A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction

The segmentation of land and sea in remote sensing imagery is of great significance for coastline extraction and dynamic monitoring. Traditional coastline recognition and extraction methods based on spectral features and image processing can only generate limited image feature results when facing th...

Full description

Saved in:
Bibliographic Details
Main Authors: Yanru Song, Bai Xue, Yueyue Meng, Xiang Qin, Yixiao Li, Qi Liu
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10693424/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832590309535514624
author Yanru Song
Bai Xue
Yueyue Meng
Xiang Qin
Yixiao Li
Qi Liu
author_facet Yanru Song
Bai Xue
Yueyue Meng
Xiang Qin
Yixiao Li
Qi Liu
author_sort Yanru Song
collection DOAJ
description The segmentation of land and sea in remote sensing imagery is of great significance for coastline extraction and dynamic monitoring. Traditional coastline recognition and extraction methods based on spectral features and image processing can only generate limited image feature results when facing the complex textures and spatial distributions of high-spatial resolution remote sensing images, leading to low accuracy in segmentation outcomes. This paper applies a deep convolutional neural network to the problem of sea-land segmentation in high-spatial resolution remote sensing images and innovates upon the classic encoder-decoder architecture. Firstly, to enhance the network’s ability to distinguish coastlines, a dual attention mechanism is introduced into the UNet++ network to improve the learning capacity of coastline features while suppressing the learning of non-coastline features. Secondly, an improved joint loss function is adopted to enhance training effectiveness, thereby significantly improving the accuracy of semantic segmentation. Lastly, transfer learning is utilized to strengthen the detailed features of coastlines and enhance the network’s ability to identify them. Experimental results using the GID dataset for coastline segmentation demonstrate that compared to the latest algorithms such as PSPNet, CS-Deeplab v3+, and UNet++, the improved UNet++ network achieves lower boundary blurriness and more accurate segmentation results for coastlines, with fewer missed and false detections. Amidst the proliferation of high-spatial resolution remote sensing image data, the utilization of the enhanced UNet++ model for coastline extraction has demonstrated remarkable abilities in preserving boundary information and achieving superior semantic segmentation performance. This advancement enables a more refined extraction of spatial distributions, textures, and spectral features from these images, ultimately contributing to an improvement in classification accuracy.
format Article
id doaj-art-1ac845edbd3e44fb8e5d5b3c751e9347
institution Kabale University
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-1ac845edbd3e44fb8e5d5b3c751e93472025-01-24T00:01:31ZengIEEEIEEE Access2169-35362025-01-0113113201133110.1109/ACCESS.2024.346799810693424A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline ExtractionYanru Song0Bai Xue1https://orcid.org/0009-0007-5184-398XYueyue Meng2Xiang Qin3Yixiao Li4Qi Liu5China Aero Geophysical Survey and Remote Sensing Center for Nature Resources, Beijing, ChinaMNR Land Satellite Remote Sensing Application Center, Beijing, ChinaChina Aero Geophysical Survey and Remote Sensing Center for Nature Resources, Beijing, ChinaChina Aero Geophysical Survey and Remote Sensing Center for Nature Resources, Beijing, ChinaChina Aero Geophysical Survey and Remote Sensing Center for Nature Resources, Beijing, ChinaChina Aero Geophysical Survey and Remote Sensing Center for Nature Resources, Beijing, ChinaThe segmentation of land and sea in remote sensing imagery is of great significance for coastline extraction and dynamic monitoring. Traditional coastline recognition and extraction methods based on spectral features and image processing can only generate limited image feature results when facing the complex textures and spatial distributions of high-spatial resolution remote sensing images, leading to low accuracy in segmentation outcomes. This paper applies a deep convolutional neural network to the problem of sea-land segmentation in high-spatial resolution remote sensing images and innovates upon the classic encoder-decoder architecture. Firstly, to enhance the network’s ability to distinguish coastlines, a dual attention mechanism is introduced into the UNet++ network to improve the learning capacity of coastline features while suppressing the learning of non-coastline features. Secondly, an improved joint loss function is adopted to enhance training effectiveness, thereby significantly improving the accuracy of semantic segmentation. Lastly, transfer learning is utilized to strengthen the detailed features of coastlines and enhance the network’s ability to identify them. Experimental results using the GID dataset for coastline segmentation demonstrate that compared to the latest algorithms such as PSPNet, CS-Deeplab v3+, and UNet++, the improved UNet++ network achieves lower boundary blurriness and more accurate segmentation results for coastlines, with fewer missed and false detections. Amidst the proliferation of high-spatial resolution remote sensing image data, the utilization of the enhanced UNet++ model for coastline extraction has demonstrated remarkable abilities in preserving boundary information and achieving superior semantic segmentation performance. This advancement enables a more refined extraction of spatial distributions, textures, and spectral features from these images, ultimately contributing to an improvement in classification accuracy.https://ieeexplore.ieee.org/document/10693424/Coastline extractionhigh-spatial resolution remote sensing imageryUNet++dual attentionjoint loss functiontransfer learning
spellingShingle Yanru Song
Bai Xue
Yueyue Meng
Xiang Qin
Yixiao Li
Qi Liu
A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction
IEEE Access
Coastline extraction
high-spatial resolution remote sensing imagery
UNet++
dual attention
joint loss function
transfer learning
title A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction
title_full A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction
title_fullStr A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction
title_full_unstemmed A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction
title_short A Fusion Method Incorporating Dual-Attention Mechanism and Transfer Learning Into UNet++ for Remote Sensing Image Coastline Extraction
title_sort fusion method incorporating dual attention mechanism and transfer learning into unet for remote sensing image coastline extraction
topic Coastline extraction
high-spatial resolution remote sensing imagery
UNet++
dual attention
joint loss function
transfer learning
url https://ieeexplore.ieee.org/document/10693424/
work_keys_str_mv AT yanrusong afusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT baixue afusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT yueyuemeng afusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT xiangqin afusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT yixiaoli afusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT qiliu afusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT yanrusong fusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT baixue fusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT yueyuemeng fusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT xiangqin fusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT yixiaoli fusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction
AT qiliu fusionmethodincorporatingdualattentionmechanismandtransferlearningintounetforremotesensingimagecoastlineextraction