CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization
Synthetic aperture radar (SAR) is a microwave remote sensing technology offering all-weather, high-resolution imaging. The rising demand for high precision and real-time processing under complex conditions in resource-constrained environments has spurred interest in deep network-based SAR imaging, w...
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/10851410/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823859608954863616 |
|---|---|
| author | Guoru Zhou Yixin Zuo Zhe Zhang Bingchen Zhang Yirong Wu |
| author_facet | Guoru Zhou Yixin Zuo Zhe Zhang Bingchen Zhang Yirong Wu |
| author_sort | Guoru Zhou |
| collection | DOAJ |
| description | Synthetic aperture radar (SAR) is a microwave remote sensing technology offering all-weather, high-resolution imaging. The rising demand for high precision and real-time processing under complex conditions in resource-constrained environments has spurred interest in deep network-based SAR imaging, which combines traditional sparse SAR imaging methods with deep learning to optimize parameters and scene features while retaining physical model interpretability and enabling fast inference. However, the single regularization cannot entirely capture the features of complex observation scenes, and network architectures based on iterative unfolding often face memory and numerical precision constraints during training. In this article, we propose a deep equilibrium sparse SAR Imaging method for compound regularization, integrating sparse and implicit regularizations to better capture complex scene features. The deep equilibrium model (DEQ) serves as a novel deep network framework that directly computes fixed points using analytical methods, theoretically allowing for infinite forward iterations while maintaining constant memory requirements. This is particularly advantageous in memory-intensive SAR imaging applications. Finally, we validate the effectiveness and superiority of the proposed method through experiments on real SAR scenes. The experimental results show that the proposed method outperforms existing deep learning-based SAR imaging methods regarding reconstruction performance and memory usage. |
| format | Article |
| id | doaj-art-508c156c852242ef85e8545c67331c04 |
| 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-508c156c852242ef85e8545c67331c042025-02-11T00:00:18ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01184680469510.1109/JSTARS.2025.353308210851410CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound RegularizationGuoru Zhou0https://orcid.org/0009-0007-3540-5824Yixin Zuo1https://orcid.org/0000-0002-3052-4222Zhe Zhang2https://orcid.org/0000-0003-3192-3476Bingchen Zhang3Yirong Wu4Key Laboratory of Technology in Geo-Spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing, ChinaResearch Department of Cyber-Electromagnetic Space Information Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSuzhou Key Laboratory of Microwave Imaging, Processing and Application Technology, Suzhou Aerospace Information Research Institute, Suzhou, ChinaKey Laboratory of Technology in Geo-Spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Technology in Geo-Spatial Information Processing and Application System, Chinese Academy of Sciences, Beijing, ChinaSynthetic aperture radar (SAR) is a microwave remote sensing technology offering all-weather, high-resolution imaging. The rising demand for high precision and real-time processing under complex conditions in resource-constrained environments has spurred interest in deep network-based SAR imaging, which combines traditional sparse SAR imaging methods with deep learning to optimize parameters and scene features while retaining physical model interpretability and enabling fast inference. However, the single regularization cannot entirely capture the features of complex observation scenes, and network architectures based on iterative unfolding often face memory and numerical precision constraints during training. In this article, we propose a deep equilibrium sparse SAR Imaging method for compound regularization, integrating sparse and implicit regularizations to better capture complex scene features. The deep equilibrium model (DEQ) serves as a novel deep network framework that directly computes fixed points using analytical methods, theoretically allowing for infinite forward iterations while maintaining constant memory requirements. This is particularly advantageous in memory-intensive SAR imaging applications. Finally, we validate the effectiveness and superiority of the proposed method through experiments on real SAR scenes. The experimental results show that the proposed method outperforms existing deep learning-based SAR imaging methods regarding reconstruction performance and memory usage.https://ieeexplore.ieee.org/document/10851410/Compound regularizationdeep equilibrium model (DEQ)sparse microwave imagingsynthetic aperture radar (SAR) |
| spellingShingle | Guoru Zhou Yixin Zuo Zhe Zhang Bingchen Zhang Yirong Wu CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Compound regularization deep equilibrium model (DEQ) sparse microwave imaging synthetic aperture radar (SAR) |
| title | CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization |
| title_full | CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization |
| title_fullStr | CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization |
| title_full_unstemmed | CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization |
| title_short | CR-DEQ-SAR: A Deep Equilibrium Sparse SAR Imaging Method for Compound Regularization |
| title_sort | cr deq sar a deep equilibrium sparse sar imaging method for compound regularization |
| topic | Compound regularization deep equilibrium model (DEQ) sparse microwave imaging synthetic aperture radar (SAR) |
| url | https://ieeexplore.ieee.org/document/10851410/ |
| work_keys_str_mv | AT guoruzhou crdeqsaradeepequilibriumsparsesarimagingmethodforcompoundregularization AT yixinzuo crdeqsaradeepequilibriumsparsesarimagingmethodforcompoundregularization AT zhezhang crdeqsaradeepequilibriumsparsesarimagingmethodforcompoundregularization AT bingchenzhang crdeqsaradeepequilibriumsparsesarimagingmethodforcompoundregularization AT yirongwu crdeqsaradeepequilibriumsparsesarimagingmethodforcompoundregularization |