End-to-End SAR Deep Learning Imaging Method Based on Sparse Optimization

Zhao, Siyuan; Ni, Jiacheng; Liang, Jia; Xiong, Shue; Luo, Ying

doi:10.3390/rs13214429

Cited by 14 publications

(8 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to [35], we generate unlabeled training samples by downsampling the original echo data, adding system noise, and introducing echo phase disturbances. This method not only reduces the amount of data and increases imaging efficiency, but also improves the robustness and reliability of the algorithm.…”

Section: Backpropagation and Gradient Calculationmentioning

confidence: 99%

“…In [35], an end-to-end SAR deep learning imaging method based on a sparse optimization iterative algorithm was suggested to enhance the universality and generalization ability of the imaging method for SAR echo data. Li et al [36] developed a target-oriented SAR imaging model, where generalized regularization was employed to characterize target features, contributing to an improved signal-to-clutter ratio (SCR) in the reconstructed image.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

MF-JMoDL-Net: A Deep Network for Azimuth Undersampling Pattern Design and Ambiguity Suppression for Sparse SAR Imaging

Wu¹,

Zhang²,

Qiu³

et al. 2023

Preprint

View full text Add to dashboard Cite

Traditionally, the range swath of a synthetic aperture radar (SAR) system is constrained by its pulse repetition frequency (PRF). Given the system complexity and resource constraints, it is often difficult to achieve high imaging performance and low ambiguity without compromising the swath. In this paper, we propose a joint optimization framework for sparse strip SAR imaging algorithms and azimuth undersampling patterns based on a deep convolutional neural network, combined with matched filter (MF) approximate measurement operators and inverse MF operators, referred to as MF-JMoDL-Net, for sparse SAR imaging methods. Compared with conventional sparse SAR imaging, MF-JMoDL-Net enables us to alleviate the limitations imposed by PRF. In the proposed scheme, joint and continuous optimization of azimuth undersampling patterns and convolutional neural network parameters are implemented to suppress azimuth ambiguity and enhance sparse SAR imaging quality. Experiments and comparisons under various conditions demonstrate the effectiveness and superiority of the proposed framework in imaging results.

show abstract

Section: Backpropagation and Gradient Calculationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

MF-JMoDL-Net: A Deep Network for Azimuth Undersampling Pattern Design and Ambiguity Suppression for Sparse SAR Imaging

Wu¹,

Zhang²,

Qiu³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…DUN-based SAR imaging methods are proposed to reconstruct SAR images with good quality in [31,32]. Zhao et al [33] proposed an end-to-end imaging network that enables SAR imaging in larger scenes. However, these methods often require retraining of the network when facing imaging requirements with different downsampled echo signal inputs, which undoubtedly increases the computational expense.…”

Section: Introductionmentioning

confidence: 99%

Sparse SAR Imaging Method for Ground Moving Target via GMTSI-Net

Chen

Luo

et al. 2022

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Ground moving targets (GMT), due to the existence of velocity in range and azimuth direction, will lead to the deviation from their true position and defocus in the azimuth direction during the synthetic aperture radar (SAR) imaging process. To address this problem and compress the amount of echo data, a sparse SAR imaging method for ground moving targets is proposed. Specifically, we first constructed a two-dimensional sparse observation model of the GMT based on matched filter operators. Then, the observation model was solved by a deep network, GMT sparse imaging network (GMTSI-Net), which was mainly obtained by unfolding an iterative soft threshold algorithm (ISTA)-based iterative solution. Furthermore, we designed an adaptive unfolding module in the imaging network to improve the adaptability of the network to the input of echo data with different sampling ratios. The proposed imaging network can achieve faster and more accurate SAR images of ground moving targets under a low sampling ratio and signal-to-noise ratio (SNR). Simulated and measured data experiments were conducted to demonstrate the performance of imaging quality of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In recent years, a more advanced synthetic aperture radar (SAR) image formation technique called sparse regularization SAR imaging has shown great potential [ 1 , 2 , 3 , 4 , 5 , 6 , 7 ]. The accurate reconstruction of sparse regularization SAR imaging is based on the assumption that the observation process of the imaging system is perfectly known [ 1 , 5 ]. However, in practice, the motion error of a radar platform will introduce envelope migrations and phase errors into the echo data, which causes serious degradation to the reconstruction quality.…”

Section: Introductionmentioning

confidence: 99%

Correction of Range-Variant Motion Error and Residual RCM in Sparse Regularization SAR Imaging

Zhang

2022

Sensors

View full text Add to dashboard Cite

Lq (0 < q ≤ 1) regularization has been confirmed effective when applied to sparse SAR imaging. However, the inaccuracies caused by motion errors in the observation model will lead to various degradations and defocus in the reconstructed image. For high-resolution and light-small SAR systems, the range-variant motion errors will decrease the accuracy of range cell migration correction (RCMC), and residual range cell migration (RCM) will exceed multiple range resolution cells and degrade the image quality substantially. Aiming at this problem, in this paper, a novel azimuth-range decoupled sparse SAR imaging method with coarse-to-fine range-variant motion errors and residual RCM correction method is proposed. First, a one-step motion compensation (MOCO) operator is proposed using the inertial navigation systems (INS)/global positioning systems (GPS) information, which can significantly reduce the residual RCM and improve the reconstruction accuracy. Second, a fine high-order phase-error correction method is performed to correct the range and cross-range-varying phase errors using a joint imaging and phase-error estimation scheme, which will further improve the image focusing quality. Experimental results indicate the effectiveness of the proposed method.

show abstract

End-to-End SAR Deep Learning Imaging Method Based on Sparse Optimization

Cited by 14 publications

References 30 publications

MF-JMoDL-Net: A Deep Network for Azimuth Undersampling Pattern Design and Ambiguity Suppression for Sparse SAR Imaging

MF-JMoDL-Net: A Deep Network for Azimuth Undersampling Pattern Design and Ambiguity Suppression for Sparse SAR Imaging

Sparse SAR Imaging Method for Ground Moving Target via GMTSI-Net

Correction of Range-Variant Motion Error and Residual RCM in Sparse Regularization SAR Imaging

Contact Info

Product

Resources

About