HexaLCSeg:来自 Hexagon 卫星图像的历史基准数据集,用于土地覆被分割 [软件和数据集]

IF 16.2 1区 地球科学 Q1 GEOCHEMISTRY & GEOPHYSICS IEEE Geoscience and Remote Sensing Magazine Pub Date : 2024-09-23 DOI:10.1109/mgrs.2024.3394248
Elif Sertel, Mustafa Erdem Kabadayi, Gafur Semi Sengul, Ilay Nur Tumer
{"title":"HexaLCSeg:来自 Hexagon 卫星图像的历史基准数据集,用于土地覆被分割 [软件和数据集]","authors":"Elif Sertel, Mustafa Erdem Kabadayi, Gafur Semi Sengul, Ilay Nur Tumer","doi":"10.1109/mgrs.2024.3394248","DOIUrl":null,"url":null,"abstract":"Historical land cover (LC) maps are significant geospatial data sources used to understand past land characteristics and accurately determine the long-term land changes that provide valuable insights into the interactions between human activities and the environment over time. This article introduces a novel open LC benchmark dataset generated from very high spatial resolution historical Hexagon (KH-9) reconnaissance satellite images to be used in deep learning (DL)-based image segmentation tasks. This new benchmark dataset, which includes very high-resolution (VHR) mono-band Hexagon images of several Turkish and Bulgarian territories from the 1970s and 1980s, covers a large geographic area. Our dataset includes eight LC classes inspired by the European Space Agency (ESA) WorldCover project except for the tree class, which we divided into subclasses, namely agricultural fruit trees and other trees. We implemented widely used U-Net++ and DeepLabv3+ segmentation architectures with appropriate hyperparameters and backbone structures to demonstrate the versatility and impact of our HexaLCSeg dataset and to compare the performance of these models for accurate and fast LC mapping of past terrain conditions. We achieved the highest accuracy using U-Net++ with an SE-ResNeXt50 backbone and obtained an F1-score of 0.8804. The findings of this study can be applied to different geographical regions with similar Hexagon images, providing valuable contributions to the field of remote sensing and LC mapping. Our dataset, related source codes, and pretrained models are available at <uri xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://github.com/RSandAI/HexaLCSeg</uri> and <uri xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">https://doi.org/10.5281/zenodo.11005344</uri>\n.","PeriodicalId":48660,"journal":{"name":"IEEE Geoscience and Remote Sensing Magazine","volume":null,"pages":null},"PeriodicalIF":16.2000,"publicationDate":"2024-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"HexaLCSeg: A historical benchmark dataset from Hexagon satellite images for land cover segmentation [Software and Data Sets]\",\"authors\":\"Elif Sertel, Mustafa Erdem Kabadayi, Gafur Semi Sengul, Ilay Nur Tumer\",\"doi\":\"10.1109/mgrs.2024.3394248\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Historical land cover (LC) maps are significant geospatial data sources used to understand past land characteristics and accurately determine the long-term land changes that provide valuable insights into the interactions between human activities and the environment over time. This article introduces a novel open LC benchmark dataset generated from very high spatial resolution historical Hexagon (KH-9) reconnaissance satellite images to be used in deep learning (DL)-based image segmentation tasks. This new benchmark dataset, which includes very high-resolution (VHR) mono-band Hexagon images of several Turkish and Bulgarian territories from the 1970s and 1980s, covers a large geographic area. Our dataset includes eight LC classes inspired by the European Space Agency (ESA) WorldCover project except for the tree class, which we divided into subclasses, namely agricultural fruit trees and other trees. We implemented widely used U-Net++ and DeepLabv3+ segmentation architectures with appropriate hyperparameters and backbone structures to demonstrate the versatility and impact of our HexaLCSeg dataset and to compare the performance of these models for accurate and fast LC mapping of past terrain conditions. We achieved the highest accuracy using U-Net++ with an SE-ResNeXt50 backbone and obtained an F1-score of 0.8804. The findings of this study can be applied to different geographical regions with similar Hexagon images, providing valuable contributions to the field of remote sensing and LC mapping. Our dataset, related source codes, and pretrained models are available at <uri xmlns:mml=\\\"http://www.w3.org/1998/Math/MathML\\\" xmlns:xlink=\\\"http://www.w3.org/1999/xlink\\\">https://github.com/RSandAI/HexaLCSeg</uri> and <uri xmlns:mml=\\\"http://www.w3.org/1998/Math/MathML\\\" xmlns:xlink=\\\"http://www.w3.org/1999/xlink\\\">https://doi.org/10.5281/zenodo.11005344</uri>\\n.\",\"PeriodicalId\":48660,\"journal\":{\"name\":\"IEEE Geoscience and Remote Sensing Magazine\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":16.2000,\"publicationDate\":\"2024-09-23\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Geoscience and Remote Sensing Magazine\",\"FirstCategoryId\":\"89\",\"ListUrlMain\":\"https://doi.org/10.1109/mgrs.2024.3394248\",\"RegionNum\":1,\"RegionCategory\":\"地球科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"GEOCHEMISTRY & GEOPHYSICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Geoscience and Remote Sensing Magazine","FirstCategoryId":"89","ListUrlMain":"https://doi.org/10.1109/mgrs.2024.3394248","RegionNum":1,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GEOCHEMISTRY & GEOPHYSICS","Score":null,"Total":0}
引用次数: 0

摘要

历史土地覆被图(LC)是重要的地理空间数据来源,可用于了解过去的土地特征并准确确定长期的土地变化,从而为深入了解人类活动与环境之间随着时间的推移而产生的相互作用提供有价值的见解。本文介绍了一种新的开放式地表植被基准数据集,该数据集由空间分辨率极高的历史性六角(KH-9)侦察卫星图像生成,可用于基于深度学习(DL)的图像分割任务。这一新的基准数据集包括 20 世纪 70 年代和 80 年代土耳其和保加利亚若干领土的超高分辨率(VHR)单波段六边形图像,覆盖了大片地理区域。我们的数据集包括 8 个 LC 类,其灵感来自欧洲航天局 (ESA) 的 WorldCover 项目,但树木类除外,我们将其分为多个子类,即农用果树和其他树木。我们采用了广泛使用的 U-Net++ 和 DeepLabv3+ 分割架构,并配备了适当的超参数和骨干结构,以证明我们的 HexaLCSeg 数据集的多功能性和影响力,并比较这些模型在准确、快速地绘制过去地形条件的 LC 地图方面的性能。我们使用带有 SE-ResNeXt50 主干网的 U-Net++ 实现了最高精度,F1 分数为 0.8804。本研究的结果可应用于具有类似 Hexagon 图像的不同地理区域,为遥感和 LC 绘图领域做出了宝贵贡献。我们的数据集、相关源代码和预训练模型可在 https://github.com/RSandAI/HexaLCSeg 和 https://doi.org/10.5281/zenodo.11005344 上查阅。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
HexaLCSeg: A historical benchmark dataset from Hexagon satellite images for land cover segmentation [Software and Data Sets]
Historical land cover (LC) maps are significant geospatial data sources used to understand past land characteristics and accurately determine the long-term land changes that provide valuable insights into the interactions between human activities and the environment over time. This article introduces a novel open LC benchmark dataset generated from very high spatial resolution historical Hexagon (KH-9) reconnaissance satellite images to be used in deep learning (DL)-based image segmentation tasks. This new benchmark dataset, which includes very high-resolution (VHR) mono-band Hexagon images of several Turkish and Bulgarian territories from the 1970s and 1980s, covers a large geographic area. Our dataset includes eight LC classes inspired by the European Space Agency (ESA) WorldCover project except for the tree class, which we divided into subclasses, namely agricultural fruit trees and other trees. We implemented widely used U-Net++ and DeepLabv3+ segmentation architectures with appropriate hyperparameters and backbone structures to demonstrate the versatility and impact of our HexaLCSeg dataset and to compare the performance of these models for accurate and fast LC mapping of past terrain conditions. We achieved the highest accuracy using U-Net++ with an SE-ResNeXt50 backbone and obtained an F1-score of 0.8804. The findings of this study can be applied to different geographical regions with similar Hexagon images, providing valuable contributions to the field of remote sensing and LC mapping. Our dataset, related source codes, and pretrained models are available at https://github.com/RSandAI/HexaLCSeg and https://doi.org/10.5281/zenodo.11005344 .
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Geoscience and Remote Sensing Magazine
IEEE Geoscience and Remote Sensing Magazine Computer Science-General Computer Science
CiteScore
20.50
自引率
2.70%
发文量
58
期刊介绍: The IEEE Geoscience and Remote Sensing Magazine (GRSM) serves as an informative platform, keeping readers abreast of activities within the IEEE GRS Society, its technical committees, and chapters. In addition to updating readers on society-related news, GRSM plays a crucial role in educating and informing its audience through various channels. These include:Technical Papers,International Remote Sensing Activities,Contributions on Education Activities,Industrial and University Profiles,Conference News,Book Reviews,Calendar of Important Events.
期刊最新文献
Spatiotemporal Big Data Empower Community Modeling, Monitoring, Evaluation, and Optimization for Sustainable Community Development: A review of challenges and opportunities Opening the Black Box: A systematic review on explainable artificial intelligence in remote sensing LuTan-1: An innovative L-band spaceborne bistatic interferometric synthetic aperture radar mission Better, Not Just More: Data-centric machine learning for Earth observation EarthNets: Empowering artificial intelligence for Earth observation
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1