RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks

Impervious Surface Area (ISA) is vital for urban planning, environmental monitoring, and water management. Traditional remote sensing methods struggle with complex urban landscapes, leading to accuracy limitations. To address this, we propose RU-Net++, a deep learning-based ISA extraction model inte...

Full description

Saved in:
Bibliographic Details
Main Authors: F. Yu, X. Tu, L. Cai, J. Zhang, Z. Wang
Format: Article
Language:English
Published: Copernicus Publications 2025-08-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1655/2025/isprs-archives-XLVIII-G-2025-1655-2025.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849694115224092672
author F. Yu
X. Tu
L. Cai
J. Zhang
Z. Wang
author_facet F. Yu
X. Tu
L. Cai
J. Zhang
Z. Wang
author_sort F. Yu
collection DOAJ
description Impervious Surface Area (ISA) is vital for urban planning, environmental monitoring, and water management. Traditional remote sensing methods struggle with complex urban landscapes, leading to accuracy limitations. To address this, we propose RU-Net++, a deep learning-based ISA extraction model integrating ResNet50 as the encoder with spatial, channel, and dual attention mechanisms. The decoder employs an Atrous Spatial Pyramid Pooling (ASPP) module and multiple refinement modules to enhance feature representation and edge restoration. Trained on GLC_FCS30D and GISA datasets, RU-Net++ outperforms traditional methods in IoU, F1 Score, and Overall Accuracy, offering a reliable tool for sustainable urban development and land-use management.
format Article
id doaj-art-2d6c38d1bfba4739ba7af0ba9a404acb
institution DOAJ
issn 1682-1750
2194-9034
language English
publishDate 2025-08-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-2d6c38d1bfba4739ba7af0ba9a404acb2025-08-20T03:20:12ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342025-08-01XLVIII-G-20251655166210.5194/isprs-archives-XLVIII-G-2025-1655-2025RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networksF. Yu0X. Tu1L. Cai2J. Zhang3Z. Wang4School of Surveying, Mapping and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Surveying, Mapping and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Surveying, Mapping and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Surveying, Mapping and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Surveying, Mapping and Urban Spatial Information, Beijing University of Civil Engineering and Architecture, Beijing, ChinaImpervious Surface Area (ISA) is vital for urban planning, environmental monitoring, and water management. Traditional remote sensing methods struggle with complex urban landscapes, leading to accuracy limitations. To address this, we propose RU-Net++, a deep learning-based ISA extraction model integrating ResNet50 as the encoder with spatial, channel, and dual attention mechanisms. The decoder employs an Atrous Spatial Pyramid Pooling (ASPP) module and multiple refinement modules to enhance feature representation and edge restoration. Trained on GLC_FCS30D and GISA datasets, RU-Net++ outperforms traditional methods in IoU, F1 Score, and Overall Accuracy, offering a reliable tool for sustainable urban development and land-use management.https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1655/2025/isprs-archives-XLVIII-G-2025-1655-2025.pdf
spellingShingle F. Yu
X. Tu
L. Cai
J. Zhang
Z. Wang
RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks
title_full RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks
title_fullStr RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks
title_full_unstemmed RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks
title_short RU-Net++: An automatic extraction method for Impervious Surface Area based on neural networks
title_sort ru net an automatic extraction method for impervious surface area based on neural networks
url https://isprs-archives.copernicus.org/articles/XLVIII-G-2025/1655/2025/isprs-archives-XLVIII-G-2025-1655-2025.pdf
work_keys_str_mv AT fyu runetanautomaticextractionmethodforimpervioussurfaceareabasedonneuralnetworks
AT xtu runetanautomaticextractionmethodforimpervioussurfaceareabasedonneuralnetworks
AT lcai runetanautomaticextractionmethodforimpervioussurfaceareabasedonneuralnetworks
AT jzhang runetanautomaticextractionmethodforimpervioussurfaceareabasedonneuralnetworks
AT zwang runetanautomaticextractionmethodforimpervioussurfaceareabasedonneuralnetworks