Article(id=1322933544632320895, tenantId=1146029695717560320, journalId=1281212831689347082, issueId=1322933542426116991, articleNumber=null, orderNo=null, doi=10.14075/j.jgg.2024.03.090, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1709568000000, receivedDateStr=2024-03-05, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1793341535956, onlineDateStr=2026-10-30, pubDate=1736870400000, pubDateStr=2025-01-15, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1793341535956, onlineIssueDateStr=2026-10-30, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1793341535956, creator=13701087609, updateTime=1793341535956, updator=13701087609, issue=Issue{id=1322933542426116991, tenantId=1146029695717560320, journalId=1281212831689347082, year='2025', volume='45', issue='1', pageStart='1', pageEnd='110', issueExtLink='null', onlineDate='null', pubDate='1736870400000', pubDateStr='2025-01-15', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1793341535431, creator='13701087609', updateTime=1793341535431, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=1, endPage=4, 12, ext={EN=ArticleExt(id=1322933544833647488, articleId=1322933544632320895, tenantId=1146029695717560320, journalId=1281212831689347082, language=EN, title=Research on Automatic Landslide Identification Based on Faster R-CNN and Mask R-CNN, columnId=null, journalTitle=Journal of Geodesy and Geodynamics, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Based on the images from Gaofen-1 satellite, taking the first section of the Three Gorges reservoir as an example, 160 landslide samples are visually interpreted and divided into training and validation samples according to the ratio of 9:1. Then, landslide automatic identification models are constructed using Mask R-CNN and Faster R-CNN algorithms. To further compare and analyze the performance of the two models under different sample ratios, calculations are performed using sample ratios of 8:2, 7:3, and 6:4. The results show that the recognition results based on Mask R-CNN model are better than Faster R-CNN in three indicators, including precision, recall and F1 score. Moreover, cross-validation proves that the performance of Mask R-CNN model is more stable.

, authors=Xianyu YU1, Sen YANG1, authorsList=Xianyu YU, Sen YANG, authorCompany=null, correspAuthors=null, authorNote=

YU Xianyu, PhD, assistant professor, majors in evaluation of landslide susceptibility, E-mail:

, correspAuthorsNote=null, copyrightStatement=All rights reserved, without authorization, 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=1322933545987081099, articleId=1322933544632320895, tenantId=1146029695717560320, journalId=1281212831689347082, language=CN, title=基于Faster R-CNN和Mask R-CNN的滑坡自动识别研究, columnId=1322506197874356701, journalTitle=大地测量与地球动力学, columnName=地壳运动, runingTitle=null, highlight=null, articleAbstract=

基于高分一号影像, 以三峡库区库首段为例, 通过目视解译出160个滑坡样本, 按照9:1比例分为训练样本和验证样本, 分别利用Faster R-CNN和Mask R-CNN算法构建滑坡自动识别模型。为进一步对比分析不同样本比例下两种模型的性能, 分别采用8:2、7:3、6:4的样本比例进行计算。研究结果表明, Mask R-CNN模型识别结果准确率、召回率和F1分数等3项指标均优于Faster R-CNN; 且经过交叉验证, 证明Mask R-CNN模型的性能更为稳定。

, authors=于宪煜1, 杨森1, authorsList=于宪煜, 杨森, authorCompany=null, correspAuthors=null, authorNote=

于宪煜,博士,副教授,主要从事滑坡易发性评价研究,E-mail:

, correspAuthorsNote=null, copyrightStatement=版权所有,未经授权。, copyrightOwner=大地测量与地球动力学编辑部, extLink=null, articleAbsUrl=null, sourceXml=JfWV6Vo6xq+D5A7a5oMLOg==, magXml=AKTriulwVVVHxiyUK0CEbA==, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=/eYOAHMDKPvpYz8pipVi0g==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=wmPIhBMg9Svn6UBniwXN7A==, mapNumber=null, fund=null)}, authors=[Author(id=1322940263945076938, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yuxianyu@hbut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322940264356118734, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940263945076938, language=EN, stringName=Xianyu YU, firstName=Xianyu, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China, bio={"content":"

YU Xianyu, PhD, assistant professor, majors in evaluation of landslide susceptibility, E-mail:

"}, bioImg=null, bioContent=

YU Xianyu, PhD, assistant professor, majors in evaluation of landslide susceptibility, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322940264700051663, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940263945076938, language=CN, stringName=于宪煜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068, bio={"content":"

于宪煜,博士,副教授,主要从事滑坡易发性评价研究,E-mail:

"}, bioImg=null, bioContent=

于宪煜,博士,副教授,主要从事滑坡易发性评价研究,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322940263840219334, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, xref=null, ext=[AuthorCompanyExt(id=1322940263852802247, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China), AuthorCompanyExt(id=1322940263865385160, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068)])]), Author(id=1322940265098510546, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, 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=1322940265211756756, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940265098510546, language=EN, stringName=Sen YANG, firstName=Sen, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322940265534718165, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940265098510546, language=CN, stringName=杨森, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322940263840219334, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, xref=null, ext=[AuthorCompanyExt(id=1322940263852802247, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China), AuthorCompanyExt(id=1322940263865385160, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068)])])], keywords=[Keyword(id=1322940267610898648, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1322940268110020828, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, orderNo=2, keyword=landslide identification), Keyword(id=1322940268483313886, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, orderNo=3, keyword=Mask R-CNN), Keyword(id=1322940268885967071, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, orderNo=4, keyword=Faster R-CNN), Keyword(id=1322940269745799393, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, orderNo=5, keyword=cross-validation), Keyword(id=1322940270140063972, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1322940270559494374, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, orderNo=2, keyword=滑坡识别), Keyword(id=1322940272245604585, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, orderNo=3, keyword=Mask R-CNN), Keyword(id=1322940272652452074, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, orderNo=4, keyword=Faster R-CNN), Keyword(id=1322940273076076779, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, orderNo=5, keyword=交叉验证)], refs=[Reference(id=1322940279103291662, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=10.3390/rs4051310, pmid=null, pmcid=null, year=2012, volume=4, issue=5, pageStart=1310, pageEnd=1336, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=Hölbling D, Füreder P, Antolini F, journalName=Remote Sensing, refType=null, unstructuredReference= Hölbling D , Füreder P , Antolini F , et al. A Semi-Automated Object-Based Approach for Landslide Detection Validated by Persistent Scatterer Interferometry Measures and Landslide Inventories[J]. Remote Sensing, 2012, 4 (5): 1310- 1336, articleTitle=A Semi-Automated Object-Based Approach for Landslide Detection Validated by Persistent Scatterer Interferometry Measures and Landslide Inventories, refAbstract=null), Reference(id=1322940280806179090, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=10.3390/ijgi8080321, pmid=null, pmcid=null, year=2019, volume=8, issue=8, pageStart=321, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=Paw-luszek K, Marczak S, Borkowski A, journalName=ISPRS International Journal of Geo-Information, refType=null, unstructuredReference= Paw-luszek K , Marczak S , Borkowski A , et al. Multi-Aspect Analysis of Object-Oriented Landslide Detection Based on an Extended Set of LiDAR-Derived Terrain Features[J]. ISPRS International Journal of Geo-Information, 2019, 8 (8): 321, articleTitle=Multi-Aspect Analysis of Object-Oriented Landslide Detection Based on an Extended Set of LiDAR-Derived Terrain Features, refAbstract=null), Reference(id=1322940281506627864, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=尹常铭. 基于机器学习的滑坡易发性区划和滑坡快速识别研究[D]. 大连: 大连理工大学, 2022, articleTitle=null, refAbstract=null), Reference(id=1322940281917669658, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Changming. Study on Landslide Susceptibility Zoning and Rapid Landslide Identification Based on Machine Learning[D]. Dalian: Dalian University of Technology, 2022, articleTitle=null, refAbstract=null), Reference(id=1322940282311934235, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=张帅娟. 变化检测和面向对象结合的高分辨率遥感影像滑坡体提取方法研究[D]. 成都: 西南交通大学, 2017, articleTitle=null, refAbstract=null), Reference(id=1322940282416791839, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Shuaijuan. Study on Landslide Extraction Method from High-Resolution Remote Sensing Images by Combining Change Detection with Object-Oriented Method[D]. Chengdu: Southwest Jiaotong University, 2017, articleTitle=null, refAbstract=null), Reference(id=1322940282773307681, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=10.1109/LGRS.2010.2101045, pmid=null, pmcid=null, year=2011, volume=8, issue=4, pageStart=701, pageEnd=705, url=null, language=null, rfNumber=5, rfOrder=6, authorNames=Lu P, Stumpf A, Kerle N, journalName=IEEE Geoscience and Remote Sensing Letters, refType=null, unstructuredReference= Lu P , Stumpf A , Kerle N , et al. Object-Oriented Change Detection for Landslide Rapid Mapping[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8 (4): 701- 705, articleTitle=Object-Oriented Change Detection for Landslide Rapid Mapping, refAbstract=null), Reference(id=1322940283154989346, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang F, Jiang M Q, Qian C, et al. Residual Attention Network for Image Classification[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, 2017, articleTitle=null, refAbstract=null), Reference(id=1322940283578614051, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=10.1109/TNNLS.2018.2876865, pmid=null, pmcid=null, year=2019, volume=30, issue=11, pageStart=3212, pageEnd=3232, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=Zhao Z Q, Zheng P, Xu S T, journalName=IEEE Transactions on Neural Networks and Learning Systems, refType=null, unstructuredReference= Zhao Z Q , Zheng P , Xu S T , et al. Object Detection with Deep Learning: A Review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30 (11): 3212- 3232, articleTitle=Object Detection with Deep Learning: A Review, refAbstract=null), Reference(id=1322940285319250214, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[M] //Navab N, Hornegger J, Wells W M, et al. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015, articleTitle=null, refAbstract=null), Reference(id=1322940285755457832, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=2022, volume=165, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=Youssef A M, Pradha B, Dikshit A, journalName=Bulletin of Engineering Geology and the Environment, refType=null, unstructuredReference= Youssef A M , Pradha B , Dikshit A , et al. Landslide Susceptibility Mapping Using CNN-1D and 2D Deep Learning Algorithms: Comparison of Their Performance at Asir Region, KSA[J]. Bulletin of Engineering Geology and the Environment, 2022, 165, articleTitle=Landslide Susceptibility Mapping Using CNN-1D and 2D Deep Learning Algorithms: Comparison of Their Performance at Asir Region, KSA, refAbstract=null), Reference(id=1322940286107779369, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=10.1109/TPAMI.2016.2577031, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=Ren S Q, He K M, Girshick R, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference= Ren S Q , He K M , Girshick R , et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149, articleTitle=Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks, refAbstract=null), Reference(id=1322940286229414186, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=He K M, Zhang X Y, Ren S Q, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[C]. European Conference on Computer Vision, Cham, 2014, articleTitle=null, refAbstract=null), Reference(id=1322940286502043948, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=张倩荧. 卷积神经网络目标检测算法及其在滑坡领域的应用研究[D]. 宜昌: 三峡大学, 2019, articleTitle=null, refAbstract=null), Reference(id=1322940286955028781, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Qianying. Research on Target Detection Algorithm of Convolutional Neural Network and Its Application in Landslide Field[D]. Yichang: China Three Gorges University, 2019, articleTitle=null, refAbstract=null), Reference(id=1322940288167182639, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=12, pageStart=1931, pageEnd=1942, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=姜万冬, 席江波, 李振洪, journalName=武汉大学学报: 信息科学版, refType=null, unstructuredReference=姜万冬, 席江波, 李振洪, 等. 模拟困难样本的Mask R-CNN滑坡分割识别[J]. 武汉大学学报: 信息科学版, 2023, 48 (12): 1931- 1942, articleTitle=模拟困难样本的Mask R-CNN滑坡分割识别, refAbstract=null), Reference(id=1322940289853292849, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=12, pageStart=1931, pageEnd=1942, url=null, language=null, rfNumber=13, rfOrder=16, authorNames=Jiang Wandong, Xi Jiangbo, Li Zhenhong, journalName=null, refType=null, unstructuredReference= Jiang Wandong , Xi Jiangbo , Li Zhenhong , et al. Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples[J]. Geomatics and Information Science of Wuhan University, 2023, 48 (12): 1931- 1942, articleTitle=null, refAbstract=null)], funds=[Fund(id=1322940278172156167, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, awardId=41807297, language=EN, fundingSource=National Natural Science Foundation of China(41807297), fundOrder=null, country=null), Fund(id=1322940278511894792, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, awardId=41807297, language=CN, fundingSource=国家自然科学基金(41807297), fundOrder=null, country=null), Fund(id=1322940278599975178, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, awardId=2020EJB004, language=EN, fundingSource=Ecological Environment Geotechnical and River and Lake Ecological Restoration Discipline Intelligence Introduction and Innovation Demonstration Base Fund(2020EJB004), fundOrder=null, country=null), Fund(id=1322940278931325197, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, awardId=2020EJB004, language=CN, fundingSource=生态环境岩土与河湖生态修复学科引智创新示范基地基金(2020EJB004), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1322940263840219334, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, xref=null, ext=[AuthorCompanyExt(id=1322940263852802247, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China), AuthorCompanyExt(id=1322940263865385160, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068)])], figs=[ArticleFig(id=1322940273906548974, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Fig. 1, caption=Gaofen-1 image of the studied area, figureFileSmall=Z0OkjJBUhMLGlSQkGu5hBA==, figureFileBig=gBb/hBLi1hGpkRuNmN3YiA==, tableContent=null), ArticleFig(id=1322940273977852143, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=图1, caption=研究区高分一号影像, figureFileSmall=Z0OkjJBUhMLGlSQkGu5hBA==, figureFileBig=gBb/hBLi1hGpkRuNmN3YiA==, tableContent=null), ArticleFig(id=1322940274359533812, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Fig. 2, caption=Faster R-CNN and Mask R-CNN flow chart, figureFileSmall=otlnWbriJjrs6Gp8p4k9gg==, figureFileBig=SC/4KPuFH5sVVhk8Xd9xsw==, tableContent=null), ArticleFig(id=1322940274430836981, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=图2, caption=Faster R-CNN和Mask R-CNN流程, figureFileSmall=otlnWbriJjrs6Gp8p4k9gg==, figureFileBig=SC/4KPuFH5sVVhk8Xd9xsw==, tableContent=null), ArticleFig(id=1322940274745409782, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Fig. 3, caption=Visual interpretation results, figureFileSmall=xPovjBM8b8b9MuaOQCdwRg==, figureFileBig=9U+KMf6KEr0LhcQA2eGVmg==, tableContent=null), ArticleFig(id=1322940276351828215, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=图3, caption=目视解译结果, figureFileSmall=xPovjBM8b8b9MuaOQCdwRg==, figureFileBig=9U+KMf6KEr0LhcQA2eGVmg==, tableContent=null), ArticleFig(id=1322940276444102906, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Fig. 4, caption=Landslide identification results, figureFileSmall=vs5TJJnCYvOdfAoTG+lUpw==, figureFileBig=uTHsgJh5EgTAf4OAbGX0JA==, tableContent=null), ArticleFig(id=1322940276502823163, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=图4, caption=滑坡识别结果, figureFileSmall=vs5TJJnCYvOdfAoTG+lUpw==, figureFileBig=uTHsgJh5EgTAf4OAbGX0JA==, tableContent=null), ArticleFig(id=1322940276582514940, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Fig. 5, caption=Recognition results of landslides with different ratios, figureFileSmall=ZleiLYoqXp6rUGt2kdEvLw==, figureFileBig=r5aXeUX2y8hNVlUdTIVW6g==, tableContent=null), ArticleFig(id=1322940276662206719, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=图5, caption=不同比例滑坡识别结果, figureFileSmall=ZleiLYoqXp6rUGt2kdEvLw==, figureFileBig=r5aXeUX2y8hNVlUdTIVW6g==, tableContent=null), ArticleFig(id=1322940276888699136, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Tab. 1, caption=

Quantitative evaluation indicators for landslide identification

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 比例 准确度/% 召回率/% F1-Score
Mask R-CNN 9:1 92.17 88.10 0.860
Faster R-CNN 9:1 87.22 84.20 0.810
), ArticleFig(id=1322940276985168129, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=表1, caption=

滑坡识别定量化评价指标

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 比例 准确度/% 召回率/% F1-Score
Mask R-CNN 9:1 92.17 88.10 0.860
Faster R-CNN 9:1 87.22 84.20 0.810
), ArticleFig(id=1322940277257797890, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Tab. 2, caption=

Cross-validation results

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 比例 准确度/% 召回率/% F1-Score
Mask R-CNN 9:1 91.21 89.21 0.881
Faster R-CNN 9:1 86.21 87.43 0.823
), ArticleFig(id=1322940277345878275, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=表2, caption=

交叉验证结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 比例 准确度/% 召回率/% F1-Score
Mask R-CNN 9:1 91.21 89.21 0.881
Faster R-CNN 9:1 86.21 87.43 0.823
), ArticleFig(id=1322940277681422596, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=EN, label=Tab. 3, caption=

Model accuracy statistics

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 比例 准确度/% 召回率/% F1-Score
Mask R-CNN 9:1 92.17 88.10 0.860
8:2 78.10 75.34 0.754
7:3 70.55 61.30 0.620
6:4 61.50 52.11 0.510
Faster R-CNN 9:1 87.22 84.20 0.810
8:2 65.11 74.11 0.616
7:3 63.10 55.10 0.561
6:4 61.25 51.21 0.511
), ArticleFig(id=1322940277769502981, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, language=CN, label=表3, caption=

模型精度统计

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称 比例 准确度/% 召回率/% F1-Score
Mask R-CNN 9:1 92.17 88.10 0.860
8:2 78.10 75.34 0.754
7:3 70.55 61.30 0.620
6:4 61.50 52.11 0.510
Faster R-CNN 9:1 87.22 84.20 0.810
8:2 65.11 74.11 0.616
7:3 63.10 55.10 0.561
6:4 61.25 51.21 0.511
)], attaches=null, journal=Journal(id=1281211523964080133, delFlag=0, nameCn=大地测量与地球动力学, nameEn=Journal of Geodesy and Geodynamics, nameHistory1=null, nameHistory2=null, issn=1671-5942, eissn=null, cn=42-1655/P, coden=null, periodic=0, 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=BeWo6OWOseISH6uPOmc2hA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Geodesy and Geodynamics, journalRemark=null, publicationField=null, createdTime=1783394231074, updatedTime=1788951966472, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=D, firstLetterEn=D, subjectCode=Science, subjectName=null, subjectCodeEn=Science, subjectNameEn=null, picCn=BeWo6OWOseISH6uPOmc2hA==, picEn=YHLfVa8gITbOo0FeIjbLDg==, jcr=null, cjcr=null, exts=[JournalExt(id=1304522356412666698, language=CN, name=大地测量与地球动力学, 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=1788951966622, updatedTime=1788951966622, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1304522356576244555, language=EN, name=Journal of Geodesy and Geodynamics, 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=1788951966661, updatedTime=1788951966661, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.jgg09.com/journalx_ddcl/authorLogOn.action, submissionEditorUrl=http://www.jgg09.com/journalx_ddcl/editorLogOn.action, submissionReviewUrl=http://www.jgg09.com/journalx_ddcl/expertLogOn.action, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1281212831689347082, websiteList=[Website(id=1281216327125799907, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, 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/ddcl/CN, language=CN, createTime=1783395376235, createBy=18614031015, updateTime=1783395439358, updateBy=18614031015, name=大地测量与地球动力学-中文, tplId=1146099689490845704, title=大地测量与地球动力学, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216715371548758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=articleTextType, value=kx, createTime=1783395468800, updateTime=1783395468800, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715346382931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=banner, value=null, createTime=1783395468794, updateTime=1783395468794, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715400908889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=grayFlag, value=0, createTime=1783395468807, updateTime=1783395468807, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715333800018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395468791, updateTime=1783395468791, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715421880411, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=minRunFlag, value=0, createTime=1783395468812, updateTime=1783395468812, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715363160149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/CN/file/pic, createTime=1783395468798, updateTime=1783395468798, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715409297498, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=silenceFlag, value=0, createTime=1783395468809, updateTime=1783395468809, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715358965844, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1783395468797, updateTime=1783395468797, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715384131671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeColor, value=null, createTime=1783395468803, updateTime=1783395468803, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216715392520280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327125799907, code=themeStyle, value=null, createTime=1783395468805, updateTime=1783395468805, creator=18614031015, updator=18614031015)]), Website(id=1281216327713002474, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1281212831689347082, 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/ddcl/EN, language=EN, createTime=1783395376375, createBy=18614031015, updateTime=1783395435863, updateBy=18614031015, name=大地测量与地球动力学-英文, tplId=1146101810881728533, title=Journal of Geodesy and Geodynamics, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1281216680483328066, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=articleTextType, value=kx, createTime=1783395460482, updateTime=1783395460483, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680453967935, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=banner, value=null, createTime=1783395460475, updateTime=1783395460475, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680521076805, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=grayFlag, value=0, createTime=1783395460491, updateTime=1783395460491, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680437190718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=logo, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic?fileId=87adUdwolRb6UqGo0QjlJQ==, createTime=1783395460471, updateTime=1783395460471, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680542048327, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=minRunFlag, value=0, createTime=1783395460496, updateTime=1783395460496, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680474939457, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/ddcl/EN/file/pic, createTime=1783395460480, updateTime=1783395460480, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680533659718, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=silenceFlag, value=0, createTime=1783395460494, updateTime=1783395460494, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680462356544, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1783395460477, updateTime=1783395460477, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680495910979, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeColor, value=null, createTime=1783395460485, updateTime=1783395460485, creator=18614031015, updator=18614031015), WebsiteProps(id=1281216680508493892, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1281216327713002474, code=themeStyle, value=null, createTime=1783395460488, updateTime=1783395460488, creator=18614031015, updator=18614031015)])], journalTitle=大地测量与地球动力学, weixinUrl=null, journalUrl=http://www.jgg09.com/CN/home, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Geodesy and Geodynamics, journalPhotoCn=BeWo6OWOseISH6uPOmc2hA==, journalPhotoEn=YHLfVa8gITbOo0FeIjbLDg==, journalFirstLetter=D, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.03.090, detailUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/10.14075/j.jgg.2024.03.090, pdfUrlCn=https://castjournals.cast.org.cn/joweb/ddcl/CN/PDF/10.14075/j.jgg.2024.03.090, pdfUrlEn=https://castjournals.cast.org.cn/joweb/ddcl/EN/PDF/10.14075/j.jgg.2024.03.090, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1736870400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于Faster R-CNN和Mask R-CNN的滑坡自动识别研究
收藏切换
于宪煜 1 , 杨森 1
大地测量与地球动力学 | 地壳运动 2025,45(1): 1-4, 12
收起
收藏切换
大地测量与地球动力学 |地壳运动 2025 , 45 (1) : 1 -4, 12
基于Faster R-CNN和Mask R-CNN的滑坡自动识别研究
全屏
[Author(id=1322940263945076938, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yuxianyu@hbut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1322940264356118734, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940263945076938, language=EN, stringName=Xianyu YU, firstName=Xianyu, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China, bio={"content":"

YU Xianyu, PhD, assistant professor, majors in evaluation of landslide susceptibility, E-mail:

"}, bioImg=null, bioContent=

YU Xianyu, PhD, assistant professor, majors in evaluation of landslide susceptibility, E-mail:

, aboutCorrespAuthor=null), CN=AuthorExt(id=1322940264700051663, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940263945076938, language=CN, stringName=于宪煜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068, bio={"content":"

于宪煜,博士,副教授,主要从事滑坡易发性评价研究,E-mail:

"}, bioImg=null, bioContent=

于宪煜,博士,副教授,主要从事滑坡易发性评价研究,E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322940263840219334, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, xref=null, ext=[AuthorCompanyExt(id=1322940263852802247, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China), AuthorCompanyExt(id=1322940263865385160, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068)])]), Author(id=1322940265098510546, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, 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=1322940265211756756, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940265098510546, language=EN, stringName=Sen YANG, firstName=Sen, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1322940265534718165, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, authorId=1322940265098510546, language=CN, stringName=杨森, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1322940263840219334, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, xref=null, ext=[AuthorCompanyExt(id=1322940263852802247, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China), AuthorCompanyExt(id=1322940263865385160, tenantId=1146029695717560320, journalId=1281212831689347082, articleId=1322933544632320895, companyId=1322940263840219334, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068)])])]
于宪煜1 , 杨森1
作者信息
  • 1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068
作者简介:

于宪煜,博士,副教授,主要从事滑坡易发性评价研究,E-mail:

Research on Automatic Landslide Identification Based on Faster R-CNN and Mask R-CNN
Xianyu YU1 , Sen YANG1
Affiliations
  • 1 School of Civil Engineering Architecture and Environment, Hubei University of Technology, 28 Nanli Road, Wuhan 430068, China
  • YU Xianyu, PhD, assistant professor, majors in evaluation of landslide susceptibility, E-mail:

出版时间: 2025-01-15 doi: 10.14075/j.jgg.2024.03.090
文章导航
收藏切换

基于高分一号影像, 以三峡库区库首段为例, 通过目视解译出160个滑坡样本, 按照9:1比例分为训练样本和验证样本, 分别利用Faster R-CNN和Mask R-CNN算法构建滑坡自动识别模型。为进一步对比分析不同样本比例下两种模型的性能, 分别采用8:2、7:3、6:4的样本比例进行计算。研究结果表明, Mask R-CNN模型识别结果准确率、召回率和F1分数等3项指标均优于Faster R-CNN; 且经过交叉验证, 证明Mask R-CNN模型的性能更为稳定。

深度学习  /  滑坡识别  /  Mask R-CNN  /  Faster R-CNN  /  交叉验证

Based on the images from Gaofen-1 satellite, taking the first section of the Three Gorges reservoir as an example, 160 landslide samples are visually interpreted and divided into training and validation samples according to the ratio of 9:1. Then, landslide automatic identification models are constructed using Mask R-CNN and Faster R-CNN algorithms. To further compare and analyze the performance of the two models under different sample ratios, calculations are performed using sample ratios of 8:2, 7:3, and 6:4. The results show that the recognition results based on Mask R-CNN model are better than Faster R-CNN in three indicators, including precision, recall and F1 score. Moreover, cross-validation proves that the performance of Mask R-CNN model is more stable.

deep learning  /  landslide identification  /  Mask R-CNN  /  Faster R-CNN  /  cross-validation
于宪煜, 杨森. 基于Faster R-CNN和Mask R-CNN的滑坡自动识别研究. 大地测量与地球动力学, 2025 , 45 (1) : 1 -4, 12 . DOI: 10.14075/j.jgg.2024.03.090
Xianyu YU, Sen YANG. Research on Automatic Landslide Identification Based on Faster R-CNN and Mask R-CNN[J]. Journal of Geodesy and Geodynamics, 2025 , 45 (1) : 1 -4, 12 . DOI: 10.14075/j.jgg.2024.03.090
传统的滑坡勘测方法通常依赖于野外实地调查,这不仅需要投入大量的时间和人力,还需要消耗大量的物资。这种方法往往需要专家长时间深入山区进行详细的地质勘查和测绘工作,不仅工作量大,而且具有相当高的危险性[1]。近年来,遥感技术的迅速发展显著提升了遥感影像的分辨率,使得研究者能够更清晰、更详细地观察地表特征,从而更准确地识别和监测滑坡。目前,利用遥感影像进行滑坡识别的主流方法有目视解译法、像元法、面向对象法[2]等,但是均具有一定的局限性。目视解译法耗时较长,并且高度依赖专家的主观经验[3]。像元法在处理高分辨率影像时发挥着关键作用,尤其是在识别滑坡时。然而,高分辨率影像常常受到“椒盐噪声”的影响,这给滑坡识别带来了挑战[4]。面向对象的影像分割技术在滑坡识别中也面临着挑战与局限性,尽管光谱信息和纹理信息等数据源丰富,但在识别准确性上存在干扰,分类算法的选择也对结果产生重大影响。因此,解决这些挑战需要综合考虑不同数据源的特点,并结合有效的分类算法以提高识别的准确性和可靠性[5]。
近年来,随着深度学习在图像分类[6]、目标检测[7]、图像分割[8]等方面取得了重要成就,地质研究领域的学者们正在积极探索将卷积神经网络(convolutional neural networks, CNN)应用于滑坡识别任务中,并取得了令人瞩目的成果。Youssef等[9]比较SVM、CNN-1D、CNN-2D等方法在沙特阿拉伯阿西尔地区滑坡识别的效果发现, CNN识别精度优于SVM。虽然CNN在模型性能方面有所提升,但仍存在计算候选框速度受限、重复计算导致速度减慢等问题[10]。
在遥感影像的滑坡识别领域,Faster R-CNN算法引入区域候选网络(region proposal network, RPN),这一创新使得滑坡区域的检测和识别更为准确和高效,为地质灾害监测和预警提供了强大的工具和技术支持,可有效解决传统方法中候选区提取过多导致准确性下降的问题[11]。张倩荧[12]探讨在Faster R-CNN中使用不同类型的池化操作对滑坡识别的影响,比较最大池化和随机池化在这一任务中的效果发现,最大池化在提高识别效率和准确性方面具有更显著的优势。姜万冬等[13]的研究表明,Mask R-CNN不仅能够进行目标检测,还能够生成像素级的分割掩码,尤其适用于复杂背景下的滑坡识别,进一步提升了滑坡识别的精度和效率。
本文基于高分一号影像,以三峡库区首段为例,对比分析不同样本比例下Faster R-CNN和Mask R-CNN的滑坡自动识别性能,并采用K折交叉验证法对所得结果进行验证。
研究区位于长江三峡库区的库首区域,使用高分一号光学影像作为高分辨率遥感影像数据源,其分辨率达到2 m。图1是本文研究区的高分一号遥感影像,拍摄于2021-07-21。
Faster R-CNN是一种高效的目标检测算法,通过引入区域候选网络(RPN)实现端到端的目标检测。首先利用滑动窗口生成一系列候选区域,然后使用分类器和边界框回归器对这些区域进行分类和定位。通过引入兴趣区域(ROI)池化模块,可将不同尺寸的区域映射到固定大小的特征图上,从而实现兴趣区域对齐。此外,Faster R-CNN还采用多任务损失函数来联合优化分类器和边界框回归器,从而提高检测性能。而Mask R-CNN在此基础上进一步引入了Mask分支,实现对检测到的目标进行精确的像素级掩码预测,从而将目标检测任务拓展到语义分割领域。ROI Align则是Mask R-CNN中改进的兴趣区域对齐层,通过更精确的插值方式来提高掩码预测的准确性。整个系统由特征提取网络、区域候选网络和兴趣区域处理网络(R-CNN)组成,实现了高效且准确的目标检测和语义分割(图2)。
本文采用准确率(P)和召回率(R)来度量识别结果的精确性和全面性,计算公式为:
$P=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FP}}$
$R=\frac{\mathrm{TP}}{\mathrm{TP}+\mathrm{FN}}$
式中,真正例(TP)代表正确检测到的目标,假正例(FP)是错误地将背景分类为目标,假负例(FN)是未能正确检测到的目标。同时,为了更全面、准确地评估模型性能,结合准确率和召回率,引入F1分数(F1-Score):
$F 1=\frac{2 P R}{P+R}$
选用Anaconda作为建立和搭建深度学习的运行环境平台,并选用PyTorch和TensorFlow的组合作为深度学习框架,其他主要辅助软件包括Python、PyCharm、ENVI、ArcGIS和QGIS。实验基于Windows 11操作系统,采用11代Intel i7处理器、16 GB RAM、NVIDIA GeForce RTX 3060显卡作为设备硬件。
解译滑坡影像时,通过影像观察其地物特征是至关重要的。这些特征主要涵盖了形状、大小、阴影、色调、颜色、纹理以及图案等方面。本文对研究区的高分一号影像作目视解译,最终解译出160处滑坡(图3)。
在实验的数据预处理阶段,首先将切片设置为256像素×256像素大小,然后将实验数据集按照9 :1的比例划分为训练集和测试集,分别按照VOC2007和COCO数据集标准制作数据集,再将数据集输入到模型中,用于测试模型性能。模型的滑坡识别结果见图4。
图4(a)~(c)是Faster R-CNN模型识别结果,图4(d)~(f)是Mask R-CNN模型识别结果。图4结果显示,Faster R-CNN模型在对滑坡形状进行分割时表现良好,这是因为滑坡通常具有与周围地物不同的形状特征。然而,对于与滑坡在颜色特征上相近的地物(如人工建筑、梯田、河滩、公路等),其识别效果较差,容易出现误判现象(图4(b)、4(c));Mask R-CNN模型在滑坡识别任务中表现出色,成功将滑坡与在颜色特征上相近的地物区分开。具体的评价指标数据见表1。
由表1可见,当训练集和测试集的比例为9 :1时,Mask R-CNN模型3项评价指标(精准率92.17%、召回率88.10%、F1-Score 0.860)均优于Faster R-CNN模型(精准率度87.22%、召回率84.20%、F1-Score 0.810)。
为了解决训练集和验证集分配不同所带来的验证效果可能存在差异性的问题,更准确地说明模型的泛化能力和鲁棒性,减少因数据划分不同而引起的偶然性,本研究采用了K折交叉验证法(K-Fold)对数据进行训练(K=5)。这一步骤可以使得验证指标相对可靠,从而更好地评估模型的能力。对5组交叉验证的结果取平均值,得到各评价指标的数据(表2)。结果显示,在9 :1比例下,Mask R-CNN模型在各项评价指标上均优于Faster R-CNN模型。根据定义可知,准确度高时,表示模型识别出的滑坡中大部分为滑坡,只有少量非滑坡被误识别为滑坡,而召回率高可以让模型找出图片中更多的滑坡。可以判定,在训练集和测试集比例为9 :1时,Mask R-CNN模型的识别效果基本优于Faster R-CNN模型。
为进一步研究不同比例下的训练数据对滑坡识别分类结果的影响,将训练集和测试集分别划分为8 :2、7 :3和6 :4,Mask R-CNN实验结果如图5 (1、2、3、4分别是样本比例为9 :1、8 :2、7 :3和6 :4的结果,A、B、C、D是4组Mask R-CNN识别结果)所示。
由图5可见,随着训练集样本数量减少,4组识别结果的置信度均下降:A组模型正确识别滑坡置信度最大降幅为0.06,B组为0.41,C组为0.37,D组为0.40。随着训练集样本数量减少,4组识别结果的识别精度均下降,误识别和漏检概率均上升:B2、B4、C3、C4、D4出现误识别现象,D3出现漏检现象。结果可见,随着训练集比例的减少,Mask R-CNN模型的识别精度都有所下降,而且对于困难样本的识别精度也大幅下降。两个模型各评价指标的数据如表3所示。
由表3可见,训练集和测试集比例为9 :1的时候,Mask R-CNN和Faster R-CNN两个模型的评价指标都为最优。而随着训练集样本比例的下降,两个模型的评价指标数值均在下降,但Mask R-CNN模型仍优于Faster R-CNN模型。
本文利用Faster R-CNN和Mask R-CNN两种算法构建滑坡自动识别模型,借助国产高分辨率遥感卫星提供的高时效性和高可靠度的数据,对三峡库区巴东秭归区域进行了滑坡识别。得出以下主要结论:
1) 利用高分一号影像数据,并结合Faster R-CNN和Mask R-CNN等深度学习算法,在巴东秭归流域开展滑坡识别方法的研究与验证。实验结果表明,所提方法不仅在有效性上得到了充分验证,而且在可靠性上也表现出较高的水平,为流域内滑坡灾害的监测与预防提供了有力支持。
2) 验证结果表明,Mask R-CNN模型在研究区成功实现了对多个滑坡的识别,展现出其在同一地区内多目标识别的优越性,而且在识别人工建筑、梯田、河滩、公路等与滑坡颜色特征相近的这类困难样本时,仍然具有较高的识别率。
3) 5组交叉验证结果显示,Mask R-CNN模型3项评价指标均优于Faster R-CNN模型。本文提供了一种可行的方法来实现滑坡的自动识别,具有实际应用潜力。
  • 国家自然科学基金(41807297)
  • 生态环境岩土与河湖生态修复学科引智创新示范基地基金(2020EJB004)
参考文献 引证文献
排序方式:
1
Hölbling D , Füreder P , Antolini F , et al. A Semi-Automated Object-Based Approach for Landslide Detection Validated by Persistent Scatterer Interferometry Measures and Landslide Inventories[J]. Remote Sensing, 2012, 4 (5): 1310- 1336
2
Paw-luszek K , Marczak S , Borkowski A , et al. Multi-Aspect Analysis of Object-Oriented Landslide Detection Based on an Extended Set of LiDAR-Derived Terrain Features[J]. ISPRS International Journal of Geo-Information, 2019, 8 (8): 321
3
尹常铭. 基于机器学习的滑坡易发性区划和滑坡快速识别研究[D]. 大连: 大连理工大学, 2022
Yin Changming. Study on Landslide Susceptibility Zoning and Rapid Landslide Identification Based on Machine Learning[D]. Dalian: Dalian University of Technology, 2022
4
张帅娟. 变化检测和面向对象结合的高分辨率遥感影像滑坡体提取方法研究[D]. 成都: 西南交通大学, 2017
Zhang Shuaijuan. Study on Landslide Extraction Method from High-Resolution Remote Sensing Images by Combining Change Detection with Object-Oriented Method[D]. Chengdu: Southwest Jiaotong University, 2017
5
Lu P , Stumpf A , Kerle N , et al. Object-Oriented Change Detection for Landslide Rapid Mapping[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8 (4): 701- 705
6
Wang F, Jiang M Q, Qian C, et al. Residual Attention Network for Image Classification[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR), Honolulu, 2017
7
Zhao Z Q , Zheng P , Xu S T , et al. Object Detection with Deep Learning: A Review[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019, 30 (11): 3212- 3232
8
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation[M] //Navab N, Hornegger J, Wells W M, et al. Lecture Notes in Computer Science. Cham: Springer International Publishing, 2015
9
Youssef A M , Pradha B , Dikshit A , et al. Landslide Susceptibility Mapping Using CNN-1D and 2D Deep Learning Algorithms: Comparison of Their Performance at Asir Region, KSA[J]. Bulletin of Engineering Geology and the Environment, 2022, 165
10
Ren S Q , He K M , Girshick R , et al. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149
11
He K M, Zhang X Y, Ren S Q, et al. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition[C]. European Conference on Computer Vision, Cham, 2014
12
张倩荧. 卷积神经网络目标检测算法及其在滑坡领域的应用研究[D]. 宜昌: 三峡大学, 2019
Zhang Qianying. Research on Target Detection Algorithm of Convolutional Neural Network and Its Application in Landslide Field[D]. Yichang: China Three Gorges University, 2019
13
姜万冬, 席江波, 李振洪, 等. 模拟困难样本的Mask R-CNN滑坡分割识别[J]. 武汉大学学报: 信息科学版, 2023, 48 (12): 1931- 1942
Jiang Wandong , Xi Jiangbo , Li Zhenhong , et al. Landslide Detection and Segmentation Using Mask R-CNN with Simulated Hard Samples[J]. Geomatics and Information Science of Wuhan University, 2023, 48 (12): 1931- 1942
2025年第45卷第1期
20
7
引用本文
BibTeX
文章信息
doi: 10.14075/j.jgg.2024.03.090
  • 接收时间:2024-03-05
  • 首发时间:2026-10-30
  • 出版时间:2025-01-15
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-03-05
基金
National Natural Science Foundation of China(41807297)
国家自然科学基金(41807297)
Ecological Environment Geotechnical and River and Lake Ecological Restoration Discipline Intelligence Introduction and Innovation Demonstration Base Fund(2020EJB004)
生态环境岩土与河湖生态修复学科引智创新示范基地基金(2020EJB004)
作者信息
    1 湖北工业大学土木建筑与环境学院, 武汉市南李路28号, 430068
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/ddcl/CN/10.14075/j.jgg.2024.03.090
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏