Publication:
HexaLCSeg: <i>A historical benchmark dataset from Hexagon satellite images for land cover segmentation</i>

dc.contributor.coauthorSertel, Elif
dc.contributor.departmentDepartment of History
dc.contributor.departmentVPRI (Vice Presidency for Research and Innovation)
dc.contributor.kuauthorKabadayı, Mustafa Erdem
dc.contributor.kuauthorŞengül, Gafur Semi
dc.contributor.kuauthorTümer, İlay Nur
dc.contributor.schoolcollegeinstituteAdministrative Unit
dc.contributor.schoolcollegeinstituteCollege of Social Sciences and Humanities
dc.date.accessioned2025-03-06T20:58:31Z
dc.date.issued2024
dc.description.abstractHistorical 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.
dc.description.indexedbyWOS
dc.description.indexedbyScopus
dc.description.publisherscopeInternational
dc.description.sponsoredbyTubitakEuN/A
dc.description.sponsorshipThis work was supported by the European Research Council (ERC) Proof of Concept Project "GeoAI_LULC_Seg: A GeoAI-based Land Use Land Cover Segmentation Process to Analyse and Predict Rural Depopulation, Agricultural Land Abandonment, and Deforestation in Bulgaria and Turkey, 1940-2040" under the European Union's Horizon 2020 Research and Innovation Program, Grant 101100837.
dc.identifier.doi10.1109/MGRS.2024.3394248
dc.identifier.eissn2168-6831
dc.identifier.grantnoEuropean Research Council (ERC) Proof of Concept Project "GeoAI_LULC_Seg: A GeoAI-based Land Use Land Cover Segmentation Process to Analyse and Predict Rural Depopulation, Agricultural Land Abandonment, and Deforestation in Bulgaria and Turkey, 1940-2040" [101100837];European Research Council (ERC) [101100837] Funding Source: European Research Council (ERC)
dc.identifier.issn2473-2397
dc.identifier.issue3
dc.identifier.quartileQ1
dc.identifier.scopus2-s2.0-85204876627
dc.identifier.urihttps://doi.org/10.1109/MGRS.2024.3394248
dc.identifier.urihttps://hdl.handle.net/20.500.14288/27484
dc.identifier.volume12
dc.identifier.wos1322577000015
dc.keywordsImage segmentation
dc.keywordsBiological system modeling
dc.keywordsEuropean space agency
dc.keywordsTransfer learning
dc.keywordsLand surface
dc.keywordsBenchmark testing
dc.keywordsSatellite images
dc.keywordsData models
dc.keywordsLand use planning
dc.keywordsHuman activity recognition
dc.keywordsReconnaissance
dc.keywordsGeospatial analysis
dc.keywordsUrban areas
dc.language.isoeng
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartofIEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
dc.subjectGeochemistry
dc.subjectGeophysics
dc.titleHexaLCSeg: <i>A historical benchmark dataset from Hexagon satellite images for land cover segmentation</i>
dc.typeJournal Article
dspace.entity.typePublication
local.contributor.kuauthorKabadayı, Mustafa Erdem
local.contributor.kuauthorŞengül, Gafur Semi
local.contributor.kuauthorTümer, İlay Nur
local.publication.orgunit1College of Social Sciences and Humanities
local.publication.orgunit1Administrative Unit
local.publication.orgunit2Department of History
local.publication.orgunit2VPRI (Vice Presidency for Research and Innovation)
relation.isOrgUnitOfPublicationbe8432df-d124-44c3-85b4-be586c2db8a3
relation.isOrgUnitOfPublication4d3a7799-f527-47f5-91c7-645f27f50626
relation.isOrgUnitOfPublication.latestForDiscoverybe8432df-d124-44c3-85b4-be586c2db8a3
relation.isParentOrgUnitOfPublicationf4c9bc01-f327-4f74-9722-e5885650451d
relation.isParentOrgUnitOfPublication3f7621e3-0d26-42c2-af64-58a329522794
relation.isParentOrgUnitOfPublication.latestForDiscoveryf4c9bc01-f327-4f74-9722-e5885650451d

Files