A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling

Remote-sensing image-change detection is indispensable for land management, environmental monitoring and related applications. In recent years, breakthroughs in satellite sensor technology have generated vast volumes of data and complex scenes, presenting significant challenges for change-detection...

Full description

Saved in:
Bibliographic Details
Main Authors: Enze Zhang, Yan Li, Haifeng Lin, Min Xia
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/13/2226
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849427528827011072
author Enze Zhang
Yan Li
Haifeng Lin
Min Xia
author_facet Enze Zhang
Yan Li
Haifeng Lin
Min Xia
author_sort Enze Zhang
collection DOAJ
description Remote-sensing image-change detection is indispensable for land management, environmental monitoring and related applications. In recent years, breakthroughs in satellite sensor technology have generated vast volumes of data and complex scenes, presenting significant challenges for change-detection algorithms. Traditional methods rely on handcrafted features, which struggle to address the impacts of multi-source data heterogeneity and imaging condition differences. In this context, technology based on deep learning has made substantial breakthroughs in change-detection performance by automatically extracting high-level feature representations of the data. However, although the existing deep-learning models improve the detection accuracy through end-to-end learning, their high parameter count and computational inefficiency hinder suitability for real-time monitoring and edge device deployment. Therefore, to address the need for lightweight solutions in scenarios with limited computing resources, this paper proposes an attention-based lightweight remote sensing change detection network (ABLRCNet), which achieves a balance between computational efficiency and detection accuracy by using lightweight residual convolution blocks (LRCBs), multi-scale spatial-attention modules (MSAMs) and feature-difference enhancement modules (FDEMs). The experimental results demonstrate that the ABLRCNet achieves excellent performance on three datasets, significantly enhancing both the accuracy and robustness of change detection, while exhibiting efficient detection capabilities in resource-limited scenarios.
format Article
id doaj-art-e15ae1a04839405d9e5e9772c1ba58eb
institution Kabale University
issn 2072-4292
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-e15ae1a04839405d9e5e9772c1ba58eb2025-08-20T03:28:59ZengMDPI AGRemote Sensing2072-42922025-06-011713222610.3390/rs17132226A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention CouplingEnze Zhang0Yan Li1Haifeng Lin2Min Xia3Reading Academy, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaReading Academy, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaCollege of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, ChinaReading Academy, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaRemote-sensing image-change detection is indispensable for land management, environmental monitoring and related applications. In recent years, breakthroughs in satellite sensor technology have generated vast volumes of data and complex scenes, presenting significant challenges for change-detection algorithms. Traditional methods rely on handcrafted features, which struggle to address the impacts of multi-source data heterogeneity and imaging condition differences. In this context, technology based on deep learning has made substantial breakthroughs in change-detection performance by automatically extracting high-level feature representations of the data. However, although the existing deep-learning models improve the detection accuracy through end-to-end learning, their high parameter count and computational inefficiency hinder suitability for real-time monitoring and edge device deployment. Therefore, to address the need for lightweight solutions in scenarios with limited computing resources, this paper proposes an attention-based lightweight remote sensing change detection network (ABLRCNet), which achieves a balance between computational efficiency and detection accuracy by using lightweight residual convolution blocks (LRCBs), multi-scale spatial-attention modules (MSAMs) and feature-difference enhancement modules (FDEMs). The experimental results demonstrate that the ABLRCNet achieves excellent performance on three datasets, significantly enhancing both the accuracy and robustness of change detection, while exhibiting efficient detection capabilities in resource-limited scenarios.https://www.mdpi.com/2072-4292/17/13/2226change detectionattention mechanismmulti-scale fusionlightweight networkdeep learning
spellingShingle Enze Zhang
Yan Li
Haifeng Lin
Min Xia
A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling
Remote Sensing
change detection
attention mechanism
multi-scale fusion
lightweight network
deep learning
title A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling
title_full A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling
title_fullStr A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling
title_full_unstemmed A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling
title_short A Lightweight Remote-Sensing Image-Change Detection Algorithm Based on Asymmetric Convolution and Attention Coupling
title_sort lightweight remote sensing image change detection algorithm based on asymmetric convolution and attention coupling
topic change detection
attention mechanism
multi-scale fusion
lightweight network
deep learning
url https://www.mdpi.com/2072-4292/17/13/2226
work_keys_str_mv AT enzezhang alightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT yanli alightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT haifenglin alightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT minxia alightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT enzezhang lightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT yanli lightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT haifenglin lightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling
AT minxia lightweightremotesensingimagechangedetectionalgorithmbasedonasymmetricconvolutionandattentioncoupling