Article(id=1236276110942589104, tenantId=1146029695717560320, journalId=1235980550691926019, issueId=1236276104999268557, articleNumber=null, orderNo=null, doi=10.3969/j.issn.0253-6099.2025.04.008, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1737993600000, receivedDateStr=2025-01-28, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1772680793747, onlineDateStr=2026-03-05, pubDate=1753977600000, pubDateStr=2025-08-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1772680793747, onlineIssueDateStr=2026-03-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1772680793747, creator=13701087609, updateTime=1772680793747, updator=13701087609, issue=Issue{id=1236276104999268557, tenantId=1146029695717560320, journalId=1235980550691926019, year='2025', volume='45', issue='4', pageStart='1', pageEnd='200', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1772680792331, creator=13701087609, updateTime=1772681498687, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1236279067746562719, tenantId=1146029695717560320, journalId=1235980550691926019, issueId=1236276104999268557, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1236279067746562720, tenantId=1146029695717560320, journalId=1235980550691926019, issueId=1236276104999268557, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=47, endPage=51, ext={EN=ArticleExt(id=1236276111265550527, articleId=1236276110942589104, tenantId=1146029695717560320, journalId=1235980550691926019, language=EN, title=Recognition of Rock Fracture in Open-Pit Mines by Borehole Imaging Based on Improved U-Net Model, columnId=1236276106018484431, journalTitle=Mining and Metallurgical Engineering, columnName=MINING, runingTitle=null, highlight=null, articleAbstract=

To improve the accuracy of fracture recognition in borehole images, a borehole fracture recognition approach for open-pit mine was proposed. First, borehole images of an open-pit mine is obtained with an intelligent borehole inspection camera, and then data augmentation is performed by using random cropping and image flipping, while median filtering is used for noise reduction and images are converted to grayscalere, so as to eliminate noise and reduce computational complexity. Next, spatial attention and channel attention mechanisms are integrated into the U-Net model to improve the semantic segmentation model for fractures, forming an AU-Net model, which can enhance the model′s ability to extract features from both overall and local image information. Experimental results show that compared to the original U-Net model, the AU-Net model can achieve lower loss and higher accuracy in the fracture recognition dataset by borehole imaging. Specifically, the mean intersection over union is improved by 4.38 percentage points, up to 82.34%, bringing better image segmentation effect.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Wenyao SONG, Mei ZHANG, Lianjun GUO, Ding DENG, Chong GAO, Xin ZHAO), CN=ArticleExt(id=1236276118546862669, articleId=1236276110942589104, tenantId=1146029695717560320, journalId=1235980550691926019, language=CN, title=基于改进U-Net模型的露天矿钻孔裂隙识别研究, columnId=1236276106219811026, journalTitle=矿冶工程杂志, columnName=采矿, runingTitle=null, highlight=null, articleAbstract=

为提高钻孔图像裂隙识别精度,提出了一种露天矿钻孔裂隙识别方法,利用智能钻孔摄像技术获取露天矿钻孔图像,并运用随机裁剪和图像翻转进行数据增广,同时采用中值滤波降噪和图像灰度化,去除噪点及减少计算量。在U-Net模型中利用空间注意力和通道注意力机制改进钻孔裂隙语义分割模型,形成AU-Net模型,以强化图像全局和局部信息的特征提取能力。实验结果表明:AU-Net模型相较于U-Net模型在钻孔图像裂隙识别数据集上可以取得更低的损失、更高的精度,均交并比提高了4.38百分点,达到82.34%,图像分割效果更好。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
郭连军(1963—),男,辽宁北票人,博士,教授,主要从事采矿工程及爆破理论技术相关方面的研究工作。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=xENrkXWrlg6iqO+HZOypgQ==, magXml=vVLgz1i4Oog8Bu2H0EjSGQ==, pdfUrl=null, pdf=d37M3mYVL4DJ73nsiw2Epg==, pdfFileSize=2555398, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=6jlzBct2oj2Sh4YdRkKHMw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=TX8kwBWSMYMPk5YzCQvZ3w==, mapNumber=null, authorCompany=null, fund=null, authors=

宋纹瑶(1995—),女,山东烟台人,硕士研究生,主要从事采矿工程相关方面的研究工作。E-mail:

, authorsList=宋纹瑶, 张梅, 郭连军, 邓丁, 高崇, 赵鑫)}, authors=[Author(id=1236348222139060980, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sj5526@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1236348222273278724, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348222139060980, language=EN, stringName=Wenyao SONG, firstName=Wenyao, middleName=null, lastName=SONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236348222428467988, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348222139060980, language=CN, stringName=宋纹瑶, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870, bio={"content":"

宋纹瑶(1995—),女,山东烟台人,硕士研究生,主要从事采矿工程相关方面的研究工作。E-mail:

"}, bioImg=null, bioContent=

宋纹瑶(1995—),女,山东烟台人,硕士研究生,主要从事采矿工程相关方面的研究工作。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236348221501526692, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=1., ext=[AuthorCompanyExt(id=1236348221518303912, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China), AuthorCompanyExt(id=1236348221530886828, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870)])]), Author(id=1236348222566880032, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, 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=1236348222793372469, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348222566880032, language=EN, stringName=Mei ZHANG, firstName=Mei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Xuanhua Vocational College of Science and Technology, Zhangjiakou 075100, Hebei, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236348222935978819, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348222566880032, language=CN, stringName=张梅, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.宣化科技职业学院,河北 张家口 075100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236348221707047616, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=2., ext=[AuthorCompanyExt(id=1236348221719630531, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221707047616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Xuanhua Vocational College of Science and Technology, Zhangjiakou 075100, Hebei, China), AuthorCompanyExt(id=1236348221736407750, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221707047616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.宣化科技职业学院,河北 张家口 075100)])]), Author(id=1236348223032447824, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=guolj@sut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1236348223187637083, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348223032447824, language=EN, stringName=Lianjun GUO, firstName=Lianjun, middleName=null, lastName=GUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236348223300883297, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348223032447824, language=CN, stringName=郭连军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236348221501526692, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=1., ext=[AuthorCompanyExt(id=1236348221518303912, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China), AuthorCompanyExt(id=1236348221530886828, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870)])]), Author(id=1236348223401546604, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, 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=1236348223506404215, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348223401546604, language=EN, stringName=Ding DENG, firstName=Ding, middleName=null, lastName=DENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236348223657399171, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348223401546604, language=CN, stringName=邓丁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236348221501526692, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=1., ext=[AuthorCompanyExt(id=1236348221518303912, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China), AuthorCompanyExt(id=1236348221530886828, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870)])]), Author(id=1236348223770645391, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, 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=1236348223913251748, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348223770645391, language=EN, stringName=Chong GAO, firstName=Chong, middleName=null, lastName=GAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.China Railway 19th Bureau Group Co., Ltd., Beijing 100176, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236348224018109359, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348223770645391, language=CN, stringName=高崇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.中铁十九局集团有限公司,北京 100176, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236348221858042581, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=3., ext=[AuthorCompanyExt(id=1236348221866431189, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221858042581, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.China Railway 19th Bureau Group Co., Ltd., Beijing 100176, China), AuthorCompanyExt(id=1236348221883208407, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221858042581, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.中铁十九局集团有限公司,北京 100176)])]), Author(id=1236348224139744188, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, 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=1236348224244601804, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348224139744188, language=EN, stringName=Xin ZHAO, firstName=Xin, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.Mining Investment Co., Ltd., China Railway 19th Bureau Group, Beijing 100161, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236348224349459422, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, authorId=1236348224139744188, language=CN, stringName=赵鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4.中铁十九局集团矿业投资有限公司,北京 100161, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236348222000648932, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=4., ext=[AuthorCompanyExt(id=1236348222025814762, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348222000648932, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.Mining Investment Co., Ltd., China Railway 19th Bureau Group, Beijing 100161, China), AuthorCompanyExt(id=1236348222042591979, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348222000648932, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.中铁十九局集团矿业投资有限公司,北京 100161)])])], keywords=[Keyword(id=1236348224601117696, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=1, keyword=borehole imaging), Keyword(id=1236348224764694545, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=2, keyword=fracture recognition), Keyword(id=1236348224932466724, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=3, keyword=U-Net network), Keyword(id=1236348225108627510, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=4, keyword=attention mechanism), Keyword(id=1236348225226068037, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=5, keyword=fracture extraction), Keyword(id=1236348225364480085, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=6, keyword=machine learning), Keyword(id=1236348225523863650, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=7, keyword=semantic segmentation), Keyword(id=1236348225637109870, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, orderNo=8, keyword=image recognition), Keyword(id=1236348225733578871, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=1, keyword=钻孔成像), Keyword(id=1236348226052345988, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=2, keyword=裂隙识别), Keyword(id=1236348226220118166, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=3, keyword=U-Net网络), Keyword(id=1236348226371113121, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=4, keyword=注意力机制), Keyword(id=1236348226534690986, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=5, keyword=裂隙提取), Keyword(id=1236348226660520120, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=6, keyword=机器学习), Keyword(id=1236348226769572033, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=7, keyword=语义分割), Keyword(id=1236348226899595467, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, orderNo=8, keyword=图像识别)], refs=[Reference(id=1236348230326342094, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=3, pageStart=16, pageEnd=21, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=魏可心, 徐振洋, 王雪松, journalName=矿冶工程, refType=null, unstructuredReference=魏可心, 徐振洋, 王雪松, 等. 填塞长度对岩体爆破损伤效果的影响研究[J]. 矿冶工程, 2024, 44(3): 16-21., articleTitle=填塞长度对岩体爆破损伤效果的影响研究, refAbstract=null), Reference(id=1236348230473142741, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=3, pageStart=16, pageEnd=21, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=WEI Kexin, XU Zhenyang, WANG Xuesong, journalName=Mining and Metallurgical Engineering, refType=null, unstructuredReference=WEI Kexin, XU Zhenyang, WANG Xuesong, et al. Influence of stemming length on damage effect of rock blasting[J]. Mining and Metallurgical Engineering, 2024, 44(3): 16-21., articleTitle=Influence of stemming length on damage effect of rock blasting, refAbstract=null), Reference(id=1236348230624137695, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=6, pageStart=11, pageEnd=15, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=熊成宇, 张建, 刘向阳, journalName=矿冶工程, refType=null, unstructuredReference=熊成宇, 张建, 刘向阳, 等. 互层状围岩隧道切槽爆破破岩规律研究[J]. 矿冶工程, 2024, 44(6): 11-15., articleTitle=互层状围岩隧道切槽爆破破岩规律研究, refAbstract=null), Reference(id=1236348230766744039, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=6, pageStart=11, pageEnd=15, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=XIONG Chengyu, ZHANG Jian, LIU Xiangyang, journalName=Mining and Metallurgical Engineering, refType=null, unstructuredReference=XIONG Chengyu, ZHANG Jian, LIU Xiangyang, et al. Rock frag-mentation patterns in tunnels with interbedded surrounding rock by blasting with slotted blastholes[J]. Mining and Metallurgical Engineering, 2024, 44(6): 11-15., articleTitle=Rock frag-mentation patterns in tunnels with interbedded surrounding rock by blasting with slotted blastholes, refAbstract=null), Reference(id=1236348230934516206, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=1, pageStart=77, pageEnd=84, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=傅鹏, journalName=爆破, refType=null, unstructuredReference=傅鹏. 岩体结构面对台阶爆破效果影响研究[J]. 爆破, 2023, 40(1): 77-84., articleTitle=岩体结构面对台阶爆破效果影响研究, refAbstract=null), Reference(id=1236348231064539641, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2023, volume=40, issue=1, pageStart=77, pageEnd=84, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=FU Peng, journalName=Blasting, refType=null, unstructuredReference=FU Peng. Influence of rock mass structure on bench blasting effect[J]. Blasting, 2023, 40(1): 77-84., articleTitle=Influence of rock mass structure on bench blasting effect, refAbstract=null), Reference(id=1236348231173591551, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=10, pageStart=169, pageEnd=172, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=赵兴东, 周鑫, 赵一凡, journalName=矿业研究与开发, refType=null, unstructuredReference=赵兴东, 周鑫, 赵一凡, 等. 基于钻孔电视探测的井筒围岩块体识别及其稳定性分析方法[J]. 矿业研究与开发, 2022, 42(10): 169-172., articleTitle=基于钻孔电视探测的井筒围岩块体识别及其稳定性分析方法, refAbstract=null), Reference(id=1236348231286837765, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=10, pageStart=169, pageEnd=172, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=ZHAO Xingdong, ZHOU Xin, ZHAO Yifan, journalName=Mining Research and Development, refType=null, unstructuredReference=ZHAO Xingdong, ZHOU Xin, ZHAO Yifan, et al. Identification and stability analysis method of surrounding rock mass in shaft based on borehole TV detection[J]. Mining Research and Development, 2022, 42(10): 169-172., articleTitle=Identification and stability analysis method of surrounding rock mass in shaft based on borehole TV detection, refAbstract=null), Reference(id=1236348231395889678, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=11, pageStart=4467, pageEnd=4476, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=葛云峰, 钟鹏, 唐辉明, journalName=岩土力学, refType=null, unstructuredReference=葛云峰, 钟鹏, 唐辉明, 等. 基于钻孔图像的岩体结构面几何信息智能测量[J]. 岩土力学, 2019, 40(11): 4467-4476., articleTitle=基于钻孔图像的岩体结构面几何信息智能测量, refAbstract=null), Reference(id=1236348231492358675, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2019, volume=40, issue=11, pageStart=4467, pageEnd=4476, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=GE Yunfeng, ZHONG Peng, TANG Huiming, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=GE Yunfeng, ZHONG Peng, TANG Huiming, et al. Intelligent measurement on geometric information of rock discontinuities based on borehole image[J]. Rock and Soil Mechanics, 2019, 40(11): 4467-4476., articleTitle=Intelligent measurement on geometric information of rock discontinuities based on borehole image, refAbstract=null), Reference(id=1236348231601410585, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2017, volume=38, issue=10, pageStart=3062, pageEnd=3066, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=王川婴, 邹先坚, 韩增强, journalName=岩土力学, refType=null, unstructuredReference=王川婴, 邹先坚, 韩增强, 等. 基于特征函数的钻孔图像结构面识别方法[J]. 岩土力学, 2017, 38(10): 3062-3066., articleTitle=基于特征函数的钻孔图像结构面识别方法, refAbstract=null), Reference(id=1236348231697879582, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2017, volume=38, issue=10, pageStart=3062, pageEnd=3066, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=WANG Chuanying, ZOU Xianjian, HAN Zengqiang, journalName=Rock and Soil Mechanics, refType=null, unstructuredReference=WANG Chuanying, ZOU Xianjian, HAN Zengqiang, et al. Recognition of structural planes in borehole image based on characteristic function[J]. Rock and Soil Mechanics, 2017, 38(10): 3062-3066., articleTitle=Recognition of structural planes in borehole image based on characteristic function, refAbstract=null), Reference(id=1236348231777571363, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=5, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=宋琨, 孙驰, 安冬, journalName=地质科技通报, refType=null, unstructuredReference=宋琨, 孙驰, 安冬, 等. 数字钻孔全景影像中结构面特征智能识别方法[J]. 地质科技通报, 2020, 39(5): 17-22., articleTitle=数字钻孔全景影像中结构面特征智能识别方法, refAbstract=null), Reference(id=1236348231882428968, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=5, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=SONG Kun, SUN Chi, AN Dong, journalName=Bulletin of Geological Science and Technology, refType=null, unstructuredReference=SONG Kun, SUN Chi, AN Dong, et al. Intelligent identification method for rock discontinuities properties by digital borehole panoramic images[J]. Bulletin of Geological Science and Technology, 2020, 39(5): 17-22., articleTitle=Intelligent identification method for rock discontinuities properties by digital borehole panoramic images, refAbstract=null), Reference(id=1236348231966315052, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=5, pageStart=96, pageEnd=100, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=吴天雨, 许英朝, 晁鹏飞, journalName=激光杂志, refType=null, unstructuredReference=吴天雨, 许英朝, 晁鹏飞. 一种提高目标图像识别准确率的数据增强技术[J]. 激光杂志, 2020, 41(5): 96-100., articleTitle=一种提高目标图像识别准确率的数据增强技术, refAbstract=null), Reference(id=1236348232058589744, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=5, pageStart=96, pageEnd=100, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=WU Tianyu, XU Yingchao, CHAO Pengfei, journalName=Laser Journal, refType=null, unstructuredReference=WU Tianyu, XU Yingchao, CHAO Pengfei. Data augmentation technology for improving target image recognition[J]. Laser Journal, 2020, 41(5): 96-100., articleTitle=Data augmentation technology for improving target image recognition, refAbstract=null), Reference(id=1236348232171835957, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2021, volume=44, issue=1, pageStart=66, pageEnd=70, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=李永盛, 何佳洲, 刘义海, journalName=舰船电子对抗, refType=null, unstructuredReference=李永盛, 何佳洲, 刘义海, 等. 基于图像检测识别的数据增强技术[J]. 舰船电子对抗, 2021, 44(1): 66-70., articleTitle=基于图像检测识别的数据增强技术, refAbstract=null), Reference(id=1236348232272499261, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2021, volume=44, issue=1, pageStart=66, pageEnd=70, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=LI Yongsheng, HE Jiazhou, LIU Yihai, journalName=Shipboard Electronic Countermeasure, refType=null, unstructuredReference=LI Yongsheng, HE Jiazhou, LIU Yihai, et al. Data enhancement technology based on image detection and recognition[J]. Shipboard Electronic Countermeasure, 2021, 44(1): 66-70., articleTitle=Data enhancement technology based on image detection and recognition, refAbstract=null), Reference(id=1236348232364773952, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2024, volume=8, issue=10, pageStart=21, pageEnd=25, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=白茹鑫, 栾尚敏, journalName=现代信息科技, refType=null, unstructuredReference=白茹鑫, 栾尚敏. 图像处理中应用图像降噪算法的研究综述[J]. 现代信息科技, 2024, 8(10): 21-25., articleTitle=图像处理中应用图像降噪算法的研究综述, refAbstract=null), Reference(id=1236348232436077125, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2024, volume=8, issue=10, pageStart=21, pageEnd=25, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=BAI Ruxin, LUAN Shangmin, journalName=Modern Information Technology, refType=null, unstructuredReference=BAI Ruxin, LUAN Shangmin. Research review of the application of image denoising algorithms in image processing[J]. Modern Information Technology, 2024, 8(10): 21-25., articleTitle=Research review of the application of image denoising algorithms in image processing, refAbstract=null), Reference(id=1236348232540934729, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=9, pageStart=364, pageEnd=369, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=郭昕刚, 许连杰, 霍金花, journalName=计算机仿真, refType=null, unstructuredReference=郭昕刚, 许连杰, 霍金花, 等. 基于非局部自相似性的图像去噪算法研究[J]. 计算机仿真, 2022, 39(9): 364-369., articleTitle=基于非局部自相似性的图像去噪算法研究, refAbstract=null), Reference(id=1236348232658375249, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2022, volume=39, issue=9, pageStart=364, pageEnd=369, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=GUO Xingang, XU Lianjie, HUO Jinhua, journalName=Computer Simulation, refType=null, unstructuredReference=GUO Xingang, XU Lianjie, HUO Jinhua, et al. Research on image denoising algorithm based on non-local self-similarity[J]. Computer Simulation, 2022, 39(9): 364-369., articleTitle=Research on image denoising algorithm based on non-local self-similarity, refAbstract=null), Reference(id=1236348232729678423, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2022, volume=58, issue=24, pageStart=29, pageEnd=46, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=张蕊, 孟晓曼, 曾志远, journalName=计算机工程与应用, refType=null, unstructuredReference=张蕊, 孟晓曼, 曾志远, 等. 图卷积神经网络在点云语义分割中的研究综述[J]. 计算机工程与应用, 2022, 58(24): 29-46., articleTitle=图卷积神经网络在点云语义分割中的研究综述, refAbstract=null), Reference(id=1236348232821953114, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, doi=null, pmid=null, pmcid=null, year=2022, volume=58, issue=24, pageStart=29, pageEnd=46, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=ZHANG Rui, MENG Xiaoman, ZENG Zhiyuan, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=ZHANG Rui, MENG Xiaoman, ZENG Zhiyuan, et al. Review of graph convolutional neural networks in point cloud semantic segmentation[J]. Computer Engineering and Applications, 2022, 58(24): 29-46., articleTitle=Review of graph convolutional neural networks in point cloud semantic segmentation, refAbstract=null)], funds=[Fund(id=1236348230074683837, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, awardId=51974187, language=CN, fundingSource=国家自然科学基金(51974187), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1236348221501526692, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=1., ext=[AuthorCompanyExt(id=1236348221518303912, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China), AuthorCompanyExt(id=1236348221530886828, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221501526692, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870)]), AuthorCompany(id=1236348221707047616, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=2., ext=[AuthorCompanyExt(id=1236348221719630531, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221707047616, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Xuanhua Vocational College of Science and Technology, Zhangjiakou 075100, Hebei, China), AuthorCompanyExt(id=1236348221736407750, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221707047616, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.宣化科技职业学院,河北 张家口 075100)]), AuthorCompany(id=1236348221858042581, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=3., ext=[AuthorCompanyExt(id=1236348221866431189, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221858042581, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.China Railway 19th Bureau Group Co., Ltd., Beijing 100176, China), AuthorCompanyExt(id=1236348221883208407, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348221858042581, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.中铁十九局集团有限公司,北京 100176)]), AuthorCompany(id=1236348222000648932, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, xref=4., ext=[AuthorCompanyExt(id=1236348222025814762, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348222000648932, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.Mining Investment Co., Ltd., China Railway 19th Bureau Group, Beijing 100161, China), AuthorCompanyExt(id=1236348222042591979, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, companyId=1236348222000648932, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.中铁十九局集团矿业投资有限公司,北京 100161)])], figs=[ArticleFig(id=1236348227230945500, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.1, caption=U-Net architecture, figureFileSmall=ZSin2N1lmWaezL56ACXNPw==, figureFileBig=Woz0OIsHnSW5vtSMb+MzEA==, tableContent=null), ArticleFig(id=1236348227373551845, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图1, caption=U-Net网络结构图, figureFileSmall=ZSin2N1lmWaezL56ACXNPw==, figureFileBig=Woz0OIsHnSW5vtSMb+MzEA==, tableContent=null), ArticleFig(id=1236348227520352497, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.2, caption=Schematic diagram of mixed attention mechanism module, figureFileSmall=daVzbLEbD8IgCmdFzuMEmQ==, figureFileBig=LsT3iS+KPYhDnlPr+jI2Rw==, tableContent=null), ArticleFig(id=1236348227625210106, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图2, caption=混合注意力机制模块结构图, figureFileSmall=daVzbLEbD8IgCmdFzuMEmQ==, figureFileBig=LsT3iS+KPYhDnlPr+jI2Rw==, tableContent=null), ArticleFig(id=1236348227780399363, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.3, caption=Schematic diagram of borehole wall image transformation, figureFileSmall=oq+9QlVHpccmsfSivSn5jA==, figureFileBig=ozPilpwIt0bCIzoaX3/fFw==, tableContent=null), ArticleFig(id=1236348227914617105, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图3, caption=孔壁图像变换示意图, figureFileSmall=oq+9QlVHpccmsfSivSn5jA==, figureFileBig=ozPilpwIt0bCIzoaX3/fFw==, tableContent=null), ArticleFig(id=1236348228069806364, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.4, caption=Horizontally flipped borehole images, figureFileSmall=TsaDphy73T3xaV8bGzPg2w==, figureFileBig=zcbn1mK3k52/cTDs+Picow==, tableContent=null), ArticleFig(id=1236348228216607017, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图4, caption=钻孔图像水平翻转, figureFileSmall=TsaDphy73T3xaV8bGzPg2w==, figureFileBig=zcbn1mK3k52/cTDs+Picow==, tableContent=null), ArticleFig(id=1236348228338241840, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.5, caption=Original and greyscale images of borehole, figureFileSmall=0ApzXoFkn9F5q1IQRzpZmA==, figureFileBig=5JD8tZ3LgrATpLyz6c77+A==, tableContent=null), ArticleFig(id=1236348228518596922, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图5, caption=钻孔图像原图及灰度图

(a)彩色原图;(b)灰度图

, figureFileSmall=0ApzXoFkn9F5q1IQRzpZmA==, figureFileBig=5JD8tZ3LgrATpLyz6c77+A==, tableContent=null), ArticleFig(id=1236348228686369101, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.6, caption=Filtered borehole images, figureFileSmall=oaMDH4LCmLjD4A46mwlglw==, figureFileBig=NzQy0vm9gsVyho6TlNICLg==, tableContent=null), ArticleFig(id=1236348228812198234, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图6, caption=滤波后的钻孔图像

(a)均值滤波;(b)中值滤波;(c)双边滤波

, figureFileSmall=oaMDH4LCmLjD4A46mwlglw==, figureFileBig=NzQy0vm9gsVyho6TlNICLg==, tableContent=null), ArticleFig(id=1236348228912861541, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.7, caption=Image annotation effects, figureFileSmall=c910yxIoR11KcFCaqzieuA==, figureFileBig=SUIKWL2kkzkLygEpBozTOQ==, tableContent=null), ArticleFig(id=1236348229055467886, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图7, caption=图像标注效果, figureFileSmall=c910yxIoR11KcFCaqzieuA==, figureFileBig=SUIKWL2kkzkLygEpBozTOQ==, tableContent=null), ArticleFig(id=1236348229168714102, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.8, caption=Loss curves of two deep learning models, figureFileSmall=UHK58neJbASxYJ/RBJa6yQ==, figureFileBig=ZuKnyBK8D8PQo0l+Wtbfrg==, tableContent=null), ArticleFig(id=1236348229311320453, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图8, caption=两种深度学习模型损失曲线, figureFileSmall=UHK58neJbASxYJ/RBJa6yQ==, figureFileBig=ZuKnyBK8D8PQo0l+Wtbfrg==, tableContent=null), ArticleFig(id=1236348229441343887, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Fig.9, caption=Comparison of image segmentation effects of two models, figureFileSmall=IOzng1foCs3Jx3K6eLcpJw==, figureFileBig=Y2W1z5pN5tKUP5nU8EF3iw==, tableContent=null), ArticleFig(id=1236348229550395801, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=图9, caption=两种模型图像分割效果比较, figureFileSmall=IOzng1foCs3Jx3K6eLcpJw==, figureFileBig=Y2W1z5pN5tKUP5nU8EF3iw==, tableContent=null), ArticleFig(id=1236348229667836318, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=EN, label=Table 1, caption=

Performance evaluation of two models

, figureFileSmall=null, figureFileBig=null, tableContent=
训练模型精确率/%召回率/%调和平均数/%均交并比/%
U-Net91.9486.9789.3977.96
AU-Net92.6386.7389.5882.34
), ArticleFig(id=1236348229843997100, tenantId=1146029695717560320, journalId=1235980550691926019, articleId=1236276110942589104, language=CN, label=表1, caption=

两种模型的评价结果

, figureFileSmall=null, figureFileBig=null, tableContent=
训练模型精确率/%召回率/%调和平均数/%均交并比/%
U-Net91.9486.9789.3977.96
AU-Net92.6386.7389.5882.34
)], attaches=null, journal=Journal(id=1235979682521329665, delFlag=0, nameCn=矿冶工程杂志, nameEn=Mining and Metallurgical Engineering, nameHistory1=null, nameHistory2=null, issn=0253-6099, eissn=null, cn=43-1104/TD, coden=null, periodic=1, language=CN, oaType=null, 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=sIAtluqp1t366oKMF09POA==, journalPrice=null, startedYear=null, abbrevIsoEn=Mining and Metallurgical Engineering, journalRemark=null, publicationField=null, createdTime=1772610119708, updatedTime=1772610494020, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=M, firstLetterEn=M, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=sIAtluqp1t366oKMF09POA==, picEn=8lFm/e3VFuRPvwuEPHk4Qg==, jcr=null, cjcr=null, exts=[JournalExt(id=1235981252583551310, language=CN, name=矿冶工程杂志, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1772610494037, updatedTime=1772610494037, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kygczz.com/Journalx_kygc/authorLogOn.action, submissionEditorUrl=http://www.kygczz.com/Journalx_kygc/editorLogOn.action, submissionReviewUrl=http://www.kygczz.com/Journalx_kygc/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1235981252633882959, language=EN, name=Mining and Metallurgical Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1772610494049, updatedTime=1772610494049, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.kygczz.com/Journalx_kygc/authorLogOn.action, submissionEditorUrl=http://www.kygczz.com/Journalx_kygc/editorLogOn.action, submissionReviewUrl=http://www.kygczz.com/Journalx_kygc/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1235980550691926019, websiteList=[Website(id=1235982099019256290, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1235980550691926019, 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/kygczz/CN, language=CN, createTime=1772610695843, createBy=18614031015, updateTime=1772610913564, updateBy=18614031015, name=矿冶工程杂志-中文, tplId=1146099689490845704, title=矿冶工程杂志, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1235983631420805700, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=articleTextType, value=kx, createTime=1772611061196, updateTime=1772611061196, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631378862657, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=banner, value=null, createTime=1772611061186, updateTime=1772611061186, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631441777223, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=grayFlag, value=0, createTime=1772611061201, updateTime=1772611061201, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631370474048, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=logo, value=https://castjournals.cast.org.cn/joweb/kygczz/CN/file/pic?fileId=seRpqoNiVtKzuWGeM8/PzA==, createTime=1772611061184, updateTime=1772611061184, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631454360137, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=minRunFlag, value=0, createTime=1772611061204, updateTime=1772611061204, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631408222787, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kygczz/CN/file/pic, createTime=1772611061193, updateTime=1772611061193, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631445971528, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=silenceFlag, value=0, createTime=1772611061202, updateTime=1772611061202, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631387251266, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1772611061188, updateTime=1772611061188, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631429194309, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=themeColor, value=null, createTime=1772611061198, updateTime=1772611061198, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983631433388614, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099019256290, code=themeStyle, value=null, createTime=1772611061199, updateTime=1772611061199, creator=18614031015, updator=18614031015)]), Website(id=1235982099262525932, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1235980550691926019, 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/kygczz/EN, language=EN, createTime=1772610695901, createBy=18614031015, updateTime=1772610917908, updateBy=18614031015, name=矿冶工程杂志-英文, tplId=1146101810881728533, title=Mining and Metallurgical Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1235983658880913998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=articleTextType, value=kx, createTime=1772611067743, updateTime=1772611067743, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658864136779, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=banner, value=null, createTime=1772611067739, updateTime=1772611067739, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658897691217, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=grayFlag, value=0, createTime=1772611067747, updateTime=1772611067747, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658855748170, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=logo, value=https://castjournals.cast.org.cn/joweb/kygczz/EN/file/pic?fileId=seRpqoNiVtKzuWGeM8/PzA==, createTime=1772611067737, updateTime=1772611067737, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658910274131, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=minRunFlag, value=0, createTime=1772611067750, updateTime=1772611067750, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658876719693, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kygczz/EN/file/pic, createTime=1772611067742, updateTime=1772611067742, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658901885522, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=silenceFlag, value=0, createTime=1772611067748, updateTime=1772611067748, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658872525388, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1772611067741, updateTime=1772611067741, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658889302607, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=themeColor, value=null, createTime=1772611067745, updateTime=1772611067745, creator=18614031015, updator=18614031015), WebsiteProps(id=1235983658893496912, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1235982099262525932, code=themeStyle, value=null, createTime=1772611067746, updateTime=1772611067746, creator=18614031015, updator=18614031015)])], journalTitle=矿冶工程杂志, weixinUrl=null, journalUrl=http://www.kygczz.com/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Mining and Metallurgical Engineering, journalPhotoCn=sIAtluqp1t366oKMF09POA==, journalPhotoEn=8lFm/e3VFuRPvwuEPHk4Qg==, journalFirstLetter=M, 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=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kygczz/CN/10.3969/j.issn.0253-6099.2025.04.008, detailUrlEn=https://castjournals.cast.org.cn/joweb/kygczz/EN/10.3969/j.issn.0253-6099.2025.04.008, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kygczz/CN/PDF/10.3969/j.issn.0253-6099.2025.04.008, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kygczz/EN/PDF/10.3969/j.issn.0253-6099.2025.04.008, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进U-Net模型的露天矿钻孔裂隙识别研究
收藏切换
PDF下载
宋纹瑶 1 , 张梅 2 , 郭连军 1 , 邓丁 1 , 高崇 3 , 赵鑫 4
矿冶工程杂志 | 采矿 2025,45(4): 47-51
收起
收藏切换
矿冶工程杂志 | 采矿 2025, 45(4): 47-51
基于改进U-Net模型的露天矿钻孔裂隙识别研究
全屏
宋纹瑶1 , 张梅2, 郭连军1 , 邓丁1, 高崇3, 赵鑫4
作者信息
  • 1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870
  • 2.宣化科技职业学院,河北 张家口 075100
  • 3.中铁十九局集团有限公司,北京 100176
  • 4.中铁十九局集团矿业投资有限公司,北京 100161
  • 宋纹瑶(1995—),女,山东烟台人,硕士研究生,主要从事采矿工程相关方面的研究工作。E-mail:

通讯作者:

郭连军(1963—),男,辽宁北票人,博士,教授,主要从事采矿工程及爆破理论技术相关方面的研究工作。E-mail:
Recognition of Rock Fracture in Open-Pit Mines by Borehole Imaging Based on Improved U-Net Model
Wenyao SONG1 , Mei ZHANG2, Lianjun GUO1 , Ding DENG1, Chong GAO3, Xin ZHAO4
Affiliations
  • 1.School of Architecture and Civil Engineering, Shenyang University of Technology, Shenyang 110870, Liaoning, China
  • 2.Xuanhua Vocational College of Science and Technology, Zhangjiakou 075100, Hebei, China
  • 3.China Railway 19th Bureau Group Co., Ltd., Beijing 100176, China
  • 4.Mining Investment Co., Ltd., China Railway 19th Bureau Group, Beijing 100161, China
出版时间: 2025-08-01 doi: 10.3969/j.issn.0253-6099.2025.04.008
文章导航
收藏切换

为提高钻孔图像裂隙识别精度,提出了一种露天矿钻孔裂隙识别方法,利用智能钻孔摄像技术获取露天矿钻孔图像,并运用随机裁剪和图像翻转进行数据增广,同时采用中值滤波降噪和图像灰度化,去除噪点及减少计算量。在U-Net模型中利用空间注意力和通道注意力机制改进钻孔裂隙语义分割模型,形成AU-Net模型,以强化图像全局和局部信息的特征提取能力。实验结果表明:AU-Net模型相较于U-Net模型在钻孔图像裂隙识别数据集上可以取得更低的损失、更高的精度,均交并比提高了4.38百分点,达到82.34%,图像分割效果更好。

钻孔成像  /  裂隙识别  /  U-Net网络  /  注意力机制  /  裂隙提取  /  机器学习  /  语义分割  /  图像识别

To improve the accuracy of fracture recognition in borehole images, a borehole fracture recognition approach for open-pit mine was proposed. First, borehole images of an open-pit mine is obtained with an intelligent borehole inspection camera, and then data augmentation is performed by using random cropping and image flipping, while median filtering is used for noise reduction and images are converted to grayscalere, so as to eliminate noise and reduce computational complexity. Next, spatial attention and channel attention mechanisms are integrated into the U-Net model to improve the semantic segmentation model for fractures, forming an AU-Net model, which can enhance the model′s ability to extract features from both overall and local image information. Experimental results show that compared to the original U-Net model, the AU-Net model can achieve lower loss and higher accuracy in the fracture recognition dataset by borehole imaging. Specifically, the mean intersection over union is improved by 4.38 percentage points, up to 82.34%, bringing better image segmentation effect.

borehole imaging  /  fracture recognition  /  U-Net network  /  attention mechanism  /  fracture extraction  /  machine learning  /  semantic segmentation  /  image recognition
宋纹瑶, 张梅, 郭连军, 邓丁, 高崇, 赵鑫. 基于改进U-Net模型的露天矿钻孔裂隙识别研究. 矿冶工程杂志, 2025 , 45 (4) : 47 -51 . DOI: 10.3969/j.issn.0253-6099.2025.04.008
Wenyao SONG, Mei ZHANG, Lianjun GUO, Ding DENG, Chong GAO, Xin ZHAO. Recognition of Rock Fracture in Open-Pit Mines by Borehole Imaging Based on Improved U-Net Model[J]. Mining and Metallurgical Engineering, 2025 , 45 (4) : 47 -51 . DOI: 10.3969/j.issn.0253-6099.2025.04.008
露天金属矿山普遍采用台阶爆破进行开采,其爆破效果对后续采矿作业的顺利进行具有重要意义。理想的爆破效果不仅能有效提升矿石开采率,还能大幅减少能源与设备消耗、提高生产效率、降低生产成本[1]。爆破效果与岩体结构、特性密切相关。天然岩体展现出复杂的非均质性,内含众多软弱结构面,如岩屑面、层理、节理、裂隙及片理等,这些结构面的存在严重干扰了岩体整体构造,进而对爆破效果产生不利影响[2-3]。深入研究和充分考虑这些结构面对岩体性质的影响,对提高爆破效果和确保工程安全至关重要。
数字钻孔摄像技术作为一项可靠的数据采集工具,广泛应用于地下结构勘探、施工监控、矿藏勘探及水文地质研究等领域。该技术通过孔内摄像,精准捕捉孔壁图像,深入分析这些图像可获取关键岩体结构面的几何信息[4]。然而,岩体裂隙数量众多,且几何结构复杂多变,因此岩体裂隙识别一直是极具挑战的难题[5]。随着机器学习的快速发展,涌现出了一系列高精度模型,如U-Net、YOLOv5模型等,使图像分割的精细度不断提升。这些方法能够较为精确地分割裂隙区域,但在复杂背景裂隙图像中,其岩石裂隙识别精度尚未深入研究;且目前深度学习裂隙识别主要应用在路面裂隙与混凝土裂隙,对露天矿炮孔裂隙的识别较少。
本文采用深度学习算法进行钻孔图像裂隙识别,在原有U-Net模型编码器中加入空间注意力和通道注意力机制,探索提高图像分割精度和准确率的有效方法,为钻孔图像结构面识别提供参考。
U-Net网络以其在分割小目标方面表现良好和结构可扩展性等特点而著称,该网络整体结构[6]呈现U形,由编码器和解码器组成,如图1所示。前半部分负责从图像中提取特征图,后半部分负责将输出结果与前半部分融合构造。图像输入后,历经4次编码流程,每次均包含2次3×3卷积步骤及1次步长为2的2×2最大池化,由此生成一系列有效特征层。解码阶段每次包含2次3×3卷积及1次2×2卷积,且每次解码的输出都会与相应编码器生成的有效特征层进行融合,此融合结果随即作为下一次解码的输入。经过4次解码操作,网络输出结果通过1次1×1卷积操作生成。在解码过程中,通过上采样得到的特征图与编码部分对应的具有相同分辨率的有效特征层进行跳层拼接。这种设计有助于保留图像的细节信息,并提高分割精度。
U-Net网络是一种创新性的神经网络架构,其独特之处在于引入了跳跃连接和U形结构。通过巧妙融合不同层次的特征,包括基于像素、区域和边缘的特征,U-Net网络实现了更精准的目标定位和分类。这种网络结构在反卷积过程中采用U形设计,从而在提供更有效的先验信息的同时,确保了良好的特征传递。在损失函数的选择上,U-Net网络采用了交叉熵损失函数。相比于其他损失函数,交叉熵损失直接度量了模型预测与真实标签之间的差异,有效克服了梯度消失问题,有助于提高训练的稳定性和收敛速度,其计算公式为:
式中:L为交叉熵损失函数;N为总样本数;yi表示第i个样本的类别;^yi为第i个样本类别的预测值。
深度学习模型中广泛采用注意力机制,尤其在自然语言处理和计算机视觉领域备受关注。在计算机视觉中,注意力机制成功运用于图像分类、目标检测和图像生成等领域,使模型能够有针对性地专注于图像的重要区域。该机制的引入有助于提高模型的解释性和处理复杂关系的能力,使其在学术研究中成为一个重要的技术工具[7]。在深度学习中,注意力机制一般划分为空间、通道和混合3种类型,用于模型对输入的不同方面进行灵活关注。本文结合空间注意力与通道注意力形成混合注意力,可以关注通道特征以及像素本身的特征,使网络聚焦于有利的信息上。
本文将混合注意力机制应用到U-Net网络采样中,增强语义信息获取。图2为混合注意力机制模块的结构图。经过前置编码器给出的输入特征F,经过通道注意力得到中间特征Fm,再经过空间注意力最终得到输出特征F′。
现场选择GD3Q-GA型4D超清全智能孔内电视系统,包括主机、抗拉电缆、深度计数器、绞车和1 300万像素探头。该系统具有高度集成、大内存、稳定性卓越、真实图像清晰、快速测像等优势。
孔壁图像变换示意见图3。钻孔孔壁成像系统基于高分辨率传感器和光学探头,利用反射棱镜成像原理,能够展示钻孔孔壁的360°全景视图,即把从锥面反射镜拍摄下来的环状图像转换为孔壁展开图,图中字母表示方向。利用计算机控制图像的采集和处理,将模拟图像转换为数字形式并储存。控制系统确保系统稳定运行,而绞车和支架用于调整系统位置。
现场布置孔径250 mm、孔距7 m、孔深11~16 m、排距7 m。为了高效利用有限数据资源并提升模型训练成效,采用随机裁剪和图像翻转两种数据增广方法。首先,对采集图像随机裁剪,生成一系列尺寸为512像素×512像素、但涵盖原始图像不同区域的训练样本,既丰富样本多样性,又模拟了对象在视野中的不同位置,有助于模型从局部特征中识别整体对象。
在图像识别领域,水平翻转作为一种数据增强手段被广泛应用,在语义分割任务中具有重要意义[8]。它能够在不改变图像中物体形状和状态的前提下,有效保留图像的关键特征信息,同时引入更多可能的变化形式[9]。这种技术不仅丰富了训练数据的多样性,还在一定程度上提升了模型的鲁棒性,使其能够在图像水平方向发生翻转的情况下,依然能够准确识别物体的类别以及边界信息。钻孔图像水平翻转如图4所示。对裁剪后的图像进行水平翻转,进一步拓宽了数据集的多样性,促使模型更好地学习图像内容的方向无关性。运用上述方法后,163张原始图片扩展至326张图片。
原始图像是三通道彩色图像,每个像素由3个分量构成,每个分量取值范围为0~255,因此每个像素可呈现超过1 600万种颜色变化。为了减少计算复杂性,采用基于加权平均的图像灰度化法[10],将三通道彩色图像转换为单通道灰度图像,如图5所示。这一转换使得每个像素点的变化范围缩小至255种。
由于钻孔中地质条件复杂,在进行钻孔图像采集时,常受光反射条件、温度、摄像设备的传感器及自身电路等因素影响,使采集图片出现噪点,造成部分关键图像信息丢失,影响后续的裂隙识别。鉴于此,为了保证结构面信息识别的完整性,本文采用传统的滤波降噪[11]去除噪点。常用的滤波降噪方法有:均值滤波、中值滤波及双边滤波,如图6所示。
均值滤波是一种比较经典的线性滤波算法,通过计算图像中每个像素周围邻域内像素值的平均值来实现。这样的操作有助于模糊图像中不必要的细节和噪声,但会导致图像细节丢失,且对于某些类型的噪声(如椒盐噪声),其效果可能不佳。
中值滤波属于非线性灰度转换的数字平滑滤波器技术,该方法通过计算像素邻域内像素值的中值来替代目标像素值,以此实现图像的平滑处理。与均值滤波不同,中值滤波更适用于处理椒盐噪声等突发性噪声,因此它能有效地保留图像的细节信息。
双边滤波这种非线性的图像滤波方法结合了空间域和像素值域的信息,在图像去噪的同时能够保持图像的边缘和细节特征。但其滤波过程计算复杂度较高,耗费时间长。
图6可见,均值滤波所得图像更模糊,中值滤波和双边滤波降噪效果差距不大,都能较好地突出裂隙边缘的细节,整个图像比较清晰。但在处理过程中中值滤波速度较快,因此选用中值滤波对钻孔图像数据集进行降噪处理。
本文数据集共326张图片,其中训练数据集占总数的70%,验证数据集占30%。首先将图片进行视觉目标分类格式(VOC)标注,包含两类目标:将背景设置为黑色,将裂隙设置为红色,重点标注红色裂隙的轮廓,确保准确贴合实际形状,标注效果如图7所示。
两种模型训练时,将训练集的批尺寸设置为8,可以权衡计算机性能与模型训练效果。设定学习率初值为0.01,并采用学习率衰减机制,以动态调整学习率,从而更有效引导模型的训练进程。对模型进行迭代次数300次的批次训练,过少的迭代次数可能导致模型不能充分学习数据特征,而过高的迭代次数可能导致过拟合。
采用语义分割中常用的评价指标(包括精确率、召回率、调和平均数、均交并比以及训练损失和验证损失[12])来评价模型的去噪效果。其中,精确率(查准率)表示正确预测为正的样本占所有预测为正样本的比例。均交并比是语义分割的标准度量,用于评估模型的分割性能,通过计算真实值和预测值交集与并集的比值来进行衡量。计算公式为:
式中:P为精确率;TP为标签为正、预测为正;FP为标签为负、预测为正;M为均交并比;R为召回率;F为调和平均数;nii为类别i被正确预测为类别i的像素个数;nji为类别j被错误预测为类别i的像素个数;nij为类别i被错误预测为类别j的像素个数;k为像素点数量;ncls为包含背景的目标类别个数;ti为真实标签中目标类别i的总像素个数。
两种网络模型在相同的实验参数配置下进行训练,表1是两种模型的评价结果。AU-Net是在U-Net模型的基础进行改进,添加了空间注意力与通道注意力模块。
表1可以看出,两种深度学习模型的精确率、召回率、调和平均数均在86%以上,相差不大,这是由于精确率、召回率和调和平均数评价指标包括背景识别与目标识别两部分,而结构面图像中背景区域往往大于目标区域,且两者区域大小差别较大,通过准确分割大部分背景区域可以实现较高的精确率、召回率和调和平均数值。均交并比是一个良好评估模型分割性能的指标,AU-Net模型的均交并比为82.34%,较U-Net网络模型的均交并比(77.96%)高出4.38百分点,均交并比越高代表分割性能越好,说明AU-Net模型能提高分割效果。
图8是两种深度学习模型在本文数据集上的训练损失曲线图。两种模型的损失率最初呈现迅速下降趋势,最后都趋于平稳。其中AU-Net模型训练损失和验证损失的值更低。损失曲线表明,AU-Net模型的实际输出值与期望值吻合程度比U-Net模型的更优。
为验证模型可靠性,选用3组不同的孔壁图像输入训练好的模型中进行识别测试。图9是两种深度学习网络模型关于钻孔裂缝分割效果对比图。从图9可以看出,区域1中U-Net模型对复杂结构面中较细的部分识别效果差,区域2中U-Net模型分割出现了空洞和噪声,区域3中U-Net模型分割结构面时出现缺失要素的情况,而AU-Net模型能够全面具体地掌握结构面的特征信息,并未出现上述情况,说明AU-Net模型分割结构面时具有良好的稳定性。
1)使用超清全智能孔内电视对矿山钻孔进行数据采集,可以获得清晰的钻孔图像,进行图像灰度化和滤波图像处理,减少计算量和去除噪点,得到训练所需的数据集,为后续的语义精准分割奠定了基础。
2)在U-Net网络语义分割方法中融合了通道注意力与空间注意力模块,可以获取图像中的语义依赖关系。空间注意力机制避免了在连续的下采样过程中空间位置的丢失。它通过提取每层特征图的空间注意力矩阵,并将该矩阵应用于语义信息路径的相应特征图上,从而改善小目标的分割效果。
3)AU-Net模型的精确率为92.63%,均交并比为82.34%,比U-Net模型表现出更高的分割精度和精确率,且能有效减轻图像背景噪声对分割结果的影响。
  • 国家自然科学基金(51974187)
参考文献 引证文献
排序方式:
[1]
魏可心, 徐振洋, 王雪松, 等. 填塞长度对岩体爆破损伤效果的影响研究[J]. 矿冶工程, 2024, 44(3): 16-21.
WEI Kexin, XU Zhenyang, WANG Xuesong, et al. Influence of stemming length on damage effect of rock blasting[J]. Mining and Metallurgical Engineering, 2024, 44(3): 16-21.
[2]
熊成宇, 张建, 刘向阳, 等. 互层状围岩隧道切槽爆破破岩规律研究[J]. 矿冶工程, 2024, 44(6): 11-15.
XIONG Chengyu, ZHANG Jian, LIU Xiangyang, et al. Rock frag-mentation patterns in tunnels with interbedded surrounding rock by blasting with slotted blastholes[J]. Mining and Metallurgical Engineering, 2024, 44(6): 11-15.
[3]
傅鹏. 岩体结构面对台阶爆破效果影响研究[J]. 爆破, 2023, 40(1): 77-84.
FU Peng. Influence of rock mass structure on bench blasting effect[J]. Blasting, 2023, 40(1): 77-84.
[4]
赵兴东, 周鑫, 赵一凡, 等. 基于钻孔电视探测的井筒围岩块体识别及其稳定性分析方法[J]. 矿业研究与开发, 2022, 42(10): 169-172.
ZHAO Xingdong, ZHOU Xin, ZHAO Yifan, et al. Identification and stability analysis method of surrounding rock mass in shaft based on borehole TV detection[J]. Mining Research and Development, 2022, 42(10): 169-172.
[5]
葛云峰, 钟鹏, 唐辉明, 等. 基于钻孔图像的岩体结构面几何信息智能测量[J]. 岩土力学, 2019, 40(11): 4467-4476.
GE Yunfeng, ZHONG Peng, TANG Huiming, et al. Intelligent measurement on geometric information of rock discontinuities based on borehole image[J]. Rock and Soil Mechanics, 2019, 40(11): 4467-4476.
[6]
王川婴, 邹先坚, 韩增强, 等. 基于特征函数的钻孔图像结构面识别方法[J]. 岩土力学, 2017, 38(10): 3062-3066.
WANG Chuanying, ZOU Xianjian, HAN Zengqiang, et al. Recognition of structural planes in borehole image based on characteristic function[J]. Rock and Soil Mechanics, 2017, 38(10): 3062-3066.
[7]
宋琨, 孙驰, 安冬, 等. 数字钻孔全景影像中结构面特征智能识别方法[J]. 地质科技通报, 2020, 39(5): 17-22.
SONG Kun, SUN Chi, AN Dong, et al. Intelligent identification method for rock discontinuities properties by digital borehole panoramic images[J]. Bulletin of Geological Science and Technology, 2020, 39(5): 17-22.
[8]
吴天雨, 许英朝, 晁鹏飞. 一种提高目标图像识别准确率的数据增强技术[J]. 激光杂志, 2020, 41(5): 96-100.
WU Tianyu, XU Yingchao, CHAO Pengfei. Data augmentation technology for improving target image recognition[J]. Laser Journal, 2020, 41(5): 96-100.
[9]
李永盛, 何佳洲, 刘义海, 等. 基于图像检测识别的数据增强技术[J]. 舰船电子对抗, 2021, 44(1): 66-70.
LI Yongsheng, HE Jiazhou, LIU Yihai, et al. Data enhancement technology based on image detection and recognition[J]. Shipboard Electronic Countermeasure, 2021, 44(1): 66-70.
[10]
白茹鑫, 栾尚敏. 图像处理中应用图像降噪算法的研究综述[J]. 现代信息科技, 2024, 8(10): 21-25.
BAI Ruxin, LUAN Shangmin. Research review of the application of image denoising algorithms in image processing[J]. Modern Information Technology, 2024, 8(10): 21-25.
[11]
郭昕刚, 许连杰, 霍金花, 等. 基于非局部自相似性的图像去噪算法研究[J]. 计算机仿真, 2022, 39(9): 364-369.
GUO Xingang, XU Lianjie, HUO Jinhua, et al. Research on image denoising algorithm based on non-local self-similarity[J]. Computer Simulation, 2022, 39(9): 364-369.
[12]
张蕊, 孟晓曼, 曾志远, 等. 图卷积神经网络在点云语义分割中的研究综述[J]. 计算机工程与应用, 2022, 58(24): 29-46.
ZHANG Rui, MENG Xiaoman, ZENG Zhiyuan, et al. Review of graph convolutional neural networks in point cloud semantic segmentation[J]. Computer Engineering and Applications, 2022, 58(24): 29-46.
2025年第45卷第4期
PDF下载
62
27
引用本文
BibTeX
文章信息
doi: 10.3969/j.issn.0253-6099.2025.04.008
  • 接收时间:2025-01-28
  • 首发时间:2026-03-05
  • 出版时间:2025-08-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-01-28
基金
国家自然科学基金(51974187)
作者信息
    1.沈阳工业大学 建筑与土木工程学院,辽宁 沈阳 110870
    2.宣化科技职业学院,河北 张家口 075100
    3.中铁十九局集团有限公司,北京 100176
    4.中铁十九局集团矿业投资有限公司,北京 100161

通讯作者:

郭连军(1963—),男,辽宁北票人,博士,教授,主要从事采矿工程及爆破理论技术相关方面的研究工作。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kygczz/CN/10.3969/j.issn.0253-6099.2025.04.008
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