Article(id=1211299028617269270, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1211299024825611053, articleNumber=null, orderNo=null, doi=10.12284/hyxb2023054, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1654531200000, receivedDateStr=2022-06-07, revisedDate=1666713600000, revisedDateStr=2022-10-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1766725793269, onlineDateStr=2025-12-26, pubDate=1677600000000, pubDateStr=2023-03-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1766725793269, onlineIssueDateStr=2025-12-26, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1766725793269, creator=13701087609, updateTime=1766725793269, updator=13701087609, issue=Issue{id=1211299024825611053, tenantId=1146029695717560320, journalId=1149651085930835976, year='2023', volume='45', issue='3', pageStart='1', pageEnd='158', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1766725792365, creator=13701087609, updateTime=1766924576395, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1212132785515532522, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1211299024825611053, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1212132785515532523, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1211299024825611053, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=125, endPage=135, ext={EN=ArticleExt(id=1211299028852150296, articleId=1211299028617269270, tenantId=1146029695717560320, journalId=1149651085930835976, language=EN, title=Research on automatic identification method of mangrove based on CU-Net model: Taking the Qi’ao Island in Zhuhai City, Guangdong Province as an example, columnId=1194652705852465724, journalTitle=Haiyang Xuebao, columnName=Article, runingTitle=null, highlight=null, articleAbstract=

Mangroves are important for maintaining biodiversity as well as ecological balance. Therefore, it is necessary to extract mangrove vegetation information efficiently and accurately and to monitor it in real time. A deep learning method for pixel-level accurate extraction of mangroves from high-resolution remote sensing images is presented in this paper. For the problem of low accuracy of mangrove remote sensing classification, CU-Net model for mangrove identification is constructed by introducing CLoss loss function by strengthening image center information and weakening edge information, and adding Dropout and Batch Normalization layers. And a new prediction model is constructed by sliding overlap splicing method, which effectively solves the problem of insufficient edge information and splicing traces in the prediction results. The recognition results of the proposed method are compared with the prediction results of U-Net, SegNet and DenseNet models as well as the traditional SVM and RF methods. The results show that the proposed model has stronger generalization ability and better recognition effect compared with other deep learning models. In the two test areas, the average OA and MIoU reach 94.43% and 88.12%, respectively. The average F1-score in mangrove and ordinary trees reach 95.96% and 90.49%, respectively. The accuracy is significantly higher than that of traditional SVM and RF methods, as well as several other neural networks. The effectiveness of the model in the field of mangrove recognition is verified, which can provide a new idea for the field of high resolution remote sensing mangrove recognition.

, correspAuthors=Xiaoping Rui, Xi Zhang, authorNote=null, correspAuthorsNote=null, copyrightStatement=Copyright © 2023 Pratacultural Science. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Mingge Yu, Xiaoping Rui, Yarong Zou, Xi Zhang), CN=ArticleExt(id=1211299032798990472, articleId=1211299028617269270, tenantId=1146029695717560320, journalId=1149651085930835976, language=CN, title=基于CU-Net模型的红树林自动识别方法研究, columnId=1149698756456657529, journalTitle=海洋学报, columnName=论文, runingTitle=null, highlight=null, articleAbstract=

红树林对维护生物多样性以及生态平衡等具有重要意义。因此,高效、精确地提取红树林植被信息以及实时对其进行监测十分必要。本文提出了一种高分辨率遥感影像红树林像素级精确提取的深度学习方法。针对红树林遥感分类精度不高的问题,通过强化图像中心信息,弱化边缘信息的方法引入CLoss损失函数,添加Dropout、Batch Normalization层构建了适用于红树林识别的CU-Net模型,采用滑动重叠拼接方法构建了新的预测模型,有效解决了预测结果边缘信息不足以及有拼接痕迹的问题。将本文方法的识别结果与U-Net、SegNet、DenseNet模型的预测结果以及传统的SVM、RF方法进行对比,结果表明,本文模型相较于其他深度学习模型泛化能力更强,识别效果更好,在两个测试区域的平均总体精度、平均交并比分别达到了94.43%、88.12%,平均F1-分数在红树林和普通树木的精度分别达到了95.96%、90.49%,精度明显高于传统的SVM、RF方法,也高于其他几种神经网络方法,验证了该模型在红树林识别领域的有效性,可为高分辨率遥感红树林识别领域提供一条新的思路。

, correspAuthors=芮小平, 张茜, authorNote=null, correspAuthorsNote=
*芮小平,教授,主要从事地理信息系统理论与应用方面的研究。E-mail:;
张茜,副研究员,主要从事海洋遥感方面的研究。E-mail:
, copyrightStatement=版权所有©《海洋学报》编辑部 2023, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=NNU6GbnUPbnLw2OFTjs2Zg==, magXml=FqI5AyE7iKig83ziJuN2Ag==, pdfUrl=null, pdf=ovz6FoeeSXAT26pYAwpzwg==, pdfFileSize=2785929, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=BuW7DiWNU8lId2RTYR9orw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=gh+71zClTgDfG5Gp7dsk/Q==, mapNumber=null, authorCompany=null, fund=null, authors=

蔚铭阁(1998-),女,河南省汝州市人,研究方向为深度学习和深度迁移学习识别红树林。E-mail:

, authorsList=蔚铭阁, 芮小平, 邹亚荣, 张茜)}, authors=[Author(id=1215304249001562549, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yumg@hhu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215304249102225851, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304249001562549, language=EN, stringName=Mingge Yu, firstName=Mingge, middleName=null, lastName=Yu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215304249198694850, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304249001562549, language=CN, stringName=蔚铭阁, firstName=铭阁, middleName=null, lastName=蔚, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 河海大学 地球科学与工程学院,江苏 南京 211100, bio={"content":"

蔚铭阁(1998-),女,河南省汝州市人,研究方向为深度学习和深度迁移学习识别红树林。E-mail:

"}, bioImg=null, bioContent=

蔚铭阁(1998-),女,河南省汝州市人,研究方向为深度学习和深度迁移学习识别红树林。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215304248468885902, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=1, ext=[AuthorCompanyExt(id=1215304248477274511, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248468885902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 河海大学 地球科学与工程学院,江苏 南京 211100)])]), Author(id=1215304249290969542, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ruixp@hhu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1215304249370661323, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304249290969542, language=EN, stringName=Xiaoping Rui, firstName=Xiaoping, middleName=null, lastName=Rui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215304249483907540, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304249290969542, language=CN, stringName=芮小平, firstName=小平, middleName=null, lastName=芮, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 河海大学 地球科学与工程学院,江苏 南京 211100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215304248468885902, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=1, ext=[AuthorCompanyExt(id=1215304248477274511, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248468885902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 河海大学 地球科学与工程学院,江苏 南京 211100)])]), Author(id=1215304250746393050, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215304250859639266, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304250746393050, language=EN, stringName=Yarong Zou, firstName=Yarong, middleName=null, lastName=Zou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215304250935136741, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304250746393050, language=CN, stringName=邹亚荣, firstName=亚荣, middleName=null, lastName=邹, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2 自然资源部国家卫星海洋应用中心,北京 100081
3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215304248628269466, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=2, ext=[AuthorCompanyExt(id=1215304248636658076, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248628269466, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 自然资源部国家卫星海洋应用中心,北京 100081)]), AuthorCompany(id=1215304248817013157, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=3, ext=[AuthorCompanyExt(id=1215304248825401767, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248817013157, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081)])]), Author(id=1215304251035800045, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangxi@mail.nsoas.org.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1215304251132269043, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304251035800045, language=EN, stringName=Xi Zhang, firstName=Xi, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, *, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215304251224543733, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, authorId=1215304251035800045, language=CN, stringName=张茜, firstName=茜, middleName=null, lastName=张, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, *, address=2 自然资源部国家卫星海洋应用中心,北京 100081
3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215304248628269466, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=2, ext=[AuthorCompanyExt(id=1215304248636658076, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248628269466, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 自然资源部国家卫星海洋应用中心,北京 100081)]), AuthorCompany(id=1215304248817013157, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=3, ext=[AuthorCompanyExt(id=1215304248825401767, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248817013157, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081)])])], keywords=[Keyword(id=1215304251396510205, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1215304251472007682, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, orderNo=2, keyword=mangrove identification), Keyword(id=1215304251560088068, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, orderNo=3, keyword=high-resolution remote-sensing images), Keyword(id=1215304251702694412, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, orderNo=4, keyword=convolutional neural network), Keyword(id=1215304251824329232, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1215304251899826711, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, orderNo=2, keyword=红树林识别), Keyword(id=1215304252004684319, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, orderNo=3, keyword=高分辨率遥感影像), Keyword(id=1215304252122124839, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, orderNo=4, keyword=卷积神经网络)], refs=[Reference(id=1215304256412898004, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Lee S Y, Primavera J H, Dahdouh-Guebas F, et al. Ecological role and services of tropical mangrove ecosystems: a reassessment[J]. Global Ecology and Biogeography, 2014, 23(7): 726−743., articleTitle=null, refAbstract=null), Reference(id=1215304256517755607, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Giri C, Ochieng E, Tieszen L L, et al. Status and distribution of mangrove forests of the world using Earth observation satellite data[J]. Global Ecology and Biogeography, 2011, 20(1): 154−159., articleTitle=null, refAbstract=null), Reference(id=1215304256639390426, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, 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=Field C D. Rehabilitation of mangrove ecosystems: an overview[J]. Marine Pollution Bulletin, 1999, 37(8−12): 383−392., articleTitle=null, refAbstract=null), Reference(id=1215304256740053727, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=甄佳宁, 廖静娟, 沈国状. 1987以来海南省清澜港红树林变化的遥感监测与分析[J]. 湿地科学, 2019, 17(1): 44−51., articleTitle=null, refAbstract=null), Reference(id=1215304256857494241, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, 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=Zhen Jianing, Liao Jingjuan, Shen Guozhuang. Remote sensing monitoring and analysis on the dynamics of mangrove forests in Qinglan Habor of Hainan Province since 1987[J]. Wetland Science, 2019, 17(1): 44−51., articleTitle=null, refAbstract=null), Reference(id=1215304256937186020, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaiphasa C, De Boer W F, Skidmore A K, et al. Impact of solid shrimp pond waste materials on mangrove growth and mortality: a case study from Pak Phanang, Thailand[J]. Hydrobiologia, 2007, 591(1): 47−57., articleTitle=null, refAbstract=null), Reference(id=1215304257037849319, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=冯家莉, 刘凯, 朱远辉, 等. 无人机遥感在红树林资源调查中的应用[J]. 热带地理, 2015, 35(1): 35−42., articleTitle=null, refAbstract=null), Reference(id=1215304257239175916, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, 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=Feng Jiali, Liu Kai, Zhu Yuanhui, et al. Application of unmanned aerial vehicles to mangrove resources monitoring[J]. Tropical Geography, 2015, 35(1): 35−42., articleTitle=null, refAbstract=null), Reference(id=1215304257344033521, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=罗丹, 李正会, 王德智, 等. 海口市东寨港红树林面积动态变化分析[J]. 农村经济与科技, 2013, 24(2): 97−99., articleTitle=null, refAbstract=null), Reference(id=1215304257461474038, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Luo Dan, Li Zhenghui, Wang Dezhi, et al. Analysis on dynamic change of mangrove area in Dongzhai Port, Haikou City[J]. Rural Economy and Science-Technology, 2013, 24(2): 97−99., articleTitle=null, refAbstract=null), Reference(id=1215304257562137341, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=李春干, 代华兵. 红树林空间分布信息遥感提取方法[J]. 湿地科学, 2014, 12(5): 580−589., articleTitle=null, refAbstract=null), Reference(id=1215304257633440512, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Chungan, Dai Huabing. Extraction of mangroves spatial distribution using remotely sensed data[J]. Wetland Science, 2014, 12(5): 580−589., articleTitle=null, refAbstract=null), Reference(id=1215304257734103811, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=梁超, 刘利, 刘建强, 等. 基于HY-1C CZI影像光谱指数重构数据MNF变换的红树林提取[J]. 海洋学报, 2020, 42(4): 104−112., articleTitle=null, refAbstract=null), Reference(id=1215304257817989895, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Liang Chao, Liu Li, Liu Jianqiang, et al. Extracting mangrove information using MNF transformation based on HY-1C CZI spectral indices reconstruction data[J]. Haiyang Xuebao, 2020, 42(4): 104−112., articleTitle=null, refAbstract=null), Reference(id=1215304257914458892, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Jia Mingming, Wang Zongming, Wang Chao, et al. A new vegetation index to detect periodically submerged mangrove forest using single-tide sentinel-2 imagery[J]. Remote Sensing, 2019, 11(17): 2043., articleTitle=null, refAbstract=null), Reference(id=1215304258006733586, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Muhsoni F F, Sambah A B, Mahmudi M, et al. Comparison of different vegetation indices for assessing mangrove density using sentinel-2 imagery[J]. International Journal of GEOMATE, 2018, 14(45): 42−51., articleTitle=null, refAbstract=null), Reference(id=1215304258094813973, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Baloloy A B, Blanco A C, Ana R R C S, et al. Development and application of a new mangrove vegetation index (MVI) for rapid and accurate mangrove mapping[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166: 95−117., articleTitle=null, refAbstract=null), Reference(id=1215304258187088664, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Manna S, Raychaudhuri B. Retrieval of leaf area index and stress conditions for Sundarban mangroves using Sentinel-2 data[J]. International Journal of Remote Sensing, 2020, 41(3): 1019−1039., articleTitle=null, refAbstract=null), Reference(id=1215304258275169051, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=徐芳, 张英, 翟亮, 等. 基于Sentinel-2的潮间红树林提取方法[J]. 测绘通报, 2020(2): 49−54., articleTitle=null, refAbstract=null), Reference(id=1215304258346472223, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Fang, Zhang Ying, Zhai Liang, et al. Extraction method of intertidal mangrove by using Sentinel-2 images[J]. Bulletin of Surveying and Mapping, 2020(2): 49−54., articleTitle=null, refAbstract=null), Reference(id=1215304258405192483, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=刘凯, 龚辉, 曹晶晶, 等. 基于多类型无人机数据的红树林遥感分类对比[J]. 热带地理, 2019, 39(4): 492−501., articleTitle=null, refAbstract=null), Reference(id=1215304258463912743, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Kai, Gong Hui, Cao Jingjing, et al. Comparison of mangrove remote sensing classification based on multi-type UAV data[J]. Tropical Geography, 2019, 39(4): 492−501., articleTitle=null, refAbstract=null), Reference(id=1215304259701232426, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=李想, 刘凯, 朱远辉, 等. 基于资源三号影像的红树林物种分类研究[J]. 遥感技术与应用, 2018, 33(2): 360−369., articleTitle=null, refAbstract=null), Reference(id=1215304259806090027, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Xiang, Liu Kai, Zhu Yuanhui, et al. Study on mangrove species classification based on ZY-3 image[J]. Remote Sensing Technology and Application, 2018, 33(2): 360−369., articleTitle=null, refAbstract=null), Reference(id=1215304259898364717, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Ballanti L, Blesius L, Hines E, et al. Tree species classification using hyperspectral imagery: a comparison of two classifiers[J]. Remote Sensing, 2016, 8(6): 445., articleTitle=null, refAbstract=null), Reference(id=1215304260024193845, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Wing B M, Ritchie M W, Boston K, et al. Prediction of understory vegetation cover with airborne Lidar in an interior ponderosa pine forest[J]. Remote Sensing of Environment, 2012, 124: 730−741., articleTitle=null, refAbstract=null), Reference(id=1215304260141634359, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Mondal P, Liu Xue, Fatoyinbo T E, et al. Evaluating combinations of sentinel-2 data and machine-learning algorithms for mangrove mapping in West Africa[J]. Remote Sensing, 2019, 11(24): 2928., articleTitle=null, refAbstract=null), Reference(id=1215304260229714745, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=蒙良莉. 基于哨兵多源遥感数据的红树林信息提取算法研究[D]. 南宁: 南宁师范大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1215304260326183742, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Meng Liangli. Mangrove information extraction algorithm based on multi-source remote sensing data of sentinel[D]. Nanning: Nanning Normal University, 2020., articleTitle=null, refAbstract=null), Reference(id=1215304260418458434, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Carranza-García M, García-Gutiérrez J, Riquelme J C. A framework for evaluating land use and land cover classification using convolutional neural networks[J]. Remote Sensing, 2019, 11(3): 274., articleTitle=null, refAbstract=null), Reference(id=1215304260523316037, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=黄亦其, 刘琪, 赵建晔, 等. 基于深度卷积神经网络的红树林物种无人机监测研究[J]. 中国农机化学报, 2020, 41(2): 141−146, 189., articleTitle=null, refAbstract=null), Reference(id=1215304260623979338, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yiqi, Liu Qi, Zhao Jianye, et al. Research on unmanned aerial surveillance of mangrove species based on deep convolutional neural network[J]. Journal of Chinese Agricultural Mechanization, 2020, 41(2): 141−146, 189., articleTitle=null, refAbstract=null), Reference(id=1215304260754002767, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Lassalle G, Ferreira M P, La Rosa L E C, et al. Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 189: 220−235., articleTitle=null, refAbstract=null), Reference(id=1215304260879831892, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[C]//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015: 234−241., articleTitle=null, refAbstract=null), Reference(id=1215304261014049625, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 3431−3440., articleTitle=null, refAbstract=null), Reference(id=1215304261085352798, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929−1958., articleTitle=null, refAbstract=null), Reference(id=1215304261152461665, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille: PMLR, 2015: 448−456., articleTitle=null, refAbstract=null), Reference(id=1215304261253124964, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale: JMLR, 2011: 315−323, articleTitle=null, refAbstract=null)], funds=[Fund(id=1215304256207377103, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, awardId=null, language=CN, fundingSource=海南省重点研发计划(高新技术专项);国家自然科学基金(41771478)。, fundOrder=null, country=null)], companyList=[AuthorCompany(id=1215304248468885902, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=1, ext=[AuthorCompanyExt(id=1215304248477274511, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248468885902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 河海大学 地球科学与工程学院,江苏 南京 211100)]), AuthorCompany(id=1215304248556966293, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=1, ext=[AuthorCompanyExt(id=1215304248561160598, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248556966293, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China)]), AuthorCompany(id=1215304248628269466, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=2, ext=[AuthorCompanyExt(id=1215304248636658076, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248628269466, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 自然资源部国家卫星海洋应用中心,北京 100081)]), AuthorCompany(id=1215304248720544158, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=2, ext=[AuthorCompanyExt(id=1215304248724738463, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248720544158, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2National Satellite Ocean Application Service, Ministry of Natural Resources, Beijing 100081, China)]), AuthorCompany(id=1215304248817013157, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=3, ext=[AuthorCompanyExt(id=1215304248825401767, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248817013157, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081)]), AuthorCompany(id=1215304248913482155, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, xref=3, ext=[AuthorCompanyExt(id=1215304248921870765, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, companyId=1215304248913482155, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3Key Laboratory of Space Ocean Remote Sensing and Application, Ministry of Natural Resources, Beijing 100081, China)])], figs=[ArticleFig(id=1215304252361200178, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 1, caption=Geographic location of the study area and regional remote-sensing images, figureFileSmall=2wS1kXWJb30f8BIsek0L9g==, figureFileBig=QR0xmnH/LDokd0Hw514ruw==, tableContent=null), ArticleFig(id=1215304252453474874, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图1, caption=研究区地理位置及区域遥感影像1, figureFileSmall=2wS1kXWJb30f8BIsek0L9g==, figureFileBig=QR0xmnH/LDokd0Hw514ruw==, tableContent=null), ArticleFig(id=1215304252575109703, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 2, caption=Schematic diagram of overlapping sliding window cropping, figureFileSmall=wwOzfvTJcRWURo+/ZWxs5Q==, figureFileBig=F4ZMlJw5jt7SaD/116uVLg==, tableContent=null), ArticleFig(id=1215304252654801489, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图2, caption=滑动窗口裁剪示意图, figureFileSmall=wwOzfvTJcRWURo+/ZWxs5Q==, figureFileBig=F4ZMlJw5jt7SaD/116uVLg==, tableContent=null), ArticleFig(id=1215304252734493269, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 3, caption=GF-1 sample set of fused images and their corresponding labels, figureFileSmall=i/KqhVj46UDNTUg1vpD71A==, figureFileBig=TEvIQpZOjBPW98jw9H5PHA==, tableContent=null), ArticleFig(id=1215304252826767963, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图3, caption=融合后的 GF-1 样本集影像和标签图, figureFileSmall=i/KqhVj46UDNTUg1vpD71A==, figureFileBig=TEvIQpZOjBPW98jw9H5PHA==, tableContent=null), ArticleFig(id=1215304252923236957, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 4, caption=Flow chart of the method applied in this paper, figureFileSmall=Y/BXlRxPxvckOYP4C/j9kg==, figureFileBig=2zJlSb8WqslLArJxqj3OyA==, tableContent=null), ArticleFig(id=1215304252994540129, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图4, caption=本文方法流程图, figureFileSmall=Y/BXlRxPxvckOYP4C/j9kg==, figureFileBig=2zJlSb8WqslLArJxqj3OyA==, tableContent=null), ArticleFig(id=1215304253099397736, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 5, caption=CU-Net model structure, figureFileSmall=tMv9/m9ICrZqn4fmz+s55g==, figureFileBig=DXbgjdVAiZ9Q93/ZDqNsnQ==, tableContent=null), ArticleFig(id=1215304253179089514, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图5, caption=CU-Net模型结构, figureFileSmall=tMv9/m9ICrZqn4fmz+s55g==, figureFileBig=DXbgjdVAiZ9Q93/ZDqNsnQ==, tableContent=null), ArticleFig(id=1215304253237809774, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 6, caption=CLoss calculation area diagram, figureFileSmall=H2c5dICdfwuoin7PzfwcXg==, figureFileBig=lYjmJXmufiifuxWTKM1zNg==, tableContent=null), ArticleFig(id=1215304253313307255, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图6, caption=CLoss 计算区域示意图, figureFileSmall=H2c5dICdfwuoin7PzfwcXg==, figureFileBig=lYjmJXmufiifuxWTKM1zNg==, tableContent=null), ArticleFig(id=1215304253405581951, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 7, caption=Feature-mapping maps of 10 convolutional layers of the input image, figureFileSmall=DlOMEluTvJmM9NRB+SjUCA==, figureFileBig=W9lNXvuAzhvw+bq5D6eNiA==, tableContent=null), ArticleFig(id=1215304253472690820, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图7, caption=输入图像的10 个卷积层特征映射图, figureFileSmall=DlOMEluTvJmM9NRB+SjUCA==, figureFileBig=W9lNXvuAzhvw+bq5D6eNiA==, tableContent=null), ArticleFig(id=1215304253560771208, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 8, caption=Diagram of prediction method, figureFileSmall=X1+nCQchLIcok0cOtQO0vA==, figureFileBig=0sKW56jya1ve1mo4qtmuhQ==, tableContent=null), ArticleFig(id=1215304253636268690, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图8, caption=预测方法示意图, figureFileSmall=X1+nCQchLIcok0cOtQO0vA==, figureFileBig=0sKW56jya1ve1mo4qtmuhQ==, tableContent=null), ArticleFig(id=1215304253690794646, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 9, caption=Accuracy and loss graphs for the training and validation datasets, figureFileSmall=JTAgPsB1ZkyNvZVxUZR9RA==, figureFileBig=hhGyXyEOXsFGNKpQbDhgbg==, tableContent=null), ArticleFig(id=1215304253770486424, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图9, caption=训练集和验证集的准确率和损失值, figureFileSmall=JTAgPsB1ZkyNvZVxUZR9RA==, figureFileBig=hhGyXyEOXsFGNKpQbDhgbg==, tableContent=null), ArticleFig(id=1215304253850178206, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 10, caption=Comparison of mangrove identification results in the test area, figureFileSmall=oeB8a6DMjNkhgvpKh6qBOQ==, figureFileBig=jR/1wfEkAt2LuM0BX+v+CA==, tableContent=null), ArticleFig(id=1215304253950841505, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图10, caption=测试区红树林识别结果对比图, figureFileSmall=oeB8a6DMjNkhgvpKh6qBOQ==, figureFileBig=jR/1wfEkAt2LuM0BX+v+CA==, tableContent=null), ArticleFig(id=1215304255213327016, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Fig. 11, caption=Difference images for the six methods in the test area, figureFileSmall=lnuDq4ov0RlEM5IRboJUyw==, figureFileBig=nuyRe4IaenhqZuuY0kzXxA==, tableContent=null), ArticleFig(id=1215304255305601709, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=图11, caption=测试区域6种方法的差分图像, figureFileSmall=lnuDq4ov0RlEM5IRboJUyw==, figureFileBig=nuyRe4IaenhqZuuY0kzXxA==, tableContent=null), ArticleFig(id=1215304255402070706, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Table 1, caption=

GF-1 satellite image parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
载荷谱段号谱段范围/μm空间分辨率/m幅宽/km
全色相机10.45~0.90260
多光谱相机20.45~0.52860
30.52~0.59860
40.63~0.69860
50.77~0.89860
), ArticleFig(id=1215304255485956787, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=表1, caption=

GF-1卫星影像参数

, figureFileSmall=null, figureFileBig=null, tableContent=
载荷谱段号谱段范围/μm空间分辨率/m幅宽/km
全色相机10.45~0.90260
多光谱相机20.45~0.52860
30.52~0.59860
40.63~0.69860
50.77~0.89860
), ArticleFig(id=1215304255569842871, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Table 2, caption=

Network training parameters setting

, figureFileSmall=null, figureFileBig=null, tableContent=
参数具体设置
批处理大小16
学习率0.000 1
训练次数300
优化器Adam
), ArticleFig(id=1215304255628563132, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=表2, caption=

网络训练参数设置

, figureFileSmall=null, figureFileBig=null, tableContent=
参数具体设置
批处理大小16
学习率0.000 1
训练次数300
优化器Adam
), ArticleFig(id=1215304255712449217, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Table 3, caption=

Test area 1 precision evaluation results

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区CU-NetU-NetSegNetDenseNetSVMRF
红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木
总体精度/%94.0091.5492.0188.3379.8073.91
平均交并比/%87.2183.3583.3676.1865.3160.59
F1-分数/%95.7889.1693.3984.2994.4285.2691.1372.0983.4654.8175.4554.60
), ArticleFig(id=1215304255796335300, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=表3, caption=

测试区域1的精度评价结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区CU-NetU-NetSegNetDenseNetSVMRF
红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木
总体精度/%94.0091.5492.0188.3379.8073.91
平均交并比/%87.2183.3583.3676.1865.3160.59
F1-分数/%95.7889.1693.3984.2994.4285.2691.1372.0983.4654.8175.4554.60
), ArticleFig(id=1215304255905387205, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=EN, label=Table 4, caption=

Test area 2 precision evaluation results

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区CU-NetU-NetSegNetDenseNetSVMRF
红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木
总体精度/%94.8691.2892.5986.6764.3872.69
平均交并比/%89.0383.7784.7475.0351.6057.30
F1-分数/%96.1491.8291.0588.6192.1592.3286.6874.8546.9955.3348.6271.86
), ArticleFig(id=1215304255989273287, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1211299028617269270, language=CN, label=表4, caption=

测试区域2的精度评价结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区CU-NetU-NetSegNetDenseNetSVMRF
红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木红树林其他树木
总体精度/%94.8691.2892.5986.6764.3872.69
平均交并比/%89.0383.7784.7475.0351.6057.30
F1-分数/%96.1491.8291.0588.6192.1592.3286.6874.8546.9955.3348.6271.86
)], attaches=null, journal=Journal(id=1146441459026210850, delFlag=0, nameCn=海洋学报, nameEn=Haiyang Xuebao, nameHistory1=null, nameHistory2=null, issn=0253-4193, eissn=null, cn=11-2055/P, coden=null, periodic=0, language=CN, oaType=否, 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=uYi7hkkrve+l8pIcwqcaQQ==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1751262543687, updatedTime=1761729782936, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=H, firstLetterEn=H, subjectCode=Natural Sciences, subjectName=Natural Sciences, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=uYi7hkkrve+l8pIcwqcaQQ==, picEn=C0WLQb7uW3ok8EkkVOAGuw==, jcr=null, cjcr=null, exts=[JournalExt(id=1190344242636624294, language=CN, name=海洋学报, 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.hyxbocean.cn/, createdTime=1761729782971, updatedTime=1761729782971, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.hyxb.org.cn/aos/ch/author/login.aspx, submissionEditorUrl=http://www.hyxb.org.cn/aos/ch/login.aspx, submissionReviewUrl=http://www.hyxb.org.cn/aos/ch/auditor/login.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190344242712121767, language=EN, name=Haiyang Xuebao, 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.aosocean.com/, createdTime=1761729782989, updatedTime=1761729782989, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.hyxb.org.cn/aos/ch/author/login.aspx, submissionEditorUrl=http://www.hyxb.org.cn/aos/ch/login.aspx, submissionReviewUrl=http://www.hyxb.org.cn/aos/ch/auditor/login.aspx, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1149651085930835976, websiteList=[Website(id=1188165202219512001, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1149651085930835976, 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/hyxb/CN, language=CN, createTime=1761210259251, createBy=18614031015, updateTime=1761210330879, updateBy=18614031015, name=海洋学报-中文, tplId=1146099689490845704, title=海洋学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1188166688563413602, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=articleTextType, value=kx, createTime=1761210613623, updateTime=1761210613623, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688538247775, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=banner, value=null, createTime=1761210613617, updateTime=1761210613617, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688529859166, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=logo, value=https://castjournals.cast.org.cn/joweb/hyxb/CN/file/pic?fileId=BDEio/cxHnid8OD4QxrAYQ==, createTime=1761210613615, updateTime=1761210613615, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688555024993, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/hyxb/CN/file/pic, createTime=1761210613621, updateTime=1761210613621, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688546636384, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761210613619, updateTime=1761210613619, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688575996515, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=themeColor, value=null, createTime=1761210613626, updateTime=1761210613626, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166688596968036, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202219512001, code=themeStyle, value=null, createTime=1761210613631, updateTime=1761210613631, creator=18614031015, updator=18614031015)]), Website(id=1188165202282426564, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1149651085930835976, 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/hyxb/EN, language=EN, createTime=1761210259266, createBy=18614031015, updateTime=1761210377920, updateBy=18614031015, name=海洋学报-英文, tplId=1146101810881728533, title=Haiyang Xuebao, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1188166798101856873, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=articleTextType, value=kx, createTime=1761210639739, updateTime=1761210639739, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798076691046, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=banner, value=null, createTime=1761210639733, updateTime=1761210639733, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798068302437, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=logo, value=https://castjournals.cast.org.cn/joweb/hyxb/EN/file/pic?fileId=BDEio/cxHnid8OD4QxrAYQ==, createTime=1761210639731, updateTime=1761210639731, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798093468264, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/hyxb/EN/file/pic, createTime=1761210639737, updateTime=1761210639737, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798085079655, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761210639735, updateTime=1761210639735, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798106051178, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=themeColor, value=null, createTime=1761210639740, updateTime=1761210639740, creator=18614031015, updator=18614031015), WebsiteProps(id=1188166798110245483, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1188165202282426564, code=themeStyle, value=null, createTime=1761210639741, updateTime=1761210639741, creator=18614031015, updator=18614031015)])], journalTitle=海洋学报, weixinUrl=null, journalUrl=http://www.hyxbocean.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Haiyang Xuebao, journalPhotoCn=uYi7hkkrve+l8pIcwqcaQQ==, journalPhotoEn=C0WLQb7uW3ok8EkkVOAGuw==, journalFirstLetter=H, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/hyxb/CN/10.12284/hyxb2023054, detailUrlEn=https://castjournals.cast.org.cn/joweb/hyxb/EN/10.12284/hyxb2023054, pdfUrlCn=https://castjournals.cast.org.cn/joweb/hyxb/CN/PDF/10.12284/hyxb2023054, pdfUrlEn=https://castjournals.cast.org.cn/joweb/hyxb/EN/PDF/10.12284/hyxb2023054, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于CU-Net模型的红树林自动识别方法研究
收藏切换
PDF下载
蔚铭阁 1 , 芮小平 1, * , 邹亚荣 2, 3 , 张茜 2, 3, *
海洋学报 | 论文 2023,45(3): 125-135
收起
收藏切换
海洋学报 | 论文 2023, 45(3): 125-135
基于CU-Net模型的红树林自动识别方法研究
全屏
蔚铭阁1 , 芮小平1, * , 邹亚荣2, 3, 张茜2, 3, *
作者信息
  • 1 河海大学 地球科学与工程学院,江苏 南京 211100
  • 2 自然资源部国家卫星海洋应用中心,北京 100081
  • 3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081
  • 蔚铭阁(1998-),女,河南省汝州市人,研究方向为深度学习和深度迁移学习识别红树林。E-mail:

通讯作者:

*芮小平,教授,主要从事地理信息系统理论与应用方面的研究。E-mail:;
张茜,副研究员,主要从事海洋遥感方面的研究。E-mail:
Research on automatic identification method of mangrove based on CU-Net model: Taking the Qi’ao Island in Zhuhai City, Guangdong Province as an example
Mingge Yu1 , Xiaoping Rui1, * , Yarong Zou2, 3, Xi Zhang2, 3, *
Affiliations
  • 1School of Earth Sciences and Engineering, Hohai University, Nanjing 211100, China
  • 2National Satellite Ocean Application Service, Ministry of Natural Resources, Beijing 100081, China
  • 3Key Laboratory of Space Ocean Remote Sensing and Application, Ministry of Natural Resources, Beijing 100081, China
出版时间: 2023-03-01 doi: 10.12284/hyxb2023054
文章导航
收藏切换

红树林对维护生物多样性以及生态平衡等具有重要意义。因此,高效、精确地提取红树林植被信息以及实时对其进行监测十分必要。本文提出了一种高分辨率遥感影像红树林像素级精确提取的深度学习方法。针对红树林遥感分类精度不高的问题,通过强化图像中心信息,弱化边缘信息的方法引入CLoss损失函数,添加Dropout、Batch Normalization层构建了适用于红树林识别的CU-Net模型,采用滑动重叠拼接方法构建了新的预测模型,有效解决了预测结果边缘信息不足以及有拼接痕迹的问题。将本文方法的识别结果与U-Net、SegNet、DenseNet模型的预测结果以及传统的SVM、RF方法进行对比,结果表明,本文模型相较于其他深度学习模型泛化能力更强,识别效果更好,在两个测试区域的平均总体精度、平均交并比分别达到了94.43%、88.12%,平均F1-分数在红树林和普通树木的精度分别达到了95.96%、90.49%,精度明显高于传统的SVM、RF方法,也高于其他几种神经网络方法,验证了该模型在红树林识别领域的有效性,可为高分辨率遥感红树林识别领域提供一条新的思路。

深度学习  /  红树林识别  /  高分辨率遥感影像  /  卷积神经网络

Mangroves are important for maintaining biodiversity as well as ecological balance. Therefore, it is necessary to extract mangrove vegetation information efficiently and accurately and to monitor it in real time. A deep learning method for pixel-level accurate extraction of mangroves from high-resolution remote sensing images is presented in this paper. For the problem of low accuracy of mangrove remote sensing classification, CU-Net model for mangrove identification is constructed by introducing CLoss loss function by strengthening image center information and weakening edge information, and adding Dropout and Batch Normalization layers. And a new prediction model is constructed by sliding overlap splicing method, which effectively solves the problem of insufficient edge information and splicing traces in the prediction results. The recognition results of the proposed method are compared with the prediction results of U-Net, SegNet and DenseNet models as well as the traditional SVM and RF methods. The results show that the proposed model has stronger generalization ability and better recognition effect compared with other deep learning models. In the two test areas, the average OA and MIoU reach 94.43% and 88.12%, respectively. The average F1-score in mangrove and ordinary trees reach 95.96% and 90.49%, respectively. The accuracy is significantly higher than that of traditional SVM and RF methods, as well as several other neural networks. The effectiveness of the model in the field of mangrove recognition is verified, which can provide a new idea for the field of high resolution remote sensing mangrove recognition.

deep learning  /  mangrove identification  /  high-resolution remote-sensing images  /  convolutional neural network
蔚铭阁, 芮小平, 邹亚荣, 张茜. 基于CU-Net模型的红树林自动识别方法研究. 海洋学报, 2023 , 45 (3) : 125 -135 . DOI: 10.12284/hyxb2023054
Mingge Yu, Xiaoping Rui, Yarong Zou, Xi Zhang. Research on automatic identification method of mangrove based on CU-Net model: Taking the Qi’ao Island in Zhuhai City, Guangdong Province as an example[J]. Haiyang Xuebao, 2023 , 45 (3) : 125 -135 . DOI: 10.12284/hyxb2023054
红树林是热带、亚热带海岸带海陆交错区生产能力最高的海洋生态系统之一[1],在净化海水、防风消浪、固碳储碳、维护生物多样性等方面发挥着重要作用[2],是珍稀濒危水禽重要栖息地,也是鱼、虾、蟹、贝类生长繁殖场所。因此,高效、精确地提取红树林植被信息以及对其进行实时监测十分必要。红树林多生长在潮间带和沼泽等特殊区域,在进行大规模监测时,传统的人工实地调查方法需要耗费大量人力物力以及时间成本[3]。而遥感技术的快速发展为红树林信息的提取及监测提供了强有力的手段,可以实现大范围、长时序、快速准确的观测[4-5]
目前识别红树林的方法主要包括目视解译[6-7]、植被指数[8-14]、面向对象[15-20]等方法。人工目视解译方法由于不需要实地踏勘在一段时间内被广泛使用,但其对解译人员专业知识依赖程度较高,人力、物力等投入大,无法在较短时间内完成大面积红树林识别。而只依靠植被指数进行红树林识别的方法易受到雾、云、雨天气的影响,难以区分红树林与普通树木,提取精度较低。最常用的面向对象的支持向量机分类方法(SVM)[17]因潮汐条件不确定,很难找到有代表性的训练样本,所提取的斑块较为破碎,参数设置无法科学寻优。面向对象的随机森林(RF)[18]分类器的发展弥补了这一限制,但该方法容易受到斑点噪声干扰而出现“椒盐现象”。以上方法大多采用的数据源为Landsat、SPOT、Quickbird等多光谱卫星影像,基于其波谱信息进行红树林信息提取。
近年来,深度学习被广泛应用于目标识别、图像分类等领域。其数据源主要是高分辨率的遥感影像,主要基于影像的光学信息,依靠卷积神经网络进行深层次特征的精确提取,并且该方法对输入图像的大小也没有限制,具有较强的鲁棒性,因此在大规模图像处理方面备受欢迎[21]。黄亦其等[22]利用改进的LeNet-5网络实现了红树林物种的分类,总体识别精度达到了87.31%;Lassalle等[23]将深度学习与高分辨率卫星图像结合,实现了红树林个体树冠的圈定。但整体上该方法在红树林识别方面的应用研究还较少,存在预测结果边缘信息不足以及拼接痕迹的问题。
因此,本文以GF-1高分辨率遥感影像为基础,通过引入新的损失函数,构建了用于红树林精确识别的CU-Net模型,另外,提出滑动重叠拼接方法进行结果预测,有效解决了边缘信息不足以及拼接痕迹的问题,以期进一步提高红树林识别精度,为红树林的监测、管理工作提供技术支持,也为红树林信息提取领域提供一种新的研究思路。
淇澳岛位于广东省珠海市香洲区东北部13 km,珠江口内西侧处,其地理坐标范围为22°23′08″~22°26′52″N,113°35′31″~113°40′18″E,全岛面积为23.8 km2,是伶仃洋岛群中陆地面积最大的岛屿。该区域属于南亚热带海洋性气候,年平均气温为22.4°C,年降水量为1 964.4 mm。1998年始,珠海市政府就投入大量资金引种扩种红树林,2000年正式批准成立淇澳岛红树林保护区,现今红树林湿地面积达到394.6 hm2,该地区树木种类繁多,红树林面积较大,生态环境良好,是一个复杂且具有代表性的研究领域,可以很好地验证模型在提取红树林时的抗干扰能力。该研究区地理位置及区域遥感影像如图1所示。
本文实验数据采用珠海市淇澳岛的GF-1卫星遥感影像数据。GF-1卫星于2013年4月26日发射,有两台高分相机(PMS1、PMS2),本文使用的是PMS1相机于2021年2月1日12时34分拍摄的高分辨率遥感影像,该时刻潮汐相对较低,红树林裸露率高,特征较为明显。该影像包括空间分辨率为2 m的全色影像和8 m的多光谱影像,GF-1卫星影像的参数见表1。本文数据集真实标签是基于2021年4月份去淇澳岛实地踏勘的结果以及对高分影像目视解译综合结果进行制作的,具有一定的可靠性。
本文首先从研究区域选择了一部分既含有红树林又含有其他树木的GF-1遥感影像作为样本区影像。接着对GF-1样本区的全色影像和多光谱影像进行了辐射校正、大气校正、正射校正,之后通过ENVI 5.3的NNDiffuse Pan Sharpening工具对校正后的全色影像和多光谱影像进行融合,并将该影像的波段4、波段3、波段2按顺序提取出来。在融合完成之后,本文基于实地踏勘结果以及对GF-1进行目视解译的结果使用ArcGIS 10.7创建训练集区域的矢量标签,并将不同类型字段值修改为转为栅格的灰度值,随后用Feature to Raster工具完成GF-1红树林标签数据集的制作,在此过程中,我们用红色(像素值为255,0,0)对红树林部分进行标注,用绿色(像素值为0,255,0)对其他类型的树木进行标注。标注完成后,利用Python代码对处理后的影像及标签进行滑动窗口(256像素×256像素)裁剪,该方法的裁剪示意图如图2所示。为防止过拟合,对原数据集采用旋转(水平、垂直)、对角镜像、添加噪声(高斯噪声、椒盐噪声等)的方式进行数据增强。增强后得到样本数据集4 000组,其中训练集3 000组,验证集1 000组。本实验GF-1样本集的影像图和标签图一一对应,如图3所示。
红树林识别的重点在于通过卷积神经网络学习更深层次的特征从而准确的将红树林与其他树木分辨出来。本文方法流程图如图4所示。具体步骤如下:
(1)数据预处理:对GF-1影像进行融合等预处理,以处理后的影像为基础通过目视解读进行人工标注获得真实的样本标签,利用滑动窗口裁剪方法生成256像素×256像素的样本数据集,将其格式由tiff转换为png,最后进行数据增强处理,划分为训练集和验证集。
(2)构建CU-Net模型:为了使模型更快收敛达到最优以及更精确的进行特征提取,我们改进了U-Net网络,构建了CU-Net模型。
(3)训练CU-Net模型:将GF-1样本集输入CU-Net模型进行训练,调整参数,保存最优GF-1红树林识别模型。
(4)构建滑动拼接预测模型:采用滑动重叠拼接的方法构建一个预测模型,以便消除边界拼接痕迹、丰富图像边缘信息。
(5)预测结果识别:将测试集输入预测模型进行预测成图,得到红树林识别结果。
(6)精度评价:将测试区的预测图与真值图进行对比,选择总体精度(OA)、F1-分数(F1-Score)、平均交并比(MIoU)等评价指标进行精度评价。
Ronneberger等[24]根据端到端的全卷积神经网络[25]提出了U-Net网络,该网络因形状呈“U”型而得名,左半部分是压缩路径,由两个3×3的卷积层加上ReLU非线性变换再加上一个2×2的最大池压层组成的一个下采样模块,主要作用是进行特征提取。右半部分是扩展路径,由一个上采样的卷积层加上特征拼接加上两个3×3的卷积层再加上ReLU非线性变换反复构成,主要用来实现精准定位。压缩路径和扩展路径均有4块采样模块,最后通过特征拼接加上两个3×3的卷积层加上一个1×1的卷积层和Softmax函数得到分类结果。CU-Net网络以U-Net网络为基础架构,在第四和第五组卷积操作后分别添加了概率为0.6的Dropout[26]层,即在每次训练迭代中,以0.6的概率丢弃神经元,可有效防止过拟合,并在每次卷积之后添加批归一化(Batch Normalization, BN)[27]处理层,对输入数据先进行归一化处理再输入下一层,可有效提升网络训练速度,CU-Net模型结构如图5所示(图中D表示结果图)。归一化层数学表达式为
$ {{{y}}^{(k)}} = {\gamma ^{(k)}}{\overline x ^{(k)}} + {\beta ^{(k)}} \text{,} $
式中,$ {y^{(k)}} $代表第$ k $层的归一化处理结果;$ {\overline x ^{(k)}} $代表标准差归一化结果;$ {\gamma ^{(k)}} $$ {\beta ^{(k)}} $表示学习参数。
另外,CU-Net采用忽略边缘交叉熵函数作为损失函数,以分类交叉熵函数(CELoss)为基础进行改进,记为CLoss,其表达式为
$ {\rm{CLoss}} = \frac{1}{{r \times N}}\sum\limits_{i = 1}^{r \times N} {\sum\limits_{c = 1}^M {y_c^i} } {\rm{lg}} (p_c^i) \text{,} $
式中,$ r $为所选区域像元数目(a)占整个图像像元数目(A)的比例,即$ r = a/A $$ N $为样本图像像元总数;$ M $为包括背景类别的类别总数;$ y_c^i $$ \left\{ {c = 1,2,\cdots ,M} \right\} $$ M $通道由0和1组成的张量;$ p_c^i\left\{ {c = 1,2,\cdots ,M} \right\} $为样本向前传播所获得的$ M $层像素类别概率值组成的张量。$ y_c^i $$ p_c^i $之间差值一般由损失函数loss量化计算,差值越小,参数越接近最优,模型效果越好。
该损失函数计算区域示意图如图6所示,即在进行损失值计算时,选择中间$ a $区域进行计算,而不是整个图像区域A,因为图像中间区域邻域范围广阔,结合自身特征信息以及周边邻域信息,很容易判定所属类别,但边缘区域由于裁剪操作导致其邻域信息丢失,仅剩的信息不足以判断出其所属类别,一般的模型在训练时为了降低损失值,会将缺乏特征信息的边缘区域与真实值强制拟合,就会出现图像边缘信息缺失导致的过拟合问题,此损失函数可以有效解决这个问题,并在一定程度上提高分类精度。
卷积神经网络的一个重要组件就是卷积层,它承担了深度学习过程中的大部分计算工作,主要由带有一组固定权重神经元的卷积核叠加组成,多个卷积核滑动对某个区域做卷积运算,即可实现神经网络对高层次抽象特征的提取。卷积操作表达式为
$ {Y_{s,t}} = f\left(\sum\limits_{{{{\rm{m}} = 1}}}^M {\sum\limits_{n = 1}^N {{\omega _{m,n}}} } \times {x_{i + m,j + n}} + b\right) \text{,} $
式中,$ M $$ N $分别表示卷积核的宽和高;$ {\omega _{m,n}} $表示卷积核第$ m $$ n $列的权值参数;$ b $为偏置参数;$ i $$ j $分别表示卷积核在特征图上滑动了$ i $行、$ j $列;$ {x_{i + m,j + n}} $为特征图第$ i + m $行,$ j + n $列的像素值;$ f( \cdot ) $为非线性激活函数;$ {Y_{s,t}} $表示特征图经卷积运算后输出的第$ s $$ t $列像素值。
卷积层通常与激活函数结合使用,通过引入非线性因素模拟生物神经元受到激励的过程,去除数据冗余,以实现更好的特征映射,其常用的激活函数有Sigmoid、tanh和ReLU,其中ReLU函数相较于其他两种函数无需对输入归一化,并且具有稀疏激活性[28],即能够模仿神经元只对输入信号的小部分选择性响应,大量信号被刻意屏蔽,这样可以提高学习的精度,更好更快地提取稀疏特征,也能有效的防止过拟合,本文选取ReLU激活函数,其表达式为
$ f(x) = \max (0,x) . $
本文将CU-Net模型的卷积层进行特征提取的过程进行了可视化。该模型的特征提取器共包括10个(5组)卷积层,均采用3×3的卷积核,第1~5组分别有32、64、128、256、512个卷积核,将各组所有通道提取的特征图进行融合即可得到每个卷积层的特征映射图。本文模型识别红树林的特征映射图如图7所示。
在训练好模型进行预测时,如果将较大的待预测遥感影像直接输入到模型中会导致内存溢出,因此一般将待预测图像裁剪为一系列较小的图像,然后分别输入模型进行预测,最后将预测结果按照裁剪顺序拼接成一张最终结果图像。因为每张图像块边缘区域的上下文信息较少,所以先用规则格网裁剪再拼接的传统预测方法效果不好,预测结果精度较低,还会出现明显的拼接痕迹。为了解决这个问题,本文构建了一个预测模型,采用滑动重叠的方法进行结果预测,即先把大图像裁剪成一系列与相邻图像块有特定重复区域的图像块,并把它们存在链表里,然后创建生成器,之后进行预测,最后对预测结果只取中间部分进行拼接。该方法相较于传统的预测方法而言,其裁剪图像边缘部分的信息不再取决于单一的一幅图像,而是结合了周围图像的语义信息,其信息更加丰富和准确,因此预测结果也更好,并且由于其重叠拼接的特性,可以很好地消除拼接痕迹。传统预测方法与本文预测方法示意图如图8所示,其中,$ A $代表真实裁剪的预测图,$ a $代表拼接结果,相邻图像裁剪时其重叠比例为$ 1 - \sqrt {a/A} $
实验平台采用英特尔Xeon(R) Gold 6130 @ 2.10 GHz十六核处理器,配置48.0 G内存(DDR4 2666 MHz),搭载Nvidia GeForce GTX 1080Ti显存的显卡。实验以Anaconda3(64 bit)为载体进行环境配置,采用Windows 10专业版64位操作系统,通过conda命令创建一个虚拟环境,在环境内安装Python3.6版本,选择TensorFlow2.6作为深度学习框架,利用框架中集成的Keras工具进行模型搭建,选择与计算机配置匹配的CUDA 11.2版本作为GPU运算平台,搭载cuDNN 8.1.0作为深度学习GPU加速库,最后采用PyCharm 2018进行深度学习程序开发、编译,保证实验顺利进行。网络具体的参数设置如表2
精度评价对本文而言是指将实验方法得出的红树林识别结果图与通过目视解译人工绘制的真实标签图进行对比,从而评价该实验方法的准确性。为了对红树林识别的效果进行定量描述,本文利用混淆矩阵进行精度评价。混淆矩阵是一个统计分类模型分类结果的$ {{M}} \times {{M}} $矩阵,其中$ {{M}} $为类别数,本文类别数为3,混淆矩阵为3×3矩阵。
本文选择总体精度(OA)、F1-分数(F1-Score)、平均交并比(mIoU)3个评价因子进行精度评价 ,总体精度表示每一个随机样本预测的分类结果与真实类型一致的概率,F1-分数是分类模型精确率和召回率的调和平均值,平均交并比表示预测类别样本与实际类别样本的交集与并集之比,平均交并比是对每一类交并比求和平均的结果。计算公式分别如式(5)至式(7)所示。
$ {\rm{OA}} = \frac{{TP + TN}}{{TP + TN + FP + FN}} \text{,} $
$ {\rm{F1}}{\text{-}}{\rm{Score}} = 2 \times \frac{{TP}}{{TN+FP+2TP}}\text{,} $
$ {\rm{mIoU}} = \frac{1}{n} \times \sum\limits_i^n {\frac{{TP}}{{TP + TN + FP}}} \text{,} $
式中,$ TP $表示分类正确的红树林像素点;$ FP $表示分类错误的红树林像素点;$ TN $表示分类正确的非红树林像素点;$ FN $表示分类错误的非红树林像素点;$ n $为类别数。
为了验证本文改进模型的能力,本文基于GF-1高分辨率遥感影像选取两块样本区之外的区域作为测试区域,大小均为1 000像素×1 000像素。图9展示的结果为CU-Net网络的训练集和测试集准确率和损失。
该模型在训练过程中的训练集和测试集的准确率随着迭代次数增加缓慢升高,逐渐趋近于1,而损失值缓慢降低,逐渐趋近于0,两者均逐渐趋于平稳,模型逐渐收敛达到最优。
本文基于两块测试区域将所提方法结果与传统的SVM、RF方法以及经典的U-Net、SegNet、DenseNet网络的预测结果进行对比。本文方法与其他5种方法的测试图像、真实标签图像、预测图像对比图如图10所示。其中,红色表示红树林识别结果,绿色表示其他类型树木识别结果,黑色为背景。
根据图10所示的实验结果对比图可以看出,本文所提出的模型相较于其他模型目视效果最好,对红树林区域识别较为精准,可以较为准确地区分红树林与普通树木。传统的SVM、RF方法进行红树林提取对比实验时,只能选择可见光以及近红外的波谱信息进行分析提取,而这几个波段对植被信息反映的强度有限,只能粗略提取红树林分布,对于精确识别的结果会有很大限制,所以精确提取效果较差,破碎感较为严重。
为了便于分析,在图10中用蓝色框表示红树林未被正确识别出来的部分,白色框表示其他树木未被正确识别的部分。观察本文所提出CU-Net模型两个测试区域的结果图,发现仅有蓝色框区域将红树林部分错分为其他树木以及白色框部分少许其他树木的漏分、错分问题,大部分区域均被准确识别,在红树林识别中展现出了优越的能力。U-Net、SegNet、DenseNet模型两个测试区域识别结果看上去错分部分较多且斑块较为破碎,说明模型对红树林特征学习不足,整体效果一般。
为了更加直观展示各种方法预测的效果,本文将各种方法得到的预测结果与真实标签做差分,两个测试区域的差分图像如图11所示。其中,黄色部分是将其他树木误分为红树林区域,红色部分是将背景误分为红树林,绿色部分是未被准确识别的其他树木。差分图像中颜色区域越多,表明分类越不准确,效果越差。基于图11差分图像对比结果整体来看,本文所提出的CU-Net模型在两个测试区域的红色部分和黄色部分最少,相较于其他几个模型识别效果最好,但仍存在一些漏分和错分现象,整体上可以大范围的分辨红树林与普通树木,表明该模型对红树林信息掌握度较高。其次是SegNet模型,该模型在识别红树林任务中也具有一定优越性,对红树林的提取结果仅次于CU-Net模型。U-Net、DenseNet模型黄色部分和红色部分较多,在分辨红树林和普通树木的能力有所欠缺,特征提取不够深刻,误分现象相对严重,斑块较为破碎,整体识别效果不好。
图11的SVM、RF方法的差分图像结果图可以看出,传统方法基于本文GF-1数据源的误差太大,对于粗略提取红树林分布有一定准确性,可以看出红树林和其他树木聚集的区域。但在精确提取红树林任务中,错分、漏分现象严重,并且此方法提取的红树林较为离散,大范围成片提取效果欠佳。
对各方法结果进行目视分析后,本文又基于预测结果与真值图进行混淆矩阵的计算,对实验结果进行了精度评价,以便更加精确的对各个方法在红树林提取中的有效性进行评估。测试区域1的精度评价结果如表3所示。测试区域2的精度评价结果如表4所示。
表3表4可以看出,本文所提出的模型进行红树林识别的总体精度最高,说明可以很好地分辨出红树林和其他普通树木。另外,相比于原始的U-Net网络,CU-Net在测试区域1的总体精度、平均交并比分别提高了2.46%和3.86%,红树林的F1-分数提高了2.39%,其他树木的F1-分数提高了4.87%,测试区域2的总体精度、平均交并比分别提高了3.58%和5.26%,红树林的F1-分数提高了5.09%,其他树木的F1-分数提高了3.21%。这些数据进一步说明本文在U-Net网络基础上改进的CU-Net模型可以深层次提取红树林特征,很好区分红树林与其他树木。除U-Net网络外,本文方法获得的精度相较于SegNet、DenseNet、SVM、RF方法在两个测试区域的平均总体精度分别提升了2.13%、6.93%、22.34%、21.13%。以上数据充分表明了该方法在红树林识别方面的优越性,其在两个测试区域的平均总体精度、平均交并比分别达到了94.43%和88.12%,F1-分数在红树林和其他树木的平均精度分别达到了95.96%和90.49%。因此,结合目视解译结果以及精度评价结果整体来看,在精确识别红树林工作中,该模型具有一定的红树林信息挖掘能力。
为了实现快速、准确的大面积提取红树林,本文提出了一种高分辨率遥感影像红树林像素级精确提取的深度学习方法。通过建立CU-Net模型以及以滑动重叠拼接方法为基础的预测模型,有效解决了预测结果边缘信息不足以及有拼接痕迹的问题,实现了红树林的高精度提取。另外,为了验证该模型的有效性,将其与U-Net、SegNet、DenseNet模型以及传统的SVM、RF方法进行了对照。实验结果表明,本文方法在两个测试区域红树林识别的平均总体精度、平均交并比以及F1-分数分别达到了94.43%、88.12%、95.96%,精度高于其他几种模型,可以为红树林的保护、管理提供技术支持。
但是,本文提出的模型存在小部分漏分、错分问题,后续研究会从以下两个方面进行尝试:(1)完善样本集,样本集对训练结果有很大影响,后续会继续丰富样本集,提升准确率。(2)将Landsat等多光谱卫星的波谱特征引入到基于高分影像的深度学习方法中,以期得到更为精确的红树林识别结果。
  • 海南省重点研发计划(高新技术专项);国家自然科学基金(41771478)。
参考文献 引证文献
排序方式:
1
Lee S Y, Primavera J H, Dahdouh-Guebas F, et al. Ecological role and services of tropical mangrove ecosystems: a reassessment[J]. Global Ecology and Biogeography, 2014, 23(7): 726−743.
2
Giri C, Ochieng E, Tieszen L L, et al. Status and distribution of mangrove forests of the world using Earth observation satellite data[J]. Global Ecology and Biogeography, 2011, 20(1): 154−159.
3
Field C D. Rehabilitation of mangrove ecosystems: an overview[J]. Marine Pollution Bulletin, 1999, 37(8−12): 383−392.
4
甄佳宁, 廖静娟, 沈国状. 1987以来海南省清澜港红树林变化的遥感监测与分析[J]. 湿地科学, 2019, 17(1): 44−51.
Zhen Jianing, Liao Jingjuan, Shen Guozhuang. Remote sensing monitoring and analysis on the dynamics of mangrove forests in Qinglan Habor of Hainan Province since 1987[J]. Wetland Science, 2019, 17(1): 44−51.
5
Vaiphasa C, De Boer W F, Skidmore A K, et al. Impact of solid shrimp pond waste materials on mangrove growth and mortality: a case study from Pak Phanang, Thailand[J]. Hydrobiologia, 2007, 591(1): 47−57.
6
冯家莉, 刘凯, 朱远辉, 等. 无人机遥感在红树林资源调查中的应用[J]. 热带地理, 2015, 35(1): 35−42.
Feng Jiali, Liu Kai, Zhu Yuanhui, et al. Application of unmanned aerial vehicles to mangrove resources monitoring[J]. Tropical Geography, 2015, 35(1): 35−42.
7
罗丹, 李正会, 王德智, 等. 海口市东寨港红树林面积动态变化分析[J]. 农村经济与科技, 2013, 24(2): 97−99.
Luo Dan, Li Zhenghui, Wang Dezhi, et al. Analysis on dynamic change of mangrove area in Dongzhai Port, Haikou City[J]. Rural Economy and Science-Technology, 2013, 24(2): 97−99.
8
李春干, 代华兵. 红树林空间分布信息遥感提取方法[J]. 湿地科学, 2014, 12(5): 580−589.
Li Chungan, Dai Huabing. Extraction of mangroves spatial distribution using remotely sensed data[J]. Wetland Science, 2014, 12(5): 580−589.
9
梁超, 刘利, 刘建强, 等. 基于HY-1C CZI影像光谱指数重构数据MNF变换的红树林提取[J]. 海洋学报, 2020, 42(4): 104−112.
Liang Chao, Liu Li, Liu Jianqiang, et al. Extracting mangrove information using MNF transformation based on HY-1C CZI spectral indices reconstruction data[J]. Haiyang Xuebao, 2020, 42(4): 104−112.
10
Jia Mingming, Wang Zongming, Wang Chao, et al. A new vegetation index to detect periodically submerged mangrove forest using single-tide sentinel-2 imagery[J]. Remote Sensing, 2019, 11(17): 2043.
11
Muhsoni F F, Sambah A B, Mahmudi M, et al. Comparison of different vegetation indices for assessing mangrove density using sentinel-2 imagery[J]. International Journal of GEOMATE, 2018, 14(45): 42−51.
12
Baloloy A B, Blanco A C, Ana R R C S, et al. Development and application of a new mangrove vegetation index (MVI) for rapid and accurate mangrove mapping[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2020, 166: 95−117.
13
Manna S, Raychaudhuri B. Retrieval of leaf area index and stress conditions for Sundarban mangroves using Sentinel-2 data[J]. International Journal of Remote Sensing, 2020, 41(3): 1019−1039.
14
徐芳, 张英, 翟亮, 等. 基于Sentinel-2的潮间红树林提取方法[J]. 测绘通报, 2020(2): 49−54.
Xu Fang, Zhang Ying, Zhai Liang, et al. Extraction method of intertidal mangrove by using Sentinel-2 images[J]. Bulletin of Surveying and Mapping, 2020(2): 49−54.
15
刘凯, 龚辉, 曹晶晶, 等. 基于多类型无人机数据的红树林遥感分类对比[J]. 热带地理, 2019, 39(4): 492−501.
Liu Kai, Gong Hui, Cao Jingjing, et al. Comparison of mangrove remote sensing classification based on multi-type UAV data[J]. Tropical Geography, 2019, 39(4): 492−501.
16
李想, 刘凯, 朱远辉, 等. 基于资源三号影像的红树林物种分类研究[J]. 遥感技术与应用, 2018, 33(2): 360−369.
Li Xiang, Liu Kai, Zhu Yuanhui, et al. Study on mangrove species classification based on ZY-3 image[J]. Remote Sensing Technology and Application, 2018, 33(2): 360−369.
17
Ballanti L, Blesius L, Hines E, et al. Tree species classification using hyperspectral imagery: a comparison of two classifiers[J]. Remote Sensing, 2016, 8(6): 445.
18
Wing B M, Ritchie M W, Boston K, et al. Prediction of understory vegetation cover with airborne Lidar in an interior ponderosa pine forest[J]. Remote Sensing of Environment, 2012, 124: 730−741.
19
Mondal P, Liu Xue, Fatoyinbo T E, et al. Evaluating combinations of sentinel-2 data and machine-learning algorithms for mangrove mapping in West Africa[J]. Remote Sensing, 2019, 11(24): 2928.
20
蒙良莉. 基于哨兵多源遥感数据的红树林信息提取算法研究[D]. 南宁: 南宁师范大学, 2020.
Meng Liangli. Mangrove information extraction algorithm based on multi-source remote sensing data of sentinel[D]. Nanning: Nanning Normal University, 2020.
21
Carranza-García M, García-Gutiérrez J, Riquelme J C. A framework for evaluating land use and land cover classification using convolutional neural networks[J]. Remote Sensing, 2019, 11(3): 274.
22
黄亦其, 刘琪, 赵建晔, 等. 基于深度卷积神经网络的红树林物种无人机监测研究[J]. 中国农机化学报, 2020, 41(2): 141−146, 189.
Huang Yiqi, Liu Qi, Zhao Jianye, et al. Research on unmanned aerial surveillance of mangrove species based on deep convolutional neural network[J]. Journal of Chinese Agricultural Mechanization, 2020, 41(2): 141−146, 189.
23
Lassalle G, Ferreira M P, La Rosa L E C, et al. Deep learning-based individual tree crown delineation in mangrove forests using very-high-resolution satellite imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2022, 189: 220−235.
24
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation[C]//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015: 234−241.
25
Long J, Shelhamer E, Darrell T. Fully convolutional networks for semantic segmentation[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 3431−3440.
26
Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: a simple way to prevent neural networks from overfitting[J]. The Journal of Machine Learning Research, 2014, 15(1): 1929−1958.
27
Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille: PMLR, 2015: 448−456.
28
Glorot X, Bordes A, Bengio Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. Fort Lauderdale: JMLR, 2011: 315−323
2023年第45卷第3期
PDF下载
217
91
引用本文
BibTeX
文章信息
doi: 10.12284/hyxb2023054
  • 接收时间:2022-06-07
  • 首发时间:2025-12-26
  • 出版时间:2023-03-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2022-06-07
  • 修回日期:2022-10-26
基金
海南省重点研发计划(高新技术专项);国家自然科学基金(41771478)。
作者信息
    1 河海大学 地球科学与工程学院,江苏 南京 211100
    2 自然资源部国家卫星海洋应用中心,北京 100081
    3 自然资源部空间海洋遥感与应用研究重点实验室,北京 100081

通讯作者:

*芮小平,教授,主要从事地理信息系统理论与应用方面的研究。E-mail:;
张茜,副研究员,主要从事海洋遥感方面的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/hyxb/CN/10.12284/hyxb2023054
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