SAR Parametric Super-Resolution Image Reconstruction Methods Based on ADMM and Deep Neural Network

Wei, Yangkai; Li, Yinchuan; Ding, Zegang; Wang, Yan; Zeng, Tao; Li, Teng

doi:10.1109/tgrs.2021.3052793

Cited by 29 publications

(13 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CNN block D is implemented via a UNET with four pooling and non-pooling layers and 3 × 3 trainable filters. The parameters of blocks Q and D are then optimized to minimize (9). Since SAR images are complex-valued, all networks are trained using frequency domain complex-valued as input, and training losses are computed on the complex images.…”

Section: Experiments and Analysis Of Resultsmentioning

confidence: 99%

“…In recent years, deep network‐based methods have been applied to the sparse SAR imaging [6–10] tackling the reconstruction parameters including the iteration stepsize, threshold, and so forth, for an accelerated computation. For example, Yonel et al.…”

Section: Introductionmentioning

confidence: 99%

“…In recent years, deep network-based methods have been applied to the sparse SAR imaging [6][7][8][9][10] tackling the reconstruction parameters including the iteration stepsize, threshold, and so forth, for an accelerated computation. For example, Yonel et al [6] proposed a structure-specific passive SAR imaging network based on an iterative soft thresholding algorithm (ISTA).…”

Section: Introductionmentioning

confidence: 99%

“…For example, Yonel et al [6] proposed a structure-specific passive SAR imaging network based on an iterative soft thresholding algorithm (ISTA). Reference [9] proposed two parametric methods for SAR super-resolution imaging based on ADMM and deep neural network. Reference [10] established a target-oriented SAR imaging method via Deep Matched Filter-Alternating Direction Method of Multipliers-Net (MF-ADMM-Net), which improved the signal-to-clutter ratio (SCR) of the reconstructed image.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Data‐driven sampling pattern design for sparse spotlight SAR imaging

Zhao

Huang

Quan

et al. 2022

Electronics Letters

View full text Add to dashboard Cite

This paper proposes a joint optimization method for the imaging algorithm and sampling scheme of sparse spotlight synthetic aperture radar (SAR) imaging based on deep convolutional neural networks. Traditional compressed sensing-based sparse SAR imaging has been widely studied. Deep learning and sparse unfolding networks have been introduced into sparse SAR imaging, but most current works focus only on the imaging stage and simply adopt the conventional uniform or random downsampling scheme. Considering that the imaging quality also depends on the sampling pattern besides the imaging algorithm, this paper introduces a learning-based strategy to jointly optimize the sampling scheme and the imaging network parameters of the reconstruction module. In a deep learning-based image reconstruction scheme, joint and continuous optimization of the sampling patterns and convolutional neural network parameters is achieved to improve the image quality. Simulation results based on real SAR image data set illustrate the effectiveness and superiority of the proposed framework. Data availability statement:The data that support the findings of this study are available from US Air Force at https://www.sdms.afrl.af.mil/ index.php?collection=mstar. The data set is open for public use.

show abstract

Section: Experiments and Analysis Of Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Data‐driven sampling pattern design for sparse spotlight SAR imaging

Zhao

Huang

Quan

et al. 2022

Electronics Letters

View full text Add to dashboard Cite

show abstract

“…L INE spectrum estimation or frequency estimation is a fundamental problem in signal processing, and has many applications in direction-of-arrival (DOA) estimation in sensor array processing [1], wideband channel estimation [2], and modern imaging modalities [3]. In line spectrum estimation, the observed signal x[n] can be represented as a superposition of K complex sinusoids (i.e.…”

Section: Introductionmentioning

confidence: 99%

Gridless DOA Estimation Under the Multi-Frequency Model

Wakin

Gerstoft

2022

ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Direction-of-arrival (DOA) estimation is widely applied in acoustic source localization. A multi-frequency model is suitable for characterizing the broadband structure in acoustic signals. In this paper, the continuous (gridless) DOA estimation problem with multiple frequencies is considered. This problem is formulated as an atomic norm minimization (ANM) problem. The ANM problem is equivalent to a semi-definite program (SDP) which can be solved by an off-the-shelf SDP solver. The dual certificate condition is provided to certify the optimality of the SDP solution so that the sources can be localized by finding the roots of a polynomial. We also construct the dual polynomial to satisfy the dual certificate condition and show that such a construction exists when the source amplitude has a uniform magnitude. In multi-frequency ANM, spatial aliasing of DOAs at higher frequencies can cause challenges. We discuss this issue extensively and propose a robust solution to combat aliasing. Numerical results support our theoretical findings and demonstrate the effectiveness of the proposed method.

show abstract

Super-Resolution of Synthetic Aperture Radar Complex Data by Deep-Learning

et al. 2023

View full text Add to dashboard Cite

One of the greatest limitations of Synthetic Aperture Radar imagery is the capability to obtain an arbitrarily high spatial resolution. Indeed, despite optical sensors, this capability is not just limited by the sensor technology. Instead, improving the SAR spatial resolution requires large transmitted bandwidth and relatively long synthetic apertures that for regulatory and practical reasons are impossible to be met. This issue gets particularly relevant when dealing with Stripmap mode acquisitions and with relatively low carrier frequency sensors (where relatively large bandwidth signals are more difficult to be transmitted). To overcome this limitation, in this paper a deep learning based framework is proposed to enhance the spatial resolution of low-resolution SAR images while retaining the complex image accuracy. Results on simulated and real SAR data demonstrate the effectiveness of the proposed framework.

show abstract

SAR Parametric Super-Resolution Image Reconstruction Methods Based on ADMM and Deep Neural Network

Cited by 29 publications

References 40 publications

Data‐driven sampling pattern design for sparse spotlight SAR imaging

Data‐driven sampling pattern design for sparse spotlight SAR imaging

Gridless DOA Estimation Under the Multi-Frequency Model

Super-Resolution of Synthetic Aperture Radar Complex Data by Deep-Learning

Contact Info

Product

Resources

About