Article(id=1251559137763602470, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1251559134307500754, articleNumber=null, orderNo=null, doi=10.3981/j.issn.1000-7857.2025.12.00121, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1765296000000, receivedDateStr=2025-12-10, revisedDate=1772294400000, revisedDateStr=2026-03-01, acceptedDate=null, acceptedDateStr=null, onlineDate=1776324551286, onlineDateStr=2026-04-16, pubDate=1774627200000, pubDateStr=2026-03-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1776324551286, onlineIssueDateStr=2026-04-16, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1776324551286, creator=13701087609, updateTime=1776324551286, updator=13701087609, issue=Issue{id=1251559134307500754, tenantId=1146029695717560320, journalId=1146031591421210625, year='2026', volume='44', issue='6', pageStart='1', pageEnd='112', issueExtLink='null', onlineDate='null', pubDate='1774627200000', pubDateStr='2026-03-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1776324550463, creator='13701087609', updateTime=1776332259412, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1251591468125733729, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1251559134307500754, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1251591468125733730, tenantId=1146029695717560320, journalId=1146031591421210625, issueId=1251559134307500754, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=76, endPage=82, ext={EN=ArticleExt(id=1251559138149478441, articleId=1251559137763602470, tenantId=1146029695717560320, journalId=1146031591421210625, language=EN, title=An open−pit mine segmentation method based on SAM and prompt learning, columnId=1150494642224591153, journalTitle=Science & Technology Review, columnName=Exclusive, runingTitle=null, highlight=null, articleAbstract=

Accurately acquiring the spatial distribution of open−pit mines is vital for "green mine" development and dynamic geological monitoring. To overcome the inherent challenges of dataset scarcity, drastic intra− and inter−class differences, and complex topological structures in this field, we propose a segmentation framework integrating hybrid semantic prompting and topological awareness. We constructed a specific dataset named Mine Semantic Segmentation (MSS). MSS contains 7,622 finely annotated images of open−pit mines. Based on MSS, we propose an instance segmentation method called Mine Segment Anything Model (Mine−SAM). Mine−SAM employs a dual−encoder structure. It also utilizes multi−scale feature aggregation techniques. The model couples global context from foundation models with local fine−grained features from expert models. Mine−SAM achieved an Average Precision box (PA,box) of 64.4%. The Average Precision mask (PA,mask) score reached 65.2%. In addition, we developed a semantic segmentation method named SemMSeg. This method combines graph convolutional networks (GCN) with pixel−level contrastive learning. The GCN captures spatial dependencies among mining elements. It also enforces structural constraints within the model. SemMSeg achieved an Intersection over Union (IoU) of 73.38%. The precision of the method reached 85.03%. These techniques provide a technical path for automatic mine monitoring. The findings contribute to the intelligent interpretation of remote sensing imagery.

, authors=null, authorsList=Mingze SUN, Jun WANG, Wanqiu ZHANG, Kun LIU, Gang LIN, authorCompany=null, correspAuthors=Wanqiu ZHANG, Gang LIN, authorNote=null, correspAuthorsNote=null, copyrightStatement=All rights reserved. Unauthorized reproduction is prohibited., 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, fund=null), CN=ArticleExt(id=1251559140724781137, articleId=1251559137763602470, tenantId=1146029695717560320, journalId=1146031591421210625, language=CN, title=基于SAM和提示学习的露天矿山分割方法, columnId=1150494642375586098, journalTitle=科技导报, columnName=特色专题, runingTitle=null, highlight=null, articleAbstract=

精准获取露天矿山的空间分布信息,是推进“绿色矿山”建设与地质环境动态监测的关键前提,为克服露天矿山分割领域中数据集缺乏、类内类间差距大和拓扑结构复杂的问题,提出一种融合混合语义提示与拓扑感知的分割框架。构建了包含7622张精细标注影像的矿山语义分割数据集(mine semantic segmentation,MSS),并提出了融合双编码器结构与多尺度特征聚合的混合语义提示实例分割方法(mine segment anything model,Mine−SAM),将基础模型的全局上下文与专家模型的局部细粒度特征深度耦合,该方法在目标检测平均精度(average precision box,PA,box)和实例分割平均精度(average precision mask,PA,mask)指标上分别达到64.4%和65.2%;同时开发了结合图卷积网络与像素级对比学习的语义分割方法(semantic mine segmentation,SemMSeg),通过图卷积网络捕捉矿区要素间的空间依赖与结构约束,实现了交并比(intersection over union,IoU)73.38%和精确度(Precision)85.03%的分割精度,为露天矿山自动监测提供了可靠技术路径,对推动遥感图像智能解译具有不可或缺的应用价值。

, authors=

孙铭泽,硕士研究生,研究方向为矿区生态修复,电子信箱:

, authorsList=孙铭泽, 王军, 张婉秋, 刘琨, 林刚, authorCompany=null, correspAuthors=张婉秋, 林刚, authorNote=null, correspAuthorsNote=
张婉秋(通信作者),博士研究生,研究方向为矿区生态修复,电子信箱:;
林刚(通信作者),副研究员,研究方向为矿山资源综合利用、资源耦合系统建模等,电子信箱:
, copyrightStatement=版权所有,未经授权,不得转载。, copyrightOwner=《科技导报》编辑部, extLink=null, articleAbsUrl=null, sourceXml=gutyzLiTVTh5+THFMRjiag==, magXml=DxH5mvJmbyVFLYqR/9x7YA==, pdfUrl=null, pdf=2posH81xXxcU7hLgYmAKKw==, pdfFileSize=6636439, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=lH5tOQvpyiNlO3/WHcFauQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Z/spGL+GhXFBjcjppOwK5A==, mapNumber=null, fund=null)}, authors=[Author(id=1251567855968399563, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=35986138@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251567856090034384, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567855968399563, language=EN, stringName=Mingze SUN, firstName=Mingze, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567856387829976, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567855968399563, language=CN, stringName=孙铭泽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1山东建筑大学土木工程学院,济南 250101, bio={"content":"

孙铭泽,硕士研究生,研究方向为矿区生态修复,电子信箱:

"}, bioImg=null, bioContent=

孙铭泽,硕士研究生,研究方向为矿区生态修复,电子信箱:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855393779878, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=1, ext=[AuthorCompanyExt(id=1251567855406362791, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1251567855414751400, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1山东建筑大学土木工程学院,济南 250101)])]), Author(id=1251567856488493276, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, 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=1251567858078134497, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567856488493276, language=EN, stringName=Jun WANG, firstName=Jun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858162020582, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567856488493276, language=CN, stringName=王军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1山东建筑大学土木工程学院,济南 250101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855393779878, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=1, ext=[AuthorCompanyExt(id=1251567855406362791, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1251567855414751400, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1山东建筑大学土木工程学院,济南 250101)])]), Author(id=1251567858250100969, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=BQT2200204006T@student.cumtb.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1251567858338181356, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858250100969, language=EN, stringName=Wanqiu ZHANG, firstName=Wanqiu, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858426261744, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858250100969, language=CN, stringName=张婉秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855527997615, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=2, ext=[AuthorCompanyExt(id=1251567855536386223, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855527997615, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China), AuthorCompanyExt(id=1251567855544774832, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855527997615, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083)])]), Author(id=1251567858518536433, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, 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=1251567858619199734, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858518536433, language=EN, stringName=Kun LIU, firstName=Kun, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858694697207, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858518536433, language=CN, stringName=刘琨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3自然资源部国土卫星遥感应用中心,北京 100048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855637049525, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=3, ext=[AuthorCompanyExt(id=1251567855645438135, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855637049525, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China), AuthorCompanyExt(id=1251567855649632440, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855637049525, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3自然资源部国土卫星遥感应用中心,北京 100048)])]), Author(id=1251567858761806075, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lingang@igsnrr.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1251567858845692160, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858761806075, language=EN, stringName=Gang LIN, firstName=Gang, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, 5, *, address=4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
5College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858929578243, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858761806075, language=CN, stringName=林刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, 5, *, address=4中国科学院地理科学与资源研究所,北京 100101
5中国科学院大学资源环境学院,北京 100049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855733518524, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=4, ext=[AuthorCompanyExt(id=1251567855746101438, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855733518524, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China), AuthorCompanyExt(id=1251567855754490047, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855733518524, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4中国科学院地理科学与资源研究所,北京 100101)]), AuthorCompany(id=1251567855855153348, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=5, ext=[AuthorCompanyExt(id=1251567855863541955, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855855153348, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China), AuthorCompanyExt(id=1251567855871930564, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855855153348, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5中国科学院大学资源环境学院,北京 100049)])])], keywords=[Keyword(id=1251567859088961802, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, orderNo=1, keyword=open−pit mine segmentation), Keyword(id=1251567859193819406, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, orderNo=2, keyword=instance segmentation), Keyword(id=1251567859273511186, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, orderNo=3, keyword=prompt learning), Keyword(id=1251567859378368792, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, orderNo=4, keyword=graph convolution network), Keyword(id=1251567859483226400, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, orderNo=1, keyword=露天矿山分割), Keyword(id=1251567859588084006, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, orderNo=2, keyword=实例分割), Keyword(id=1251567859671970092, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, orderNo=3, keyword=提示学习), Keyword(id=1251567859739078963, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, orderNo=4, keyword=图卷积网络)], refs=[Reference(id=1251567863476203914, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2024, volume=16, issue=5, pageStart=789, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Meng X L, Zhang D, Dong S J, journalName=Remote Sensing, refType=null, unstructuredReference=Meng X L, Zhang D, Dong S J, et al. Open−pit granite mining area extraction using UAV aerial images and the novel GIPNet[J]. Remote Sensing, 2024, 16(5): 789., articleTitle=Open−pit granite mining area extraction using UAV aerial images and the novel GIPNet, refAbstract=null), Reference(id=1251567863568478604, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2024, volume=16, issue=24, pageStart=4648, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Li Z B, Zhao Y L, Ren H, journalName=Remote Sensing, refType=null, unstructuredReference=Li Z B, Zhao Y L, Ren H, et al. A novel index for detecting bare coal in open−pit mining areas based on Landsat imagery[J]. Remote Sensing, 2024, 16(24): 4648., articleTitle=A novel index for detecting bare coal in open−pit mining areas based on Landsat imagery, refAbstract=null), Reference(id=1251567863673336205, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=14, pageStart=6384, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Qiao Q H, Li Y Y, Lü H Q, journalName=Applied Sciences, refType=null, unstructuredReference=Qiao Q H, Li Y Y, H Q. Open−pit mining area extraction using multispectral remote sensing images: A deep learning extraction method based on Transformer[J]. Applied Sciences, 2024, 14(14): 6384., articleTitle=Open−pit mining area extraction using multispectral remote sensing images: A deep learning extraction method based on Transformer, refAbstract=null), Reference(id=1251567863732056461, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2022, volume=31, issue=7, pageStart=102, pageEnd=111, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=宋仁忠, 郑慧玉, 王党朝, journalName=中国矿业, refType=null, unstructuredReference=宋仁忠, 郑慧玉, 王党朝, . 基于深度学习和高分辨率遥感影像的露天矿地物分类方法[J]. 中国矿业, 2022, 31(7): 102-111., articleTitle=基于深度学习和高分辨率遥感影像的露天矿地物分类方法, refAbstract=null), Reference(id=1251567863811748239, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2023, volume=36, issue=6, pageStart=5, pageEnd=10,16, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=李茹, 鲁海峰, journalName=唐山学院学报, refType=null, unstructuredReference=李茹, 鲁海峰. 基于多尺度卷积神经网络的矿山监控图像识别研究[J]. 唐山学院学报, 2023, 36(6): 5-10,16., articleTitle=基于多尺度卷积神经网络的矿山监控图像识别研究, refAbstract=null), Reference(id=1251567863895634321, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2023, volume=61, issue=null, pageStart=4401220, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Zhou G D, Xu J H, Chen W T, journalName=IEEE Transactions on Geoscience and Remote Sensing, refType=null, unstructuredReference=Zhou G D, Xu J H, Chen W T, et al. Deep feature enhancement method for land cover with irregular and sparse spatial distribution features: A case study on open−pit mining[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 4401220., articleTitle=Deep feature enhancement method for land cover with irregular and sparse spatial distribution features: A case study on open−pit mining, refAbstract=null), Reference(id=1251567863971131795, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2024, volume=14, issue=1, pageStart=9716, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=Wang Y, Yang L, Liu X, journalName=Scientific Reports, refType=null, unstructuredReference=Wang Y, Yang L, Liu X, et al. An improved semantic segmentation algorithm for high−resolution remote sensing images based on DeepLabv3[J]. Scientific Reports, 2024, 14(1): 9716., articleTitle=An improved semantic segmentation algorithm for high−resolution remote sensing images based on DeepLabv3, refAbstract=null), Reference(id=1251567864055017877, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2023, volume=15, issue=20, pageStart=4949, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=Silva M, Hermosilla G, Villavicencio G, journalName=Remote Sensing, refType=null, unstructuredReference=Silva M, Hermosilla G, Villavicencio G, et al. Automated detection and analysis of massive mining waste deposits using sentinel−2 satellite imagery and artificial intelligence[J]. Remote Sensing, 2023, 15(20): 4949., articleTitle=Automated detection and analysis of massive mining waste deposits using sentinel−2 satellite imagery and artificial intelligence, refAbstract=null), Reference(id=1251567864122126743, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=21, pageStart=3474, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=Wang C S, Chang L L, Zhao L R, journalName=Remote Sensing, refType=null, unstructuredReference=Wang C S, Chang L L, Zhao L R, et al. Automatic identification and dynamic monitoring of open−pit mines based on improved mask R−CNN and transfer learning[J]. Remote Sensing, 2020, 12(21): 3474., articleTitle=Automatic identification and dynamic monitoring of open−pit mines based on improved mask R−CNN and transfer learning, refAbstract=null), Reference(id=1251567864185041304, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2024, volume=17, issue=null, pageStart=16476, pageEnd=16486, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=Zhu Y Q, Chen W T, He W X, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Zhu Y Q, Chen W T, He W X, et al. CUG_MISDataset: A remote sensing instance segmentation dataset for improved wide−area high−precision mining land occupation recognition[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 16476-16486., articleTitle=CUG_MISDataset: A remote sensing instance segmentation dataset for improved wide−area high−precision mining land occupation recognition, refAbstract=null), Reference(id=1251567864268927387, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=1, pageStart=107, pageEnd=115, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=王寅达, 陈嘉辉, 彭玲, journalName=中国科学院大学学报(中英文), refType=null, unstructuredReference=王寅达, 陈嘉辉, 彭玲, . 高分辨率关系图卷积网络遥感语义分割方法[J]. 中国科学院大学学报(中英文), 2025, 42(1): 107-115., articleTitle=高分辨率关系图卷积网络遥感语义分割方法, refAbstract=null), Reference(id=1251567864365396380, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2025, volume=18, issue=null, pageStart=17622, pageEnd=17637, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=Li X J, Kong P, Chen W T, journalName=IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, refType=null, unstructuredReference=Li X J, Kong P, Chen W T, et al. EDG−Net: Edge−enhanced dynamic graph convolutional network for remote sensing scene classification of mining−disturbed land[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 17622-17637., articleTitle=EDG−Net: Edge−enhanced dynamic graph convolutional network for remote sensing scene classification of mining−disturbed land, refAbstract=null), Reference(id=1251567864461865373, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2025, volume=40, issue=1, pageStart=2583334, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=Zheng G X, Jiang Z G, Zhang H, journalName=Geocarto International, refType=null, unstructuredReference=Zheng G X, Jiang Z G, Zhang H. HRRF: A hierarchical recursive reasoning framework for high−resolution remote sensing semantic segmentation[J]. Geocarto International, 2025, 40(1): 2583334., articleTitle=HRRF: A hierarchical recursive reasoning framework for high−resolution remote sensing semantic segmentation, refAbstract=null), Reference(id=1251567864558334369, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Kirillov A, Mintun E, Ravi N, et al. Segment anything[C]//Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2024: 3992−4003., articleTitle=null, refAbstract=null), Reference(id=1251567864629637537, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu T, Feng R S, Feng R Y, et al. Inpaint anything: Segment anything meets image inpainting[EB/OL]. 2023: arXiv: 2304.06790. https://arxiv.org/abs/2304.06790., articleTitle=null, refAbstract=null), Reference(id=1251567864721912229, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2025, volume=51, issue=11, pageStart=76, pageEnd=86, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=李天文, 童星, 李俊涛, journalName=工矿自动化, refType=null, unstructuredReference=李天文, 童星, 李俊涛, . 面向露天矿山无人机遥感影像机械小目标识别的CDMG−YOLO模型[J]. 工矿自动化, 2025, 51(11): 76-86., articleTitle=面向露天矿山无人机遥感影像机械小目标识别的CDMG−YOLO模型, refAbstract=null), Reference(id=1251567864805798311, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2026, volume=31, issue=1, pageStart=212, pageEnd=242, url=null, language=null, rfNumber=[17], rfOrder=16, authorNames=陈诗琪, 杨学, 朱荣强, journalName=中国图象图形学报, refType=null, unstructuredReference=陈诗琪, 杨学, 朱荣强, . 面向遥感图像解译的参数高效微调研究综述[J]. 中国图象图形学报, 2026, 31(1): 212-242., articleTitle=面向遥感图像解译的参数高效微调研究综述, refAbstract=null), Reference(id=1251567864872907177, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Bolya D, Zhou C, Xiao F Y, et al. YOLACT: Real−time instance segmentation[C]//Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2019: 9156−9165., articleTitle=null, refAbstract=null), Reference(id=1251567864948404651, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=2, pageStart=1011, pageEnd=1024, url=null, language=null, rfNumber=[19], rfOrder=18, authorNames=董霁红, 王立兵, 冯晓彤, journalName=煤炭学报, refType=null, unstructuredReference=董霁红, 王立兵, 冯晓彤, . 黄河流域煤炭−煤电−煤化工场地特征精准智能识别方法及应用[J]. 煤炭学报, 2024, 49(2): 1011-1024., articleTitle=黄河流域煤炭−煤电−煤化工场地特征精准智能识别方法及应用, refAbstract=null), Reference(id=1251567865040679342, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu E J, Shen Y L, Wallis P, et al. LoRA: Low−rank adaptation of large language models[EB/OL]. 2021: arXiv: 2106.09685. https://arxiv.org/abs/2106.09685., articleTitle=null, refAbstract=null), Reference(id=1251567865111982514, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu J D, Ji W, Liu Y P, et al. Medical SAM adapter: Adapting segment anything model for medical image segmentation[EB/OL]. 2023: arXiv: 2304.12620. https://arxiv.org/abs/2304.12620., articleTitle=null, refAbstract=null), Reference(id=1251567865216840116, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=He K M, Gkioxari G, Dollár P, et al. Mask R−CNN[C]//Proceedings of IEEE International Conference on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2017: 2980−2988., articleTitle=null, refAbstract=null), Reference(id=1251567865283948981, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen K, Pang J M, Wang J Q, et al. Hybrid task cascade for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 4969−4978., articleTitle=null, refAbstract=null), Reference(id=1251567865351057848, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Cheng B W, Misra I, Schwing A G, et al. Masked−attention mask transformer for universal image segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2022: 1280−1289., articleTitle=null, refAbstract=null), Reference(id=1251567866965864891, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U−Net: Convolutional networks for biomedical image segmentation[M]. Medical Image Computing and Computer−Assisted Intervention–MICCAI 2015. Cham: Springer International Publishing, 2015: 234−241., articleTitle=null, refAbstract=null), Reference(id=1251567867045556670, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao H S, Shi J P, Qi X J, et al. Pyramid scene parsing network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 6230−6239., articleTitle=null, refAbstract=null), Reference(id=1251567867116859841, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen L C, Zhu Y K, Papandreou G, et al. Encoder−decoder with atrous separable convolution for semantic image s egmentation[M]. Computer Vision–ECCV 2018. Cham: Springer International Publishing, 2018: 833−851., articleTitle=null, refAbstract=null)], funds=[Fund(id=1251567863115493761, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, awardId=2023YFE0208000, language=CN, fundingSource=国家重点研发计划项目(2023YFE0208000), fundOrder=null, country=null), Fund(id=1251567863199379843, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, awardId=42202280, language=CN, fundingSource=国家青年科学基金项目(42202280), fundOrder=null, country=null), Fund(id=1251567863291654532, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, awardId=42571497, language=CN, fundingSource=国家自然科学基金面上项目(42571497), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1251567855393779878, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=1, ext=[AuthorCompanyExt(id=1251567855406362791, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1251567855414751400, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1山东建筑大学土木工程学院,济南 250101)]), AuthorCompany(id=1251567855527997615, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=2, ext=[AuthorCompanyExt(id=1251567855536386223, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855527997615, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China), AuthorCompanyExt(id=1251567855544774832, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855527997615, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083)]), AuthorCompany(id=1251567855637049525, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=3, ext=[AuthorCompanyExt(id=1251567855645438135, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855637049525, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China), AuthorCompanyExt(id=1251567855649632440, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855637049525, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3自然资源部国土卫星遥感应用中心,北京 100048)]), AuthorCompany(id=1251567855733518524, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=4, ext=[AuthorCompanyExt(id=1251567855746101438, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855733518524, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China), AuthorCompanyExt(id=1251567855754490047, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855733518524, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4中国科学院地理科学与资源研究所,北京 100101)]), AuthorCompany(id=1251567855855153348, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=5, ext=[AuthorCompanyExt(id=1251567855863541955, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855855153348, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China), AuthorCompanyExt(id=1251567855871930564, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855855153348, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5中国科学院大学资源环境学院,北京 100049)])], figs=[ArticleFig(id=1251567859915239736, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=w1tGnVGg98MFG/VhOeeFwQ==, figureFileBig=NqgTV/2aN41X065w7zOr9A==, tableContent=null), ArticleFig(id=1251567859994931517, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=图1, caption=基于混合语义提示的SAM改进框架, figureFileSmall=w1tGnVGg98MFG/VhOeeFwQ==, figureFileBig=NqgTV/2aN41X065w7zOr9A==, tableContent=null), ArticleFig(id=1251567860171092292, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=JLIDun5M6FsiQx77u/Pe1g==, figureFileBig=8FWPdZUOBgNnoCY+i68HTQ==, tableContent=null), ArticleFig(id=1251567860254978376, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=图2, caption=结合图卷积与像素级对比学习的语义分割整体网络框架, figureFileSmall=JLIDun5M6FsiQx77u/Pe1g==, figureFileBig=8FWPdZUOBgNnoCY+i68HTQ==, tableContent=null), ArticleFig(id=1251567860368224591, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=52n4o6lxT0+5h6SRZCaH2w==, figureFileBig=USruT0UkF+LM8QtBL/yPsg==, tableContent=null), ArticleFig(id=1251567860443722068, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=图3, caption=在MSS数据集上的可视化实验, figureFileSmall=52n4o6lxT0+5h6SRZCaH2w==, figureFileBig=USruT0UkF+LM8QtBL/yPsg==, tableContent=null), ArticleFig(id=1251567860531802455, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=bKWbqknpuDtCA0rVFcEueQ==, figureFileBig=LM8aSHdmuMcksjfEPOSybg==, tableContent=null), ArticleFig(id=1251567860615688537, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=图4, caption=MSS数据集上的可视化实验, figureFileSmall=bKWbqknpuDtCA0rVFcEueQ==, figureFileBig=LM8aSHdmuMcksjfEPOSybg==, tableContent=null), ArticleFig(id=1251567860745711967, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
方法${{{P}_{\text{A,}\text{box}}}} $$ {{{P}_{\text{A,}\text{box}}^{\text{50}}} }$$ {{{P}_{\text{A,}\text{box}}^{\text{75}}}} $${{ {P}_{\text{A,mask}}}} $$ {{{P}_{\text{A}\text{,}\text{mask}}^{\text{50}}}} $${{ P_{\text{A,mask}}^{\text{75}}}} $
Mask R−CNN[22]59.877.768.756.078.469.0
HTC[23]61.679.070.060.979.370.5
Mask2Former[24]62.478.570.262.379.771.4
SAM−seg (Mask R−CNN)63.380.873.763.180.972.9
RSPrompter−anchor62.281.171.355.680.263.9
Mine−SAM64.481.273.765.281.873.5
), ArticleFig(id=1251567860863152483, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=表1, caption=

在MSS数据集上的实例分割对比实验(单位/%)

, figureFileSmall=null, figureFileBig=null, tableContent=
方法${{{P}_{\text{A,}\text{box}}}} $$ {{{P}_{\text{A,}\text{box}}^{\text{50}}} }$$ {{{P}_{\text{A,}\text{box}}^{\text{75}}}} $${{ {P}_{\text{A,mask}}}} $$ {{{P}_{\text{A}\text{,}\text{mask}}^{\text{50}}}} $${{ P_{\text{A,mask}}^{\text{75}}}} $
Mask R−CNN[22]59.877.768.756.078.469.0
HTC[23]61.679.070.060.979.370.5
Mask2Former[24]62.478.570.262.379.771.4
SAM−seg (Mask R−CNN)63.380.873.763.180.972.9
RSPrompter−anchor62.281.171.355.680.263.9
Mine−SAM64.481.273.765.281.873.5
), ArticleFig(id=1251567860972204392, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
$ {{{{U}}_{\text{Box}}}} $$ {{{{U}}_{\text{Mask}}}} $${{ {{F}}_{\text{SAM}}}} $${{ {{F}}_{\text{Seg}} }}$$ {{{{F}}_{\text{agg}} }}$$ {{{{P}}_{\text{A,}\text{box}} }}$/%$ {{{{P}}_{\text{A,}\text{ma}\text{sk}}}} $/%
注:“√”表示模型中引入了该组件;空白表示未引入该组件。
63.164.7
59.358.2
56.157.2
60.761.3
58.359.1
59.661.6
61.863.7
63.464.2
64.465.2
), ArticleFig(id=1251567862545068397, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=表2, caption=

在MSS数据集上的Mine−SAM组件消融实验

, figureFileSmall=null, figureFileBig=null, tableContent=
$ {{{{U}}_{\text{Box}}}} $$ {{{{U}}_{\text{Mask}}}} $${{ {{F}}_{\text{SAM}}}} $${{ {{F}}_{\text{Seg}} }}$$ {{{{F}}_{\text{agg}} }}$$ {{{{P}}_{\text{A,}\text{box}} }}$/%$ {{{{P}}_{\text{A,}\text{ma}\text{sk}}}} $/%
注:“√”表示模型中引入了该组件;空白表示未引入该组件。
63.164.7
59.358.2
56.157.2
60.761.3
58.359.1
59.661.6
61.863.7
63.464.2
64.465.2
), ArticleFig(id=1251567862633148785, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
方法IoUF1−scorePrecisionRecall
U−Net[25]63.6377.7876.2679.36
PSPNet[26]66.6980.0277.4882.73
DeepLabv3+[27]71.3183.2682.1084.44
SemMSeg73.3884.6585.0385.06
), ArticleFig(id=1251567862742200694, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=表3, caption=

在MSS数据集上的语义分割对比试验(单位/%)

, figureFileSmall=null, figureFileBig=null, tableContent=
方法IoUF1−scorePrecisionRecall
U−Net[25]63.6377.7876.2679.36
PSPNet[26]66.6980.0277.4882.73
DeepLabv3+[27]71.3183.2682.1084.44
SemMSeg73.3884.6585.0385.06
), ArticleFig(id=1251567862863835513, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
图卷
MLP
FFN
IoU/
%
F1−score/
%
Precision/
%
Recall/
%
注:“√”表示模型中引入了该组件;空白表示未引入该组件。
67.5280.6182.0879.2
69.0281.6782.2381.12
69.2981.8683.1183.69
73.3884.6585.0385.06
), ArticleFig(id=1251567862968693115, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, language=CN, label=表4, caption=

在MSS数据集上的拓扑结构解析模块消融实验

, figureFileSmall=null, figureFileBig=null, tableContent=
图卷
MLP
FFN
IoU/
%
F1−score/
%
Precision/
%
Recall/
%
注:“√”表示模型中引入了该组件;空白表示未引入该组件。
67.5280.6182.0879.2
69.0281.6782.2381.12
69.2981.8683.1183.69
73.3884.6585.0385.06
)], attaches=null, journal=Journal(id=1125356956822126595, delFlag=0, nameCn=科技导报, nameEn=Science & Technology Review, nameHistory1=null, nameHistory2=null, issn=1000-7857, eissn=, cn=11-1421/N, coden=null, periodic=3, language=CN, oaType=0, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=wfghvu3bhh/dKxuZ+ucVHA==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Rev, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1784015846012, createdBy=null, updatedBy=13041195026, firstLetterCn=K, firstLetterEn=K, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=wfghvu3bhh/dKxuZ+ucVHA==, picEn=yjSfclmpNm7ihn9NbTZ69g==, jcr=null, cjcr=null, exts=[JournalExt(id=1283818766098219763, language=CN, name=科技导报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国科学技术协会, publishedBy=科技导报社, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.kjdb.org/CN/home, createdTime=1784015846037, updatedTime=1784015846037, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.kjdb.org/CN/column/column7.shtml, submissionAuthorUrl=https://kjdbauthor.cast.org.cn/webm, submissionEditorUrl=https://kjdbeditor.cast.org.cn/webm/, submissionReviewUrl=https://kjdbauthor.cast.org.cn/webm, submissionCeEditorUrl=https://kjdbeditor.cast.org.cn/webm/, submissionAeEditorUrl=https://kjdbeditor.cast.org.cn/webm/, option={"copyright":""}), JournalExt(id=1283818766144357108, language=EN, name=Science & Technology Review, 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=http://www.kjdb.org/EN/home, createdTime=1784015846048, updatedTime=1784015846048, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.kjdb.org/EN/column/column7.shtml, submissionAuthorUrl=https://kjdbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://kjdbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://kjdbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031591421210625, websiteList=[Website(id=1146104741081231361, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031591421210625, 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/kjdb/CN, language=CN, createTime=1751182263881, createBy=18614031015, updateTime=1751778001962, updateBy=18614031015, name=科技导报, tplId=1146099689490845704, title=科技导报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148021146403992296, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=articleTextType, value=kx, createTime=1751639170504, updateTime=1751639170504, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146378826469, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=banner, value=null, createTime=1751639170498, updateTime=1751639170498, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146366243556, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=9GHSf7eGlIPH0Tv/OOdstA==, createTime=1751639170495, updateTime=1751639170495, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146395603687, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751639170502, updateTime=1751639170502, creator=18614031015, updator=18614031015), WebsiteProps(id=1148021146387215078, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146104741081231361, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751639170500, updateTime=1751639170500, creator=18614031015, updator=18614031015)]), Website(id=1146105254833139715, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031591421210625, 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/kjdb/EN, language=EN, createTime=1751182386363, createBy=18614031015, updateTime=1753500121937, updateBy=18614031015, name=科技导报, tplId=1146101810881728533, title=Science & Technology Review, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155838567709528217, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=articleTextType, value=kx, createTime=1753502988984, updateTime=1753502988984, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567692750998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=banner, value=null, createTime=1753502988980, updateTime=1753502988980, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567688556693, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic?fileId=9GHSf7eGlIPH0Tv/OOdstA==, createTime=1753502988979, updateTime=1753502988979, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567705333912, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/EN/file/pic, createTime=1753502988983, updateTime=1753502988983, creator=18614031015, updator=18614031015), WebsiteProps(id=1155838567701139607, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146105254833139715, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1753502988982, updateTime=1753502988982, creator=18614031015, updator=18614031015)])], journalTitle=科技导报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Science & Technology Review, journalPhotoCn=wfghvu3bhh/dKxuZ+ucVHA==, journalPhotoEn=yjSfclmpNm7ihn9NbTZ69g==, journalFirstLetter=K, journalRecommend=null, journalNew=null, journalCollection=1, jcrJf=null, cjcrJf=0.91, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2025.12.00121, detailUrlEn=https://castjournals.cast.org.cn/joweb/kjdb/EN/10.3981/j.issn.1000-7857.2025.12.00121, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kjdb/CN/PDF/10.3981/j.issn.1000-7857.2025.12.00121, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kjdb/EN/PDF/10.3981/j.issn.1000-7857.2025.12.00121, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1774627200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于SAM和提示学习的露天矿山分割方法
收藏切换
PDF下载
孙铭泽 1 , 王军 1 , 张婉秋 2, * , 刘琨 3 , 林刚 4, 5, *
科技导报 | 特色专题 2026,44(6): 76-82
收起
收藏切换
科技导报 |特色专题 2026 , 44 (6) : 76 -82
基于SAM和提示学习的露天矿山分割方法
全屏
[Author(id=1251567855968399563, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=35986138@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251567856090034384, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567855968399563, language=EN, stringName=Mingze SUN, firstName=Mingze, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567856387829976, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567855968399563, language=CN, stringName=孙铭泽, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1山东建筑大学土木工程学院,济南 250101, bio={"content":"

孙铭泽,硕士研究生,研究方向为矿区生态修复,电子信箱:

"}, bioImg=null, bioContent=

孙铭泽,硕士研究生,研究方向为矿区生态修复,电子信箱:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855393779878, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=1, ext=[AuthorCompanyExt(id=1251567855406362791, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1251567855414751400, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1山东建筑大学土木工程学院,济南 250101)])]), Author(id=1251567856488493276, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, 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=1251567858078134497, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567856488493276, language=EN, stringName=Jun WANG, firstName=Jun, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858162020582, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567856488493276, language=CN, stringName=王军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1山东建筑大学土木工程学院,济南 250101, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855393779878, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=1, ext=[AuthorCompanyExt(id=1251567855406362791, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China), AuthorCompanyExt(id=1251567855414751400, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855393779878, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1山东建筑大学土木工程学院,济南 250101)])]), Author(id=1251567858250100969, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=BQT2200204006T@student.cumtb.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1251567858338181356, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858250100969, language=EN, stringName=Wanqiu ZHANG, firstName=Wanqiu, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858426261744, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858250100969, language=CN, stringName=张婉秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855527997615, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=2, ext=[AuthorCompanyExt(id=1251567855536386223, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855527997615, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China), AuthorCompanyExt(id=1251567855544774832, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855527997615, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083)])]), Author(id=1251567858518536433, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, 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=1251567858619199734, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858518536433, language=EN, stringName=Kun LIU, firstName=Kun, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858694697207, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858518536433, language=CN, stringName=刘琨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3自然资源部国土卫星遥感应用中心,北京 100048, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855637049525, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=3, ext=[AuthorCompanyExt(id=1251567855645438135, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855637049525, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China), AuthorCompanyExt(id=1251567855649632440, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855637049525, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3自然资源部国土卫星遥感应用中心,北京 100048)])]), Author(id=1251567858761806075, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lingang@igsnrr.ac.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1251567858845692160, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858761806075, language=EN, stringName=Gang LIN, firstName=Gang, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, 5, *, address=4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
5College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251567858929578243, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, authorId=1251567858761806075, language=CN, stringName=林刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, 5, *, address=4中国科学院地理科学与资源研究所,北京 100101
5中国科学院大学资源环境学院,北京 100049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251567855733518524, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=4, ext=[AuthorCompanyExt(id=1251567855746101438, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855733518524, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China), AuthorCompanyExt(id=1251567855754490047, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855733518524, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4中国科学院地理科学与资源研究所,北京 100101)]), AuthorCompany(id=1251567855855153348, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, xref=5, ext=[AuthorCompanyExt(id=1251567855863541955, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855855153348, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China), AuthorCompanyExt(id=1251567855871930564, tenantId=1146029695717560320, journalId=1146031591421210625, articleId=1251559137763602470, companyId=1251567855855153348, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5中国科学院大学资源环境学院,北京 100049)])])]
孙铭泽1 , 王军1, 张婉秋2, * , 刘琨3, 林刚4, 5, *
作者信息
  • 1山东建筑大学土木工程学院,济南 250101
  • 2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083
  • 3自然资源部国土卫星遥感应用中心,北京 100048
  • 4中国科学院地理科学与资源研究所,北京 100101
  • 5中国科学院大学资源环境学院,北京 100049
通讯作者:
张婉秋(通信作者),博士研究生,研究方向为矿区生态修复,电子信箱:;
林刚(通信作者),副研究员,研究方向为矿山资源综合利用、资源耦合系统建模等,电子信箱:
An open−pit mine segmentation method based on SAM and prompt learning
Mingze SUN1 , Jun WANG1, Wanqiu ZHANG2, * , Kun LIU3, Gang LIN4, 5, *
Affiliations
  • 1School of Civil Engineering, Shandong Jianzhu University, Jinan 250101, China
  • 2College of Geoscience and Surveying Engineering, China University of Mining and Technology (Beijing), Beijing 100083, China
  • 3Land Satellite Remote Sensing Application Center, Ministry of Natural Resources, Beijing 100048, China
  • 4Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
  • 5College of Resources and Environment, University of Chinese Academy of Sciences, Beijing 100049, China
出版时间: 2026-03-28 doi: 10.3981/j.issn.1000-7857.2025.12.00121
文章导航
收藏切换

精准获取露天矿山的空间分布信息,是推进“绿色矿山”建设与地质环境动态监测的关键前提,为克服露天矿山分割领域中数据集缺乏、类内类间差距大和拓扑结构复杂的问题,提出一种融合混合语义提示与拓扑感知的分割框架。构建了包含7622张精细标注影像的矿山语义分割数据集(mine semantic segmentation,MSS),并提出了融合双编码器结构与多尺度特征聚合的混合语义提示实例分割方法(mine segment anything model,Mine−SAM),将基础模型的全局上下文与专家模型的局部细粒度特征深度耦合,该方法在目标检测平均精度(average precision box,PA,box)和实例分割平均精度(average precision mask,PA,mask)指标上分别达到64.4%和65.2%;同时开发了结合图卷积网络与像素级对比学习的语义分割方法(semantic mine segmentation,SemMSeg),通过图卷积网络捕捉矿区要素间的空间依赖与结构约束,实现了交并比(intersection over union,IoU)73.38%和精确度(Precision)85.03%的分割精度,为露天矿山自动监测提供了可靠技术路径,对推动遥感图像智能解译具有不可或缺的应用价值。

露天矿山分割  /  实例分割  /  提示学习  /  图卷积网络

Accurately acquiring the spatial distribution of open−pit mines is vital for "green mine" development and dynamic geological monitoring. To overcome the inherent challenges of dataset scarcity, drastic intra− and inter−class differences, and complex topological structures in this field, we propose a segmentation framework integrating hybrid semantic prompting and topological awareness. We constructed a specific dataset named Mine Semantic Segmentation (MSS). MSS contains 7,622 finely annotated images of open−pit mines. Based on MSS, we propose an instance segmentation method called Mine Segment Anything Model (Mine−SAM). Mine−SAM employs a dual−encoder structure. It also utilizes multi−scale feature aggregation techniques. The model couples global context from foundation models with local fine−grained features from expert models. Mine−SAM achieved an Average Precision box (PA,box) of 64.4%. The Average Precision mask (PA,mask) score reached 65.2%. In addition, we developed a semantic segmentation method named SemMSeg. This method combines graph convolutional networks (GCN) with pixel−level contrastive learning. The GCN captures spatial dependencies among mining elements. It also enforces structural constraints within the model. SemMSeg achieved an Intersection over Union (IoU) of 73.38%. The precision of the method reached 85.03%. These techniques provide a technical path for automatic mine monitoring. The findings contribute to the intelligent interpretation of remote sensing imagery.

open−pit mine segmentation  /  instance segmentation  /  prompt learning  /  graph convolution network
孙铭泽, 王军, 张婉秋, 刘琨, 林刚. 基于SAM和提示学习的露天矿山分割方法. 科技导报, 2026 , 44 (6) : 76 -82 . DOI: 10.3981/j.issn.1000-7857.2025.12.00121
Mingze SUN, Jun WANG, Wanqiu ZHANG, Kun LIU, Gang LIN. An open−pit mine segmentation method based on SAM and prompt learning[J]. Science & Technology Review, 2026 , 44 (6) : 76 -82 . DOI: 10.3981/j.issn.1000-7857.2025.12.00121
露天矿山的高效运营与科学监管高度依赖于精准的空间信息获取[12]。早期矿山识别研究主要依赖中低分辨率遥感数据与基础机器学习算法,识别结果将复杂的矿山地表元素合并简化为“建设用地”等单一类别,存在识别粒度粗和缺失细节层次等问题[3],近年来,深度学习凭借强大的特征学习能力成为该领域主流[45]。现有研究人员已基于EG−UNet、DeepLabv3+等技术有效提升了识别精度,展现了技术融合的显著进展[67]。在深度学习可用数据集方面,虽然已有Silva等[8]的矿山废弃物数据集、Wang等[9]的高分辨率开采数据集和2024年开源的CUG_MISDataset等[10]公开数据集,但仍存在标注质量不一、覆盖不均等问题,制约了模型泛化能力;此外,露天矿山具有复杂的拓扑结构,传统分割算法难以处理这种复杂的拓扑关系和多样化的矿山地貌,亟需开发图卷积网络等[1114]更先进的算法以应对这些挑战。Meta AI开发的分割一切大模型(segment anything model,SAM)凭借零样本泛化能力为样本稀缺任务提供了新思路[15],结合低秩自适应(low−rank adaptation,LoRA)等微调技术[1617],遥感影像分析正由通用分割转向针对多尺度目标、时空一致性及多源异构数据深度适配的精准语义理解。
基于上述存在问题与不足,提出一种针对露天矿山识别的基于SAM和提示学习的框架以及其改进方法,通过图结构建模、图卷积特征聚合和对比学习优化,实现了对露天矿山复杂空间布局和细微语义特征的精准建模,为后续模型的微调和性能提升提供了坚实的理论基础和技术支持。
本研究提出基于混合语义提示的SAM改进了一种实例分割方法(Mine−SAM),该框架保留SAM的预训练编码器、解码器及原提示编码器,并将其冻结参数以高效利用SAM的零样本泛化能力,同时引入外部专家模型,通过分析遥感图像特征生成适配复杂场景的提示,引导解码器生成更精确的露天矿山分割掩码(图1)。
在基于SAM的改进框架中,采用双编码器结构处理输入图像,一个是具有大规模预训练参数的SAM图像编码器$ {\varPhi}_{\mathrm{S}\mathrm{A}\mathrm{M}-\mathrm{E}\mathrm{n}\mathrm{c}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{r}} $,另一个是具有较小可学习参数的实时实例分割模型(you only look at coefficients, YOLACT)图像编码器$ {\varPhi}_{\mathrm{S}\mathrm{e}\mathrm{g}-\mathrm{E}\mathrm{n}\mathrm{c}\mathrm{o}\mathrm{d}\mathrm{e}\mathrm{r}} $[18]。通过这2个编码器分别获得具有全局依赖性的图像FSAM和具有高频细节特征的图像$ {F}_{\text{Seg}} $$ {F}_{\text{Seg}} $经预测网络进一步生成符合SAM提示格式的实例掩码$ {U}_{\text{Mask}} $与边界框$ {U}_{\text{Box}} $,其流程可表示为:
$ {U}_{\text{Mask}}={\varPhi}_{\text{Mask-Head}}({F}_{\text{Seg}}) $
${U}_{\text{Box}}={\varPhi}_{\text{Box-Head}}({F}_{\text{Seg}}) $
式中,$ {\varPhi}_{\text{Mask-Head}} $表示掩码预测头;$ {\varPhi}_{\text{Box-Head}} $表示边界框预测头网络。
采用多尺度特征聚合模块聚合SAM编码器逐层特征,此外,融合SAM多尺度增强特征、外部语义特征及经其提示编码器处理,生成最终融合提示以提升SAM实例分割能力。实例分割主要采用平均精度$ P\mathrm{_A} $作为核心评价指标,$ P\mathrm{_A} $表达式为
$ P\mathrm{_A}=\int_0^1P(R)\mathrm{d}R $
针对露天矿山复杂拓扑结构的分割难题,本研究提出面向拓扑结构与细粒度语义对齐的语义分割方法(SemMSeg)。该方法基于可微调SAM编码器提取特征,将图像转换为图结构,利用图卷积网络建模像素间空间关系[19],有效捕捉矿山区域的拓扑特征与实例依赖。结合对比学习强化特征区分能力,利用双分割头设计提升精度与鲁棒性,实现对矿山结构的精准分割(图2)。
为解决预训练模型微调时的计算瓶颈,将LoRA[20]技术引入SAM编码器部分,通过在编码器中引入低秩矩阵且仅更新这些低秩参数、保持原有权重不变,在不增加模型参数规模的前提下,实现对露天矿山分割任务的高效适配。同时,采用具有瓶颈层(bottleneck)结构的适配器(adapter)模块[21],这种结构可以在不改变原始特征维度的情况下,实现特征的非线性变换和增强。计算公式为
$ {{{X}}}_{\text{down}}={{{X}}}_{\text{in}}{{{W}}}_{\text{down}}+{{{B}}}_{\text{down}} $
式中,$ {{{X}}}_{\text{in}} $为输入特征,$ {{{W}}}_{\text{down}} $$ {{{B}}}_{\text{down}} $分别为下投影的权重矩阵和偏置项。
随后,使用修正线性单元(rectified linear unit,ReLU)激活函数对降维后的特征进行非线性变换,最后,上投影操作将激活后的特征再扩展回原始维度$ {{{X}}}_{\text{up}} $,其中,$ {{{W}}}_{\text{up}} $$ {{{B}}}_{\text{up}} $为上投影的权重矩阵和偏置项,计算公式为
${{{X}}}_{\text{up}}={{{X}}}_{\text{ac}}{{{W}}}_{\text{up}}+{{{B}}}_{\text{up}} $
像素级语义对齐策略通过对比学习机制,在特征空间拉近同类像素、推远异类像素,有效弥合了自然影像与遥感影像的域间差异,显著提升了模型对矿山复杂场景的特征辨识能力。在该方法中,对比损失针对每个像素i,以同类像素为正样本、不同类像素为负样本,对于每个像素i,对比损失可以表示为
$ {L}_{i}^{\text{NCE}}=\frac{1}{\text{|}{P}_{i}\text{|}}\sum _{{i}^{+}\in{P}_{i}}-\text{log}\frac{\text{exp}(i\cdot{i}^{+}/\tau)}{\text{exp}(i\cdot{i}^{+}/\tau)+\displaystyle\sum\limits _{{i}^{-}\in{{N}}_{i}}\text{exp}({i}\cdot{i}^{-}/\tau)} $
式中,$ {P}_{i} $为正样本集合,$ {N}_{i} $为负样本集合,τ为温度超参数,用于调节正负样本之间的对比强度。
为了构建针对广义矿山语义分割数据集MSS,收集了2020年后露天矿山的26525个露天矿点位数据,包括露天矿山、废石堆、储料场、堆积场、沉陷区及其他露天区域,选择Google Maps 16级别1.89 m分辨率的影像作为主要数据源,同时以World Imagery空间分辨率为2.4 m的影像作为补充数据源,采用SAM模型自动预分割与人工精细化校正相结合的方式,删除了模型误判的具有独特纹理的区域,并对重叠或相邻的检测目标进行合并处理,确保对矿区、废石堆等要素的精准标注。最终选取7622张影像作为数据集,按6∶4比例划分为4573张训练样本和3049张测试样本。
在MSS数据集的实例分割对比实验中,平均精度按不同IoU阈值可以细分为$ {P}_{\text{A}}^{\text{50}} $$ {P}_{\text{A}}^{\text{75}} $$ P\mathrm{_A} $,对于$ {P}_{\text{A}}^{\text{50}} $$ {P}_{\text{A}}^{\text{75}} $,其阈值分别为0.5和0.75,$ P\mathrm{_A} $则表示阈值从0.5到0.95步长为0.05上的平均精度,值越高,所需要的标准越严苛。如表1所示,Mine−SAM方法性能最优,其$ {P}_{\text{A,}\text{box}} $为64.4,$ {P}_{\text{A,}\text{box}}^{\text{50}} $为81.2,$ {P}_{\text{A,box}}^{\text{75}} $为73.7;同时,在分割性能上,$ {P}_{\text{A,}\text{mask}} $$ {P}_{\text{A}\text{,}\text{mask}}^{\text{50}} $$ {P}_{\text{A,}\text{mask}}^{\text{75}} $分别达到了65.2、81.8和73.5,均为所有方法中最佳或与最佳值持平。传统方法的分割性能均略逊于基于SAM的改进方法,这主要是由于传统的边界框标注方法难以精确覆盖复杂目标,导致无法区分“矿坑”与“普通坑洞”而输出错误框。这表明Mine−SAM在捕捉目标细节、精确定位及分割密集目标上优势显著。
为评估Mine−SAM各组件有效性,本研究在MSS数据集上开展消融实验,如表2所示,针对框提示$ {{U}}_{\text{Box}} $、掩码提示$ {{U}}_{\text{Mask}} $、SAM特征$ {{F}}_{\text{SAM}} $、外部模型特征$ {{F}}_{\text{Seg}} $及多源特征聚合模块$ {{F}}_{\text{agg}} $,测试不同模型变体的$ {{P}}_{\text{A,}\text{box}} $$ {{P}}_{\text{A,}\text{mask}} $。结果显示:仅用$ {{U}}_{\text{Mask}} $时,$ {{P}}_{\text{A,}\text{box}} $$ {{P}}_{\text{A,}\text{mask}} $分别为63.1与64.7,反之,仅用$ {{U}}_{\text{Box}} $时,2项指标降至59.3、58.2。针对编码器特征部分,移除任一组件均致性能下降,这表明$ {{F}}_{\text{SAM}} $$ {{F}}_{\text{Seg}} $$ {{F}}_{\text{agg}} $模块在全局语义提取与多尺度融合中具有互补作用,共同保障了模型的优异性能。
在MSS数据集上的可视化实验结果表明(图3),不同算法在露天矿山实例分割任务中表现出明显的性能差异。基于SAM的改进模型中,SAM−det因依赖外部检测器而在复杂纹理区域表现不稳定,而SAM−seg和RSPrompter−anchor通过改进解码器或提示策略实现了显著提升,但仍存在边界不连续等问题,本研究提出的Mine−SAM凭借混合语义提示与多尺度特征融合,在主体识别准确性和边界连续性上均优于SAM−det、SAM−seg等方法。
在MSS数据集上的实验结果如表3所示,可以明显看出SemMSeg在IoU、F1分数(F1−score)、精确度(precision)和召回率(recall)指标上分别达到了73.38%、84.65%、85.03%和85.06%,均优于其他对比方法。相比之下,传统的U−Net等方法主要依赖局部卷积算子,难以捕捉露天矿山跨越数千米的空间依赖关系,且在处理矿山细微边缘和不规则小目标时明显乏力。证明了所提出方法在分割精度和鲁棒性方面的有效性。
为探究像素对采样策略在语义分割性能方面的影响,在MSS数据集上进行消融实验,模型性能随约束策略增强而阶梯式提升,基线模型IoU为70.43%,引入图片内像素约束后升至71.45%,最终采用图片间约束的SemMSeg模型达到最优73.38%。
在拓扑结构解析模块消融实验中,以图卷积为基础,验证各子模块对性能的影响,结果表明,在图卷积基础上分别引入多层感知机(multi−layer perceptron,MLP)或前馈神经网络(feed−forward network,FFN)层可将IoU提升至69.02%与69.29%,而同时引入二者时IoU显著提高至73.38%,如表4所示。
图4所示的MSS数据集可视化对比中,本研究提出的SemMSeg方法展现出显著优势。传统算法中,U−Net和FCN虽能识别矿山整体轮廓,但存在边界缺口和过度分割问题;SegNet通过池化索引机制保留了部分边缘信息,却在复杂形态区域产生漏分错分;PSPNet与DeepLabv3+等先进模型虽提升整体精度,但对小目标及边缘细节的处理仍显不足。相比之下,SemMSeg不仅准确识别大范围矿山区域,更能精准贴合自然地物分界线,在细微边缘处有效避免分割错误,其生成结果与真实标注高度吻合,验证了该方法在复杂拓扑结构捕捉和边界细节保留方面的卓越性能。
针对露天矿山分割中存在的数据集缺乏、类内类间差异大及拓扑结构复杂等挑战,提出一种融合混合语义提示与拓扑感知的分割框架。首先,构建了高质量露天矿山分割数据集MSS,包含7622张精细标注影像,为模型训练提供了坚实数据基础;其次,提出了基于混合语义提示的实例分割方法Mine−SAM,通过融合多源提示信息在MSS数据集上实现了PA,box 为64.4%和PA,mask为 65.2%的优异性能;最后,开发了面向拓扑结构与语义对齐的语义分割方法SemMSeg,结合图卷积网络与对比学习机制,在MSS数据集上取得了IoU为 73.38%和精确度为85.03%的领先表现。在未来,露天矿山分割研究仍需聚焦于提升模型季节鲁棒性,通过引入数据增强和迁移学习等技术,提升模型在动态环境中的适应能力;同时,加强数据集的开放与标准化工作,构建全球标准数据集,提升矿山数据集的完整性。本研究为露天矿山自动化监测、环境保护与资源管理等提供科学参考,能够为矿山边界精准提取、生态修复评估和资源监管提供可靠的技术支持,提升矿山管理效率与决策水平。
  • 国家重点研发计划项目(2023YFE0208000)
  • 国家青年科学基金项目(42202280)
  • 国家自然科学基金面上项目(42571497)
参考文献 引证文献
排序方式:
[1]
Meng X L, Zhang D, Dong S J, et al. Open−pit granite mining area extraction using UAV aerial images and the novel GIPNet[J]. Remote Sensing, 2024, 16(5): 789.
[2]
Li Z B, Zhao Y L, Ren H, et al. A novel index for detecting bare coal in open−pit mining areas based on Landsat imagery[J]. Remote Sensing, 2024, 16(24): 4648.
[3]
Qiao Q H, Li Y Y, H Q. Open−pit mining area extraction using multispectral remote sensing images: A deep learning extraction method based on Transformer[J]. Applied Sciences, 2024, 14(14): 6384.
[4]
宋仁忠, 郑慧玉, 王党朝, . 基于深度学习和高分辨率遥感影像的露天矿地物分类方法[J]. 中国矿业, 2022, 31(7): 102-111.
[5]
李茹, 鲁海峰. 基于多尺度卷积神经网络的矿山监控图像识别研究[J]. 唐山学院学报, 2023, 36(6): 5-10,16.
[6]
Zhou G D, Xu J H, Chen W T, et al. Deep feature enhancement method for land cover with irregular and sparse spatial distribution features: A case study on open−pit mining[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 4401220.
[7]
Wang Y, Yang L, Liu X, et al. An improved semantic segmentation algorithm for high−resolution remote sensing images based on DeepLabv3[J]. Scientific Reports, 2024, 14(1): 9716.
[8]
Silva M, Hermosilla G, Villavicencio G, et al. Automated detection and analysis of massive mining waste deposits using sentinel−2 satellite imagery and artificial intelligence[J]. Remote Sensing, 2023, 15(20): 4949.
[9]
Wang C S, Chang L L, Zhao L R, et al. Automatic identification and dynamic monitoring of open−pit mines based on improved mask R−CNN and transfer learning[J]. Remote Sensing, 2020, 12(21): 3474.
[10]
Zhu Y Q, Chen W T, He W X, et al. CUG_MISDataset: A remote sensing instance segmentation dataset for improved wide−area high−precision mining land occupation recognition[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 16476-16486.
[11]
王寅达, 陈嘉辉, 彭玲, . 高分辨率关系图卷积网络遥感语义分割方法[J]. 中国科学院大学学报(中英文), 2025, 42(1): 107-115.
[12]
Li X J, Kong P, Chen W T, et al. EDG−Net: Edge−enhanced dynamic graph convolutional network for remote sensing scene classification of mining−disturbed land[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2025, 18: 17622-17637.
[13]
Zheng G X, Jiang Z G, Zhang H. HRRF: A hierarchical recursive reasoning framework for high−resolution remote sensing semantic segmentation[J]. Geocarto International, 2025, 40(1): 2583334.
[14]
Kirillov A, Mintun E, Ravi N, et al. Segment anything[C]//Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2024: 3992−4003.
[15]
Yu T, Feng R S, Feng R Y, et al. Inpaint anything: Segment anything meets image inpainting[EB/OL]. 2023: arXiv: 2304.06790. https://arxiv.org/abs/2304.06790.
[16]
李天文, 童星, 李俊涛, . 面向露天矿山无人机遥感影像机械小目标识别的CDMG−YOLO模型[J]. 工矿自动化, 2025, 51(11): 76-86.
[17]
陈诗琪, 杨学, 朱荣强, . 面向遥感图像解译的参数高效微调研究综述[J]. 中国图象图形学报, 2026, 31(1): 212-242.
[18]
Bolya D, Zhou C, Xiao F Y, et al. YOLACT: Real−time instance segmentation[C]//Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2019: 9156−9165.
[19]
董霁红, 王立兵, 冯晓彤, . 黄河流域煤炭−煤电−煤化工场地特征精准智能识别方法及应用[J]. 煤炭学报, 2024, 49(2): 1011-1024.
[20]
Hu E J, Shen Y L, Wallis P, et al. LoRA: Low−rank adaptation of large language models[EB/OL]. 2021: arXiv: 2106.09685. https://arxiv.org/abs/2106.09685.
[21]
Wu J D, Ji W, Liu Y P, et al. Medical SAM adapter: Adapting segment anything model for medical image segmentation[EB/OL]. 2023: arXiv: 2304.12620. https://arxiv.org/abs/2304.12620.
[22]
He K M, Gkioxari G, Dollár P, et al. Mask R−CNN[C]//Proceedings of IEEE International Conference on Computer Vision (ICCV). Piscataway, NJ: IEEE, 2017: 2980−2988.
[23]
Chen K, Pang J M, Wang J Q, et al. Hybrid task cascade for instance segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2020: 4969−4978.
[24]
Cheng B W, Misra I, Schwing A G, et al. Masked−attention mask transformer for universal image segmentation[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2022: 1280−1289.
[25]
Ronneberger O, Fischer P, Brox T. U−Net: Convolutional networks for biomedical image segmentation[M]. Medical Image Computing and Computer−Assisted Intervention–MICCAI 2015. Cham: Springer International Publishing, 2015: 234−241.
[26]
Zhao H S, Shi J P, Qi X J, et al. Pyramid scene parsing network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ: IEEE, 2017: 6230−6239.
[27]
Chen L C, Zhu Y K, Papandreou G, et al. Encoder−decoder with atrous separable convolution for semantic image s egmentation[M]. Computer Vision–ECCV 2018. Cham: Springer International Publishing, 2018: 833−851.
2026年第44卷第6期
PDF下载
504
250
引用本文
BibTeX
文章信息
doi: 10.3981/j.issn.1000-7857.2025.12.00121
  • 接收时间:2025-12-10
  • 首发时间:2026-04-16
  • 出版时间:2026-03-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-12-10
  • 修回日期:2026-03-01
基金
国家重点研发计划项目(2023YFE0208000)
国家青年科学基金项目(42202280)
国家自然科学基金面上项目(42571497)
作者信息
    1山东建筑大学土木工程学院,济南 250101
    2中国矿业大学(北京)地球科学与测绘工程学院,北京 100083
    3自然资源部国土卫星遥感应用中心,北京 100048
    4中国科学院地理科学与资源研究所,北京 100101
    5中国科学院大学资源环境学院,北京 100049

通讯作者:

张婉秋(通信作者),博士研究生,研究方向为矿区生态修复,电子信箱:;
林刚(通信作者),副研究员,研究方向为矿山资源综合利用、资源耦合系统建模等,电子信箱:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kjdb/CN/10.3981/j.issn.1000-7857.2025.12.00121
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