Article(id=1200432928116297926, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1200432923632595385, articleNumber=null, orderNo=null, doi=10.12284/hyxb2024044, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1694620800000, receivedDateStr=2023-09-14, revisedDate=1702915200000, revisedDateStr=2023-12-19, acceptedDate=null, acceptedDateStr=null, onlineDate=1764135113028, onlineDateStr=2025-11-26, pubDate=1717084800000, pubDateStr=2024-05-31, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1764135113028, onlineIssueDateStr=2025-11-26, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1764135113028, creator=13701087609, updateTime=1764135113028, updator=13701087609, issue=Issue{id=1200432923632595385, tenantId=1146029695717560320, journalId=1149651085930835976, year='2024', volume='46', issue='5', pageStart='1', pageEnd='136', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=0, articleOrder=1, issueType=-1, specialIssue=null, createTime=1764135111959, creator=13701087609, updateTime=1764135248631, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1200433496922641251, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1200432923632595385, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1200433496922641252, tenantId=1146029695717560320, journalId=1149651085930835976, issueId=1200432923632595385, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=93, endPage=102, ext={EN=ArticleExt(id=1200432928351178957, articleId=1200432928116297926, tenantId=1146029695717560320, journalId=1149651085930835976, language=EN, title=Marine cage aquaculture information extraction based on SLA-UNet, columnId=null, journalTitle=Haiyang Xuebao, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Cage aquaculture is one of the most important types of marine aquaculture. Different types of cages have varying shapes in remote sensing images, and the background is complex. Previous methods for cage extraction have not been able to fully simulate human visual behavior and efficiently utilize spectral information. To address these issues, we propose a Spectral Loopy Attention U-Net (SLA-UNet) network model for cage aquaculture information extraction. The model utilizes the Random Forest (RF) algorithm based on the Estimation of Scale Parameter (ESP) to remove redundant spectral information after band operations. It also incorporates a human-like attention mechanism to enhance the important feature channels that affect cage information extraction. Additionally, edge completion is performed to supplement the loss information, achieving high-precision extraction of cage aquaculture information. We selected Zhanjiang City, Guangdong Province and Lingao County, as the study areas. Comparisons were made with the extraction results of the Canny algorithm, Otsu algorithm, PCA_Kmeans algorithm, RF algorithm based on ESP, and the U-Net model. The extraction accuracy of the SLA-UNet model for nearshore cages is 98.3%, and the average extraction accuracy for deep-sea cages is 98.9%, validating the effectiveness of the SLA-UNet model in cage aquaculture recognition.

, correspAuthors=Jianchao Fan, authorNote=null, correspAuthorsNote=null, copyrightStatement=Haiyang Xuebao, 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=Li’na Ke, Jinhao You, Jianchao Fan), CN=ArticleExt(id=1200432932105081169, articleId=1200432928116297926, tenantId=1146029695717560320, journalId=1149651085930835976, language=CN, title=基于SLA-UNet的海水网箱养殖信息提取, columnId=1149698756456657529, journalTitle=海洋学报, columnName=论文, runingTitle=null, highlight=null, articleAbstract=

网箱养殖是海水养殖中最重要的类型之一,各类网箱在遥感影像中形状不一,且背景复杂,以往的网箱提取方法,未能完全模拟人类的视觉行为,以及高效利用光谱信息。针对上述问题,提出深度多循环注意力光谱的U-Net网络模型(Spectral Loopy Attention U-Net, SLA-UNet)进行网箱养殖信息提取,使用基于最优尺度寻优(Estimation of Scale Parameter, ESP)的随机森林(Random Forest, RF)算法,去除波段运算后的冗余光谱信息,并添加类似人眼的注意力行为机制,深化影响网箱信息提取的重要特征通道,同时进行边缘补齐补充损失信息,实现了网箱养殖信息的高精度提取。选取广东省湛江市和海南省临高县作为研究区域,与Canny算子、Otsu算法、PCA_Kmeans算法、基于ESP的RF算法、U-Net模型提取结果进行对比,所提SLA-UNet模型近岸网箱的提取精度为98.3%,深海网箱提取精度平均值为98.9%,验证了SLA-UNet模型在网箱养殖识别中的有效性。

, correspAuthors=范剑超, authorNote=null, correspAuthorsNote=
*范剑超,博士,教授,博士生导师,研究方向为海洋遥感影像人工智能分析。E-mail:
, copyrightStatement=版权所有©《海洋学报》编辑部 2024, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=c7tjM9WgLfI6lncv1YplRw==, magXml=5XJmHnHmatwfOOI+QGInaw==, pdfUrl=null, pdf=H05+N4H9O8rh9AqQTC5Qug==, pdfFileSize=2960252, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=dQFKI32eLNePYZ+l73HrUg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=+gWjyRQhJKU3DYusgiYmBw==, mapNumber=null, authorCompany=null, fund=null, authors=

柯丽娜(1978—),女,辽宁省庄河市人,教授,博士生导师,研究方向为海岸带遥感技术应用。E-mail:

, authorsList=柯丽娜, 由金浩, 范剑超)}, authors=[Author(id=1200432932625174913, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=kekesunny@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1200432932805529993, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, authorId=1200432932625174913, language=EN, stringName=Li’na Ke, firstName=Li’na, middleName=null, lastName=Ke, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Geographical, Liaoning Normal University, Dalian 116029, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200432932939747732, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, authorId=1200432932625174913, language=CN, stringName=柯丽娜, firstName=丽娜, middleName=null, lastName=柯, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.辽宁师范大学 地理科学学院,辽宁 大连 116029, bio={"content":"

柯丽娜(1978—),女,辽宁省庄河市人,教授,博士生导师,研究方向为海岸带遥感技术应用。E-mail:

"}, bioImg=null, bioContent=

柯丽娜(1978—),女,辽宁省庄河市人,教授,博士生导师,研究方向为海岸带遥感技术应用。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200432932331573608, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, xref=null, ext=[AuthorCompanyExt(id=1200432932339962218, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932331573608, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Geographical, Liaoning Normal University, Dalian 116029, China), AuthorCompanyExt(id=1200432932344156523, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932331573608, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽宁师范大学 地理科学学院,辽宁 大连 116029)])]), Author(id=1200432933082354072, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=1200432933212377507, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, authorId=1200432933082354072, language=EN, stringName=Jinhao You, firstName=Jinhao, middleName=null, lastName=You, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1. School of Geographical, Liaoning Normal University, Dalian 116029, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200432933359178153, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, authorId=1200432933082354072, language=CN, stringName=由金浩, firstName=金浩, middleName=null, lastName=由, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.辽宁师范大学 地理科学学院,辽宁 大连 116029, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200432932331573608, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, xref=null, ext=[AuthorCompanyExt(id=1200432932339962218, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932331573608, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Geographical, Liaoning Normal University, Dalian 116029, China), AuthorCompanyExt(id=1200432932344156523, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932331573608, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽宁师范大学 地理科学学院,辽宁 大连 116029)])]), Author(id=1200432933585670573, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fjchao@dlut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1200432933707305403, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, authorId=1200432933585670573, language=EN, stringName=Jianchao Fan, firstName=Jianchao, middleName=null, lastName=Fan, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2. School of Control Science and Engineering, Dalian University of Technology, Dalian 116023, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1200432934843961797, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, authorId=1200432933585670573, language=CN, stringName=范剑超, firstName=剑超, middleName=null, lastName=范, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, *, address=2.大连理工大学 控制科学与工程学院,辽宁 大连 116024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1200432932461597045, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, xref=null, ext=[AuthorCompanyExt(id=1200432932469985655, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932461597045, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. School of Control Science and Engineering, Dalian University of Technology, Dalian 116023, China), AuthorCompanyExt(id=1200432932478374265, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932461597045, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.大连理工大学 控制科学与工程学院,辽宁 大连 116024)])])], keywords=[Keyword(id=1200432935007539660, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, orderNo=1, keyword=cage aquaculture), Keyword(id=1200432935120785877, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, orderNo=2, keyword=U-Net model), Keyword(id=1200432935221449176, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, orderNo=3, keyword=Loopy Attention mechanism), Keyword(id=1200432935313723866, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, orderNo=4, keyword=deep features), Keyword(id=1200432935435358687, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, orderNo=5, keyword=highly efficient spectral characteristics), Keyword(id=1200432935515050469, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, orderNo=1, keyword=网箱养殖), Keyword(id=1200432935582159337, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, orderNo=2, keyword=U-Net模型), Keyword(id=1200432935699599852, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, orderNo=3, keyword=多循环注意力机制), Keyword(id=1200432935770903023, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, orderNo=4, keyword=深度特征), Keyword(id=1200432935867372019, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, orderNo=5, keyword=高效光谱特征)], refs=[Reference(id=1200432940653073013, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Wang Ming, Mao Dehua, Xiao Xiangming, et al. Interannual changes of coastal aquaculture ponds in China at 10-m spatial resolution during 2016–2021[J]. Remote Sensing of Environment, 2023, 284: 113347., articleTitle=null, refAbstract=null), Reference(id=1200432940715987577, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=FAO. The State of World Fisheries and Aquaculture 2020[EB/OL]. [2023-03-05]. http://doi.org/10.4060/ca9229en, articleTitle=null, refAbstract=null), Reference(id=1200432940778902140, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Mao Dehua, Yang Hong, Wang Zongming, et al. Reverse the hidden loss of China’s wetlands[J]. Science, 2022, 376(6597): 1061., articleTitle=null, refAbstract=null), Reference(id=1200432940875371136, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=邓莎萨, 张帆, 尹嫱等. 面向目视解译的全极化SAR船只精细化特征表征方法[J/OL]. [2024-02-21]. 雷达学报, 2023. https://radars.ac.cn/cn/article/doi/10.12000/JR23078. doi: 10.12000/JR23078, articleTitle=null, refAbstract=null), Reference(id=1200432940980228741, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Deng Shasa, Zhang Fan, Yin Qiang, et al. Refined ship feature characterization method of full-polarimetric synthetic aperture radar for visual interpretation[J/OL]. Journal of Radars, 2023. https://radars.ac.cn/cn/article/doi/10.12000/JR23078. doi: 10.12000/JR23078, articleTitle=null, refAbstract=null), Reference(id=1200432941093474951, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Schepaschenko D, See L, Lesiv M, et al. Recent advances in forest observation with visual interpretation of very high-resolution imagery[J]. Surveys in Geophysics, 2019, 40(4): 839−862., articleTitle=null, refAbstract=null), Reference(id=1200432941198332553, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=汪静平, 吴小丹, 马杜娟, 等. 基于机器学习的遥感反演: 不确定性因素分析[J]. 遥感学报, 2023, 27(3): 790−801., articleTitle=null, refAbstract=null), Reference(id=1200432941315773070, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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 Jingping, Wu Xiaodan, Ma Dujuan, et al. Remote sensing retrieval based on machine learning algorithm: uncertainty analysis[J]. Journal of Remote Sensing, 2023, 27(3): 790−801., articleTitle=null, refAbstract=null), Reference(id=1200432941403853458, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Virnodkar S S, Pachghare V K, Patil V C, et al. Remote sensing and machine learning for crop water stress determination in various crops: A critical review[J]. Precision Agriculture, 2020, 21(5): 1121−1155., articleTitle=null, refAbstract=null), Reference(id=1200432941491933843, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Maxwell A E, Warner T A, Guillén L A. Accuracy assessment in convolutional neural network-based deep learning remote sensing studies—Part 2: Recommendations and best practices[J]. Remote Sensing, 2021, 13(13): 2591., articleTitle=null, refAbstract=null), Reference(id=1200432941605180055, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Kechagias-Stamatis O, Aouf N. Fusing deep learning and sparse coding for SAR ATR[J]. IEEE Transactions on Aerospace and Electronic Systems, 2019, 55(2): 785−797., articleTitle=null, refAbstract=null), Reference(id=1200432941693260444, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Seto K C, Fragkias M. Mangrove conversion and aquaculture development in Vietnam: A remote sensing-based approach for evaluating the Ramsar Convention on Wetlands[J]. Global Environmental Change, 2007, 17(3/4): 486−500., articleTitle=null, refAbstract=null), Reference(id=1200432941793923743, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504−507., articleTitle=null, refAbstract=null), Reference(id=1200432941898781348, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, 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=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=1200432942032999077, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Jiayi, Zhang Hongyan, Zhang Liangpei. Supervised segmentation of very high resolution images by the use of extended morphological attribute profiles and a sparse transform[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(8): 1409−1413., articleTitle=null, refAbstract=null), Reference(id=1200432942150439594, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015: 234−241., articleTitle=null, refAbstract=null), Reference(id=1200432942272074411, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481−2495., articleTitle=null, refAbstract=null), Reference(id=1200432942385320622, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Zheng Shuai, Jayasumana S, Romera-Paredes B, et al. Conditional random fields as recurrent neural networks[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1529−1537., articleTitle=null, refAbstract=null), Reference(id=1200432942498566833, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yang, Fan Rongshuang, Yang Xiucheng, et al. Extraction of urban water bodies from high-resolution remote-sensing imagery using deep learning[J]. Water, 2018, 10(5): 585., articleTitle=null, refAbstract=null), Reference(id=1200432942586647221, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=刘岳明, 杨晓梅, 王志华, 等. 基于深度学习RCF模型的三都澳筏式养殖区提取研究[J]. 海洋学报, 2019, 41(4): 119−130., articleTitle=null, refAbstract=null), Reference(id=1200432942674727607, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yueming, Yang Xiaomei, Wang Zhihua, et al. Extracting raft aquaculture areas in Sanduao from high-resolution remote sensing images using RCF[J]. Haiyang Xuebao, 2019, 41(4): 119−130., articleTitle=null, refAbstract=null), Reference(id=1200432943819772602, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Chenxi, Jiang Tao, Zhang Zhen, et al. Extraction method of offshore mariculture area under weak signal based on multisource feature fusion[J]. Journal of Marine Science and Engineering, 2020, 8(2): 99., articleTitle=null, refAbstract=null), Reference(id=1200432943916241596, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=柯丽娜, 翟宇宁, 范剑超. 深度边缘光谱U-Net海水网箱养殖信息提取[J]. 海洋学报, 2022, 44(2): 132−142., articleTitle=null, refAbstract=null), Reference(id=1200432944008516288, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Ke Lina, Zhai Yuning, Fan Jianchao. Marine cage aquaculture information extraction based on deep edge spectral U-Net[J]. Haiyang Xuebao, 2022, 44(2): 132−142., articleTitle=null, refAbstract=null)], funds=[Fund(id=1200432940195893862, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, awardId=42076184, language=CN, fundingSource=国家自然科学基金项目(42076184), fundOrder=null, country=null), Fund(id=1200432940304945772, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, awardId=41706195, language=CN, fundingSource=国家自然科学基金项目(41706195), fundOrder=null, country=null), Fund(id=1200432940468523631, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, awardId=41-Y30F07-9001-20/22, language=CN, fundingSource=国家高分重大科研专项项目(41-Y30F07-9001-20/22), fundOrder=null, country=null), Fund(id=1200432940556604018, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, awardId=2021YFC2801000, language=CN, fundingSource=国家重点研发计划项目(2021YFC2801000), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1200432932331573608, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, xref=null, ext=[AuthorCompanyExt(id=1200432932339962218, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932331573608, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1. School of Geographical, Liaoning Normal University, Dalian 116029, China), AuthorCompanyExt(id=1200432932344156523, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932331573608, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.辽宁师范大学 地理科学学院,辽宁 大连 116029)]), AuthorCompany(id=1200432932461597045, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, xref=null, ext=[AuthorCompanyExt(id=1200432932469985655, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932461597045, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2. School of Control Science and Engineering, Dalian University of Technology, Dalian 116023, China), AuthorCompanyExt(id=1200432932478374265, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, companyId=1200432932461597045, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.大连理工大学 控制科学与工程学院,辽宁 大连 116024)])], figs=[ArticleFig(id=1200432936005784057, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 1, caption=Marine cage aquaculture area at Potou and Xiashan in Zhanjiang, figureFileSmall=2ji/onb6K8wN16uYyAi7hA==, figureFileBig=dQFKI32eLNePYZ+l73HrUg==, tableContent=null), ArticleFig(id=1200432936081281532, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图1, caption=湛江市坡头区和霞山区海水网箱养殖区, figureFileSmall=2ji/onb6K8wN16uYyAi7hA==, figureFileBig=dQFKI32eLNePYZ+l73HrUg==, tableContent=null), ArticleFig(id=1200432936274219526, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 2, caption=Marine cage aquaculture area at Lingao in Hainan Province, figureFileSmall=h9CFM+/dEfpHqNND4HEp5A==, figureFileBig=o/aREb6QsIIakHThM6xAaA==, tableContent=null), ArticleFig(id=1200432936349717002, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图2, caption=海南省临高县海水网箱养殖区, figureFileSmall=h9CFM+/dEfpHqNND4HEp5A==, figureFileBig=o/aREb6QsIIakHThM6xAaA==, tableContent=null), ArticleFig(id=1200432936429408782, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 3, caption=Marine cage aquaculture, figureFileSmall=X0ddVTeUHBxGqr1VwQpP+A==, figureFileBig=AJEyLTUf/sR7L42F3ScK6A==, tableContent=null), ArticleFig(id=1200432936546849298, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图3, caption=海水网箱养殖, figureFileSmall=X0ddVTeUHBxGqr1VwQpP+A==, figureFileBig=AJEyLTUf/sR7L42F3ScK6A==, tableContent=null), ArticleFig(id=1200432936651706904, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 4, caption=The overall flow, figureFileSmall=CIEaOj7YyiKW5zFGNME//A==, figureFileBig=fRQmdLKZM4ysT2pX/jeubg==, tableContent=null), ArticleFig(id=1200432936785924635, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图4, caption=整体流程, figureFileSmall=CIEaOj7YyiKW5zFGNME//A==, figureFileBig=fRQmdLKZM4ysT2pX/jeubg==, tableContent=null), ArticleFig(id=1200432936957891103, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 5, caption=SE attention mechanism, figureFileSmall=YWxx/6a4PXEARmRJLjg8PA==, figureFileBig=n483/Q/oQZevoO+pth4+RA==, tableContent=null), ArticleFig(id=1200432937058554401, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图5, caption=SE注意力机制, figureFileSmall=YWxx/6a4PXEARmRJLjg8PA==, figureFileBig=n483/Q/oQZevoO+pth4+RA==, tableContent=null), ArticleFig(id=1200432937209549348, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 6, caption=SLA-UNet structure, figureFileSmall=Oy97Hb9gIkExq2KL1Qj8EA==, figureFileBig=DrH6R8irdKQxNJ6amSl3sA==, tableContent=null), ArticleFig(id=1200432937285046826, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图6, caption=SLA-UNet 结构, figureFileSmall=Oy97Hb9gIkExq2KL1Qj8EA==, figureFileBig=DrH6R8irdKQxNJ6amSl3sA==, tableContent=null), ArticleFig(id=1200432937410875949, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 7, caption=Comparison of offshore cage extraction effect, figureFileSmall=TqXBMCwzxVZAboH3CXvqMA==, figureFileBig=vJR+IS153lfeAgbuRxqmqA==, tableContent=null), ArticleFig(id=1200432937566065201, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图7, caption=近岸网箱提取效果对比, figureFileSmall=TqXBMCwzxVZAboH3CXvqMA==, figureFileBig=vJR+IS153lfeAgbuRxqmqA==, tableContent=null), ArticleFig(id=1200432937691894325, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 8, caption=Extraction results of offshore cages in Potou District, figureFileSmall=S+EIhr1CHJcz/syykIfrMA==, figureFileBig=L+rXdkvjlQzbXeCPy2Y5OA==, tableContent=null), ArticleFig(id=1200432937784169016, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图8, caption=坡头区近岸网箱提取结果, figureFileSmall=S+EIhr1CHJcz/syykIfrMA==, figureFileBig=L+rXdkvjlQzbXeCPy2Y5OA==, tableContent=null), ArticleFig(id=1200432937922581054, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 9, caption=Comparison of deep-sea cage extraction effect, figureFileSmall=k0Rw4F5D9iXcNQblQ2uNsQ==, figureFileBig=OWTRNv0xqDG2qtrGKf/0BA==, tableContent=null), ArticleFig(id=1200432938010661442, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图9, caption=深海网箱提取效果对比, figureFileSmall=k0Rw4F5D9iXcNQblQ2uNsQ==, figureFileBig=OWTRNv0xqDG2qtrGKf/0BA==, tableContent=null), ArticleFig(id=1200432938111324738, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 10, caption=Deep sea cage extraction results, figureFileSmall=2j/Og4fHqDcOCTtGQge52Q==, figureFileBig=FLJt5Y+1bHx6lL2hIF6CwA==, tableContent=null), ArticleFig(id=1200432938237153862, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图10, caption=深海网箱提取结果, figureFileSmall=2j/Og4fHqDcOCTtGQge52Q==, figureFileBig=FLJt5Y+1bHx6lL2hIF6CwA==, tableContent=null), ArticleFig(id=1200432939365421641, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Fig. 11, caption=Comparison of deep-sea cage extraction effect, figureFileSmall=6gOtJsKlCl9dT/FxYPcRfg==, figureFileBig=2577YnIlhJ3mGdtN0A2Fvw==, tableContent=null), ArticleFig(id=1200432939478667852, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=图11, caption=深海网箱提取效果对比, figureFileSmall=6gOtJsKlCl9dT/FxYPcRfg==, figureFileBig=2577YnIlhJ3mGdtN0A2Fvw==, tableContent=null), ArticleFig(id=1200432939562553936, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Table 1, caption=

Accuracy verification results of nearshore cage

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区Canny算子Otsu算法PCA_Kmeans算法基于ESP的RF算法U-NetSLA-UNet
OA/%84.787.388.290.595.698.3
R/%86.389.290.391.597.898.6
MIOU/%55.762.565.767.280.283.5
), ArticleFig(id=1200432939675800148, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=表1, caption=

近岸网箱精度验证结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区Canny算子Otsu算法PCA_Kmeans算法基于ESP的RF算法U-NetSLA-UNet
OA/%84.787.388.290.595.698.3
R/%86.389.290.391.597.898.6
MIOU/%55.762.565.767.280.283.5
), ArticleFig(id=1200432939784852057, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Table 2, caption=

Accuracy verification results of deep sea cage in Zhanjiang

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区Canny算子Otsu算法PCA_Kmeans算法基于ESP的RF算法U-NetSLA-UNet
OA/%85.286.788.991.397.399.2
R/%85.488.188.589.397.598.3
MIOU/%60.563.366.872.186.291.6
), ArticleFig(id=1200432939893903963, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=表2, caption=

湛江深海网箱精度验证结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区Canny算子Otsu算法PCA_Kmeans算法基于ESP的RF算法U-NetSLA-UNet
OA/%85.286.788.991.397.399.2
R/%85.488.188.589.397.598.3
MIOU/%60.563.366.872.186.291.6
), ArticleFig(id=1200432939981984353, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=EN, label=Table 3, caption=

Accuracy verification results of deep sea cage at Lingao

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区Canny算子Otsu算法PCA_Kmeans算法基于ESP的RF算法U-NetSLA-UNet
OA/%75.179.380.285.695.198.6
R/%78.480.282.586.295.698.1
MIOU/%59.159.961.769.876.482.3
), ArticleFig(id=1200432940070064739, tenantId=1146029695717560320, journalId=1149651085930835976, articleId=1200432928116297926, language=CN, label=表3, caption=

临高县深海网箱精度验证结果

, figureFileSmall=null, figureFileBig=null, tableContent=
测试区Canny算子Otsu算法PCA_Kmeans算法基于ESP的RF算法U-NetSLA-UNet
OA/%75.179.380.285.695.198.6
R/%78.480.282.586.295.698.1
MIOU/%59.159.961.769.876.482.3
)], 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/hyxb2024044, detailUrlEn=https://castjournals.cast.org.cn/joweb/hyxb/EN/10.12284/hyxb2024044, pdfUrlCn=https://castjournals.cast.org.cn/joweb/hyxb/CN/PDF/10.12284/hyxb2024044, pdfUrlEn=https://castjournals.cast.org.cn/joweb/hyxb/EN/PDF/10.12284/hyxb2024044, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于SLA-UNet的海水网箱养殖信息提取
收藏切换
PDF下载
柯丽娜 1 , 由金浩 1 , 范剑超 2, *
海洋学报 | 论文 2024,46(5): 93-102
收起
收藏切换
海洋学报 | 论文 2024, 46(5): 93-102
基于SLA-UNet的海水网箱养殖信息提取
全屏
柯丽娜1 , 由金浩1, 范剑超2, *
作者信息
  • 1.辽宁师范大学 地理科学学院,辽宁 大连 116029
  • 2.大连理工大学 控制科学与工程学院,辽宁 大连 116024
  • 柯丽娜(1978—),女,辽宁省庄河市人,教授,博士生导师,研究方向为海岸带遥感技术应用。E-mail:

通讯作者:

*范剑超,博士,教授,博士生导师,研究方向为海洋遥感影像人工智能分析。E-mail:
Marine cage aquaculture information extraction based on SLA-UNet
Li’na Ke1 , Jinhao You1, Jianchao Fan2, *
Affiliations
  • 1. School of Geographical, Liaoning Normal University, Dalian 116029, China
  • 2. School of Control Science and Engineering, Dalian University of Technology, Dalian 116023, China
出版时间: 2024-05-31 doi: 10.12284/hyxb2024044
文章导航
收藏切换

网箱养殖是海水养殖中最重要的类型之一,各类网箱在遥感影像中形状不一,且背景复杂,以往的网箱提取方法,未能完全模拟人类的视觉行为,以及高效利用光谱信息。针对上述问题,提出深度多循环注意力光谱的U-Net网络模型(Spectral Loopy Attention U-Net, SLA-UNet)进行网箱养殖信息提取,使用基于最优尺度寻优(Estimation of Scale Parameter, ESP)的随机森林(Random Forest, RF)算法,去除波段运算后的冗余光谱信息,并添加类似人眼的注意力行为机制,深化影响网箱信息提取的重要特征通道,同时进行边缘补齐补充损失信息,实现了网箱养殖信息的高精度提取。选取广东省湛江市和海南省临高县作为研究区域,与Canny算子、Otsu算法、PCA_Kmeans算法、基于ESP的RF算法、U-Net模型提取结果进行对比,所提SLA-UNet模型近岸网箱的提取精度为98.3%,深海网箱提取精度平均值为98.9%,验证了SLA-UNet模型在网箱养殖识别中的有效性。

网箱养殖  /  U-Net模型  /  多循环注意力机制  /  深度特征  /  高效光谱特征

Cage aquaculture is one of the most important types of marine aquaculture. Different types of cages have varying shapes in remote sensing images, and the background is complex. Previous methods for cage extraction have not been able to fully simulate human visual behavior and efficiently utilize spectral information. To address these issues, we propose a Spectral Loopy Attention U-Net (SLA-UNet) network model for cage aquaculture information extraction. The model utilizes the Random Forest (RF) algorithm based on the Estimation of Scale Parameter (ESP) to remove redundant spectral information after band operations. It also incorporates a human-like attention mechanism to enhance the important feature channels that affect cage information extraction. Additionally, edge completion is performed to supplement the loss information, achieving high-precision extraction of cage aquaculture information. We selected Zhanjiang City, Guangdong Province and Lingao County, as the study areas. Comparisons were made with the extraction results of the Canny algorithm, Otsu algorithm, PCA_Kmeans algorithm, RF algorithm based on ESP, and the U-Net model. The extraction accuracy of the SLA-UNet model for nearshore cages is 98.3%, and the average extraction accuracy for deep-sea cages is 98.9%, validating the effectiveness of the SLA-UNet model in cage aquaculture recognition.

cage aquaculture  /  U-Net model  /  Loopy Attention mechanism  /  deep features  /  highly efficient spectral characteristics
柯丽娜, 由金浩, 范剑超. 基于SLA-UNet的海水网箱养殖信息提取. 海洋学报, 2024 , 46 (5) : 93 -102 . DOI: 10.12284/hyxb2024044
Li’na Ke, Jinhao You, Jianchao Fan. Marine cage aquaculture information extraction based on SLA-UNet[J]. Haiyang Xuebao, 2024 , 46 (5) : 93 -102 . DOI: 10.12284/hyxb2024044
近几十年,沿海水产养殖业的快速发展有力地支持了全球粮食安全和沿海地区的经济发展,但也对沿海生态系统造成了显著影响[1]。根据联合国粮食及农业组织(Food and Agriculture Organization of the United Nations, FAO)的数据,中国是世界上最大的水产养殖食品生产国[2]。从我国乃至全球来看,沿海养殖业的快速扩张为人类饮食提供保障的同时,部分地区海洋资源日益枯竭、海水质量下降,海岸带生态环境不断恶化,并成为生态脆弱和灾害频发的重点区域[3],海洋经济与生态环境冲突严重。精确提取海水养殖区,对解决海洋养殖经济发展与生态环境冲突具有重要意义。
遥感影像具有探测面积广,数据源丰富,分类方法成熟等特点,在海洋资源领域呈现独特的技术优势,成为海洋养殖调查监测的主要手段。目前,利用遥感数据进行海洋养殖区目标识别的分类方法可分为传统统计方法[45]、机器学习方法[67]、深度学习算法[89]等。传统统计方法通过图像像元亮度值与纹理特征来支持分类,易造成主观因素影响大,提取精度低,且人工成本高、效率低下的问题。Seto和Fragkias[10]利用Quick Bird影像,采取传统统计方法提取了越南拉姆萨尔湿地海水养殖区信息。机器学习在海水养殖信息提取中,一定程度上提高了海水养殖信息提取精度,但这类方法常常结构简单,模型学习算法受网络结构的限制,难以建立适配高分辨率遥感图像的复杂函数模型。
深度学习由Hinton[11]在2006年提出,该方法对单个像素点进行分类,在考虑光谱和空间特征的同时,对上下文信息进行提取,目前出现的网络,包括FCN[12]、DeepLabv3[13]、U-Net[14]、SegNet[15]等,在图像语义分割方面展现的优势使得越来越多的学者致力于深度学习的研究。Zhen等[16]提出将条件随机场引入卷积神经网络结构中;Chen等[17]利用卷积神经网络判别超像素是否为水体;刘岳明等[18]建立了丰富卷积特征(Richer Convolutional Features, RCF)深度学习模型,实现福建省三都澳筏式养殖区的高精度提取;Liu等[19]基于DeepLabv3网络实现了长海县筏式养殖目标提取。
相对于筏式养殖,网箱养殖属于海水养殖另外一种重要养殖方式。海水网箱养殖,根据网箱养殖离岸距离的差异,分为近岸网箱和深海网箱两种类型。近岸网箱是浮在海水面上的形状不一的箱体,沿近海分布;深海网箱为规则圆环状箱体,是一种在深远海域资源基础上发展的海水养殖方式,常见于我国广东、海南、福建等热带海洋季风气候省份海域[20]。目前深度学习在网箱提取上取得了很好的效果,但由于光谱信息低效利用的同时,还无法和视觉行为等同,体现在识别养殖目标的样本利用率、提取精度等方面的不足。因此,为提高海水养殖目标样本利用率与提取精度,充分发掘背景与养殖目标的差异化信息,提出深度多循环注意力光谱的U-Net网络(Spectral Loopy Attention U-Net, SLA-UNet)模型,基于ESP的RF算法对波段运算后的光谱信息进行过滤后,运用注意力机制的U-Net网络对网箱养殖特征通道进行加权处理的同时获得深度特征,从而有效消减海水背景对养殖目标信息提取的影响,实现网箱养殖信息的精确提取。
研究区1湛江市霞山区和坡头区位置如图1所示,介于20°13′~21°57′N,109°40′~110°58′E。位于我国广东省,终年受海洋气候的影响,冬无严寒,夏无酷暑。
研究区2海南省临高县位置如图2所示,地处 18°10′~20°10′N,108°37′~111°03′E。属热带季风气候,是我国最具有热带海洋季风气候特征的地方,全年暖热,雨量充沛。
本文对湛江市的霞山区和坡头区以及海南省的临高县进行网箱养殖信息的提取,其中养殖区类型共有两类,一类是近岸网箱养殖区,遥感影像上常呈较亮的灰白色如图3a所示;另一类为深海网箱养殖区,遥感影像上常呈深白色,如图3b
实验数据采用坡头区、霞山区、临高县GF-1卫星的PMS1高分辨率遥感影像,包括空间分辨率为2 m的全色影像和8 m的多光谱影像,数据预处理包括:大气校正、辐射定标、几何校正、图像融合、图像裁剪、波段选择、波段运算等。其中采用ENVI 5.3中的NNDiffuse Pan Sharpening 工具对校正后的全色影像和多光谱影像进行融合,并采用式(1)至式(4)进行比值指数计算:
$ R_1=G/\mathrm{NIR}\text{,} $
$ {{R}_{2}} = (R - G)/(R + G) \text{,} $
$ R_3=(\mathrm{NIR}-R)/(\mathrm{NIR}+R)\text{,} $
$ R_4=({{\mathrm{NIR}}-G}){/({\text{NIR}}+G)} \text{,} $
式中,R为红光波段反射率;G为绿光波段反射率;NIR为近红外波段反射率;R1为比值指数;R2、R3、R4为归一化比值指数。
通过基于ESP的RF算法进行冗余光谱信息的去除,采用目视解译创建网箱养殖矢量标签,并分别对海水背景及养殖网箱目标赋值。运用pycharm2022平台对上述的遥感影像及真值数据进行裁剪,通过纹理特征与离海距离,获得可以区分近岸网箱和深海网箱的尺寸为256 × 256像素的标签数据集。为保证模型的拟合,对数据集进行增殖操作,共得到样本数据集200对,并按照7∶2∶1比例划分为训练集、测试集、验证集。
本文的实验环境:CPU采用Intel Core i7 4.0-GHz,GPU采用NVIDIA GeForce RTX,32 GB,构建基于Conda的Pytorch深度学习环境,结合GDAL、NumPy作为地学处理与数字矩阵处理插件进行实现。
网箱养殖信息提取的核心是去除冗余光谱信息后与赋予注意力模块的神经网络获取的网箱养殖深度特征进行结合,在获取高效光谱特征的同时,对深度特征进行筛选,实现海水养殖区的精准提取,流程如图4所示,具体步骤如下:
使用基于ESP的RF算法提取高效光谱信息后,在U-Net网络的卷积层后加入SE注意力机制,添加权重赋予,建立SLA-UNet网络。将标签数据输入模型,使用transform模块进行归一化处理后进行模型训练,达到最优拟合后完成训练。将结果输入到包含总体精度(OA)、召回率(R)、平均交并比(MIOU)3种函数的精度验证模块,完成模型的验证。
注意力机制是人类视觉行为在计算机上的映射,合理处理视觉信息,在视觉范围内对一部分信息关注,忽略其他信息。
图5为神经网络添加注意力机制的流程,左侧的Feature map(X)在卷积操作之后引入SE机制,在通道维度(C维度)进行权重赋予,不同颜色通道代表权重差异,每一个特征通道重要性产生梯度,使神经网络模拟人眼重点关注Feature map(X *)中权重值大的通道。
SE注意力机制实现的关键流程如下:通过挤压操作(Squeeze)将各通道的二维特征(H×W)压缩为实数后经过激励操作(Excitation),进行各通道的赋值,并通过连接层建立通道间的相关性,其中保证输出权重数量与输入通道相等,最后通过归一化加权(Scale)将权重系数用乘法的方式加权到特征通道中,即逐通道乘以权重系数。
使用SLA-UNet网络对网箱养殖进行提取,具体操作示意图如图6所示,涉及的关键操作包括:
(1)卷积操作。初始学习率设置为10−4;使用3 × 3卷积核进行特征提取,卷积操作后进行线性整流函数处理,同时为防止边缘信息丢失,添加padding参数设置,补全处理过程损失的特征信息。为防止过拟合,设置权重衰减为5 × 10−4。迭代次数为200,当轮次达到130轮次时,达到最优效果。
(2)添加SE注意力机制。卷积处理后,在通道维度赋权重,从而重点关注利于网箱养殖区提取的特征,忽视干扰特征。
(3)池化操作。采用步长为2的2 × 2最大池化操作,进行下采样,降低维度,过滤次要高频信息,减少通道数,增大感受野。
(4)反池化操作。在卷积层操作后进行上采样,实现精准定位,进行维度恢复。
(5)跳跃连接结构。通过跳跃连接实现深度特征与高效光谱特征拼接合并,使图像具备多维度的高效光谱特征,有效恢复养殖目标语义信息,增强网络模型的学习能力。
采用总体精度(OA)、平均交并比(MIOU)、召回率(R)3个指标进行精度评估,具体见式(5)至式(7):
$ \mathrm{OA}=\mathrm{\frac{\mathrm{(TP+TN)}}{(TP+TN+FP+FN)}}\text{,} $
$ \mathrm{R=\frac{TP}{(TP+FN)}}\text{,} $
$ {{\mathrm{MIOU}} = }\frac{{1}}{{{k + 1}}}\sum\limits_{{i = 0}}^{k} {\frac{{{{p}_{{ii}}}}}{{\displaystyle\sum\limits_{{j = 0}}^{k} {{{p}_{{ij}}} + \sum\limits_{{j = 0}}^{k} {{{p}_{{ji}}}} - {{p}_{{ii}}}} }}} \text{,} $
$ {{\mathrm{MIOU}} = }\frac{{1}}{{{k + 1}}}\sum\limits_{{i = 0}}^{k} {\frac{{\rm{TP}}}{{\rm{FN + FP + TP}}}} \text{,} $
式中,TP为预测正确的正例比例;FP为预测错误的假正例比例;FN为预测错误的假反例比例;TN为预测正确的真反例比例;piji类别预测为j类别比例。同时式(7a)和式(7b)分别为正反例表达模式。
将SLA-UNet模型提取的近岸网箱结果,与Canny算子、Otsu算法、PCA_Kmeans算法、基于ESP的RF算法、U-Net模型的结果进行对比,原影像、真值图以及各算法提取结果如图7所示,各模型精度指标见表1,其中白色区域为近岸网箱识别结果,黑色区域为海水背景。
根据实验结果,Canny算子、Otsu算法、PCA_Kmeans算法对于形状复杂且没有固定大小的近岸网箱难以提取正确的边界,同时存在较多的错提漏提现象。基于ESP的RF算法与U-Net模型在一定程度上减少了错提漏提现象,但也对背景造成错误提取,并产生了较重的提取目标黏连。SLA-UNet模型能够成功降低养殖目标的粘连现象,相较于其他对比算法精度明显提升,其总体精度达98.3%,召回率达到98.6%,平均交并比为83.5%,相比其他算法,提取结果显著优化。
利用SLA-UNet模型对坡头区近岸网箱养殖区域进行提取,结果如图8,坡头区近岸网箱养殖区域面积为0.33 km2,主要分布于南三镇北部近岸海湾内,究其原因,近岸网箱抗风浪能力较差,受气候因素影响程度较大,分布于近岸海湾内,能够缓解气候及风浪潮的影响。
将SLA-UNet模型提取的深海网箱结果,与Canny算子、Otsu算法、PCA_Kmeans算法、基于ESP的RF算法、U-Net模型的结果进行对比,原影像、真值图及各算法提取结果如图9所示,各模型精度指标见表2,其中白色区域为深海网箱的识别结果。
根据实验结果,Canny算子、Otsu算法、PCA_Kmeans算法,对于与海水光谱相近,且养殖面积较小的深海网箱来说,总体精度达到85.2%~88.9%,平均交并比达到60.5%~66.8%,精度相对较低,易产生网箱边界模糊,边界缺失、错提漏提等。基于ESP的RF算法与U-Net模型虽然在一定程度上减少了海浪的误差影响,但对于网箱群中非网箱高亮点有一定的错提现象。SLA-UNet模型的深海网箱提取结果,能够将高亮点认定为海水背景,相较于其他对比算法精度明显提升,总体精度为99.2%,召回率为98.3%,平均交并比为91.6%,提取结果显著优化。
使用SLA-UNet模型对霞山区、坡头区深海网箱进行提取,提取结果如图10所示,共提取深海网箱面积0.27 km2,主要分布在特呈岛和南三镇周边的深海地区。这也与深海网箱抗风浪能力相吻合。
使用SLA-UNet模型提取临高县的深海网箱,将提取结果与Canny算子、Otsu算法、PCA_Kmeans算法、基于ESP的RF算法、U-Net模型的结果进行对比,原影像、真值图以及各算法的提取结果如图11所示,各模型精度指标见表3,其中白色区域为深海网箱的识别结果,黑色区域为背景。
根据实验分析,各类算法结果均受到复杂的背景信息影响,精度及提取结果相较于湛江市有所下降,其中SLA-UNet模型提取结果最好、精度最高,总体精度为98.6%,召回率为98.1%,平均交并比为82.3%。
所提SLA-UNet网络模型,将高效光谱信息与添加注意力机制的U-Net网络结合,既获得了高效光谱信息,又充分模拟人眼视觉行为,从而达到有效降低复杂背景条件下对网箱提取的影响,以及“黏连”现象的产生,实现了对网箱养殖目标的有效提取。
本文研究结果表明:(1)SLA-UNet网络模型具有较好的网箱养殖提取能力。SLA-UNet模型对坡头区近岸网箱提取总体精度为98.3%,召回率为98.6%,平均交并比为83.5%;对坡头区、霞山区深海网箱提取总体精度为99.2%,召回率为98.3%,平均交并比为91.6%。对临高县深海网箱提取总体精度为98.6%,召回率为98.1%,平均交并比为82.3%。
(2)利用较少的样本完成了研究区的网箱养殖提取,提高了样本的利用效率,展现了模型对于样本利用率的提升。
(3)在模型的适用性方面,利用SLA-UNet模型对背景更为复杂的海南省临高县深海网箱进行提取,虽然提取精度对比湛江市有所降低,并且漏提、黏连现象增多,但是总体精度与召回率仍然达到98%以上,平均交并比达到82.3%,证明了模型具有较强的适用性。
文章使用的模型虽然提升了提取精度与提取效果,但是仍存在小部分漏提、错提现象,且在背景更为复杂的临高县深海网箱提取中,SLA-UNet模型产生精度及提取效果的降低、错提漏提现象上升等问题。究其原因,临高县相较于湛江市海洋环境差异较大,海水波浪强度远高于湛江市,对提取结果产生剧烈影响,另外,临高县处于海水面下的深海网箱面积远高于湛江市,且分布较为密集,造成深海网箱提取难度增大,并且产生部分黏连现象。说明模型的适用性有待加强,未来可以建立更丰富的模型样本集,并推广应用范围及区域,以提高该方法在网箱养殖提取方面的普适能力。
  • 国家自然科学基金项目(42076184)
  • 国家自然科学基金项目(41706195)
  • 国家高分重大科研专项项目(41-Y30F07-9001-20/22)
  • 国家重点研发计划项目(2021YFC2801000)
参考文献 引证文献
排序方式:
1
Wang Ming, Mao Dehua, Xiao Xiangming, et al. Interannual changes of coastal aquaculture ponds in China at 10-m spatial resolution during 2016–2021[J]. Remote Sensing of Environment, 2023, 284: 113347.
2
FAO. The State of World Fisheries and Aquaculture 2020[EB/OL]. [2023-03-05]. http://doi.org/10.4060/ca9229en
3
Mao Dehua, Yang Hong, Wang Zongming, et al. Reverse the hidden loss of China’s wetlands[J]. Science, 2022, 376(6597): 1061.
4
邓莎萨, 张帆, 尹嫱等. 面向目视解译的全极化SAR船只精细化特征表征方法[J/OL]. [2024-02-21]. 雷达学报, 2023. https://radars.ac.cn/cn/article/doi/10.12000/JR23078. doi: 10.12000/JR23078
Deng Shasa, Zhang Fan, Yin Qiang, et al. Refined ship feature characterization method of full-polarimetric synthetic aperture radar for visual interpretation[J/OL]. Journal of Radars, 2023. https://radars.ac.cn/cn/article/doi/10.12000/JR23078. doi: 10.12000/JR23078
5
Schepaschenko D, See L, Lesiv M, et al. Recent advances in forest observation with visual interpretation of very high-resolution imagery[J]. Surveys in Geophysics, 2019, 40(4): 839−862.
6
汪静平, 吴小丹, 马杜娟, 等. 基于机器学习的遥感反演: 不确定性因素分析[J]. 遥感学报, 2023, 27(3): 790−801.
Wang Jingping, Wu Xiaodan, Ma Dujuan, et al. Remote sensing retrieval based on machine learning algorithm: uncertainty analysis[J]. Journal of Remote Sensing, 2023, 27(3): 790−801.
7
Virnodkar S S, Pachghare V K, Patil V C, et al. Remote sensing and machine learning for crop water stress determination in various crops: A critical review[J]. Precision Agriculture, 2020, 21(5): 1121−1155.
8
Maxwell A E, Warner T A, Guillén L A. Accuracy assessment in convolutional neural network-based deep learning remote sensing studies—Part 2: Recommendations and best practices[J]. Remote Sensing, 2021, 13(13): 2591.
9
Kechagias-Stamatis O, Aouf N. Fusing deep learning and sparse coding for SAR ATR[J]. IEEE Transactions on Aerospace and Electronic Systems, 2019, 55(2): 785−797.
10
Seto K C, Fragkias M. Mangrove conversion and aquaculture development in Vietnam: A remote sensing-based approach for evaluating the Ramsar Convention on Wetlands[J]. Global Environmental Change, 2007, 17(3/4): 486−500.
11
Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504−507.
12
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.
13
Li Jiayi, Zhang Hongyan, Zhang Liangpei. Supervised segmentation of very high resolution images by the use of extended morphological attribute profiles and a sparse transform[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(8): 1409−1413.
14
Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for biomedical image segmentation[C]//Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015: 234−241.
15
Badrinarayanan V, Kendall A, Cipolla R. SegNet: A deep convolutional encoder-decoder architecture for image segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(12): 2481−2495.
16
Zheng Shuai, Jayasumana S, Romera-Paredes B, et al. Conditional random fields as recurrent neural networks[C]//Proceedings of the 2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1529−1537.
17
Chen Yang, Fan Rongshuang, Yang Xiucheng, et al. Extraction of urban water bodies from high-resolution remote-sensing imagery using deep learning[J]. Water, 2018, 10(5): 585.
18
刘岳明, 杨晓梅, 王志华, 等. 基于深度学习RCF模型的三都澳筏式养殖区提取研究[J]. 海洋学报, 2019, 41(4): 119−130.
Liu Yueming, Yang Xiaomei, Wang Zhihua, et al. Extracting raft aquaculture areas in Sanduao from high-resolution remote sensing images using RCF[J]. Haiyang Xuebao, 2019, 41(4): 119−130.
19
Liu Chenxi, Jiang Tao, Zhang Zhen, et al. Extraction method of offshore mariculture area under weak signal based on multisource feature fusion[J]. Journal of Marine Science and Engineering, 2020, 8(2): 99.
20
柯丽娜, 翟宇宁, 范剑超. 深度边缘光谱U-Net海水网箱养殖信息提取[J]. 海洋学报, 2022, 44(2): 132−142.
Ke Lina, Zhai Yuning, Fan Jianchao. Marine cage aquaculture information extraction based on deep edge spectral U-Net[J]. Haiyang Xuebao, 2022, 44(2): 132−142.
2024年第46卷第5期
PDF下载
191
69
引用本文
BibTeX
文章信息
doi: 10.12284/hyxb2024044
  • 接收时间:2023-09-14
  • 首发时间:2025-11-26
  • 出版时间:2024-05-31
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-09-14
  • 修回日期:2023-12-19
基金
国家自然科学基金项目(42076184)
国家自然科学基金项目(41706195)
国家高分重大科研专项项目(41-Y30F07-9001-20/22)
国家重点研发计划项目(2021YFC2801000)
作者信息
    1.辽宁师范大学 地理科学学院,辽宁 大连 116029
    2.大连理工大学 控制科学与工程学院,辽宁 大连 116024

通讯作者:

*范剑超,博士,教授,博士生导师,研究方向为海洋遥感影像人工智能分析。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/hyxb/CN/10.12284/hyxb2024044
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