Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression

Water extraction from Synthetic Aperture Radar (SAR) images is crucial for water resource management and maintaining the sustainability of ecosystems. Though great progress has been achieved, there are still some challenges, such as an insufficient ability to extract water edge details, an inability...

Full description

Saved in:
Bibliographic Details
Main Authors: Meijun Gao, Wenjie Dong, Lifu Chen, Zhongwu Wu
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2366
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850228258377826304
author Meijun Gao
Wenjie Dong
Lifu Chen
Zhongwu Wu
author_facet Meijun Gao
Wenjie Dong
Lifu Chen
Zhongwu Wu
author_sort Meijun Gao
collection DOAJ
description Water extraction from Synthetic Aperture Radar (SAR) images is crucial for water resource management and maintaining the sustainability of ecosystems. Though great progress has been achieved, there are still some challenges, such as an insufficient ability to extract water edge details, an inability to detect small water bodies, and a weak ability to suppress background noise. To address these problems, we propose the Global Context Attention Feature Fusion Network (GCAFF-Net) in this article. It includes an encoder module for hierarchical feature extraction and a decoder module for merging multi-scale features. The encoder utilizes ResNet-101 as the backbone network to generate four-level features of different resolutions. In the middle-level feature fusion stage, the Attention Feature Fusion module (AFFM) is presented for multi-scale feature learning to improve the performance of fine water segmentation. In the advanced feature encoding stage, the Global Context Atrous Spatial Pyramid Pooling (GCASPP) is constructed to adaptively integrate the water information in SAR images from a global perspective, thereby enhancing the network’s ability to express water boundaries. In the decoder module, an attention modulation module (AMM) is introduced to rearrange the distribution of feature importance from the channel-space sequence perspective, so as to better extract the detailed features of water bodies. In the experiment, SAR images from Sentinel-1 system are utilized, and three different water areas with different features and scales are selected for independent testing. The Pixel Accuracy (PA) and Intersection over Union (IoU) values for water extraction are 95.24% and 91.63%, respectively. The results indicate that the network can extract more integral water edges and better detailed features, enhancing the accuracy and generalization of water body extraction. Compared with the several existing classical semantic segmentation models, GCAFF-Net embodies superior performance, which can also be used for typical target segmentation from SAR images.
format Article
id doaj-art-2492ab657a854f2ba4199915e9ec9821
institution OA Journals
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-2492ab657a854f2ba4199915e9ec98212025-08-20T02:04:34ZengMDPI AGApplied Sciences2076-34172025-02-01155236610.3390/app15052366Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise SuppressionMeijun Gao0Wenjie Dong1Lifu Chen2Zhongwu Wu3School of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, ChinaSchool of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, ChinaSchool of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, ChinaSchool of Electrical and Information Engineering, Changsha University of Science and Technology, Changsha 410114, ChinaWater extraction from Synthetic Aperture Radar (SAR) images is crucial for water resource management and maintaining the sustainability of ecosystems. Though great progress has been achieved, there are still some challenges, such as an insufficient ability to extract water edge details, an inability to detect small water bodies, and a weak ability to suppress background noise. To address these problems, we propose the Global Context Attention Feature Fusion Network (GCAFF-Net) in this article. It includes an encoder module for hierarchical feature extraction and a decoder module for merging multi-scale features. The encoder utilizes ResNet-101 as the backbone network to generate four-level features of different resolutions. In the middle-level feature fusion stage, the Attention Feature Fusion module (AFFM) is presented for multi-scale feature learning to improve the performance of fine water segmentation. In the advanced feature encoding stage, the Global Context Atrous Spatial Pyramid Pooling (GCASPP) is constructed to adaptively integrate the water information in SAR images from a global perspective, thereby enhancing the network’s ability to express water boundaries. In the decoder module, an attention modulation module (AMM) is introduced to rearrange the distribution of feature importance from the channel-space sequence perspective, so as to better extract the detailed features of water bodies. In the experiment, SAR images from Sentinel-1 system are utilized, and three different water areas with different features and scales are selected for independent testing. The Pixel Accuracy (PA) and Intersection over Union (IoU) values for water extraction are 95.24% and 91.63%, respectively. The results indicate that the network can extract more integral water edges and better detailed features, enhancing the accuracy and generalization of water body extraction. Compared with the several existing classical semantic segmentation models, GCAFF-Net embodies superior performance, which can also be used for typical target segmentation from SAR images.https://www.mdpi.com/2076-3417/15/5/2366SARwater segmentationneural networkattention mechanism
spellingShingle Meijun Gao
Wenjie Dong
Lifu Chen
Zhongwu Wu
Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression
Applied Sciences
SAR
water segmentation
neural network
attention mechanism
title Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression
title_full Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression
title_fullStr Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression
title_full_unstemmed Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression
title_short Automatic Extraction of Water Body from SAR Images Considering Enhanced Feature Fusion and Noise Suppression
title_sort automatic extraction of water body from sar images considering enhanced feature fusion and noise suppression
topic SAR
water segmentation
neural network
attention mechanism
url https://www.mdpi.com/2076-3417/15/5/2366
work_keys_str_mv AT meijungao automaticextractionofwaterbodyfromsarimagesconsideringenhancedfeaturefusionandnoisesuppression
AT wenjiedong automaticextractionofwaterbodyfromsarimagesconsideringenhancedfeaturefusionandnoisesuppression
AT lifuchen automaticextractionofwaterbodyfromsarimagesconsideringenhancedfeaturefusionandnoisesuppression
AT zhongwuwu automaticextractionofwaterbodyfromsarimagesconsideringenhancedfeaturefusionandnoisesuppression