Semantic enhancement and change consistency network for semantic change detection in remote sensing images

Semantic Change Detection (SCD) identifies binary change information and determines the ‘from-to’ types, revealing not only ‘where’ changes occurred but also ‘what’ the changes are. It has become a popular research topic in remote sensing, with many models proposed, yet challenges remain. Semantic e...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhenghao Jiang, Biao Wang, Peng Zhang, Yanlan Wu, Zhiyuan Ye, Hui Yang
Format: Article
Language:English
Published: Taylor & Francis Group 2025-08-01
Series:International Journal of Digital Earth
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/17538947.2025.2496790
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849224328527216640
author Zhenghao Jiang
Biao Wang
Peng Zhang
Yanlan Wu
Zhiyuan Ye
Hui Yang
author_facet Zhenghao Jiang
Biao Wang
Peng Zhang
Yanlan Wu
Zhiyuan Ye
Hui Yang
author_sort Zhenghao Jiang
collection DOAJ
description Semantic Change Detection (SCD) identifies binary change information and determines the ‘from-to’ types, revealing not only ‘where’ changes occurred but also ‘what’ the changes are. It has become a popular research topic in remote sensing, with many models proposed, yet challenges remain. Semantic extraction remains insufficient, and inconsistencies in change features hinder SCD progress. Segment Anything Model 2 (SAM2) has proven effective in extracting global features. However, when processing remote sensing images, SAM2's performance declines. This is particularly evident in images containing diverse ground objects, where interclass similarities are pronounced and intraclass variations are substantial. The model struggles because it lacks semantic information from the local features of adjacent objects. This paper proposes a semantic enhancement and change consistency network(SCNet). By enhancing the model's ability to extract semantic information from complex land-cover classes, we incorporate multi-scale adaptive modules, leveraging the efficient zero-shot capability of SAM2. Specifically, we have designed a semantic alignment module (SA) to enhance change information consistency. This module continuously supervises segmentation and final detection results using interactive self-attention. SCNet achieves state-of-the-art performance on the SECOND, Hi-UCD-mini, and SJH-SCD (our custom) datasets, demonstrating an impressive balance between efficiency and accuracy. The code will be available at https://github.com/XiaoJ058/RS-SCD.
format Article
id doaj-art-e0485ffd1c6c41989a3f670a4f1e729f
institution Kabale University
issn 1753-8947
1753-8955
language English
publishDate 2025-08-01
publisher Taylor & Francis Group
record_format Article
series International Journal of Digital Earth
spelling doaj-art-e0485ffd1c6c41989a3f670a4f1e729f2025-08-25T11:28:31ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552025-08-0118110.1080/17538947.2025.2496790Semantic enhancement and change consistency network for semantic change detection in remote sensing imagesZhenghao Jiang0Biao Wang1Peng Zhang2Yanlan Wu3Zhiyuan Ye4Hui Yang5School of Resources and Environmental Engineering, Anhui University, Hefei, People’s Republic of ChinaSchool of Resources and Environmental Engineering, Anhui University, Hefei, People’s Republic of ChinaSchool of Artificial Intelligence, Anhui University, Hefei, People’s Republic of ChinaSchool of Artificial Intelligence, Anhui University, Hefei, People’s Republic of ChinaState Grid Information & Telecommunication Group Co., Ltd, Hefei, People’s Republic of ChinaInstitutes of Physical Science and Information Technology, Anhui University, Hefei, People’s Republic of ChinaSemantic Change Detection (SCD) identifies binary change information and determines the ‘from-to’ types, revealing not only ‘where’ changes occurred but also ‘what’ the changes are. It has become a popular research topic in remote sensing, with many models proposed, yet challenges remain. Semantic extraction remains insufficient, and inconsistencies in change features hinder SCD progress. Segment Anything Model 2 (SAM2) has proven effective in extracting global features. However, when processing remote sensing images, SAM2's performance declines. This is particularly evident in images containing diverse ground objects, where interclass similarities are pronounced and intraclass variations are substantial. The model struggles because it lacks semantic information from the local features of adjacent objects. This paper proposes a semantic enhancement and change consistency network(SCNet). By enhancing the model's ability to extract semantic information from complex land-cover classes, we incorporate multi-scale adaptive modules, leveraging the efficient zero-shot capability of SAM2. Specifically, we have designed a semantic alignment module (SA) to enhance change information consistency. This module continuously supervises segmentation and final detection results using interactive self-attention. SCNet achieves state-of-the-art performance on the SECOND, Hi-UCD-mini, and SJH-SCD (our custom) datasets, demonstrating an impressive balance between efficiency and accuracy. The code will be available at https://github.com/XiaoJ058/RS-SCD.https://www.tandfonline.com/doi/10.1080/17538947.2025.2496790Semantic change detectionremote sensingsemantic enhancementchange inconsistenciessemantic align
spellingShingle Zhenghao Jiang
Biao Wang
Peng Zhang
Yanlan Wu
Zhiyuan Ye
Hui Yang
Semantic enhancement and change consistency network for semantic change detection in remote sensing images
International Journal of Digital Earth
Semantic change detection
remote sensing
semantic enhancement
change inconsistencies
semantic align
title Semantic enhancement and change consistency network for semantic change detection in remote sensing images
title_full Semantic enhancement and change consistency network for semantic change detection in remote sensing images
title_fullStr Semantic enhancement and change consistency network for semantic change detection in remote sensing images
title_full_unstemmed Semantic enhancement and change consistency network for semantic change detection in remote sensing images
title_short Semantic enhancement and change consistency network for semantic change detection in remote sensing images
title_sort semantic enhancement and change consistency network for semantic change detection in remote sensing images
topic Semantic change detection
remote sensing
semantic enhancement
change inconsistencies
semantic align
url https://www.tandfonline.com/doi/10.1080/17538947.2025.2496790
work_keys_str_mv AT zhenghaojiang semanticenhancementandchangeconsistencynetworkforsemanticchangedetectioninremotesensingimages
AT biaowang semanticenhancementandchangeconsistencynetworkforsemanticchangedetectioninremotesensingimages
AT pengzhang semanticenhancementandchangeconsistencynetworkforsemanticchangedetectioninremotesensingimages
AT yanlanwu semanticenhancementandchangeconsistencynetworkforsemanticchangedetectioninremotesensingimages
AT zhiyuanye semanticenhancementandchangeconsistencynetworkforsemanticchangedetectioninremotesensingimages
AT huiyang semanticenhancementandchangeconsistencynetworkforsemanticchangedetectioninremotesensingimages