GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images

Semantic change detection (SCD) in remote sensing images can simultaneously obtain changed areas and the transformation of ground objects, providing finer grained information support in ground observation applications. Recently, multitask networks have become the main paradigm for SCD, but their det...

Full description

Saved in:
Bibliographic Details
Main Authors: Qing Ding, Fengyan Wang, Mingchang Wang, Ying Zhang, Gui Cheng
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11017612/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849694554437976064
author Qing Ding
Fengyan Wang
Mingchang Wang
Ying Zhang
Gui Cheng
author_facet Qing Ding
Fengyan Wang
Mingchang Wang
Ying Zhang
Gui Cheng
author_sort Qing Ding
collection DOAJ
description Semantic change detection (SCD) in remote sensing images can simultaneously obtain changed areas and the transformation of ground objects, providing finer grained information support in ground observation applications. Recently, multitask networks have become the main paradigm for SCD, but their detection performance is still affected by limited multi-scale feature extraction and insufficient cross-task information interaction. To address these issues, we propose a global–local awareness integrated network (GLAI-Net) for SCD in remote sensing images. We design a parallel encoding structure and utilize convolutional neural networks and transformer to achieve multi-scale modeling of images and enhance feature expression ability. Meanwhile, we propose multi-scale feature fusion (MSFF) modules in GLAI-Net to enhance the focus of detail features on changed objects with different sizes. Between the classification and change detection decoding branches, we propose semantic change response (SCR) modules in GLAI-Net that fully utilize the correlation between different tasks to improve the consistency and accuracy of detection results. Qualitative and quantitative results on the Landsat-SCD and SECOND datasets indicate that the proposed GLAI-Net outperforms the comparison methods in SCD performance, with SeKs of 0.5182 and 0.2063, respectively. In addition, the ablation experiment results confirm the effectiveness of MSFF and SCR modules in improving feature diversity and optimizing SCD performance.
format Article
id doaj-art-b519533aa8f94ca59d519d7af2e7f38c
institution DOAJ
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-b519533aa8f94ca59d519d7af2e7f38c2025-08-20T03:20:01ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118142911430710.1109/JSTARS.2025.357475511017612GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing ImagesQing Ding0https://orcid.org/0000-0002-8731-9596Fengyan Wang1https://orcid.org/0000-0002-3460-9928Mingchang Wang2https://orcid.org/0000-0002-2806-858XYing Zhang3Gui Cheng4College of Geo-Exploration Science and Technology, Jilin University, Changchun, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, Changchun, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, Changchun, ChinaCollege of Geo-Exploration Science and Technology, Jilin University, Changchun, ChinaXi’an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi’an, ChinaSemantic change detection (SCD) in remote sensing images can simultaneously obtain changed areas and the transformation of ground objects, providing finer grained information support in ground observation applications. Recently, multitask networks have become the main paradigm for SCD, but their detection performance is still affected by limited multi-scale feature extraction and insufficient cross-task information interaction. To address these issues, we propose a global–local awareness integrated network (GLAI-Net) for SCD in remote sensing images. We design a parallel encoding structure and utilize convolutional neural networks and transformer to achieve multi-scale modeling of images and enhance feature expression ability. Meanwhile, we propose multi-scale feature fusion (MSFF) modules in GLAI-Net to enhance the focus of detail features on changed objects with different sizes. Between the classification and change detection decoding branches, we propose semantic change response (SCR) modules in GLAI-Net that fully utilize the correlation between different tasks to improve the consistency and accuracy of detection results. Qualitative and quantitative results on the Landsat-SCD and SECOND datasets indicate that the proposed GLAI-Net outperforms the comparison methods in SCD performance, with SeKs of 0.5182 and 0.2063, respectively. In addition, the ablation experiment results confirm the effectiveness of MSFF and SCR modules in improving feature diversity and optimizing SCD performance.https://ieeexplore.ieee.org/document/11017612/Deep learningglobal–local awarenessmultitask learningremote sensing imagessemantic change detection (SCD)
spellingShingle Qing Ding
Fengyan Wang
Mingchang Wang
Ying Zhang
Gui Cheng
GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning
global–local awareness
multitask learning
remote sensing images
semantic change detection (SCD)
title GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images
title_full GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images
title_fullStr GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images
title_full_unstemmed GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images
title_short GLAI-Net: Global–Local Awareness Integrated Network for Semantic Change Detection in Remote Sensing Images
title_sort glai net global x2013 local awareness integrated network for semantic change detection in remote sensing images
topic Deep learning
global–local awareness
multitask learning
remote sensing images
semantic change detection (SCD)
url https://ieeexplore.ieee.org/document/11017612/
work_keys_str_mv AT qingding glainetglobalx2013localawarenessintegratednetworkforsemanticchangedetectioninremotesensingimages
AT fengyanwang glainetglobalx2013localawarenessintegratednetworkforsemanticchangedetectioninremotesensingimages
AT mingchangwang glainetglobalx2013localawarenessintegratednetworkforsemanticchangedetectioninremotesensingimages
AT yingzhang glainetglobalx2013localawarenessintegratednetworkforsemanticchangedetectioninremotesensingimages
AT guicheng glainetglobalx2013localawarenessintegratednetworkforsemanticchangedetectioninremotesensingimages