Datum
2023-12-11Schlagwort
600 Technik FotovoltaikDeep learningErneuerbare EnergienMaschinelles LernenBildsegmentierungObjekterkennungMetadata
Zur Langanzeige
Aufsatz
Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning
Zusammenfassung
In 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.
Zitierform
In: Remote Sensing Volume 15 / Issue 24 (2023-12-11) eissn:2072-4292Förderhinweis
Gefördert durch den Publikationsfonds der Universität KasselZitieren
@article{doi:10.17170/kobra-202401249423,
author={Kleebauer, Maximilian and Marz, Christopher and Reudenbach, Christoph and Braun, Martin},
title={Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning},
journal={Remote Sensing},
year={2023}
}
0500 Oax 0501 Text $btxt$2rdacontent 0502 Computermedien $bc$2rdacarrier 1100 2023$n2023 1500 1/eng 2050 ##0##http://hdl.handle.net/123456789/15394 3000 Kleebauer, Maximilian 3010 Marz, Christopher 3010 Reudenbach, Christoph 3010 Braun, Martin 4000 Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning / Kleebauer, Maximilian 4030 4060 Online-Ressource 4085 ##0##=u http://nbn-resolving.de/http://hdl.handle.net/123456789/15394=x R 4204 \$dAufsatz 4170 5550 {{Fotovoltaik}} 5550 {{Deep learning}} 5550 {{Erneuerbare Energien}} 5550 {{Maschinelles Lernen}} 5550 {{Bildsegmentierung}} 5550 {{Objekterkennung}} 7136 ##0##http://hdl.handle.net/123456789/15394
2024-01-24T13:29:59Z 2024-01-24T13:29:59Z 2023-12-11 doi:10.17170/kobra-202401249423 http://hdl.handle.net/123456789/15394 Gefördert durch den Publikationsfonds der Universität Kassel eng Namensnennung 4.0 International http://creativecommons.org/licenses/by/4.0/ solar photovoltaic systems photovoltaic plants remote sensing machine learning deep learning object detection image segmentation 600 Multi-Resolution Segmentation of Solar Photovoltaic Systems Using Deep Learning Aufsatz In 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. open access Kleebauer, Maximilian Marz, Christopher Reudenbach, Christoph Braun, Martin 21 Seiten doi:10.3390/rs15245687 Fotovoltaik Deep learning Erneuerbare Energien Maschinelles Lernen Bildsegmentierung Objekterkennung publishedVersion eissn:2072-4292 Issue 24 Remote Sensing Volume 15 false 5687
Die folgenden Lizenzbestimmungen sind mit dieser Ressource verbunden: