Show simple item record

Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning

dc.date.accessioned2024-01-24T13:29:59Z
dc.date.available2024-01-24T13:29:59Z
dc.date.issued2023-12-11
dc.identifierdoi:10.17170/kobra-202401249423
dc.identifier.urihttp://hdl.handle.net/123456789/15394
dc.description.sponsorshipGefördert durch den Publikationsfonds der Universität Kassel
dc.language.isoeng
dc.rightsNamensnennung 4.0 International*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/*
dc.subjectsolar photovoltaic systemseng
dc.subjectphotovoltaic plantseng
dc.subjectremote sensingeng
dc.subjectmachine learningeng
dc.subjectdeep learningeng
dc.subjectobject detectioneng
dc.subjectimage segmentationeng
dc.subject.ddc600
dc.titleMulti-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learningeng
dc.typeAufsatz
dcterms.abstractIn the realm of solar photovoltaic system image segmentation, existing deep learning networks focus almost exclusively on single image sources both in terms of sensors used and image resolution. This often prevents the wide deployment of such networks. Our research introduces a novel approach to train a network on a diverse range of image data, spanning UAV, aerial, and satellite imagery at both native and aggregated resolutions of 0.1 m, 0.2 m, 0.3 m, 0.8 m, 1.6 m, and 3.2 m. Using extensive hyperparameter tuning, we first determined the best possible parameter combinations for the network based on the DeepLabV3 ResNet101 architecture. We then trained a model using the wide range of different image sources. The final network offers several advantages. It outperforms networks trained with single image sources in multiple test applications as measured by the F1-Score (95.27%) and IoU (91.04%). The network is also able to work with a variety of target imagery due to the fact that a diverse range of image data was used to train it. The model is made freely available for further applications.eng
dcterms.accessRightsopen access
dcterms.creatorKleebauer, Maximilian
dcterms.creatorMarz, Christopher
dcterms.creatorReudenbach, Christoph
dcterms.creatorBraun, Martin
dcterms.extent21 Seiten
dc.relation.doidoi:10.3390/rs15245687
dc.subject.swdFotovoltaikger
dc.subject.swdDeep learningger
dc.subject.swdErneuerbare Energienger
dc.subject.swdMaschinelles Lernenger
dc.subject.swdBildsegmentierungger
dc.subject.swdObjekterkennungger
dc.type.versionpublishedVersion
dcterms.source.identifiereissn:2072-4292
dcterms.source.issueIssue 24
dcterms.source.journalRemote Sensingeng
dcterms.source.volumeVolume 15
kup.iskupfalse
dcterms.source.articlenumber5687


Files in this item

Thumbnail
Name:
license_rdf
Size:
908bytes
Format:
application/rdf+xml
View/Open
Thumbnail
Name:
remotesensing_15_05687_v3.pdf
Size:
7.702Mb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record

Namensnennung 4.0 International
Except where otherwise noted, this item's license is described as Namensnennung 4.0 International