A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing

The sparse imaging network of synthetic aperture radar (SAR) is usually designed end to end and has a limited adaptability to radar systems of different bands. Meanwhile, the implementation of the sparse imaging algorithm depends on the sparsity of the target scene and usually adopts a fixed <inl...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaopeng Li, Mengyang Zhan, Yiheng Liang, Yinwei Li, Gang Xu, Bingnan Wang
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/7/1279
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769646150909952
author Xiaopeng Li
Mengyang Zhan
Yiheng Liang
Yinwei Li
Gang Xu
Bingnan Wang
author_facet Xiaopeng Li
Mengyang Zhan
Yiheng Liang
Yinwei Li
Gang Xu
Bingnan Wang
author_sort Xiaopeng Li
collection DOAJ
description The sparse imaging network of synthetic aperture radar (SAR) is usually designed end to end and has a limited adaptability to radar systems of different bands. Meanwhile, the implementation of the sparse imaging algorithm depends on the sparsity of the target scene and usually adopts a fixed <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>L</mi></mrow><mrow><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula> regularization solution, which has a mediocre reconstruction effect on complex scenes. In this paper, a novel SAR imaging deep unfolding network based on approximate observation is proposed for multi-band SAR systems. Firstly, the approximate observation module is separated from the optimal solution network model and selected according to the multi-band radar echo. Secondly, to realize the SAR imaging of non-sparse scenes, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>L</mi></mrow><mrow><mi>p</mi></mrow></msub></mrow></semantics></math></inline-formula> regularization is used to constrain the uncertain transform domain of the target scene. The adaptive optimization of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>L</mi></mrow><mrow><mi>p</mi></mrow></msub></mrow></semantics></math></inline-formula> parameters is realized by using a data-driven approach. Furthermore, considering that phase errors may be introduced in the real SAR system during echo acquisition, an error estimation module is added to the network to estimate and compensate for the phase errors. Finally, the results from both simulated and real data experiments demonstrate that the proposed method exhibits outstanding performance under 0.22 THz and 9.6 GHz echo data: high-resolution SAR focused images are achieved under four different sparsity conditions of 20%, 40%, 60%, and 80%. These results fully validate the strong adaptability and robustness of the proposed method to diverse SAR system configurations and complex target scenarios.
format Article
id doaj-art-5480fc92479d4239bcd3a117a68e3326
institution DOAJ
issn 2072-4292
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-5480fc92479d4239bcd3a117a68e33262025-08-20T03:03:21ZengMDPI AGRemote Sensing2072-42922025-04-01177127910.3390/rs17071279A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and AutofocusingXiaopeng Li0Mengyang Zhan1Yiheng Liang2Yinwei Li3Gang Xu4Bingnan Wang5School of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaSchool of Optoelectronic Information and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, ChinaState Key Laboratory of Millimeter Waves, Southeast University, Nanjing 210096, ChinaNational Key Laboratory of Microwave Imaging Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, ChinaThe sparse imaging network of synthetic aperture radar (SAR) is usually designed end to end and has a limited adaptability to radar systems of different bands. Meanwhile, the implementation of the sparse imaging algorithm depends on the sparsity of the target scene and usually adopts a fixed <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>L</mi></mrow><mrow><mn>1</mn></mrow></msub></mrow></semantics></math></inline-formula> regularization solution, which has a mediocre reconstruction effect on complex scenes. In this paper, a novel SAR imaging deep unfolding network based on approximate observation is proposed for multi-band SAR systems. Firstly, the approximate observation module is separated from the optimal solution network model and selected according to the multi-band radar echo. Secondly, to realize the SAR imaging of non-sparse scenes, <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>L</mi></mrow><mrow><mi>p</mi></mrow></msub></mrow></semantics></math></inline-formula> regularization is used to constrain the uncertain transform domain of the target scene. The adaptive optimization of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><msub><mrow><mi>L</mi></mrow><mrow><mi>p</mi></mrow></msub></mrow></semantics></math></inline-formula> parameters is realized by using a data-driven approach. Furthermore, considering that phase errors may be introduced in the real SAR system during echo acquisition, an error estimation module is added to the network to estimate and compensate for the phase errors. Finally, the results from both simulated and real data experiments demonstrate that the proposed method exhibits outstanding performance under 0.22 THz and 9.6 GHz echo data: high-resolution SAR focused images are achieved under four different sparsity conditions of 20%, 40%, 60%, and 80%. These results fully validate the strong adaptability and robustness of the proposed method to diverse SAR system configurations and complex target scenarios.https://www.mdpi.com/2072-4292/17/7/1279synthetic aperture radar (SAR)sparse samplingapproximate observation operators<i>L<sub>p</sub></i> regularizationautofocusing
spellingShingle Xiaopeng Li
Mengyang Zhan
Yiheng Liang
Yinwei Li
Gang Xu
Bingnan Wang
A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing
Remote Sensing
synthetic aperture radar (SAR)
sparse sampling
approximate observation operators
<i>L<sub>p</sub></i> regularization
autofocusing
title A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing
title_full A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing
title_fullStr A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing
title_full_unstemmed A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing
title_short A Novel Deep Unfolding Network for Multi-Band SAR Sparse Imaging and Autofocusing
title_sort novel deep unfolding network for multi band sar sparse imaging and autofocusing
topic synthetic aperture radar (SAR)
sparse sampling
approximate observation operators
<i>L<sub>p</sub></i> regularization
autofocusing
url https://www.mdpi.com/2072-4292/17/7/1279
work_keys_str_mv AT xiaopengli anoveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT mengyangzhan anoveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT yihengliang anoveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT yinweili anoveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT gangxu anoveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT bingnanwang anoveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT xiaopengli noveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT mengyangzhan noveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT yihengliang noveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT yinweili noveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT gangxu noveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing
AT bingnanwang noveldeepunfoldingnetworkformultibandsarsparseimagingandautofocusing