DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection
Benefiting from continuous innovations in deep learning algorithms, the accuracy of building change detection (BCD) in remote sensing (RS) has significantly improved. Numerous networks combining CNN and transformer architectures have emerged, yet effectively balancing local detail and global context...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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/10829681/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832590384863117312 |
|---|---|
| author | Shengning Zhou Genji Yuan Zhen Hua Jinjiang Li |
| author_facet | Shengning Zhou Genji Yuan Zhen Hua Jinjiang Li |
| author_sort | Shengning Zhou |
| collection | DOAJ |
| description | Benefiting from continuous innovations in deep learning algorithms, the accuracy of building change detection (BCD) in remote sensing (RS) has significantly improved. Numerous networks combining CNN and transformer architectures have emerged, yet effectively balancing local detail and global context features remains a topic of ongoing discussion. Furthermore, accurately leveraging edge information within RS images to enhance the recognition of structural changes in buildings is another critical challenge. To address these issues, this article proposes a BCD network based on dynamic gate fusion and edge graph perception (DGFEG). First, a hybrid backbone, MCTrans, is employed as the encoder to extract multiscale detailed features and global positional information of buildings. Second, a dynamic gate fusion module is introduced to dynamically weight and fuse the concatenated and differential features obtained by the encoder, enhancing the semantic representation of actual building change regions. Finally, an edge graph perception module integrates edge information with the fused features, leveraging the spatial similarity of graph structures and the interaction of edge features to suppress irrelevant edge interference, thereby improving the model's sensitivity and accuracy in detecting subtle building changes. In experiments, DGFEG was tested on real-world change scenarios and multiple RSCD datasets. The results demonstrate its superior performance compared to existing state-of-the-art methods, proving its excellence and broad application potential in tackling complex BCD tasks. |
| format | Article |
| id | doaj-art-3483ecc155b542feb356fb76687fed81 |
| institution | Kabale University |
| 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-3483ecc155b542feb356fb76687fed812025-01-24T00:00:56ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01183581359810.1109/JSTARS.2025.352620810829681DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change DetectionShengning Zhou0Genji Yuan1https://orcid.org/0000-0002-8710-2266Zhen Hua2https://orcid.org/0000-0003-1638-2974Jinjiang Li3https://orcid.org/0000-0002-2080-8678School of Information and electronic engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaSchool of Information and electronic engineering, Shandong Technology and Business University, Yantai, ChinaSchool of Computer Science and Technology, Shandong Technology and Business University, Yantai, ChinaBenefiting from continuous innovations in deep learning algorithms, the accuracy of building change detection (BCD) in remote sensing (RS) has significantly improved. Numerous networks combining CNN and transformer architectures have emerged, yet effectively balancing local detail and global context features remains a topic of ongoing discussion. Furthermore, accurately leveraging edge information within RS images to enhance the recognition of structural changes in buildings is another critical challenge. To address these issues, this article proposes a BCD network based on dynamic gate fusion and edge graph perception (DGFEG). First, a hybrid backbone, MCTrans, is employed as the encoder to extract multiscale detailed features and global positional information of buildings. Second, a dynamic gate fusion module is introduced to dynamically weight and fuse the concatenated and differential features obtained by the encoder, enhancing the semantic representation of actual building change regions. Finally, an edge graph perception module integrates edge information with the fused features, leveraging the spatial similarity of graph structures and the interaction of edge features to suppress irrelevant edge interference, thereby improving the model's sensitivity and accuracy in detecting subtle building changes. In experiments, DGFEG was tested on real-world change scenarios and multiple RSCD datasets. The results demonstrate its superior performance compared to existing state-of-the-art methods, proving its excellence and broad application potential in tackling complex BCD tasks.https://ieeexplore.ieee.org/document/10829681/Attention mechanismbuilding change detection (BCD)dynamic gate fusion (DGF)edge graph perception (EGP)remote sensing (RS) images |
| spellingShingle | Shengning Zhou Genji Yuan Zhen Hua Jinjiang Li DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Attention mechanism building change detection (BCD) dynamic gate fusion (DGF) edge graph perception (EGP) remote sensing (RS) images |
| title | DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection |
| title_full | DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection |
| title_fullStr | DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection |
| title_full_unstemmed | DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection |
| title_short | DGFEG: Dynamic Gate Fusion and Edge Graph Perception Network for Remote Sensing Change Detection |
| title_sort | dgfeg dynamic gate fusion and edge graph perception network for remote sensing change detection |
| topic | Attention mechanism building change detection (BCD) dynamic gate fusion (DGF) edge graph perception (EGP) remote sensing (RS) images |
| url | https://ieeexplore.ieee.org/document/10829681/ |
| work_keys_str_mv | AT shengningzhou dgfegdynamicgatefusionandedgegraphperceptionnetworkforremotesensingchangedetection AT genjiyuan dgfegdynamicgatefusionandedgegraphperceptionnetworkforremotesensingchangedetection AT zhenhua dgfegdynamicgatefusionandedgegraphperceptionnetworkforremotesensingchangedetection AT jinjiangli dgfegdynamicgatefusionandedgegraphperceptionnetworkforremotesensingchangedetection |