=云南省交通投资建设集团有限公司科技创新项目(YCIC-YF-2023-16), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1178019431688061408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=1, ext=[AuthorCompanyExt(id=1178019431696450017, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431688061408, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering, Southwest Forestry University, Kunming 650224, China), AuthorCompanyExt(id=1178019431700644322, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431688061408, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南林业大学土木工程学院, 昆明 650224)]), AuthorCompany(id=1178019431767753187, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=2, ext=[AuthorCompanyExt(id=1178019431776141796, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431767753187, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Baoshan Longying Expressway Co. , Ltd. , Baoshan 678000, China), AuthorCompanyExt(id=1178019431780336101, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431767753187, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 保山隆营高速公路有限公司, 保山 678000)]), AuthorCompany(id=1178019431855833574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, xref=3, ext=[AuthorCompanyExt(id=1178019431864222183, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431855833574, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Broadvision Engineering Consultants Co. , Ltd. , Kunming 650220, China), AuthorCompanyExt(id=1178019431872610792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, companyId=1178019431855833574, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 云南省交通规划设计研究院有限公司, 昆明 650220)])], figs=[ArticleFig(id=1178019433588081162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Fig.1, caption=Examples of the training dataset, figureFileSmall=wqUr+i+ZG419zbz/Tbj07Q==, figureFileBig=bnnuvagsBNLilcIWehGMkA==, tableContent=null), ArticleFig(id=1178019433655190027, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=图1, caption=训练数据示例, figureFileSmall=wqUr+i+ZG419zbz/Tbj07Q==, figureFileBig=bnnuvagsBNLilcIWehGMkA==, tableContent=null), ArticleFig(id=1178019433730687500, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Fig.2, caption=Conv-C3 module, figureFileSmall=QsBvDwoGBnwAjqnsB2frEw==, figureFileBig=kXIXXF3VtN7esdd4hMFF8g==, tableContent=null), ArticleFig(id=1178019433785213453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=图2, caption=Conv-C3模块, figureFileSmall=QsBvDwoGBnwAjqnsB2frEw==, figureFileBig=kXIXXF3VtN7esdd4hMFF8g==, tableContent=null), ArticleFig(id=1178019433848128014, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Fig.3, caption=FPN-PAN module, figureFileSmall=VqlBkP76en7sV+W7qbIcew==, figureFileBig=rH7BXlXkevYpLb7xZa9EjA==, tableContent=null), ArticleFig(id=1178019433911042575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=图3, caption=FPN-PAN模块, figureFileSmall=VqlBkP76en7sV+W7qbIcew==, figureFileBig=rH7BXlXkevYpLb7xZa9EjA==, tableContent=null), ArticleFig(id=1178019434015900176, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Fig.4, caption=YOLO-Tunnel model structure diagram, figureFileSmall=jr81SWi/7T/x7VWxioCCDQ==, figureFileBig=7EnX/nrW1uonMpKOTCO5cA==, tableContent=null), ArticleFig(id=1178019434066231825, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=图4, caption=YOLO-Tunnel模型结构图, figureFileSmall=jr81SWi/7T/x7VWxioCCDQ==, figureFileBig=7EnX/nrW1uonMpKOTCO5cA==, tableContent=null), ArticleFig(id=1178019434120757778, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Fig.5, caption=Comparison of different balance weights, figureFileSmall=jJo5jf7fAhCGIdW49qMkHg==, figureFileBig=nGTPmsmtLK4F18kGMwV4gw==, tableContent=null), ArticleFig(id=1178019434171089427, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=图5, caption=不同平衡权重对比, figureFileSmall=jJo5jf7fAhCGIdW49qMkHg==, figureFileBig=nGTPmsmtLK4F18kGMwV4gw==, tableContent=null), ArticleFig(id=1178019434234003988, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Fig.6, caption=Comparison results between the proposed model and other models, figureFileSmall=Vb9MmuCVNtX43BeJlaVZOg==, figureFileBig=8gI9I7GKoFhurnCmPeY9Nw==, tableContent=null), ArticleFig(id=1178019434288529941, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=图6, caption=本文模型与其他模型对比结果

红色框代表不密实;粉色框代表空洞;橙色框代表脱空

, figureFileSmall=Vb9MmuCVNtX43BeJlaVZOg==, figureFileBig=8gI9I7GKoFhurnCmPeY9Nw==, tableContent=null), ArticleFig(id=1178019434347250198, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Table 1, caption=

Number of different target sizes

, figureFileSmall=null, figureFileBig=null, tableContent=
尺寸 边长像素 比例 数量/个
小尺寸 0~100 0~0.16 133
中尺寸 100~300 0.16~0.47 1 332
大尺寸 >300 >0.47 247
), ArticleFig(id=1178019434405970455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=表1, caption=

不同目标尺寸数量

, figureFileSmall=null, figureFileBig=null, tableContent=
尺寸 边长像素 比例 数量/个
小尺寸 0~100 0~0.16 133
中尺寸 100~300 0.16~0.47 1 332
大尺寸 >300 >0.47 247
), ArticleFig(id=1178019434477273624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Table 2, caption=

Depth distribution of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 深度分布
YOLO-Tunnel1 3-6-9-3-3
YOLO-Tunnel2 3-3-6-9-3
YOLO-Tunnel3 3-6-9-6-3
YOLO-Tunnel4 3-6-9-12-3
YOLO-Tunnel5 3-6-9-12-6
), ArticleFig(id=1178019434540188185, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=表2, caption=

不同模型深度分布

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 深度分布
YOLO-Tunnel1 3-6-9-3-3
YOLO-Tunnel2 3-3-6-9-3
YOLO-Tunnel3 3-6-9-6-3
YOLO-Tunnel4 3-6-9-12-3
YOLO-Tunnel5 3-6-9-12-6
), ArticleFig(id=1178019434619879962, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Table 3, caption=

Model detection speed comparison

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 参数量/M 运算量/G 推理时间/ms
YOLOv5s 7.0 16.0 19.1
YOLO-A 6.8 4.7 19.4
YOLO-B 7.1 18.7 20.4
YOLO-Tunnel1 7.1 5.4 22.8
YOLO-Tunnel2 7.2 5.4 22.3
YOLO-Tunnel3 7.1 5.5 23.3
YOLO-Tunnel4 7.4 5.8 24.5
YOLO-Tunnel5 8.0 5.9 24.8
), ArticleFig(id=1178019434678600219, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=表3, caption=

模型检测速度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 参数量/M 运算量/G 推理时间/ms
YOLOv5s 7.0 16.0 19.1
YOLO-A 6.8 4.7 19.4
YOLO-B 7.1 18.7 20.4
YOLO-Tunnel1 7.1 5.4 22.8
YOLO-Tunnel2 7.2 5.4 22.3
YOLO-Tunnel3 7.1 5.5 23.3
YOLO-Tunnel4 7.4 5.8 24.5
YOLO-Tunnel5 8.0 5.9 24.8
), ArticleFig(id=1178019434737320476, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Table 4, caption=

Comparison of model detection performance

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 精确率/% 召回率/% mAP/% F1
YOLOv5s 72.2 63.1 69.5 0.67
YOLO-A 74.9 66.9 74.6 0.72
YOLO-B 69.8 65.0 70.3 0.70
YOLO-Tunnel1 76.4 70.9 75.2 0.72
YOLO-Tunnel2 67.0 71.8 71.4 0.69
YOLO-Tunnel3 73.4 68.4 72.6 0.71
YOLO-Tunnel4 71.0 70.7 71.9 0.71
YOLO-Tunnel5 78.8 67.6 74.3 0.72
), ArticleFig(id=1178019434804429341, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=表4, caption=

模型检测精度对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 精确率/% 召回率/% mAP/% F1
YOLOv5s 72.2 63.1 69.5 0.67
YOLO-A 74.9 66.9 74.6 0.72
YOLO-B 69.8 65.0 70.3 0.70
YOLO-Tunnel1 76.4 70.9 75.2 0.72
YOLO-Tunnel2 67.0 71.8 71.4 0.69
YOLO-Tunnel3 73.4 68.4 72.6 0.71
YOLO-Tunnel4 71.0 70.7 71.9 0.71
YOLO-Tunnel5 78.8 67.6 74.3 0.72
), ArticleFig(id=1178019434863149598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Table 5, caption=

Comparison of model improvements

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 识别率/% 精确
率/%
召回
率/%
mAP/
%
F1 推理
时间/
ms
不密实 空洞 脱空
YOLOV5s 66.6 55.0 87.2 72.2 63.1 69.5 0.67 19.1
YOLO-Tunnel 80.4 63.3 89.0 74.7 72.1 77.6 0.72 21.8
), ArticleFig(id=1178019434917675551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=表5, caption=

模型改进对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 识别率/% 精确
率/%
召回
率/%
mAP/
%
F1 推理
时间/
ms
不密实 空洞 脱空
YOLOV5s 66.6 55.0 87.2 72.2 63.1 69.5 0.67 19.1
YOLO-Tunnel 80.4 63.3 89.0 74.7 72.1 77.6 0.72 21.8
), ArticleFig(id=1178019434984784416, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=EN, label=Table 6, caption=

Comparison with other models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 mAP/% 推理时间/ms
Faster R-CNN 43.0 405.8
YOLOv3-SPP 34.2 20.3
YOLOv5s 69.5 19.1
YOLOv5-Tunnel 77.6 21.8
), ArticleFig(id=1178019435064476193, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149789679798678163, language=CN, label=表6, caption=

与其他模型的对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 mAP/% 推理时间/ms
Faster R-CNN 43.0 405.8
YOLOv3-SPP 34.2 20.3
YOLOv5s 69.5 19.1
YOLOv5-Tunnel 77.6 21.8
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, 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.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, 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.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, 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/kxjsygc/CN/10.12404/j.issn.1671-1815.2404733, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404733, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404733, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404733, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进YOLOv5的隧道衬砌病害精确检测方法
收藏切换
PDF下载
方力涵 1 , 张庆文 1, * , 李卫国 2 , 邹大晴 2 , 陆久飞 3
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(16): 6812-6820
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(16): 6812-6820
基于改进YOLOv5的隧道衬砌病害精确检测方法
全屏
方力涵1 , 张庆文1, * , 李卫国2, 邹大晴2, 陆久飞3
作者信息
  • 1 西南林业大学土木工程学院, 昆明 650224
  • 2 保山隆营高速公路有限公司, 保山 678000
  • 3 云南省交通规划设计研究院有限公司, 昆明 650220
  • 方力涵(1994—),男,汉族,湖北黄石人,硕士。研究方向:计算机视觉。E-mail:

通讯作者:

* 张庆文(1966—),男,汉族,云南鹤庆人,博士,教授。研究方向:隧道工程。E-mail:
Tunnel Lining Defects Precision Detection Method Based on Improved YOLOv5
Li-han FANG1 , Qing-wen ZHANG1, * , Wei-guo LI2, Da-qing ZOU2, Jiu-fei LU3
Affiliations
  • 1 School of Civil Engineering, Southwest Forestry University, Kunming 650224, China
  • 2 Baoshan Longying Expressway Co. , Ltd. , Baoshan 678000, China
  • 3 Broadvision Engineering Consultants Co. , Ltd. , Kunming 650220, China
出版时间: 2025-06-08 doi: 10.12404/j.issn.1671-1815.2404733
文章导航
收藏切换

隧道衬砌检测是隧道建造与维护的一项重要质量管理内容。因衬砌内部病害种类多样、边界模糊,导致病害识别不准、模型训练困难。而依靠人工识别或现有模型无法实现快速、准确得检测病害。针对上述问题,以云南隧道B-scan取得的1 922个衬砌雷达样本创建数据集,用于训练模型,并提出一种基于YOLOv5的隧道衬砌病害检测模型YOLO-Tunnel。通过改进Backbone与Neck,提升了模型特征提取能力、增加感受野、提升模型定位能力;根据数据集规模和目标尺寸比例,选择合适的模型尺寸和平衡权重,进一步提高模型识别能力。结果表明:YOLO-Tunnel相比YOLOv5s有更好的病害检测精度同时也满足实时检测需求,其中准确率、召回率、均值平均精度(mAP)分别提高了2.5、9.0、8.1个百分点,推理时间增加了2.7 ms,为21.8 ms。研究成果为进一步提高隧道衬砌病害识别性能及模型优化方向提供参考。

探地雷达  /  衬砌检测  /  深度学习  /  目标检测

Tunnel lining detection is an important element of quality management in tunnel construction and maintenance. Due to the variety of internal lining defects and unclear boundaries makes it challenging to identify these problems and train models effectively. Relying on manual detection or existing models, it is not possible to achieve fast and accurate defect detection. To address the above problems, A dataset consisted of 1 922 liner radar samples collected from Yunnan Tunnel B-scan was developed for training the model. A tunnel lining defect detection model YOLO-Tunnel based on YOLOv5 was proposed, which improved the model feature extraction ability, increased the receptive field, and improved the model localization ability by upgraded the Backbone and Neck. And further improved the model detection ability by selected the appropriate model size and balanced weight based on the dataset's scale and target size proportions. The results show that YOLO-Tunnel has better defect detection accuracy compared to YOLOv5s and also meets the real-time detection requirements, in which the precision, recall, and mAP are increased by 2.5, 9.0, and 8.1 percentage points, respectively, with the inference time increases by 2.7 ms to 21.8 ms. The research results provide a reference for further improving the performance of the detection of tunnel lining detection and the direction of optimization of the model reference.

ground penetrating radar  /  lining inspection  /  deep learning  /  objection detection
方力涵, 张庆文, 李卫国, 邹大晴, 陆久飞. 基于改进YOLOv5的隧道衬砌病害精确检测方法. 科学技术与工程, 2025 , 25 (16) : 6812 -6820 . DOI: 10.12404/j.issn.1671-1815.2404733
Li-han FANG, Qing-wen ZHANG, Wei-guo LI, Da-qing ZOU, Jiu-fei LU. Tunnel Lining Defects Precision Detection Method Based on Improved YOLOv5[J]. Science Technology and Engineering, 2025 , 25 (16) : 6812 -6820 . DOI: 10.12404/j.issn.1671-1815.2404733
截至2022年底,中国投入运营的公路、铁路隧道的总里程达4.9×104 km[1-2]。由于隧道地质环境复杂(如围岩压力变异、列车振动、气候温度、地下水等),施工、设计、后期养护维修等诸多原因,随着隧道年限增加,隧道衬砌结构性能逐渐劣化,内部出现薄弱环节,产生渗水、裂缝、空洞、不密实等结构性病害[3]。这些病害恶化隧道服役性能,降低了隧道结构的耐久性和承载性,影响隧道的正常运营,甚至威胁线路行车安全和人民的生命安全。且隧道的病害发展是有一个过程,如果能在隧道病害恶化之前发现,并采取整治措施,则可以大大提高营运隧道的安全性[4]
传统的隧道检测方法大多为人工巡检,通过观测或者借助工具对隧道衬砌的裂缝、渗漏水、空洞等病害进行检测,但检测结果因受检测人员的工程经验存在较大偏差且信息化程度不足。目前探地雷达、摄像测量、激光扫描等无损检测检测手段成为主流,为隧道的长期安全运营提供了重要的技术支撑[5],快速、自动化、实时检测成为隧道衬砌病害无损检测技术的发展趋势。传统的图像处理算法,如Canny边缘检测器[6]、SIFT(scale invariant feature transform)特征提取器[7],SURF(speeded up robust features)特征提取器[8]以及专门针对裂缝病害检测的算法等,在实际应用中多依赖于人为调参,导致效率低,周期长,鲁棒性差,且病害检测准确率难以满足需要。
随着人工智能技术的发展,利用机器学习自动化识别隧道衬砌病害已成为新的趋势。高永涛等[9]根据反射波信号提取病害信号缺陷特征,利用支持向量机(support vector machines,SVM)SVM算法对缺陷特征的训练二分类模型, 实现了病害水平分布范围的自动识别。王平让等[10]利用图像灰度信息简化运算过程实现隧道衬砌裂缝的快速识别。从机器学习中脱颖而出的深度学习在计算机视觉领域表现更为优秀,基于深度学习的语义分割模型和目标检测模型R-CNN[11] (region-based convolutional neural networks)系列、YOLO[12] (you only look once)系列被用于病害的自动化检测中。
在表观病害检测方面,王建锋等[13]采用改进Mask匀光算法和拼接缝去除法提高图像质量,构建改进型的VGG19检测模型,提高隧道衬砌裂缝检测准确率。薛亚东等[14]构建了基于Faster R-CNN的地铁隧道衬砌表面病害识别模型并结合聚类算法进行优化,提升了病害识别准确率。朱家松等[15]在YOLOv5模型中添加注意力机制,使用BiFPN(bidirectional feature pyramid network)和Ghost Bottleneck 改进模型,提升模型检测隧道衬砌表面病害识别能力。吴刚等[16]结合K-means聚类优化YOLOv4模型结构提升对盾构表面病害的识别效果。彭雨诺等 [17]基于YOLOv4提出了增加混合空洞金字塔的YOLO-lump 和小窗口滑动的YOLO-crack分别应对桥梁表面的块状病害检测和裂缝病害检测。
表观病害大多是裂缝与渗水,病害特征与衬砌内部病害特征不一致。对于内部病害检测的研究,冯德山等[18]采用Faster R-CNN和YOLOv3对隧道衬砌内的钢拱架、钢筋网、施工缝进行识别并分析模型识别不同目标的效果。杜义康等[19]利用数值模拟与真实雷达图像组成的样本拟建立仿真探地雷达图像数据库,提出迁移学习检测隧道衬砌的脱空、空洞、不密实的方法。崔广炎等[20]从轻量化角度出发改进Faster R-CNN用于识别衬砌内部仿真数据和真实数据。
上述研究通过对模型改进及参数优化在隧道衬砌表观的病害处理均取得较好效果,但目前对于隧道衬砌内部病害的目标检测的研究并不充分。隧道衬砌雷达图像通常是仅有灰度信息的图像,其相对彩色图像缺少了2/3的信息量;衬砌内部的病害成因可能一致,但规模不同,导致不同病害之间具有一定相似性;各种外部环境因素导致雷达反射信号不明显,目标分辨不清,这容易将病害判定为背景。深度学习模型需要大量数据来运算才能收敛到一个满意的效果,同时隧道衬砌雷达图像的这些特征均不利于模型的特征提取,也难以进行病害分类。鉴于此,通过改进模型结构、调整模型尺寸、优化平衡,提出一种基于YOLOv5[21]的改进模型YOLO-Tunnel,使其在小规模数据集中也能训练出更加优秀的效果,同时可以用于实时检测隧道衬砌内部的空洞、脱空、不密实。可用于帮助人工判断衬砌图像缺陷,减少工作量,提升工作效率。输出的结果可以整理出不同病害种类和数量。
在深度学习模型训练过程,需要从指定的数据集中提取特定信息供模型学习,而深度学习中常用的图像数据集,如CIFAR、Open Images Dataset、COCO、PASCAL VOC等,这些数据集中的图像均由相机拍摄的可见光构成,场景取自于日常生活,数据集庞大、标签复杂、目标清晰。然而在隧道衬砌的病害检测领域,是探地雷达经过正演后成像得出的图像,通常为灰度图。衬砌病害方面,空洞、脱空、不密实有其独特的特征,也有相似之处。因此利用常规数据集对模型进行预训练的思路是不可行的。
目前这一研究领域还未建立有规模的、专业的公开数据集。通过LTD系列探地雷达天线采集云南部分隧道衬砌雷达数据并对其进行标准化成像处理。数据经过地质雷达数据软件IDSP7成像、零点调节、滤波、背景消除、信号增益后,输出成内部结构清晰、灰度适中的图像,并整理成隧道衬砌图像数据库。
提取数据库中有病害的图像,根据目标检测需求在Labelimg中标注,制作模型训练数据集。目前整理的数据集包含1 922 张图像,数据集中包含许多不适合用于训练的图片,所以最终分配是训练集1 089张,验证集160张,测试集673张。目标信息包括两部分:目标类别即空洞、脱空、不密实和目标位置,采用一个矩形的真实边界框(Ground truth)完整得框住整个病害,同时要求其尽可能小。YOLO的数据标签包含目标类别、名称、目标中心点位置和边界框尺寸。部分训练数据如图1所示,分别展示了空洞、脱空和不密实特征。
YOLOv5是按照COCO数据集的尺寸大小区分目标大小,对分辨率小于32×32的称为小目标,大于96×96的称为大目标,中尺寸介于两者之间。在YOLOv5的Input环节,输入特征图尺寸被按比例压缩或填充至640×640,然后通过Mosaic方式将4张图像进行成一张,目标尺寸也按照同样的比例缩放,本数据集的图像尺寸长边平均约为1 000像素,因此通过缩放拼接后的小目标映射到原尺寸约为100×100,对应原尺寸比例约为0.16×0.16。将训练集和验证集中的目标尺寸按照大小分类,结果如表1所示,中尺寸目标占总目标数的78%。
YOLO作为一种单阶段的模型,它将目标检测转变成一个回归问题,利用一个神经网络,得到边界框的位置和标签。相对R-CNN为主的双阶段模型,YOLO的精度略低但拥有更快的检测速度,满足实时监测的需求。YOLOv5包括 Input、Backbone、Neck和Head 4个网络结构,分别用于数据处理、特征提取、特征融合和目标预测。
病害之间相似度过高,且目标尺寸大多为大尺寸,经过多次卷积运算后任然能保证一定的分辨率,因此可以提高模型的特征提取能力以便有更好的表现。模型的Backbone结构主要负责图像的压缩与升维,由此在获得模型在卷积过程中的不同维度与不同尺寸的特征层。YOLOv5的6.1版本用一个6×6的Conv层等效代替了以前的Focus层,因此模型的Backbone部分由5个Conv模块,4个C3模块和1个SPPF池化模块构成。C3模块内部用Concat方法拼接,Conv模块是由卷积(Conv)、批量归一化(BN)、激活函数组合而成,用于增强特征提取。C3模块是YOLOv5中对残差特征学习的主要模块,目的是在不增加计算量的情况下提高特征表达能力。在Backbone中新增图2所示的Conv-C3模块,其中Conv的步长(Step)为2、卷积核(Ksize)尺寸为3×3,并将第一层的Conv输出维度分别调整为32,之后每个Conv的输出均为上一层C3的2倍,这样保证最终输出到SPPF的维度为1 024,就可保持后续Neck和Head的其他层结构和维度不变,最后调整Neck的Concat连接到相同尺寸特征层的C3或Conv模块。Backbone增加Conv-C3模块后,输入特征会多经历一轮压缩与升维,输出SPPF的特征层尺寸为10×10,为改进前的1/4;按照式(1)计算,Head部分每个预测层的感受野约为改进前的4倍,更大的感受野适用于更大的目标尺寸。
fout=(fin-1)Step+Ksize
式(1)中:fout为输出层感受野;fin为输入层感受野;Step为步长;Ksize为卷积核尺寸。
改进Backbone部分的模型称为YOLO-A。
一个特征提取网络的深层包含更多的语义信息,包括目标的形状,纹理,类别等高维抽象特征,但输入特征经过多次被卷积和池化操作,会逐渐抛弃原始图像中的位置和细节信息,导致有相似语义信息的目标容易被误判。而网络的浅层拥有更高的分辨率,包含更多的位置和细节信息,但语义信息较少。YOLOv5模型中Neck网络结构的FPN-PAN组合能更好地混合多维度特征层信息并增加一条Backbone到Head之间的信息路径。
特征金字塔(feature pyramid network,FPN)FPN[22]是将高维特征通过上取样(Up sample),对Backbone中同一维度不同尺寸的特征层进行拼接,这种操作可以融合低维特征的位置信息和高维特征的语义信息,从而将不同复杂程度的目标在不同的特征层中分别识别。路径聚合网络(path aggregation network,PAN)[23]通过利用低维度特征层的定位信息增强整个特征层次,低维信息不必经过Backbone和FPN的高维Conv层,直接通过PAN的Conv层输出到Head层的各个预测特征层,从而缩短了部分从输入到输出之间的信息路径。
在FPN结构的第2个C3模块后添加一组Conv-UP-Concat-C3模块,输出160×160×128的特征层,Concat拼接Backbone的同维C3模块。PAN的第1个C3模块之前添加一组Conv-Concat-C3模块,输出80×80×256的特征层,新增模块的Concat拼接FPN的第3个Conv层,其结构如图3所示。Head层分辨检测PAN最后3个C3模块,检测尺寸和维度和初始模型一致。改进Neck部分的模型称为YOLO-B。
将Backbone和Neck两个部分的改进结合在一起,构成图4所示的模型结构。在Backbone新增一组Conv-C3模块并将FPN新增模块中的Concat拼接到Backbone的第2个C3模块,该系列模型称为YOLO-Tunnel。在Backbone结构中不同位置C3模块的深度的组合称为模型的深度分布,YOLOv5s的深度分布从低维到高维分别为3、6、9、3。YOLO-Tunnel相比YOLOv5s多一个Conv-C3模块,需要调整深度分布。不同模型名称与其深度分布如表2所示。
本实验中,评价指标分为检测精度和检测速度两部分。检测精度包括精确率(Precision)、召回率(Recall)、mAP(mean average precision)和F1(F1 score)。其中,精确率用于描述正确检测到的目标数占所有检测到的目标数的比例;召回率用于描述正确检测到的目标数占应该被正确检测到的目标数的比例;mAP为各类别的AP平均值,用于平衡所有标签的检测指标;F1为用于平衡精确率和召回率,其中的1代表两者权重一致。
检测速度包括推理时间、模型参数量(Params)和浮点运算量(FLOPs)。推理时间是指一张图像从输入到输出结果的总耗时,包括图片处理、模型计算、后处理耗时这与处理硬件和软件有直接关联。模型参数量是指模型中训练的总参数量。浮点运算量是指模型每秒计算量,考量一个模型的计算量的标准。
YOLO-Tunnel模型改进对比试验,比较改进前后的模型尺寸和推理速度,验证了所提出的改进模型对于隧道病害检测性能的影响。改进模型的深度倍率(depth multiple)和宽度倍率(weight multiple)参照YOLOv5s模型尺寸,分别设置为0.33和0.5。YOLO-A的深度分布与YOLO-Tunnel1一致。模型尺寸和推理速度对比如表3所示。
通过参数量对比可知,改变模型结构只是略微改变模型参数量。通过YOLOv5s和YOLO-A的对比可知,降低第一层卷积的维度减小了模型的整体运算量,但是推理时间并没有减少。因为推理时间基本是由计算和访存两方面组成的,在GPU的加速下,小模型的计算时间并不多,更多的时间花费在了内存访问中。本文模型改进为增加模块,这些模块增加了模型复杂程度,也增加了模型推理时间。通过YOLOv5s和YOLO-B的对比可知,增加FPN-PAN模块使得模型整体更复杂,增加了模型推理时间。对比YOLO-Tunnel2和YOLO-Tunnel5,随着C3重复次数从8次提高到12次,推理时间增加了2.5 ms。
通过表4的数据可知,单独改进Backbone的YOLO-A相比YOLOv5s模型性能均有提升,因此增加C3模块能提高模型性能。
而单独改进Neck的YOLO-B在召回率有提升但精确率下降。除了YOLO-Tunnel2的精确率稍低,同时改进Backbone和Neck能给模型带来精确率和召回率的普遍提升。观察YOLO-Tunnel系列与YOLO-A的对比,Neck部分的改进虽然降低了平均精确率,但是提高了整体的召回率,因此增加Neck模块也是有必要的。
其中深度分布为3、6、9、3、3的YOLO-Tunnel1模型在本次实验中拥有最好的检测性能,相比YOLOv5s,其精确率、召回率均有提升,mAP提升了4.7个百分点。YOLO-Tunnel5与YOLO-Tunnel1相比,精确率较高但召回率较低,因此最终选取综合水平更好的YOLO-Tunnel1作为之后的模型尺寸改进及平衡权重调整的基础模型。
模型的尺寸通常会对训练结果有较大影响。本实验参照YOLOv5的模型的深度和宽度倍率,对YOLO-Tunnel系列设置nsml 4个不同尺寸的模型,其中YOLO-Tunnel1的模型尺寸为s
根据YOLOv5作者Glenn[24]在github社区的描述,loss.py中的平衡权重是调整Neck结构中最后3个C3模块到Head结构的目标损失权重(object loss),YOLOv5的初始平权重略为
self.balance={3:[4.0,1.0,0.4]}.get(m.nl[4.0,1.0,0.25,0.06,0.02])
式(2)中:[4.0,1.0,0.4]这3个参数对应初始模型的第17、20、23层的C3模块,主要用于小尺寸、中尺寸和大尺寸的目标检测,参数的设定是以COCO数据集为基础,根据以往训练经验的人工调参结果。
本数据集中有78%的中尺寸目标,因此增强中尺寸目标的权重而降低大小目标的权重,以改进模型为基础尝试多种平衡权重并根据经验将其调整为
self.balance={3:[3.5,1.5,0.3]}.get(m.nl[4.0,1.0,0.25,0.06,0.02])
通过YOLOv5和YOLO-Tunnel的不同尺寸模型在两个平衡权重下训练的结果得到图5。通过其mAP的对比可知,模型尺寸对检测性能有影响,整体上较小的模型尺寸在本数据集有更好的表现。因为灰度图像的信息量较少且病害特征不明显,而原有模型的特征提取能力不足,增加卷积结构能有效提高模型的特征提取能力。如果单纯提高模型深度,如改变模型深度倍率,也能增加模型卷积结构,但缺少残差结构导致模型训练不容易收敛,难以提高模型识别能力。且较小的数据集不足以支撑参数量更大的模型,因此减小模型尺寸也能提升模型性能。最终通过改变模型尺寸来适应数据集特点。
不同的尺寸的模型调整平衡权重后,mAP有不同程度的变化,其中尺寸为n的YOLO-Tunnel检测效果最好。
根据表5的对比可知,与YOLOV5s相比,YOLO-Tunnel在不密实、空洞和脱空的识别率分别提高了13.8、8.3、1.8个百分点,精确率、召回率和mAP分别提高了2.5、9.0、8.1个百分点。因为模型增加了两组新模块导致推理时间增加2.7 ms。由此可见,在隧道衬砌内部病害识别方面,YOLO-Tunnel全面领先YOLOV5s。
本实验将YOLO-Tunnel与Faster R-CNN[25]、YOLOv3-SPP[26]、YOLOv5s进行mAP和推理时间的比较,实验结果如表6所示。Faster R-CNN的并不占优势,而且推理时间较长1 s仅能处理两张图像,不能满足实时检测的需求;YOLOv3-SPP的mAP就代表模型完全没有收敛,训练效果差。YOLOv5-Tunnel拥有最好的性能,在保证推理时间满足快速检测的同时拥有最高的mAP。
图6为不同模型在验证集的隧道衬砌雷达图像的检测结果。图像Ⅰ~Ⅴ为隧道衬砌病害雷达图像。Faster R-CNN拥有最高的平均置信度为76.57%,但存在1个漏检3个误检,其中有两次误检将背景识别成病害,高置信度、低召回率就是过拟合的状态,这就导致该模型识别效果较差;YOLOv3-SPP存在1个漏检1个误检,出现了一次将背景识别成目标的情况;YOLOv5s出现了一次漏检;YOLOv5-Tunnel出现一次误检。以上结果说明YOLOv5系列相对Faster R-CNN和YOLOv3-SPP误检概率更低,能更好得滤除背景,并没有将病害图像Ⅴ中的钢拱架识别成不密实。YOLOv5系列相对YOLOv3最大的优势在于数据的预处理,图像在输入网络之前会有拼接与增强,这就使得小样本的数据集也可以训练出更好的效果。所提出的YOLOv5-Tunnel比YOLOv5s有更高的召回表现,且病害置信度更高,因此能在本验证集集中有最好的表现。
人工识别隧道衬砌内部病害困难、效率低,而且病害雷达图像由于信息量较少、病害难以分辨的特点导致现有模型特征提取困难。基于YOLOv5提出一个改进模型YOLO-Tunnel,用于快速准确识别隧道衬砌内部病害。得出如下结论。
(1)结合雷达图像的特点,在Backbon和Neck结构中新增模块并调模型整深度分布,提升特征提取能力,提高病害检测性能。
(2)模型优化方面:模型尺寸受数据集规模影响,较小规模的数据集需要小尺寸模型匹配;平衡权重需要根据数据集尺寸及模型结构进行调整以达到更好训练效果;训练小规模数据集时首先进行数据增强操作能够有效提高训练效果。
(3)通过本模型和其他模型进行对比,实验结果证明了本文方法的有效性,并适合辅助人工判别隧道衬砌病害。
  • 云南省交通投资建设集团有限公司科技创新项目(YCIC-YF-2023-16)
参考文献 引证文献
排序方式:
[1]
中华人民共和国交通运输部. 2022年交通运输行业发展统计公报[J]. 中国水运, 2023(7): 29-33.
Ministry of Transport of the People's Republic of China. Statistical bulletin on the development of the transportation industry in 2022[J]. China Water Transport, 2023(7): 29-33.
[2]
巩江峰, 王伟, 黎旭, 等. 截至2022年底中国铁路隧道情况统计及2022年新开通项目重点隧道概况[J]. 隧道建设, 2023, 43(4): 721-738.
Gong Jiangfeng, Wang Wei, Li Xu, et al. Statistics of railway tunnels in China by the end of 2022 and overview of key tunnels of projects newly put into operation in 2022[J]. Tunnel Construction, 2023, 43(4): 721-738.
[3]
刘德军, 仲飞, 黄宏伟, 等. 运营隧道衬砌病害诊治的现状与发展[J]. 中国公路学报, 2021, 34(11): 178-199.
Liu Dejun, Zhong Fei, Huang Hongwei, et al. Present status and development trend of diagnosis and treatment of tunnel lining diseases[J]. China Journal of Highway and Transport, 2021, 34(11): 178-199.
[4]
张隽. 探地雷达检测技术与管理[M]. 长春: 吉林大学出版社, 2021.
Zhang Juan. Ground penetrating radar detection technology and management[M]. Changchun: Jilin University Press, 2021.
[5]
董亚楠. 基于深度学习的隧道衬砌结构多病害智能识别[D]. 济南: 山东大学, 2020.
Dong Yanan. Intelligent detection of multiple defect in tunnel lining structure based on deep learning[D]. Jinan: Shandong University, 2020.
[6]
Canny J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8: DOI: 10.1109/TPAMI.1986.4767851.
[7]
Lowe D. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2003, 20: 91-110.
[8]
Bay H, Tuytelaars T, Gool L V. SURF: speeded up robust features[M]. Berlin: Springer, 2006.
[9]
高永涛, 徐俊, 吴顺川, 等. 基于GPR反射波信号多维分析的隧道病害智能辨识[J]. 工程科学学报, 2018, 40(3): 293-301.
Gao Yongtao, Xu Jun, Wu Shunchuan, et al. An intelligent identification method to detect tunnel defects based on the multidimensional analysis of GPR reflections[J]. Chines Journal of Engineering, 2018, 40(3): 293-301.
[10]
王平让, 黄宏伟, 薛亚东. 基于图像结构信息的隧道衬砌裂缝实时快速识别[J]. 科学技术与工程, 2022, 22(29): 13075-13082.
Wang Pingrang, Huang Hongwei, Xue Yadong. Real-time fast recognition of tunnel lining cracks based on image structure information[J]. Science Technology and Engineering, 2022, 22(29): 13075-13082.
[11]
Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation tech report(v5)[C]// IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH: IEEE, 2014: DOI: 10.1109/cvpr.2014.81.
[12]
Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]// Computer Vision & Pattern Recognition. Las Vegas, NV: IEEE, 2016: DOI: 10.1109/CVPR.2016.91.
[13]
王建锋, 刘文豪, 潘清云. 基于图像处理与深度学习的隧道衬砌裂缝检测[J]. 北京交通大学学报, 2022, 46(5): 19-29.
Wang Jianfeng, Liu Wenhao, Pan Qingyun. Crack detection for tunnel lining based on image processing and deep learning[J]. Journal of Beijing Jiaotong University, 2022, 46(5): 19-29.
[14]
薛亚东, 高健, 李宜城, 等. 基于深度学习的地铁隧道衬砌病害检测模型优化[J]. 湖南大学学报(自然科学版), 2020, 47(7): 137-146.
Xue Yadong, Gao Jian, Li Yicheng, et al. Optimization of shield tunnel lining defect detection model based on deep learning[J]. Journal of Hunan University(Natural Sciences), 2020, 47(7): 137-146.
[15]
朱家松, 郑澳, 雷占占, 等. 基于改进YOLOv5的地铁隧道附属设施与衬砌表观病害检测方法[J]. 铁道科学与工程学报, 2023, 20(3): 1008-1019.
Zhu Jiasong, Zheng Ao, Lei Zhanzhan, et al. Metro tunnel accessorial facilities and lining diseases detection method based on improved YOLOv5[J]. Journal of Railway Science and Engineering, 2023, 20(3): 1008-1019.
[16]
吴刚, 罗炜, 王小龙, 等. 基于深度学习的盾构隧道衬砌表观病害检测模型研究[J]. 现代隧道技术, 2023, 60(4): 67-75.
Wu Gang, Luo Wei, Wang Xiaolong, et al. Study on a deep learning-based model for detecting apparent defects inshield tunnel lining[J]. Modern Tunnelling Technology, 2023, 60(4): 67-75.
[17]
彭雨诺, 刘敏, 万智, 等. 基于改进YOLO的双网络桥梁表观病害快速检测算法[J]. 自动化学报, 2022, 48(4): 1018-1032.
Peng Yunuo, Liu Min, Wan Zhi, et al. A dual deep network based on the improved YOLO for fast bridge surface defect detection[J]. Acta Automatica Sinica, 2022, 48(4): 1018-1032.
[18]
冯德山, 杨子龙. 基于深度学习的隧道衬砌结构物探地雷达图像自动识别[J]. 地球物理学进展, 2020, 35(4): 1552-1556.
Feng Deshan, Yang Zilong. Automatic recognition of ground penetrating radar image of tunnel lining structure based on deep learning[J]. Progress in Geophysics, 2020, 35(4): 1552-1556.
[19]
杜义康, 罗建利, 郭瑜. 基于深度迁移学习的铁路隧道衬砌结构病害检测研究[J]. 昆明理工大学学报(自然科学版), 2023, 48(4): 45-54.
Du Yikang, Luo Jianli, Guo Yu. Detection of railway tunnel lining structure defects basedon deep transfer learning[J]. Journal of Kunming University of Science and Technology(Natural Science), 2023, 48(4): 45-54.
[20]
崔广炎, 王艳辉, 徐杰, 等. 基于改进Faster R-CNN的隧道衬砌中离散实体目标自动检测研究[J]. 铁道学报, 2024, 46(2): 171-180.
Cui Guangyan, Wang Yanhui, Xu Jie, et al. Automatic detection of discrete entity objects in tunnel lining based on improved Faster R-CNN[J]. Journal of The China Railway Society, 2024, 46(2): 171-180.
[21]
Glenn J. Ultralytics YOLOv5[EB/OL]. (2020-05-10)[2023-10-24]. https://github.com/ultralytics/yolov5. https://github.com/ultralytics/yolov5
[22]
Lin T Y, Dollar P, Girshick R, et al. Feature pyramid networks for object detection[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). New York: IEEE, 2017: DOI: 10.1109/CVPR.2017.106.
[23]
Liu S, Qi L, Qin H, et al. Path aggregation network for instance segmentation[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT: IEEE, 2018: DOI: 10.1109/CVPR.2018.00913.
[24]
Glenn J. YOLOv5(6.0/6.1) brief summary #6998[EB/OL]. (2022-05-30)[2023-10-15]. https://hub.fgit.cf/ultralytics/yolov5/issues/6998. https://hub.fgit.cf/ultralytics/yolov5/issues/6998
[25]
Ren S, He K, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149.
[26]
Redmon J, Farhadi A. YOLOv3: an incremental improvement[J]. arXiv E-prints, 2018: DOI: 10.48550/arXiv.1804.02767.
2025年第25卷第16期
PDF下载
374
150
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404733
  • 接收时间:2024-06-25
  • 首发时间:2025-07-09
  • 出版时间:2025-06-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-25
  • 修回日期:2025-03-07
基金
云南省交通投资建设集团有限公司科技创新项目(YCIC-YF-2023-16)
作者信息
    1 西南林业大学土木工程学院, 昆明 650224
    2 保山隆营高速公路有限公司, 保山 678000
    3 云南省交通规划设计研究院有限公司, 昆明 650220

通讯作者:

* 张庆文(1966—),男,汉族,云南鹤庆人,博士,教授。研究方向:隧道工程。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404733
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