BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion

Water body detection in synthetic aperture radar (SAR) imagery plays a critical role in applications such as disaster response, water resource management, and environmental monitoring. However, it remains challenging due to complex background interference in SAR images. To address this issue, a bi-e...

Full description

Saved in:
Bibliographic Details
Main Authors: Bin Han, Xin Huang, Feng Xue
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/13/15/2347
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849770540390154240
author Bin Han
Xin Huang
Feng Xue
author_facet Bin Han
Xin Huang
Feng Xue
author_sort Bin Han
collection DOAJ
description Water body detection in synthetic aperture radar (SAR) imagery plays a critical role in applications such as disaster response, water resource management, and environmental monitoring. However, it remains challenging due to complex background interference in SAR images. To address this issue, a bi-encoder and hybrid feature fuse network (BiEHFFNet) is proposed for achieving accurate water body detection. First, a bi-encoder structure based on ResNet and Swin Transformer is used to jointly extract local spatial details and global contextual information, enhancing feature representation in complex scenarios. Additionally, the convolutional block attention module (CBAM) is employed to suppress irrelevant information of the output features of each ResNet stage. Second, a cross-attention-based hybrid feature fusion (CABHFF) module is designed to interactively integrate local and global features through cross-attention, followed by channel attention to achieve effective hybrid feature fusion, thus improving the model’s ability to capture water structures. Third, a multi-scale content-aware upsampling (MSCAU) module is designed by integrating atrous spatial pyramid pooling (ASPP) with the Content-Aware ReAssembly of FEatures (CARAFE), aiming to enhance multi-scale contextual learning while alleviating feature distortion caused by upsampling. Finally, a composite loss function combining Dice loss and Active Contour loss is used to provide stronger boundary supervision. Experiments conducted on the ALOS PALSAR dataset demonstrate that the proposed BiEHFFNet outperforms existing methods across multiple evaluation metrics, achieving more accurate water body detection.
format Article
id doaj-art-d22b2ddc20e745a7a6c96d8b802fafe8
institution DOAJ
issn 2227-7390
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-d22b2ddc20e745a7a6c96d8b802fafe82025-08-20T03:02:58ZengMDPI AGMathematics2227-73902025-07-011315234710.3390/math13152347BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature FusionBin Han0Xin Huang1Feng Xue2School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaSchool of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, ChinaWater body detection in synthetic aperture radar (SAR) imagery plays a critical role in applications such as disaster response, water resource management, and environmental monitoring. However, it remains challenging due to complex background interference in SAR images. To address this issue, a bi-encoder and hybrid feature fuse network (BiEHFFNet) is proposed for achieving accurate water body detection. First, a bi-encoder structure based on ResNet and Swin Transformer is used to jointly extract local spatial details and global contextual information, enhancing feature representation in complex scenarios. Additionally, the convolutional block attention module (CBAM) is employed to suppress irrelevant information of the output features of each ResNet stage. Second, a cross-attention-based hybrid feature fusion (CABHFF) module is designed to interactively integrate local and global features through cross-attention, followed by channel attention to achieve effective hybrid feature fusion, thus improving the model’s ability to capture water structures. Third, a multi-scale content-aware upsampling (MSCAU) module is designed by integrating atrous spatial pyramid pooling (ASPP) with the Content-Aware ReAssembly of FEatures (CARAFE), aiming to enhance multi-scale contextual learning while alleviating feature distortion caused by upsampling. Finally, a composite loss function combining Dice loss and Active Contour loss is used to provide stronger boundary supervision. Experiments conducted on the ALOS PALSAR dataset demonstrate that the proposed BiEHFFNet outperforms existing methods across multiple evaluation metrics, achieving more accurate water body detection.https://www.mdpi.com/2227-7390/13/15/2347water body detectionSARbi-encoderCABHFFMSCAU
spellingShingle Bin Han
Xin Huang
Feng Xue
BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion
Mathematics
water body detection
SAR
bi-encoder
CABHFF
MSCAU
title BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion
title_full BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion
title_fullStr BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion
title_full_unstemmed BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion
title_short BiEHFFNet: A Water Body Detection Network for SAR Images Based on Bi-Encoder and Hybrid Feature Fusion
title_sort biehffnet a water body detection network for sar images based on bi encoder and hybrid feature fusion
topic water body detection
SAR
bi-encoder
CABHFF
MSCAU
url https://www.mdpi.com/2227-7390/13/15/2347
work_keys_str_mv AT binhan biehffnetawaterbodydetectionnetworkforsarimagesbasedonbiencoderandhybridfeaturefusion
AT xinhuang biehffnetawaterbodydetectionnetworkforsarimagesbasedonbiencoderandhybridfeaturefusion
AT fengxue biehffnetawaterbodydetectionnetworkforsarimagesbasedonbiencoderandhybridfeaturefusion