CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images

Building extraction is significant for the intelligent interpretation of high-resolution remote sensing images (HRSIs). However, in some complex scenarios where the features of the building and its adjacent ground objects are similar, the current segmentation model cannot distinguish them effectivel...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongjie Yang, Xianjun Gao, Yuanwei Yang, Minghan Jiang, Kangliang Guo, Bo Liu, Shaohua Li, Shengyan Yu
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10556688/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849424327851638784
author Dongjie Yang
Xianjun Gao
Yuanwei Yang
Minghan Jiang
Kangliang Guo
Bo Liu
Shaohua Li
Shengyan Yu
author_facet Dongjie Yang
Xianjun Gao
Yuanwei Yang
Minghan Jiang
Kangliang Guo
Bo Liu
Shaohua Li
Shengyan Yu
author_sort Dongjie Yang
collection DOAJ
description Building extraction is significant for the intelligent interpretation of high-resolution remote sensing images (HRSIs). However, in some complex scenarios where the features of the building and its adjacent ground objects are similar, the current segmentation model cannot distinguish them effectively. Therefore, we propose a complex scenarios adaptive network (CSA-Net) for building extraction. CSA-Net is comprised of the hierarchical-context feature extraction (HFE) module, the global-local feature interaction (GFI) module, and the multiscale-adaptive feature fusion (MFF) structure. The HFE obtains high-level semantic information at different levels and fuses it with low-level detailed information by skipping connections to enhance the reasoning and perception ability of building structure in complex scenes. Then, the GFI acquires global-local features of buildings and their surrounding environment via dense multiscale dilated convolution. The information can be shared through efficient interaction among features, and irrelevant backgrounds can be suppressed. Then, in the up-sampling process, the MFF alleviates the feature loss and enhances the robustness of the network by using feature fusion after layer-by-layer adaptive weight allocation. Experiments show that CSA-Net outperforms other comparable methods, with intersection over union values of 79.99%, 89.75%, and 73.59%, respectively, on the Google Arlinton, WHU, and Massachusetts building datasets. The visual comparison results demonstrate that our method can enhance the accuracy of building extraction in complex scenes. Meanwhile, the efficiency results indicate our approach strikes a balance between calculation parameters and time and achieves high levels of efficiency.
format Article
id doaj-art-644be5d55c8f4c6383e4b233ddfc2af6
institution Kabale University
issn 1939-1404
2151-1535
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-644be5d55c8f4c6383e4b233ddfc2af62025-08-20T03:30:14ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352024-01-011793895310.1109/JSTARS.2024.341398710556688CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing ImagesDongjie Yang0https://orcid.org/0000-0001-7815-3523Xianjun Gao1https://orcid.org/0000-0003-1144-8479Yuanwei Yang2Minghan Jiang3Kangliang Guo4Bo Liu5https://orcid.org/0000-0002-2268-6176Shaohua Li6https://orcid.org/0000-0002-0223-0796Shengyan Yu7School of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaKey Laboratory of Mine Environmental Monitoring and Improving around Poyang Lake of Ministry of Natural Resources, East China University of Technology, Nanchang, ChinaSchool of Geosciences, Yangtze University, Wuhan, ChinaInner Mongolia Autonomous Region Surveying and Mapping Geographic Information Center, Hohhot, ChinaBuilding extraction is significant for the intelligent interpretation of high-resolution remote sensing images (HRSIs). However, in some complex scenarios where the features of the building and its adjacent ground objects are similar, the current segmentation model cannot distinguish them effectively. Therefore, we propose a complex scenarios adaptive network (CSA-Net) for building extraction. CSA-Net is comprised of the hierarchical-context feature extraction (HFE) module, the global-local feature interaction (GFI) module, and the multiscale-adaptive feature fusion (MFF) structure. The HFE obtains high-level semantic information at different levels and fuses it with low-level detailed information by skipping connections to enhance the reasoning and perception ability of building structure in complex scenes. Then, the GFI acquires global-local features of buildings and their surrounding environment via dense multiscale dilated convolution. The information can be shared through efficient interaction among features, and irrelevant backgrounds can be suppressed. Then, in the up-sampling process, the MFF alleviates the feature loss and enhances the robustness of the network by using feature fusion after layer-by-layer adaptive weight allocation. Experiments show that CSA-Net outperforms other comparable methods, with intersection over union values of 79.99%, 89.75%, and 73.59%, respectively, on the Google Arlinton, WHU, and Massachusetts building datasets. The visual comparison results demonstrate that our method can enhance the accuracy of building extraction in complex scenes. Meanwhile, the efficiency results indicate our approach strikes a balance between calculation parameters and time and achieves high levels of efficiency.https://ieeexplore.ieee.org/document/10556688/Attentionbuilding extractiondeep learningglobal-local featuresremote sensing images
spellingShingle Dongjie Yang
Xianjun Gao
Yuanwei Yang
Minghan Jiang
Kangliang Guo
Bo Liu
Shaohua Li
Shengyan Yu
CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Attention
building extraction
deep learning
global-local features
remote sensing images
title CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images
title_full CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images
title_fullStr CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images
title_full_unstemmed CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images
title_short CSA-Net: Complex Scenarios Adaptive Network for Building Extraction for Remote Sensing Images
title_sort csa net complex scenarios adaptive network for building extraction for remote sensing images
topic Attention
building extraction
deep learning
global-local features
remote sensing images
url https://ieeexplore.ieee.org/document/10556688/
work_keys_str_mv AT dongjieyang csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT xianjungao csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT yuanweiyang csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT minghanjiang csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT kangliangguo csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT boliu csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT shaohuali csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages
AT shengyanyu csanetcomplexscenariosadaptivenetworkforbuildingextractionforremotesensingimages