首页 期刊 论文 学科刊群 资讯 加盟 关于
EN
image
Article(id=1149780475323048383, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149780466032669506, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2403371, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1715097600000, receivedDateStr=2024-05-08, revisedDate=1735833600000, revisedDateStr=2025-01-03, acceptedDate=null, acceptedDateStr=null, onlineDate=1752058627205, onlineDateStr=2025-07-09, pubDate=1744041600000, pubDateStr=2025-04-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752058627205, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752058627205, creator=13701087609, updateTime=1752058627205, updator=13701087609, issue=Issue{id=1149780466032669506, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='10', pageStart='3969', pageEnd='4395', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752058624990, creator=13701087609, updateTime=1768456644259, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218558743898411553, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149780466032669506, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218558743898411554, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149780466032669506, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=4239, endPage=4245, ext={EN=ArticleExt(id=1149780475989942731, articleId=1149780475323048383, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Surface Defect Segmentation Method for Thin Strip Cast Rolled Steel Plates Based on Improved TransUNet, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

A semantic segmentation-based method for defect segmentation on thin strip cast and rolled steel plates was proposed to accurately and quickly identify surface defects. Firstly, defect images from the production line were annotated using Labeling software to create a defect segmentation dataset. Secondly, a TransUNet network model was established to recognize and segment surface defects, integrating an optimized DANet dual-attention fusion network to enhance model segmentation performance. Finally, comparative experiments between the improved model and other segmentation models were designed. The feasibility and effectiveness of the proposed method are verified through analysis of experimental results and evaluation metrics. The experiments demonstrate that the improved network achieves a segmentation accuracy of 96.85%, an average intersection over union of 96.99%, and a similarity coefficient of 92.98% for foreign object defects on thin strip cast and rolled steel plates, respectively increasing by 1.19%, 0.61%, and 0.63% compared to the TransUNet network. Additionally, the improved network achieves a segmentation accuracy of 92.86% on the publicly available hot-rolled strip steel defect dataset, indicating its versatility and providing technical guidance for intelligent detection of surface defects on steel plates.

, correspAuthors=Kai ZENG, 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=Zhi-hua MA, Bo CHEN, Kai ZENG, Jun-lei QIAN, Peng-cheng XIAO, Li-guang ZHU), CN=ArticleExt(id=1149780501843632434, articleId=1149780475323048383, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于改进TransUNet的薄带铸轧钢板表面缺陷分割方法, 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=

为准确快速地识别出薄带铸轧钢板表面缺陷,提出了一种基于语义分割的薄带铸轧钢板表面缺陷分割方法。首先,通过Labeling软件对来源于薄带铸轧产线的钢板表面缺陷图像进行标注,创建缺陷分割数据集;其次,建立TransUNet网络模型对钢板表面缺陷进行识别和分割,引入优化的(dual attention network,DANet)双重注意力融合网络提升模型分割性能;最后,设计改进模型与其他分割模型的对比试验,根据试验结果和评价指标对改进模型进行分析,验证了本文方法的可行性和有效性。试验表明,改进网络针对薄带铸轧钢板表面异物缺陷的分割准确率为96.85%、平均交并比为96.99%、相似性系数达到92.98%,相较于TransUNet网络分别提升了1.19、0.61、0.63个百分点。此外,改进网络在公开的热轧带钢缺陷数据集上的分割准确率为92.86%,具有一定的通用性,可为钢板表面缺陷智能化检测提供技术指导。

, correspAuthors=曾凯, authorNote=null, correspAuthorsNote=
* 曾凯(1990—),男,汉族,河北唐山人,博士,讲师。研究方向:机器视觉检测。E-mail:。
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=lRM6Tih652uOZEV3rD9LLA==, magXml=z4LYQaLU5H41kcTvOwBvvQ==, pdfUrl=null, pdf=JxnqZVqbD7yQonQ7yqnbuQ==, pdfFileSize=10220194, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jX9w/lOrjHhyC5J0lKGnWQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=eYiE2M48DlWOo7L4nqFWPQ==, mapNumber=null, authorCompany=null, fund=null, authors=

马智华(1999—),男,汉族,河北唐山人,硕士研究生。研究方向:图像处理、视觉检测。E-mail:。

, authorsList=马智华, 陈波, 曾凯, 钱俊磊, 肖鹏程, 朱立光)}, authors=[Author(id=1218525110890320518, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hua2022111209@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1218525111016149651, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525110890320518, language=EN, stringName=Zhi-hua MA, firstName=Zhi-hua, middleName=null, lastName=MA, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525111116812953, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525110890320518, language=CN, stringName=马智华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北理工大学电气工程学院, 唐山 063210, bio={"content":"

马智华(1999—),男,汉族,河北唐山人,硕士研究生。研究方向:图像处理、视觉检测。E-mail:。

"}, bioImg=null, bioContent=

马智华(1999—),男,汉族,河北唐山人,硕士研究生。研究方向:图像处理、视觉检测。E-mail:。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525110085014081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=1, ext=[AuthorCompanyExt(id=1218525110097596995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110105985605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北理工大学电气工程学院, 唐山 063210)])]), Author(id=1218525111230059172, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, 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=1218525111389442739, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525111230059172, language=EN, stringName=Bo CHEN, firstName=Bo, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525111490106047, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525111230059172, language=CN, stringName=陈波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北理工大学电气工程学院, 唐山 063210, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525110085014081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=1, ext=[AuthorCompanyExt(id=1218525110097596995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110105985605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北理工大学电气工程学院, 唐山 063210)])]), Author(id=1218525111653683914, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=kevinzengkai@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1218525111775318743, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525111653683914, language=EN, stringName=Kai ZENG, firstName=Kai, middleName=null, lastName=ZENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, 4, *, address=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China
2 College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, China
3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China
4 Tangshan Iron and Steel Enterprise Process Control and Optimization Technology Innovation Center, Tangshan 063000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525111943090914, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525111653683914, language=CN, stringName=曾凯, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, 3, 4, *, address=1 华北理工大学电气工程学院, 唐山 063210
2 华北理工大学冶金与能源学院, 唐山 063210
3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000
4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525110085014081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=1, ext=[AuthorCompanyExt(id=1218525110097596995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110105985605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北理工大学电气工程学院, 唐山 063210)]), AuthorCompany(id=1218525110336672337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=2, ext=[AuthorCompanyExt(id=1218525110345060947, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110336672337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110361838167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110336672337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 华北理工大学冶金与能源学院, 唐山 063210)]), AuthorCompany(id=1218525110458307162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=3, ext=[AuthorCompanyExt(id=1218525110487667295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China), AuthorCompanyExt(id=1218525110500250207, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000)]), AuthorCompany(id=1218525110613496422, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=4, ext=[AuthorCompanyExt(id=1218525110630273641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110613496422, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Tangshan Iron and Steel Enterprise Process Control and Optimization Technology Innovation Center, Tangshan 063000, China), AuthorCompanyExt(id=1218525110638662251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110613496422, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000)])]), Author(id=1218525112031171304, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, 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=1218525112165389048, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525112031171304, language=EN, stringName=Jun-lei QIAN, firstName=Jun-lei, middleName=null, lastName=QIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 4, address=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China
4 Tangshan Iron and Steel Enterprise Process Control and Optimization Technology Innovation Center, Tangshan 063000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525112257663746, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525112031171304, language=CN, stringName=钱俊磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 4, address=1 华北理工大学电气工程学院, 唐山 063210
4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525110085014081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=1, ext=[AuthorCompanyExt(id=1218525110097596995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110105985605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北理工大学电气工程学院, 唐山 063210)]), AuthorCompany(id=1218525110613496422, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=4, ext=[AuthorCompanyExt(id=1218525110630273641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110613496422, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Tangshan Iron and Steel Enterprise Process Control and Optimization Technology Innovation Center, Tangshan 063000, China), AuthorCompanyExt(id=1218525110638662251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110613496422, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000)])]), Author(id=1218525112408658700, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, 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=1218525112517710613, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525112408658700, language=EN, stringName=Peng-cheng XIAO, firstName=Peng-cheng, middleName=null, lastName=XIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, China
3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525112668705572, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525112408658700, language=CN, stringName=肖鹏程, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 华北理工大学冶金与能源学院, 唐山 063210
3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525110336672337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=2, ext=[AuthorCompanyExt(id=1218525110345060947, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110336672337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110361838167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110336672337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 华北理工大学冶金与能源学院, 唐山 063210)]), AuthorCompany(id=1218525110458307162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=3, ext=[AuthorCompanyExt(id=1218525110487667295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China), AuthorCompanyExt(id=1218525110500250207, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000)])]), Author(id=1218525112760980271, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, 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=1218525112911975228, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525112760980271, language=EN, stringName=Li-guang ZHU, firstName=Li-guang, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 5, address=3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China
5 College of Materials Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1218525113054581577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, authorId=1218525112760980271, language=CN, stringName=朱立光, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 5, address=3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000
5 河北科技大学材料科学与工程学院, 石家庄 050018, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1218525110458307162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=3, ext=[AuthorCompanyExt(id=1218525110487667295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China), AuthorCompanyExt(id=1218525110500250207, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000)]), AuthorCompany(id=1218525110743519858, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=5, ext=[AuthorCompanyExt(id=1218525110772879993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110743519858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 College of Materials Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China), AuthorCompanyExt(id=1218525110781268604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110743519858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 河北科技大学材料科学与工程学院, 石家庄 050018)])])], keywords=[Keyword(id=1218525113285268322, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, orderNo=1, keyword=thin strip casting and rolling), Keyword(id=1218525113390125935, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, orderNo=2, keyword=semantic segmentation), Keyword(id=1218525113499177846, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, orderNo=3, keyword=defect identification), Keyword(id=1218525113625006977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, orderNo=4, keyword=dual attention), Keyword(id=1218525113784390538, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, orderNo=1, keyword=薄带铸轧), Keyword(id=1218525113943774099, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, orderNo=2, keyword=语义分割), Keyword(id=1218525114077991839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, orderNo=3, keyword=缺陷识别), Keyword(id=1218525114203820969, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, orderNo=4, keyword=双重注意力)], refs=[Reference(id=1218525117336965230, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=6, pageStart=21, pageEnd=26, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=周东生, 冯庆晓, 李化龙, journalName=连铸, refType=null, unstructuredReference=周东生, 冯庆晓, 李化龙. 薄带铸轧产品特性及应用进展[J]. 连铸, 2020(6): 21-26, 33., articleTitle=薄带铸轧产品特性及应用进展, refAbstract=null), Reference(id=1218525117420851316, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=6, pageStart=21, pageEnd=26, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Zhou Dongsheng, Feng Qingxiao, Li Hualong, journalName=Continuous Casting, refType=null, unstructuredReference=Zhou Dongsheng, Feng Qingxiao, Li Hualong. Characteristics and application progress of thin strip casting and rolling products[J]. Continuous Casting, 2020(6): 21-26, 33., articleTitle=Characteristics and application progress of thin strip casting and rolling products, refAbstract=null), Reference(id=1218525117521514619, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2018, volume=30, issue=1, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王国栋, journalName=钢铁研究学报, refType=null, unstructuredReference=王国栋. 钢铁全流程和一体化工艺技术创新方向的探讨[J]. 钢铁研究学报, 2018, 30(1): 1-7., articleTitle=钢铁全流程和一体化工艺技术创新方向的探讨, refAbstract=null), Reference(id=1218525117617983616, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2018, volume=30, issue=1, pageStart=1, pageEnd=7, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Wang Guodong, journalName=Journal of Iron and Steel Research, refType=null, unstructuredReference=Wang Guodong. Exploration of innovation direction in steel full process and integrated process technology[J]. Journal of Iron and Steel Research, 2018, 30(1): 1-7., articleTitle=Exploration of innovation direction in steel full process and integrated process technology, refAbstract=null), Reference(id=1218525117722841220, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=11, pageStart=1809, pageEnd=1822, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Ding ZY, Zhao X, Misra R D K, journalName=Metals, refType=null, unstructuredReference=Ding ZY, Zhao X, Misra R D K, et al. Deep learning-based understanding of defects in continuous casting product[J]. Metals, 2023, 13(11): 1809-1822., articleTitle=Deep learning-based understanding of defects in continuous casting product, refAbstract=null), Reference(id=1218525117819310214, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=4, pageStart=534, pageEnd=545, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=汪水泽, 高军恒, 吴桂林, journalName=工程科学学报, refType=null, unstructuredReference=汪水泽, 高军恒, 吴桂林, 等. 薄板坯连铸连轧技术发展现状及展望[J]. 工程科学学报, 2022, 44(4): 534-545., articleTitle=薄板坯连铸连轧技术发展现状及展望, refAbstract=null), Reference(id=1218525117924167821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=4, pageStart=534, pageEnd=545, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Wang Shuize, Gao Junheng, Wu Guilin, journalName=Journal of Engineering Science, refType=null, unstructuredReference=Wang Shuize, Gao Junheng, Wu Guilin, et al. Development status and prospects of thin slab continuous casting and rolling technology[J]. Journal of Engineering Science, 2022, 44 (4): 534-545., articleTitle=Development status and prospects of thin slab continuous casting and rolling technology, refAbstract=null), Reference(id=1218525118029025427, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=11, pageStart=3342, pageEnd=3362, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=严毅, 邓超, 李琳, journalName=中国图象图形学报, refType=null, unstructuredReference=严毅, 邓超, 李琳, 等. 深度学习背景下的图像语义分割方法综述[J]. 中国图象图形学报, 2023, 28(11): 3342-3362., articleTitle=深度学习背景下的图像语义分割方法综述, refAbstract=null), Reference(id=1218525118146465945, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=11, pageStart=3342, pageEnd=3362, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Yan Yi, Deng Chao, Li Lin, journalName=Chinese Journal of Image and Graphics, refType=null, unstructuredReference=Yan Yi, Deng Chao, Li Lin, et al. A review of image semantic segmentation methods in the context of deep learning[J]. Chinese Journal of Image and Graphics, 2023, 28(11): 3342-3362., articleTitle=A review of image semantic segmentation methods in the context of deep learning, refAbstract=null), Reference(id=1218525118234546334, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2020, volume=66, issue=6, pageStart=519, pageEnd=531, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=黄鹏, 郑淇, 梁超, journalName=武汉大学学报(理学版), refType=null, unstructuredReference=黄鹏, 郑淇, 梁超. 图像分割方法综述[J]. 武汉大学学报(理学版), 2020, 66(6): 519-531., articleTitle=图像分割方法综述, refAbstract=null), Reference(id=1218525118431678626, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2020, volume=66, issue=6, pageStart=519, pageEnd=531, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Huang Peng, Zheng Qi, Liang Chao, journalName=Journal of Wuhan University (Science Edition), refType=null, unstructuredReference=Huang Peng, Zheng Qi, Liang Chao. Overview of image segmentation methods[J]. Journal of Wuhan University (Science Edition), 2020, 66(6): 519-531., articleTitle=Overview of image segmentation methods, refAbstract=null), Reference(id=1218525118528147624, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=6, pageStart=946, pageEnd=952, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=王道累, 刘易腾, 杜文斌, journalName=计算机辅助设计与图形学学报, refType=null, unstructuredReference=王道累, 刘易腾, 杜文斌, 等. 基于级联孪生密集网络的金属表面缺陷检测方法[J]. 计算机辅助设计与图形学学报, 2022, 34(6): 946-952., articleTitle=基于级联孪生密集网络的金属表面缺陷检测方法, refAbstract=null), Reference(id=1218525118637199532, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=6, pageStart=946, pageEnd=952, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Wang Daolei, Liu Yiteng, Du Wenbin, journalName=Journal of Computer Aided Design and Graphics, refType=null, unstructuredReference=Wang Daolei, Liu Yiteng, Du Wenbin, et al. Metal surface defect detection method based on cascaded twin dense network[J]. Journal of Computer Aided Design and Graphics, 2022, 34 (6): 946-952., articleTitle=Metal surface defect detection method based on cascaded twin dense network, refAbstract=null), Reference(id=1218525118754640048, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=3, pageStart=413, pageEnd=424, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=王昱翔, 葛洪伟, journalName=南京大学学报(自然科学版), refType=null, unstructuredReference=王昱翔, 葛洪伟. 基于U2-Net的金属表面缺陷检测算法[J]. 南京大学学报(自然科学版), 2023, 59(3): 413-424., articleTitle=基于U2-Net的金属表面缺陷检测算法, refAbstract=null), Reference(id=1218525118846914738, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=3, pageStart=413, pageEnd=424, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Wang Yuxiang, Ge Hongwei, journalName=Journal of Nanjing University (Natural Science Edition), refType=null, unstructuredReference=Wang Yuxiang, Ge Hongwei. Metal surface defect detection algorithm based on U2 Net[J]. Journal of Nanjing University (Natural Science Edition), 2023, 59(3): 413-424., articleTitle=Metal surface defect detection algorithm based on U2 Net, refAbstract=null), Reference(id=1218525118930800823, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=234, pageEnd=241, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Ronneberger O, Fischer P, Brox T, journalName=Medical Image Computing and Computer-assisted Intervention, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[C]// Medical Image Computing and Computer-assisted Intervention. Munich: Springer, 2015: 234-241., articleTitle=U-net: convolutional networks for biomedical image segmentation, refAbstract=null), Reference(id=1218525119039852732, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=Chen J N, Lu Y Y, Yu Q H, journalName=arXiv reprient arXiv: 2102.04306, refType=null, unstructuredReference=Chen J N, Lu Y Y, Yu Q H, et al. TransUNet transformers make strong encoders for medical image segmentation[J]. arXiv reprient arXiv: 2102.04306, 2021., articleTitle=TransUNet transformers make strong encoders for medical image segmentation, refAbstract=null), Reference(id=1218525119132127424, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=Dosovitskiy A, Beyer L, Kolesnikov A, journalName=arXiv reprient arXiv: 2010.11929, refType=null, unstructuredReference=Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words: transformers for image recognition at scale[J]. arXiv reprient arXiv: 2010.11929, 2020., articleTitle=An image is worth 16×16 words: transformers for image recognition at scale, refAbstract=null), Reference(id=1218525119253762247, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=5, pageStart=1513, pageEnd=1520, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=李原, 李燕君, 刘进超, journalName=电子与信息学报, refType=null, unstructuredReference=李原, 李燕君, 刘进超, 等. 基于改进Res-UNet网络的钢铁表面缺陷图像分割研究[J]. 电子与信息学报, 2022, 44(5): 1513-1520., articleTitle=基于改进Res-UNet网络的钢铁表面缺陷图像分割研究, refAbstract=null), Reference(id=1218525119354425548, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=5, pageStart=1513, pageEnd=1520, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=Li Yuan, Li Yanjun, Liu Jinchao, journalName=Journal of Electronics and Information Technology, refType=null, unstructuredReference=Li Yuan, Li Yanjun, Liu Jinchao, et al. Research on steel surface defect image segmentation based on improved Res-UNet network[J]. Journal of Electronics and Information Technology, 2022, 44(5): 1513-1520., articleTitle=Research on steel surface defect image segmentation based on improved Res-UNet network, refAbstract=null), Reference(id=1218525119459283155, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=3, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=戴张杰, 黄成永, 刘威, journalName=钢铁, refType=null, unstructuredReference=戴张杰, 黄成永, 刘威, 等. 基于Mask-RCNN的转炉炉口形貌检测[J]. 钢铁, 2023, 58(3): 73-78., articleTitle=基于Mask-RCNN的转炉炉口形貌检测, refAbstract=null), Reference(id=1218525119555752153, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=58, issue=3, pageStart=73, pageEnd=78, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=Dai Zhangjie, Huang Chengyong, Liu Wei, journalName=Iron and Steel, refType=null, unstructuredReference=Dai Zhangjie, Huang Chengyong, Liu Wei, et al. Detection of converter mouth morphology based on Mask-RCNN[J]. Iron and Steel, 2023, 58 (3): 73-78., articleTitle=Detection of converter mouth morphology based on Mask-RCNN, refAbstract=null), Reference(id=1218525119639638236, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=11, pageStart=1347, pageEnd=1357, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=李福民, 侯炬才, 刘颂, journalName=钢铁研究学报, refType=null, unstructuredReference=李福民, 侯炬才, 刘颂, 等. 基于计算机视觉和Re-Unet网络的烧结混合料粒度识别模型[J]. 钢铁研究学报, 2023, 35(11): 1347-1357., articleTitle=基于计算机视觉和Re-Unet网络的烧结混合料粒度识别模型, refAbstract=null), Reference(id=1218525119757078753, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=35, issue=11, pageStart=1347, pageEnd=1357, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=Li Fumin, Hou Jucai, Liu Song, journalName=Journal of Iron and Steel Research, refType=null, unstructuredReference=Li Fumin, Hou Jucai, Liu Song, et al. Particle size recognition model for sintered mixtures based on computer vision and Re-Unet network[J]. Journal of Iron and Steel Research, 2023, 35 (11): 1347-1357., articleTitle=Particle size recognition model for sintered mixtures based on computer vision and Re-Unet network, refAbstract=null), Reference(id=1218525119845159143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2024, volume=48, issue=2, pageStart=50, pageEnd=59, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=蒋博涵, 陈先中, 侯庆文, journalName=冶金自动化, refType=null, unstructuredReference=蒋博涵, 陈先中, 侯庆文, 等. 基于BS-TransUNet网络的高炉雷达料线分割方法[J]. 冶金自动化, 2024, 48(2): 50-59., articleTitle=基于BS-TransUNet网络的高炉雷达料线分割方法, refAbstract=null), Reference(id=1218525119924850925, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2024, volume=48, issue=2, pageStart=50, pageEnd=59, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=Jiang Bohan, Chen Xianzhong, Hou Qingwen, journalName=Metallurgical Automation, refType=null, unstructuredReference=Jiang Bohan, Chen Xianzhong, Hou Qingwen, et al. A radar material line segmentation method for blast furnaces based on BS-TransUNet network[J]. Metallurgical Automation, 2024, 48 (2): 50-59., articleTitle=A radar material line segmentation method for blast furnaces based on BS-TransUNet network, refAbstract=null), Reference(id=1218525120012931310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=3146, pageEnd=3154, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=Fu J, Liu J, Tian H J, journalName=Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, refType=null, unstructuredReference=Fu J, Liu J, Tian H J, et al. Dual attention network for scene segmentation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 3146-3154., articleTitle=Dual attention network for scene segmentation, refAbstract=null), Reference(id=1218525120084234484, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=33, pageStart=21, pageEnd=27, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=李新叶, 宋维, journalName=科学技术与工程, refType=null, unstructuredReference=李新叶, 宋维. 基于深度学习的图像语义分割研究进展[J]. 科学技术与工程, 2019, 19(33): 21-27., articleTitle=基于深度学习的图像语义分割研究进展, refAbstract=null), Reference(id=1218525120172314874, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=33, pageStart=21, pageEnd=27, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=Li Xinye, Song Wei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Xinye, Song Wei. Research progress in image semantic segmentation based on deep learning[J]. Science Technology and Engineering, 2019, 19(33): 21-27., articleTitle=Research progress in image semantic segmentation based on deep learning, refAbstract=null), Reference(id=1218525120289755390, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=30, pageStart=12796, pageEnd=12805, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=宋泽冈, 刘艳莉, 张长兴, journalName=科学技术与工程, refType=null, unstructuredReference=宋泽冈, 刘艳莉, 张长兴. 基于机器视觉的桥梁裂缝检测应用及发展综述[J]. 科学技术与工程, 2023, 23(30): 12796-12805., articleTitle=基于机器视觉的桥梁裂缝检测应用及发展综述, refAbstract=null), Reference(id=1218525120373641477, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=30, pageStart=12796, pageEnd=12805, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=Song Zegang, Liu Yanli, Zhang Changxing, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Song Zegang, Liu Yanli, Zhang Changxing. Application and development review of bridge crack detection based on machine vision[J]. Science Technology and Engineering, 2023, 23 (30): 12796-12805., articleTitle=Application and development review of bridge crack detection based on machine vision, refAbstract=null), Reference(id=1218525120491081993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2024, volume=133, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=Chen J, Wang C C, Shi F, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=Chen J, Wang C C, Shi F, et al. DSNet: a dynamic squeeze network for real-time weld seam image segmentation[J]. Engineering Applications of Artificial Intelligence, 2024, 133.DOI: 10.1016/j.engappai.2024.108278., articleTitle=DSNet: a dynamic squeeze network for real-time weld seam image segmentation, refAbstract=null), Reference(id=1218525120600133901, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2024, volume=224, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=Fu H, Song Q H, Gong J X, journalName=Measurement, refType=null, unstructuredReference=Fu H, Song Q H, Gong J X, et al. Automatic detection and pixel-level quantification of surface microcracks in ceramics grinding: an exploration with Mask R-CNN and TransUNet[J]. Measurement, 2024, 224.DOI: 10.1016/j.measurement.2023.113895., articleTitle=Automatic detection and pixel-level quantification of surface microcracks in ceramics grinding: an exploration with Mask R-CNN and TransUNet, refAbstract=null), Reference(id=1218525120809849107, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, doi=null, pmid=null, pmcid=null, year=2023, volume=72, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[21], rfOrder=33, authorNames=Hu F, Song K C, Zhang Y M, journalName=IEEE Transactions on Instrumentation & Measurement, refType=null, unstructuredReference=Hu F, Song K C, Zhang Y M, et al. Cross position aggregation network for few-shot strip steel surface defect segmentation[J]. IEEE Transactions on Instrumentation & Measurement, 2023, 72: 1-10., articleTitle=Cross position aggregation network for few-shot strip steel surface defect segmentation, refAbstract=null)], funds=[Fund(id=1218525116779122762, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, awardId=51904107, language=CN, fundingSource=国家自然科学基金(51904107), fundOrder=null, country=null), Fund(id=1218525116896563285, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, awardId=236Z1017G, language=CN, fundingSource=中央引导地方科技发展资金项目(236Z1017G), fundOrder=null, country=null), Fund(id=1218525117022392414, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, awardId=22130220G, language=CN, fundingSource=唐山市市级科技计划(22130220G), fundOrder=null, country=null), Fund(id=1218525117127250019, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, awardId=22130204G, language=CN, fundingSource=唐山市市级科技计划(22130204G), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1218525110085014081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=1, ext=[AuthorCompanyExt(id=1218525110097596995, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110105985605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110085014081, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北理工大学电气工程学院, 唐山 063210)]), AuthorCompany(id=1218525110336672337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=2, ext=[AuthorCompanyExt(id=1218525110345060947, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110336672337, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, China), AuthorCompanyExt(id=1218525110361838167, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110336672337, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 华北理工大学冶金与能源学院, 唐山 063210)]), AuthorCompany(id=1218525110458307162, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=3, ext=[AuthorCompanyExt(id=1218525110487667295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China), AuthorCompanyExt(id=1218525110500250207, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110458307162, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000)]), AuthorCompany(id=1218525110613496422, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=4, ext=[AuthorCompanyExt(id=1218525110630273641, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110613496422, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 Tangshan Iron and Steel Enterprise Process Control and Optimization Technology Innovation Center, Tangshan 063000, China), AuthorCompanyExt(id=1218525110638662251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110613496422, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000)]), AuthorCompany(id=1218525110743519858, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, xref=5, ext=[AuthorCompanyExt(id=1218525110772879993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110743519858, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 College of Materials Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China), AuthorCompanyExt(id=1218525110781268604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, companyId=1218525110743519858, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5 河北科技大学材料科学与工程学院, 石家庄 050018)])], figs=[ArticleFig(id=1218525114606474178, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Fig.1, caption=Surface defect segmentation process for thin strip cast and rolled steel plates, figureFileSmall=DvPrU727X1z9Yx8n8zvbFA==, figureFileBig=6XeRgFGHFoV7FrdQ3eXzgg==, tableContent=null), ArticleFig(id=1218525114719720394, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=图1, caption=薄带铸轧钢板表面缺陷分割流程, figureFileSmall=DvPrU727X1z9Yx8n8zvbFA==, figureFileBig=6XeRgFGHFoV7FrdQ3eXzgg==, tableContent=null), ArticleFig(id=1218525114887492570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Fig.2, caption=Image annotation and data expansion, figureFileSmall=hHdM7bwE01xvDvUkGk/ADQ==, figureFileBig=FWQCcd7Ksa8fVKu3lwebIw==, tableContent=null), ArticleFig(id=1218525114996544481, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=图2, caption=图像标注与数据扩充, figureFileSmall=hHdM7bwE01xvDvUkGk/ADQ==, figureFileBig=FWQCcd7Ksa8fVKu3lwebIw==, tableContent=null), ArticleFig(id=1218525115088819174, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Fig.3, caption=Improved TransUNet image segmentation model, figureFileSmall=hmzKcIQxeuCDfOX0mF0tfQ==, figureFileBig=Ou5AJp5aRP/y38r2aNPF8A==, tableContent=null), ArticleFig(id=1218525115206259694, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=图3, caption=改进的TransUNet模型

Layer Norm层归一化;MSA 多头自注意力机制;MLP 多层感知机;Transformer Layer 编码层; H为特征图的高;W为特征图的宽;D为图像块数量;n_patch为图像块

, figureFileSmall=hmzKcIQxeuCDfOX0mF0tfQ==, figureFileBig=Ou5AJp5aRP/y38r2aNPF8A==, tableContent=null), ArticleFig(id=1218525115319505913, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Fig.4, caption=Dual attention fusion network, figureFileSmall=Jpt8Icp3rLQroBUVeF5REA==, figureFileBig=dvG7E00WEYNh7iCZJhAjWg==, tableContent=null), ArticleFig(id=1218525115432752130, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=图4, caption=双重注意融合网络

Conv为卷积;reshape为重塑;transpose为转置;softmax为归一化指数函数;C×C为矩阵大小;Pin和Pout为输入和输出;C、H和W分别为局部特征图A的通道数、高度和宽度;特征图A重塑后得到3个新的特征图B、C和D;像素数N=H×W;S为空间注意图;X为通道关注图;U表示矩阵乘法;⊕表示逐元素求和;E为特征图

, figureFileSmall=Jpt8Icp3rLQroBUVeF5REA==, figureFileBig=dvG7E00WEYNh7iCZJhAjWg==, tableContent=null), ArticleFig(id=1218525115545997317, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Fig.5, caption=Comparison of segmentation results, figureFileSmall=vL6rqZXxIQcA3RcA8F9o3Q==, figureFileBig=x6br5A+A8xNIyDnqMZOE8A==, tableContent=null), ArticleFig(id=1218525115638272011, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=图5, caption=分割结果对比, figureFileSmall=vL6rqZXxIQcA3RcA8F9o3Q==, figureFileBig=x6br5A+A8xNIyDnqMZOE8A==, tableContent=null), ArticleFig(id=1218525115722158098, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Fig.6, caption=Comparison curve of segmentation model loss, figureFileSmall=0jO0FN/k+iH2eb9Ry3w/TQ==, figureFileBig=M4MHSLIUBHrPLAAtx8I5pg==, tableContent=null), ArticleFig(id=1218525115818627099, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=图6, caption=分割模型损失对比曲线, figureFileSmall=0jO0FN/k+iH2eb9Ry3w/TQ==, figureFileBig=M4MHSLIUBHrPLAAtx8I5pg==, tableContent=null), ArticleFig(id=1218525115944456226, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Table 1, caption=

Experimental results of encoding layer verification

, figureFileSmall=null, figureFileBig=null, tableContent=
编码层数 4 8 12 16 20
F1/% 95.72 97.05 96.86 96.49 96.58
mIoU/% 95.68 96.99 96.80 96.44 96.53
), ArticleFig(id=1218525116087062568, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=表1, caption=

编码层数验证试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
编码层数 4 8 12 16 20
F1/% 95.72 97.05 96.86 96.49 96.58
mIoU/% 95.68 96.99 96.80 96.44 96.53
), ArticleFig(id=1218525116229668908, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Table 2, caption=

The segmentation results of different models on the TSCRD dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
分割模型 TSCRD数据集
PA/% F1/% mIoU/%
UNet 96.82 96.21 96.17
U2Net 95.21 96.23 96.19
SwinUNet 95.08 95.21 95.20
TransUNet 95.66 96.43 96.38
TransUNet(本文模型) 96.85 97.05 96.99
), ArticleFig(id=1218525116342915124, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=表2, caption=

不同模型对TSCRD数据集分割结果

, figureFileSmall=null, figureFileBig=null, tableContent=
分割模型 TSCRD数据集
PA/% F1/% mIoU/%
UNet 96.82 96.21 96.17
U2Net 95.21 96.23 96.19
SwinUNet 95.08 95.21 95.20
TransUNet 95.66 96.43 96.38
TransUNet(本文模型) 96.85 97.05 96.99
), ArticleFig(id=1218525116464549946, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=EN, label=Table 3, caption=

The segmentation results of different models on the FSSD-12 dataset

, figureFileSmall=null, figureFileBig=null, tableContent=
分割模型 FSSD-12数据集
PA/% F1/% mIoU/%
UNet 92.43 88.65 88.20
U2Net 90.10 90.86 90.26
SwinUNet 91.95 86.21 85.87
TransUNet 91.83 89.38 88.75
TransUNet(本文模型) 92.86 89.76 89.13
), ArticleFig(id=1218525116573601857, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149780475323048383, language=CN, label=表3, caption=

不同模型对FSSD-12数据集分割结果

, figureFileSmall=null, figureFileBig=null, tableContent=
分割模型 FSSD-12数据集
PA/% F1/% mIoU/%
UNet 92.43 88.65 88.20
U2Net 90.10 90.86 90.26
SwinUNet 91.95 86.21 85.87
TransUNet 91.83 89.38 88.75
TransUNet(本文模型) 92.86 89.76 89.13
)], 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.1671-1815.2403371, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2403371, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2403371, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2403371, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进TransUNet的薄带铸轧钢板表面缺陷分割方法
收藏切换
PDF下载
马智华 1 , 陈波 1 , 曾凯 1, 2, 3, 4, * , 钱俊磊 1, 4 , 肖鹏程 2, 3 , 朱立光 3, 5
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(10): 4239-4245
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(10): 4239-4245
基于改进TransUNet的薄带铸轧钢板表面缺陷分割方法
全屏
马智华1 , 陈波1, 曾凯1, 2, 3, 4, * , 钱俊磊1, 4, 肖鹏程2, 3, 朱立光3, 5
作者信息
  • 1 华北理工大学电气工程学院, 唐山 063210
  • 2 华北理工大学冶金与能源学院, 唐山 063210
  • 3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000
  • 4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000
  • 5 河北科技大学材料科学与工程学院, 石家庄 050018

    • 马智华(1999—),男,汉族,河北唐山人,硕士研究生。研究方向:图像处理、视觉检测。E-mail:。

通讯作者:

* 曾凯(1990—),男,汉族,河北唐山人,博士,讲师。研究方向:机器视觉检测。E-mail:。
Surface Defect Segmentation Method for Thin Strip Cast Rolled Steel Plates Based on Improved TransUNet
Zhi-hua MA1 , Bo CHEN1, Kai ZENG1, 2, 3, 4, * , Jun-lei QIAN1, 4, Peng-cheng XIAO2, 3, Li-guang ZHU3, 5
Affiliations
  • 1 College of Electrical Engineering, North China University of Science and Technology, Tangshan 063210, China
  • 2 College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, China
  • 3 Hebei Collaborative Innovation Center of High Quality Steel Continuous Casting Engineering Technology, Tangshan 063000, China
  • 4 Tangshan Iron and Steel Enterprise Process Control and Optimization Technology Innovation Center, Tangshan 063000, China
  • 5 College of Materials Science and Engineering, Hebei University of Science and Technology, Shijiazhuang 050018, China
出版时间: 2025-04-08 doi: 10.12404/j.issn.1671-1815.2403371
文章导航
收藏切换
摘要
收起

为准确快速地识别出薄带铸轧钢板表面缺陷,提出了一种基于语义分割的薄带铸轧钢板表面缺陷分割方法。首先,通过Labeling软件对来源于薄带铸轧产线的钢板表面缺陷图像进行标注,创建缺陷分割数据集;其次,建立TransUNet网络模型对钢板表面缺陷进行识别和分割,引入优化的(dual attention network,DANet)双重注意力融合网络提升模型分割性能;最后,设计改进模型与其他分割模型的对比试验,根据试验结果和评价指标对改进模型进行分析,验证了本文方法的可行性和有效性。试验表明,改进网络针对薄带铸轧钢板表面异物缺陷的分割准确率为96.85%、平均交并比为96.99%、相似性系数达到92.98%,相较于TransUNet网络分别提升了1.19、0.61、0.63个百分点。此外,改进网络在公开的热轧带钢缺陷数据集上的分割准确率为92.86%,具有一定的通用性,可为钢板表面缺陷智能化检测提供技术指导。

薄带铸轧  /  语义分割  /  缺陷识别  /  双重注意力

A semantic segmentation-based method for defect segmentation on thin strip cast and rolled steel plates was proposed to accurately and quickly identify surface defects. Firstly, defect images from the production line were annotated using Labeling software to create a defect segmentation dataset. Secondly, a TransUNet network model was established to recognize and segment surface defects, integrating an optimized DANet dual-attention fusion network to enhance model segmentation performance. Finally, comparative experiments between the improved model and other segmentation models were designed. The feasibility and effectiveness of the proposed method are verified through analysis of experimental results and evaluation metrics. The experiments demonstrate that the improved network achieves a segmentation accuracy of 96.85%, an average intersection over union of 96.99%, and a similarity coefficient of 92.98% for foreign object defects on thin strip cast and rolled steel plates, respectively increasing by 1.19%, 0.61%, and 0.63% compared to the TransUNet network. Additionally, the improved network achieves a segmentation accuracy of 92.86% on the publicly available hot-rolled strip steel defect dataset, indicating its versatility and providing technical guidance for intelligent detection of surface defects on steel plates.

thin strip casting and rolling  /  semantic segmentation  /  defect identification  /  dual attention
马智华, 陈波, 曾凯, 钱俊磊, 肖鹏程, 朱立光. 基于改进TransUNet的薄带铸轧钢板表面缺陷分割方法. 科学技术与工程, 2025 , 25 (10) : 4239 -4245 . DOI: 10.12404/j.issn.1671-1815.2403371
Zhi-hua MA, Bo CHEN, Kai ZENG, Jun-lei QIAN, Peng-cheng XIAO, Li-guang ZHU. Surface Defect Segmentation Method for Thin Strip Cast Rolled Steel Plates Based on Improved TransUNet[J]. Science Technology and Engineering, 2025 , 25 (10) : 4239 -4245 . DOI: 10.12404/j.issn.1671-1815.2403371
正文
收起
在钢铁领域加快发展新质生产力的背景下,以短流程为特点的薄板坯连铸连轧、薄带铸轧等技术,成为促进钢铁生产流程智能化、绿色化、高端化的前沿模式。薄带铸轧作为一种新型的薄规格带钢生产工艺,相较于传统的热连轧与冷轧技术,具备生产薄规格、高强度产品的天然优势,解决了批量生产热轧薄规格产品的技术难题,现已逐渐成为当今钢铁工业最具发展潜力的一项冶金前沿新技术[1-2]。然而,薄带铸轧的铸速高达30~150 m/min,在高速生产过程中表面易出现夹渣、油斑、水垢等异物缺陷,破坏了产品的外观与性能。通过对钢板表面缺陷的分割,可在有效识别缺陷的同时,快速将缺陷从复杂的背景中分离,并可进一步分析缺陷的形貌细节特征和严重程度,有助于及时发现生产过程中存在的工艺问题,从而优化工艺参数和生产流程,提高生产效率、保证产品质量的稳定性。
随着计算机视觉技术的不断发展,利用图像分割技术对钢板表面缺陷进行自动化检测已经成为新的研究热点。然而,传统的图像分割方法通常依赖人工设计的特征和规则,往往受限于特征提取和表达能力,泛化能力相对较差,难以满足复杂场景下分割准确性和鲁棒性要求[3-6]。
近年来,深度学习技术被广泛应用于自然图像、医学图像等相关检测研究,图像分割更是为工业领域缺陷检测提供了全新的思路和方法[7-8]。Ronneberger等[9]提出了基于卷积神经网络的融合浅层和深层图像特征的图像分割网络U-Net,在自然图像分割领域大获成功,但其在面对复杂图像时仍存在分割效果不理想的问题。Chen等[10]针对U-Net网络在图像理解和处理方面的局限性,提出融合U-Net和Transformer[11]的TransUNet模型,有效提高了网络模型的分割定位能力,被广泛应用于各领域的图像分割任务中。尽管机器视觉和深度学习技术在冶金领域已被广泛应用,但将这两种技术结合用于薄带铸轧钢板表面缺陷检测的研究却很少。针对钢铁表面缺陷难以分割的问题,李原等[12]提出了融合残差结构的Res-UNet算法,提升基线算法分割精度的同时证明了深度学习在钢铁表面缺陷检测和实际应用场景中的有效性。戴张杰等[13]提出了基于Mask-RCNN的转炉炉口形貌检测方法,为炼钢工序自动化提供了新形式。李福民等[14]构建了基于机器视觉和Re-UNet网络的烧结混合料粒度识别模型,有效解决了当前烧结混合料粒度检测滞后的问题。蒋博涵等[15]提出一种基于高炉雷达冶炼图像和TransUNet网络模型的端到端料线提取语义分割方法,有效改善了料线提取精度和稳定性。以上研究成果不仅显示了深度学习在图像分割领域的进步与发展,也为薄带铸轧钢板表面缺陷检测带来了创新性的解决思路和策略。
由于钢板表面缺陷的复杂性和尺度变化等问题,使得缺陷区域的细节信息难以捕捉,传统语义分割模型在缺陷分割方面的应用仍然十分受限。针对此类问题,现引入DANet[16]网络中的空间注意力模块(position attention module,PAM)和通道注意力模块(channel attention module,CAM)改进TransUNet网络模型,以期增强模型对于缺陷区域的表征能力和关注度、提升模型分割精度,设计相关试验对改进TransUNet模型在实际应用中的有效性和可靠性进行验证。
1 缺陷分割方法与流程
收起
图1为基于改进TransUNet的薄带铸轧钢板表面缺陷分割方法流程。通过部署在某钢厂新型薄带铸轧产线上的成像系统对钢板进行数字成像,再对采集到原始图像进行数据增强和标注处理后构建薄带铸轧钢板表面缺陷分割数据集,最后将该数据集导入到改进TransUNet模型中进行训练和测试获得最终试验结果。
1.1 图像采集与数据集构建
深度学习图像分割模型的训练效果依赖数据集的规模与质量[17-18],目前针对薄带铸轧钢板表面缺陷分割识别的研究较少,缺乏可公开获取的铸轧钢板表面缺陷数据集。因此,为了提高模型的分割性能,获取充足的高质量图像数据显得尤为关键。本研究所用图像数据通过Basler高清工业相机在运行的薄带铸轧产线拍摄获得,采集到原始图像共计773张,包含水垢、油污等多种不规则形状异物缺陷。原始图像尺寸较大,受模型和设备显存限制不能直接作为网络的输入,通过对原始图像以窗口裁剪的方式进行加工,筛选得到470张含有表面异物缺陷的有效图像数据,按照8∶2的比例进行训练集和验证集的划分。
为防止因数据量不足导致模型过拟合,本文研究采用多种数据增强处理方法,包括亮度调整、对比度调节、以及添加高斯噪声和模糊效果等方式对训练集数据进行扩充,最终建立包含1 974张图像和对应标签的薄带铸轧钢板表面缺陷分割数据集TSCRD(thin strip casting and rolling dataset)。图2展示了薄带铸轧表面异物缺陷的图像和相应标签,以及采用不同数据增强技术得到的图像样本。
1.2 缺陷分割模型优化与改进
1.2.1 改进模型介绍
TransUNet结合了Transformer和U-Net网络的优点,通过使用混合CNN-Transformer架构作为编码器以及级联上采样来实现对目标的准确识别和分割[19-20]。相比于传统U-Net网络模型,TransUNet具有更高的空间感知能力和更好的上下文信息理解能力。TransUNet采用U型结构减少了CNN提取细致像素信息过程中的损失,通过继承Transformer的自注意力机制完成了对空间细节信息的补充。图3为本文提出的用于薄带铸轧钢板表面缺陷分割任务的改进TransUNet模型,将Dual Attention双重注意模块集成到跳跃连接中可有效地过滤传统跳跃连接传输的冗余特征,从位置和通道两方面自适应的学习图像特征,更有效地捕获全局依赖关系和长程上下文信息,帮助解码器更准确地完成图像重建工作,有效地提升模型整体性能和泛化能力。
1.2.2 双重注意融合网络
DANet双重注意融合网络被广泛应用于各种语义分割任务中,其通过并联空间注意力PAM和通道注意力CAM提高了对特征的像素级识别能力。为提升TransUNet语义分割网络的编解码效率,参考DANet原始网络,提出基于双重注意力的Dual Attention模块,整体结构如图4所示。通过最大限度地利用位置和通道特征,滤除特征提取获得的不相关信息,缩小了语义差距,进一步提升了模型的特征表示与分割性能。
该模块对应的特征表示和结果输出公式为
Sji= e x p ( B i C j ) ∑ i = 1 N e x p ( B i C j )
Epj= ∑ i = 1 N(SjiDi)+Aj
Xji= e x p ( A i A j ) ∑ i = 1 N e x p ( A i A j )
Ecj= ∑ i = 1 N(XjiAi)+Aj
$\begin{aligned} P_{\text {out }}= & \operatorname{Conv}\left(\operatorname{Conv}\left\{P_{\mathrm{AM}}\left[\operatorname{Conv}\left(P_{\text {in }}\right)\right]\right\}+\right. \\ & \left.\operatorname{Conv}\left\{C_{\mathrm{AM}}\left[\operatorname{Conv}\left(P_{\text {in }}\right)\right]\right\}\right) \end{aligned}$
式中:Sji为第i个位置对第j个位置的影响;Bi为特征图被处理后第i个位置的新特征;Cj为特征图被处理后第j个位置的新特征;Aj为A的元素;Di为D第i列的元素;Epj为PAM的输出特征;Xji表示第i个通道对第j个通道的影响;Ai为A第i列的元素;Ecj为CAM的输出特征;Pin为输入;Pout为输出;Conv为卷积运算;PAM、CAM分别为空间特征提取和通道特征提取。
2 模型训练与结果分析
收起
2.1 模型训练参数
本文研究所采用的训练及测试环境与硬件设备配置如下:Windows 10操作系统,13th Gen Intel(R) Core(TM) i7-13700KF@3.40 GHz,64 G内存,显卡为NVIDIA GeForce RTX 4070Ti,显存12G,Pytorch版本为2.0.0,Python版本为3.9,CUDA版本11.8。为避免超参数对试验结果造成影响,将各网络模型超参数进行统一设置,经过多次试验,最终选定学习率为0.01、动量为0.9、权重衰减为1×10-4、迭代次数为100、批处理大小为16、选用随机梯度下降(stochastic gradient descent,SGD)作为本次试验的优化算法。
2.2 评价指标
为综合评价改进的TransUNet分割网络模型性能,选取全局像素准确率PA(pixel accuracy)、F1分数(F1-score)、平均交并比mIoU(mean intersection over union)、Dice相似度系数(dice similarity coefficient)4种常用语义分割模型评价指标对模型进行评价。
PA表示网络模型预测正确的像素点个数与总的像素点个数之比;F1分数综合考虑了模型的精确率(precision)和召回率(recall),可以实现对模型整体性能的量化评估,F1值越接近1代表模型性能越稳定;平均交并比mIoU计算所有类别真实值和预测值两个集合的交集与并集的比值,式(6)给出了mIoU的计算公式;Dice相似度系数用于度量预测结果与真实标签的重叠度,越接近1代表模型性能越好,计算公式为
mIoU= 1 2 ∑ i = 0 1 P i ⋂ T i P i ⋃ T i
Dice(P,T)=2 P ⋂ T P + T
式中:Pi为第i类的预测结果;Ti为第i类的真实标签;P为预测图像;T为标签图像。
2.3 试验验证
2.3.1 编码层数试验
Transformer编码层数是影响TransUNet网络分割性能的重要因素之一,编码层数对模型的训练效果有显著影响。编码层数过深可能会导致模型过拟合,模型在训练数据上表现出色,在未见过的数据上表现不佳,产生特征崩塌现象;编码层数过浅也可能导致欠拟合,模型没有足够的能力捕获数据的关键特征,难以达到理想的分割效果。实际应用中需要根据数据集的规模和复杂程度选择合适的编码层数以实现最佳的模型性能。通过设置不同的Transformer编码层数(4、8、12、16、20层)来寻找最优的层数配置,测定不同层数对应的F1分数和mIoU值进行结果分析,试验数据如表1所示。
由表1可知,当编码层数(transformer layers)为8时,F1分数达到最高值97.05%,mIoU也达到最高值96.99%,随着层数的增加,F1分数和mIoU均略有降低。上述试验结果表明8层编码层数能够更好地平衡模型的泛化能力和复杂度,更容易获得最佳的分割性能。
2.3.2 算法改进前后对比
为进一步测试本文模型的分割性能,分别使用UNet、U2Net、SwinUNet、TransUNet和改进的TransUNet在薄带铸轧钢板表面缺陷分割数据集TSCRD和东北大学开源带钢表面缺陷分割数据集FSSD-12上进行试验[21]。FSSD-12包含12种带钢表面常见缺陷,原始数据集每类缺陷对应50张图像,数据集扩充后包含1 560张图像数据。试验结果如表2和表3所示。
由表2和表3可以看出,与其他算法相比较,本文方法在自建薄带铸轧钢板表面缺陷数据集上体现出良好性能,分割准确率达到96.85%,平均交并比96.99%,模型改进前后Dice相似度系数分别为92.35%和92.98%,指标上升0.63个百分点,提升效果较为明显。此外,在面对复杂度更高的带钢数据集时仍能保持较高的分割质量,对应评价指标数值较基线模型均有提升。上述分析表明改进的TransUNet语义分割模型在冶金缺陷分割领域具有较大的应用潜力。
2.3.3 验证结果可视化
5种模型对FSSD-12和TSCRD两个数据集的分割效果与标签对比如图5所示,从上到下选取了4种带钢表面缺陷和1组薄带铸轧钢板表面缺陷。可以看出,5种图像分割模型均能较好地识别出缺陷的主体结构,但结合边缘细节和漏分割、误分割的情况来看,本文提出的改进TransUNet网络模型的分割效果最好。UNet和U2Net有一定的错误分割,未能完全捕捉到缺陷的细节;SwinUNet辨识度较低、边缘部分较模糊且存在较多噪点,在第5幅图中现象尤为明显;TransUNet边缘部分相较清晰,但有一定的错误分割现象。改进TransUNet模型图像分割边缘清晰、较基线网络的分割连贯性和一致性明显提升,基本上实现了对缺陷的精确分割,分割效果与标签图像最为接近,充分体现了本文模型较其他算法模型对解决类似问题更具优势。综合上述分析,改进的TransUNet语义分割模型能在保持图像主体结构的同时,对小区域和边缘识别表现最为出色,说明其在捕捉全局和局部细节方面的能力较强,验证了本研究所提出改进网络具备的优良性能。
网络训练过程中损失曲线是评估模型训练效果和性能的重要依据,其中训练损失反映了模型对已知数据的学习程度,而验证损失则展示了模型对未知数据的预测能力。为深入理解模型训练过程与模型性能,本文研究绘制了图6所示的,优化前后两个分割模型在前50个训练周期内的(loss-epoch)损失对比曲线。从图6(a)的训练损失可以观察到,相比于基线模型,优化后的TransUNet在训练初期的损失下降速度更快,且整个训练过程中的损失值普遍低于基线模型。尽管两个模型的损失值在训练过程中都有所波动,优化模型的波动幅度更小,这表明优化模型具有更高的稳定性。图6(b)显示了两个模型在验证集上的表现,较低的验证损失值说明优化模型拥有更强的泛化能力和稳定性,表明其对训练数据的推广能力更优。
3 结论
收起
(1)针对短流程生产过程中钢板表面缺陷检测问题,提出了基于TransUNet网络和DANet双重注意融合网络的改进TransUNet薄带铸轧钢板表面缺陷分割模型,在自制小规模铸轧钢板表面缺陷分割数据集上实现了对钢板表面异物缺陷的精准分割,为薄带铸轧钢板表面缺陷识别提供了新方法。
(2)对比了多种语义分割模型对钢板表面缺陷分割效果。试验结果表明,本文研究提出的优化模型表现最好,分割准确率达到96.85%,平均交并比为96.99%,可为钢板生产过程中的质量控制提供有力的技术支持,对指导工业生产有一定的积极意义。
(3)未来的工作将聚焦算法的进一步优化:一是扩充缺陷类别和训练样本,二是对模型处理速度进行分析和提升,以期满足更多实际生产条件下的结果验证与应用拓展。
基金
收起
  • 国家自然科学基金(51904107)
  • 中央引导地方科技发展资金项目(236Z1017G)
  • 唐山市市级科技计划(22130220G)
  • 唐山市市级科技计划(22130204G)
文献
收起
参考文献 引证文献
排序方式：
[1]
周东生, 冯庆晓, 李化龙. 薄带铸轧产品特性及应用进展[J]. 连铸, 2020(6): 21-26, 33.
Zhou Dongsheng, Feng Qingxiao, Li Hualong. Characteristics and application progress of thin strip casting and rolling products[J]. Continuous Casting, 2020(6): 21-26, 33.
[2]
王国栋. 钢铁全流程和一体化工艺技术创新方向的探讨[J]. 钢铁研究学报, 2018, 30(1): 1-7.
Wang Guodong. Exploration of innovation direction in steel full process and integrated process technology[J]. Journal of Iron and Steel Research, 2018, 30(1): 1-7.
[3]
Ding ZY, Zhao X, Misra R D K, et al. Deep learning-based understanding of defects in continuous casting product[J]. Metals, 2023, 13(11): 1809-1822.
[4]
汪水泽, 高军恒, 吴桂林, 等. 薄板坯连铸连轧技术发展现状及展望[J]. 工程科学学报, 2022, 44(4): 534-545.
Wang Shuize, Gao Junheng, Wu Guilin, et al. Development status and prospects of thin slab continuous casting and rolling technology[J]. Journal of Engineering Science, 2022, 44 (4): 534-545.
[5]
严毅, 邓超, 李琳, 等. 深度学习背景下的图像语义分割方法综述[J]. 中国图象图形学报, 2023, 28(11): 3342-3362.
Yan Yi, Deng Chao, Li Lin, et al. A review of image semantic segmentation methods in the context of deep learning[J]. Chinese Journal of Image and Graphics, 2023, 28(11): 3342-3362.
[6]
黄鹏, 郑淇, 梁超. 图像分割方法综述[J]. 武汉大学学报(理学版), 2020, 66(6): 519-531.
Huang Peng, Zheng Qi, Liang Chao. Overview of image segmentation methods[J]. Journal of Wuhan University (Science Edition), 2020, 66(6): 519-531.
[7]
王道累, 刘易腾, 杜文斌, 等. 基于级联孪生密集网络的金属表面缺陷检测方法[J]. 计算机辅助设计与图形学学报, 2022, 34(6): 946-952.
Wang Daolei, Liu Yiteng, Du Wenbin, et al. Metal surface defect detection method based on cascaded twin dense network[J]. Journal of Computer Aided Design and Graphics, 2022, 34 (6): 946-952.
[8]
王昱翔, 葛洪伟. 基于U2-Net的金属表面缺陷检测算法[J]. 南京大学学报(自然科学版), 2023, 59(3): 413-424.
Wang Yuxiang, Ge Hongwei. Metal surface defect detection algorithm based on U2 Net[J]. Journal of Nanjing University (Natural Science Edition), 2023, 59(3): 413-424.
[9]
Ronneberger O, Fischer P, Brox T. U-net: convolutional networks for biomedical image segmentation[C]// Medical Image Computing and Computer-assisted Intervention. Munich: Springer, 2015: 234-241.
[10]
Chen J N, Lu Y Y, Yu Q H, et al. TransUNet transformers make strong encoders for medical image segmentation[J]. arXiv reprient arXiv: 2102.04306, 2021.
[11]
Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words: transformers for image recognition at scale[J]. arXiv reprient arXiv: 2010.11929, 2020.
[12]
李原, 李燕君, 刘进超, 等. 基于改进Res-UNet网络的钢铁表面缺陷图像分割研究[J]. 电子与信息学报, 2022, 44(5): 1513-1520.
Li Yuan, Li Yanjun, Liu Jinchao, et al. Research on steel surface defect image segmentation based on improved Res-UNet network[J]. Journal of Electronics and Information Technology, 2022, 44(5): 1513-1520.
[13]
戴张杰, 黄成永, 刘威, 等. 基于Mask-RCNN的转炉炉口形貌检测[J]. 钢铁, 2023, 58(3): 73-78.
Dai Zhangjie, Huang Chengyong, Liu Wei, et al. Detection of converter mouth morphology based on Mask-RCNN[J]. Iron and Steel, 2023, 58 (3): 73-78.
[14]
李福民, 侯炬才, 刘颂, 等. 基于计算机视觉和Re-Unet网络的烧结混合料粒度识别模型[J]. 钢铁研究学报, 2023, 35(11): 1347-1357.
Li Fumin, Hou Jucai, Liu Song, et al. Particle size recognition model for sintered mixtures based on computer vision and Re-Unet network[J]. Journal of Iron and Steel Research, 2023, 35 (11): 1347-1357.
[15]
蒋博涵, 陈先中, 侯庆文, 等. 基于BS-TransUNet网络的高炉雷达料线分割方法[J]. 冶金自动化, 2024, 48(2): 50-59.
Jiang Bohan, Chen Xianzhong, Hou Qingwen, et al. A radar material line segmentation method for blast furnaces based on BS-TransUNet network[J]. Metallurgical Automation, 2024, 48 (2): 50-59.
[16]
Fu J, Liu J, Tian H J, et al. Dual attention network for scene segmentation[C]// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 3146-3154.
[17]
李新叶, 宋维. 基于深度学习的图像语义分割研究进展[J]. 科学技术与工程, 2019, 19(33): 21-27.
Li Xinye, Song Wei. Research progress in image semantic segmentation based on deep learning[J]. Science Technology and Engineering, 2019, 19(33): 21-27.
[18]
宋泽冈, 刘艳莉, 张长兴. 基于机器视觉的桥梁裂缝检测应用及发展综述[J]. 科学技术与工程, 2023, 23(30): 12796-12805.
Song Zegang, Liu Yanli, Zhang Changxing. Application and development review of bridge crack detection based on machine vision[J]. Science Technology and Engineering, 2023, 23 (30): 12796-12805.
[19]
Chen J, Wang C C, Shi F, et al. DSNet: a dynamic squeeze network for real-time weld seam image segmentation[J]. Engineering Applications of Artificial Intelligence, 2024, 133.DOI: 10.1016/j.engappai.2024.108278.
[20]
Fu H, Song Q H, Gong J X, et al. Automatic detection and pixel-level quantification of surface microcracks in ceramics grinding: an exploration with Mask R-CNN and TransUNet[J]. Measurement, 2024, 224.DOI: 10.1016/j.measurement.2023.113895.
[21]
Hu F, Song K C, Zhang Y M, et al. Cross position aggregation network for few-shot strip steel surface defect segmentation[J]. IEEE Transactions on Instrumentation & Measurement, 2023, 72: 1-10.
2025年第25卷第10期
PDF下载
372
151
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2403371
  • 接收时间：2024-05-08
  • 首发时间：2025-07-09
  • 出版时间：2025-04-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期：2024-05-08
  • 修回日期：2025-01-03
基金
国家自然科学基金(51904107)
中央引导地方科技发展资金项目(236Z1017G)
唐山市市级科技计划(22130220G)
唐山市市级科技计划(22130204G)
作者信息
    1 华北理工大学电气工程学院, 唐山 063210
    2 华北理工大学冶金与能源学院, 唐山 063210
    3 河北省高品质钢连铸工程技术协同创新中心, 唐山 063000
    4 唐山市钢铁企业流程控制与优化技术创新中心, 唐山 063000
    5 河北科技大学材料科学与工程学院, 石家庄 050018

通讯作者:

* 曾凯(1990—),男,汉族,河北唐山人,博士,讲师。研究方向:机器视觉检测。E-mail:。
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403371
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
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
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
相关链接
论文
最新文章
热读文章
热点专题
内参
蓝皮书
产业发展报告
传播力报告
期刊分级目录
资讯
学术新闻
行业新闻
学术会议
行业会议
关于
关于我们
联系我们
北京市海淀区学院南路86号
100081
010-62199257
qkjq@cast.org.cn

中国科学技术协会版权所有 京ICP 备10216604号-4 海淀分局备案 1101084647
科技导报社主办 中国科协信息中心技术支持