ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images

Extracting road information from high-resolution remote sensing images has become a research hotspot in remote sensing image processing due to its cost-effectiveness and efficiency. Current road extraction methods generally face challenges such as large parameter sizes and limited accuracy when deal...

Full description

Saved in:
Bibliographic Details
Main Authors: Rui Xu, Zhenxing Zhuang, Renzhong Mao, Yihui Yang
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10975038/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850141383161020416
author Rui Xu
Zhenxing Zhuang
Renzhong Mao
Yihui Yang
author_facet Rui Xu
Zhenxing Zhuang
Renzhong Mao
Yihui Yang
author_sort Rui Xu
collection DOAJ
description Extracting road information from high-resolution remote sensing images has become a research hotspot in remote sensing image processing due to its cost-effectiveness and efficiency. Current road extraction methods generally face challenges such as large parameter sizes and limited accuracy when dealing with roads at different scales. To overcome these limitations, this study proposes a novel lightweight attention network model (ESLiteU2-Net) to improve both efficiency and accuracy of road extraction. Based on U2-Net, the proposed model reduces complexity by a channel reduction strategy and introduces an Efficient Spatial and Channel Attention Module (ESCA). This innovative design enables the model to better capture and reinforce road features across both spatial and channel dimensions, resulting in significant improvements in extraction accuracy and robustness while maintaining a lightweight structure. Experimental results demonstrate that ESLiteU2-Net outperforms existing methods on the CHN6-CUG and Massachusetts road datasets. Compared to U2-Net, the proposed model not only achieves superior accuracy but also reduces computational load and parameter number by 30.98% and 81.91%, respectively, achieving a balanced combination of lightweight design, efficiency, and accuracy for road extraction.
format Article
id doaj-art-513a68f87d6e4ee4bea245a2a9a9bad3
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-513a68f87d6e4ee4bea245a2a9a9bad32025-08-20T02:29:27ZengIEEEIEEE Access2169-35362025-01-0113712237123910.1109/ACCESS.2025.356345910975038ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing ImagesRui Xu0https://orcid.org/0009-0000-1433-0295Zhenxing Zhuang1https://orcid.org/0009-0009-0813-5245Renzhong Mao2Yihui Yang3School of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, Fujian, ChinaSchool of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, Fujian, ChinaSchool of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, Fujian, ChinaSchool of Computer Science and Mathematics, Fujian University of Technology, Fuzhou, Fujian, ChinaExtracting road information from high-resolution remote sensing images has become a research hotspot in remote sensing image processing due to its cost-effectiveness and efficiency. Current road extraction methods generally face challenges such as large parameter sizes and limited accuracy when dealing with roads at different scales. To overcome these limitations, this study proposes a novel lightweight attention network model (ESLiteU2-Net) to improve both efficiency and accuracy of road extraction. Based on U2-Net, the proposed model reduces complexity by a channel reduction strategy and introduces an Efficient Spatial and Channel Attention Module (ESCA). This innovative design enables the model to better capture and reinforce road features across both spatial and channel dimensions, resulting in significant improvements in extraction accuracy and robustness while maintaining a lightweight structure. Experimental results demonstrate that ESLiteU2-Net outperforms existing methods on the CHN6-CUG and Massachusetts road datasets. Compared to U2-Net, the proposed model not only achieves superior accuracy but also reduces computational load and parameter number by 30.98% and 81.91%, respectively, achieving a balanced combination of lightweight design, efficiency, and accuracy for road extraction.https://ieeexplore.ieee.org/document/10975038/Road extractionlightweightECAESCAU²-Netchannel reduction strategy
spellingShingle Rui Xu
Zhenxing Zhuang
Renzhong Mao
Yihui Yang
ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images
IEEE Access
Road extraction
lightweight
ECA
ESCA
U²-Net
channel reduction strategy
title ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images
title_full ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images
title_fullStr ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images
title_full_unstemmed ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images
title_short ESLiteU²-Net: A Lightweight U²-Net for Road Extraction From High-Resolution Remote Sensing Images
title_sort esliteu x00b2 net a lightweight u x00b2 net for road extraction from high resolution remote sensing images
topic Road extraction
lightweight
ECA
ESCA
U²-Net
channel reduction strategy
url https://ieeexplore.ieee.org/document/10975038/
work_keys_str_mv AT ruixu esliteux00b2netalightweightux00b2netforroadextractionfromhighresolutionremotesensingimages
AT zhenxingzhuang esliteux00b2netalightweightux00b2netforroadextractionfromhighresolutionremotesensingimages
AT renzhongmao esliteux00b2netalightweightux00b2netforroadextractionfromhighresolutionremotesensingimages
AT yihuiyang esliteux00b2netalightweightux00b2netforroadextractionfromhighresolutionremotesensingimages