Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery

<p>In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Accurate localized PV information, including location and size, is the basis for PV regulation and potential assessment of the energy sector. Automatic information extra...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	H. Jiang, L. Yao, N. Lu, J. Qin, T. Liu, Y. Liu, C. Zhou
Formato:	article
Lenguaje:	EN
Publicado:	Copernicus Publications 2021
Materias:	Environmental sciences GE1-350 Geology QE1-996.5
Acceso en línea:	https://doaj.org/article/b7ac224855bc43118b086d6232a04533
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b7ac224855bc43118b086d6232a04533
record_format	dspace
spelling	oai:doaj.org-article:b7ac224855bc43118b086d6232a045332021-11-19T12:51:25ZMulti-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery10.5194/essd-13-5389-20211866-35081866-3516https://doaj.org/article/b7ac224855bc43118b086d6232a045332021-11-01T00:00:00Zhttps://essd.copernicus.org/articles/13/5389/2021/essd-13-5389-2021.pdfhttps://doaj.org/toc/1866-3508https://doaj.org/toc/1866-3516<p>In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Accurate localized PV information, including location and size, is the basis for PV regulation and potential assessment of the energy sector. Automatic information extraction based on deep learning requires high-quality labeled samples that should be collected at multiple spatial resolutions and under different backgrounds due to the diversity and variable scale of PVs. We established a PV dataset using satellite and aerial images with spatial resolutions of 0.8, 0.3, and 0.1 m, which focus on concentrated PVs, distributed ground PVs, and fine-grained rooftop PVs, respectively. The dataset contains 3716 samples of PVs installed on shrub land, grassland, cropland, saline–alkali land, and water surfaces, as well as flat concrete, steel tile, and brick roofs. The dataset is used to examine the model performance of different deep networks on PV segmentation. On average, an intersection over union (IoU) greater than 85 % is achieved. In addition, our experiments show that direct cross application between samples with different resolutions is not feasible and that fine-tuning of the pre-trained deep networks using target samples is necessary. The dataset can support more work on PV technology for greater value, such as developing a PV detection algorithm, simulating PV conversion efficiency, and estimating regional PV potential. The dataset is available from Zenodo on the following website: <a href="https://doi.org/10.5281/zenodo.5171712">https://doi.org/10.5281/zenodo.5171712</a> (Jiang et al., 2021).</p>H. JiangL. YaoL. YaoL. YaoN. LuN. LuN. LuJ. QinJ. QinT. LiuY. LiuY. LiuC. ZhouCopernicus PublicationsarticleEnvironmental sciencesGE1-350GeologyQE1-996.5ENEarth System Science Data, Vol 13, Pp 5389-5401 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Environmental sciences GE1-350 Geology QE1-996.5
spellingShingle	Environmental sciences GE1-350 Geology QE1-996.5 H. Jiang L. Yao L. Yao L. Yao N. Lu N. Lu N. Lu J. Qin J. Qin T. Liu Y. Liu Y. Liu C. Zhou Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
description	<p>In the context of global carbon emission reduction, solar photovoltaic (PV) technology is experiencing rapid development. Accurate localized PV information, including location and size, is the basis for PV regulation and potential assessment of the energy sector. Automatic information extraction based on deep learning requires high-quality labeled samples that should be collected at multiple spatial resolutions and under different backgrounds due to the diversity and variable scale of PVs. We established a PV dataset using satellite and aerial images with spatial resolutions of 0.8, 0.3, and 0.1 m, which focus on concentrated PVs, distributed ground PVs, and fine-grained rooftop PVs, respectively. The dataset contains 3716 samples of PVs installed on shrub land, grassland, cropland, saline–alkali land, and water surfaces, as well as flat concrete, steel tile, and brick roofs. The dataset is used to examine the model performance of different deep networks on PV segmentation. On average, an intersection over union (IoU) greater than 85 % is achieved. In addition, our experiments show that direct cross application between samples with different resolutions is not feasible and that fine-tuning of the pre-trained deep networks using target samples is necessary. The dataset can support more work on PV technology for greater value, such as developing a PV detection algorithm, simulating PV conversion efficiency, and estimating regional PV potential. The dataset is available from Zenodo on the following website: <a href="https://doi.org/10.5281/zenodo.5171712">https://doi.org/10.5281/zenodo.5171712</a> (Jiang et al., 2021).</p>
format	article
author	H. Jiang L. Yao L. Yao L. Yao N. Lu N. Lu N. Lu J. Qin J. Qin T. Liu Y. Liu Y. Liu C. Zhou
author_facet	H. Jiang L. Yao L. Yao L. Yao N. Lu N. Lu N. Lu J. Qin J. Qin T. Liu Y. Liu Y. Liu C. Zhou
author_sort	H. Jiang
title	Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
title_short	Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
title_full	Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
title_fullStr	Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
title_full_unstemmed	Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
title_sort	multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery
publisher	Copernicus Publications
publishDate	2021
url	https://doaj.org/article/b7ac224855bc43118b086d6232a04533
work_keys_str_mv	AT hjiang multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT lyao multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT lyao multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT lyao multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT nlu multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT nlu multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT nlu multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT jqin multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT jqin multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT tliu multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT yliu multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT yliu multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery AT czhou multiresolutiondatasetforphotovoltaicpanelsegmentationfromsatelliteandaerialimagery
_version_	1718420092522332160

Multi-resolution dataset for photovoltaic panel segmentation from satellite and aerial imagery

Ejemplares similares