An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction
Deep learning has been successfully applied to solve the synthetic aperture radar (SAR) imaging problem, which shows superior imaging performance to compressive sensing (CS)-based methods under sparse sampling conditions. However, due to the computation of the large-scale matrix, the optimal searchi...
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/10815077/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542607654617088 |
|---|---|
| author | Song Zhou Jing Chen Zao Wang Yuhao Wang Pin Wen |
| author_facet | Song Zhou Jing Chen Zao Wang Yuhao Wang Pin Wen |
| author_sort | Song Zhou |
| collection | DOAJ |
| description | Deep learning has been successfully applied to solve the synthetic aperture radar (SAR) imaging problem, which shows superior imaging performance to compressive sensing (CS)-based methods under sparse sampling conditions. However, due to the computation of the large-scale matrix, the optimal searching in an iterative manner will involve tremendous computational complexity with slow convergence, which will prevent deep learning algorithms from being efficiently applied for SAR imaging. To address this problem, an efficient network is proposed for SAR imaging under sparse sampling conditions, which can be designed by an improved conjugate gradient (CG) optimization strategy. First, the large-scale matrix in the CG algorithm can be approximately decomposed by introducing a matched filtering (MF)-based operator, which will facilitate the gradient computation with high efficiency during the optimization process. Second, the strategy utilizes the advantages of CG optimization to precisely eliminate the error component with conjugate searching in each iteration to achieve fast convergence. By incorporating the improved CG into the convolutional neural network (CNN), the network can be developed to automatically learn the prior information and parameters from the training data, based on which the efficiency of the designed network can be increased dramatically to achieve high imaging performance for SAR applications, especially in the cases of wide-scene and high-resolution imaging. Experimental results show that the proposed network exhibits excellent imaging performance and high computational efficiency in SAR imaging of point targets, surface targets, and different types of real scenes. |
| format | Article |
| id | doaj-art-333ee484841c4efcba977f0df17f094e |
| 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-333ee484841c4efcba977f0df17f094e2025-01-14T00:00:48ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01182464247610.1109/JSTARS.2024.352209610815077An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image ReconstructionSong Zhou0https://orcid.org/0000-0002-2954-8673Jing Chen1https://orcid.org/0009-0009-7783-4170Zao Wang2https://orcid.org/0009-0002-0399-1762Yuhao Wang3https://orcid.org/0000-0002-8445-0361Pin Wen4https://orcid.org/0000-0003-0832-1514School of information and Engineering, Nanchang University, Nanchang, ChinaSchool of information and Engineering, Nanchang University, Nanchang, ChinaSchool of information and Engineering, Nanchang University, Nanchang, ChinaSchool of information and Engineering, Nanchang University, Nanchang, ChinaSchool of information and Engineering, Nanchang University, Nanchang, ChinaDeep learning has been successfully applied to solve the synthetic aperture radar (SAR) imaging problem, which shows superior imaging performance to compressive sensing (CS)-based methods under sparse sampling conditions. However, due to the computation of the large-scale matrix, the optimal searching in an iterative manner will involve tremendous computational complexity with slow convergence, which will prevent deep learning algorithms from being efficiently applied for SAR imaging. To address this problem, an efficient network is proposed for SAR imaging under sparse sampling conditions, which can be designed by an improved conjugate gradient (CG) optimization strategy. First, the large-scale matrix in the CG algorithm can be approximately decomposed by introducing a matched filtering (MF)-based operator, which will facilitate the gradient computation with high efficiency during the optimization process. Second, the strategy utilizes the advantages of CG optimization to precisely eliminate the error component with conjugate searching in each iteration to achieve fast convergence. By incorporating the improved CG into the convolutional neural network (CNN), the network can be developed to automatically learn the prior information and parameters from the training data, based on which the efficiency of the designed network can be increased dramatically to achieve high imaging performance for SAR applications, especially in the cases of wide-scene and high-resolution imaging. Experimental results show that the proposed network exhibits excellent imaging performance and high computational efficiency in SAR imaging of point targets, surface targets, and different types of real scenes.https://ieeexplore.ieee.org/document/10815077/Approximate observation modelconjugate gradient (CG) algorithmconvolutional neural network (CNN)regularizationsynthetic aperture radar (SAR) imaging |
| spellingShingle | Song Zhou Jing Chen Zao Wang Yuhao Wang Pin Wen An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Approximate observation model conjugate gradient (CG) algorithm convolutional neural network (CNN) regularization synthetic aperture radar (SAR) imaging |
| title | An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction |
| title_full | An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction |
| title_fullStr | An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction |
| title_full_unstemmed | An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction |
| title_short | An Efficient Network Based on Conjugate Gradient Optimization and Approximate Observation Model for SAR Image Reconstruction |
| title_sort | efficient network based on conjugate gradient optimization and approximate observation model for sar image reconstruction |
| topic | Approximate observation model conjugate gradient (CG) algorithm convolutional neural network (CNN) regularization synthetic aperture radar (SAR) imaging |
| url | https://ieeexplore.ieee.org/document/10815077/ |
| work_keys_str_mv | AT songzhou anefficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT jingchen anefficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT zaowang anefficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT yuhaowang anefficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT pinwen anefficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT songzhou efficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT jingchen efficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT zaowang efficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT yuhaowang efficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction AT pinwen efficientnetworkbasedonconjugategradientoptimizationandapproximateobservationmodelforsarimagereconstruction |