LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism
Remote sensing image change detection is crucial for monitoring dynamic surface changes, with applications ranging from environmental monitoring to disaster assessment. While traditional CNN-based methods have improved detection accuracy, they often suffer from high computational complexity and larg...
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/10897814/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850210177725235200 |
|---|---|
| author | Wenyu Liu Jindong Li Haoji Wang Run Tan Yali Fu Qichuan Tian |
| author_facet | Wenyu Liu Jindong Li Haoji Wang Run Tan Yali Fu Qichuan Tian |
| author_sort | Wenyu Liu |
| collection | DOAJ |
| description | Remote sensing image change detection is crucial for monitoring dynamic surface changes, with applications ranging from environmental monitoring to disaster assessment. While traditional CNN-based methods have improved detection accuracy, they often suffer from high computational complexity and large parameter counts, limiting their use in resource-constrained environments. To address these challenges, we propose a lightweight remote sensing change detection network (LCD-Net) that reduces model size and computational cost while maintaining high detection performance. LCD-Net employs MobileNetV2 as the encoder to efficiently extract features from bitemporal images. A temporal interaction and fusion module enhances the interaction between bitemporal features, improving temporal context awareness. Additionally, the feature fusion module (FFM) aggregates multiscale features to better capture subtle changes while suppressing background noise. The gated mechanism module in the decoder further enhances feature learning by dynamically adjusting channel weights, emphasizing key change regions. Experiments on LEVIR-CD+, SYSU, and S2Looking datasets show that LCD-Net achieves competitive performance with just 2.56M parameters and 4.45G FLOPs, making it well-suited for real-time applications in resource-limited settings. |
| format | Article |
| id | doaj-art-0a190c6c3ce74b05a7662d72f032f90f |
| institution | OA Journals |
| 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-0a190c6c3ce74b05a7662d72f032f90f2025-08-20T02:09:51ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01187769778010.1109/JSTARS.2025.354423510897814LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating MechanismWenyu Liu0https://orcid.org/0009-0001-8988-7933Jindong Li1https://orcid.org/0009-0007-2228-3696Haoji Wang2https://orcid.org/0009-0008-1484-9001Run Tan3https://orcid.org/0009-0001-7821-3896Yali Fu4https://orcid.org/0009-0003-2934-8211Qichuan Tian5https://orcid.org/0000-0001-7626-6858School of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Artificial Intelligence, Jilin University, Changchun, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaSchool of Artificial Intelligence, Jilin University, Changchun, ChinaSchool of Electrical and Information Engineering, Beijing University of Civil Engineering and Architecture, Beijing, ChinaRemote sensing image change detection is crucial for monitoring dynamic surface changes, with applications ranging from environmental monitoring to disaster assessment. While traditional CNN-based methods have improved detection accuracy, they often suffer from high computational complexity and large parameter counts, limiting their use in resource-constrained environments. To address these challenges, we propose a lightweight remote sensing change detection network (LCD-Net) that reduces model size and computational cost while maintaining high detection performance. LCD-Net employs MobileNetV2 as the encoder to efficiently extract features from bitemporal images. A temporal interaction and fusion module enhances the interaction between bitemporal features, improving temporal context awareness. Additionally, the feature fusion module (FFM) aggregates multiscale features to better capture subtle changes while suppressing background noise. The gated mechanism module in the decoder further enhances feature learning by dynamically adjusting channel weights, emphasizing key change regions. Experiments on LEVIR-CD+, SYSU, and S2Looking datasets show that LCD-Net achieves competitive performance with just 2.56M parameters and 4.45G FLOPs, making it well-suited for real-time applications in resource-limited settings.https://ieeexplore.ieee.org/document/10897814/Feature fusiongating mechanismlightweight networkremote sensing change detection (RSCD) |
| spellingShingle | Wenyu Liu Jindong Li Haoji Wang Run Tan Yali Fu Qichuan Tian LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Feature fusion gating mechanism lightweight network remote sensing change detection (RSCD) |
| title | LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism |
| title_full | LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism |
| title_fullStr | LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism |
| title_full_unstemmed | LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism |
| title_short | LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism |
| title_sort | lcd net a lightweight remote sensing change detection network combining feature fusion and gating mechanism |
| topic | Feature fusion gating mechanism lightweight network remote sensing change detection (RSCD) |
| url | https://ieeexplore.ieee.org/document/10897814/ |
| work_keys_str_mv | AT wenyuliu lcdnetalightweightremotesensingchangedetectionnetworkcombiningfeaturefusionandgatingmechanism AT jindongli lcdnetalightweightremotesensingchangedetectionnetworkcombiningfeaturefusionandgatingmechanism AT haojiwang lcdnetalightweightremotesensingchangedetectionnetworkcombiningfeaturefusionandgatingmechanism AT runtan lcdnetalightweightremotesensingchangedetectionnetworkcombiningfeaturefusionandgatingmechanism AT yalifu lcdnetalightweightremotesensingchangedetectionnetworkcombiningfeaturefusionandgatingmechanism AT qichuantian lcdnetalightweightremotesensingchangedetectionnetworkcombiningfeaturefusionandgatingmechanism |