Fast Super-resolution 3D SAR Imaging Using an Unfolded Deep Network

Gao, Jingkun; Ye, Yu; Li, Shizhong; Qin, Yuliang; Gao, Xueshan; Li, Xiang

doi:10.1109/icsidp47821.2019.9173392

Cited by 9 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, deep learning has been utilized for tomographic processing as well. An unfolded deep network which involves the vector approximate message passing algorithms has been proposed in [177]. Experiments with simulated and real data have been performed, which shows the spectral estimation gains speed up and achieves competitive performance.…”

Section: E Insarmentioning

confidence: 99%

Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives

Zhu

Montazeri

Ali

et al. 2021

IEEE Geosci. Remote Sens. Mag.

215

View full text Add to dashboard Cite

This is the pre-acceptance version, to read the final version please go to IEEE Geoscience and Remote Sensing Magazine on IEEE XPlore.Deep learning in remote sensing has become an international hype, but it is mostly limited to the evaluation of optical data. Although deep learning has been introduced in Synthetic Aperture Radar (SAR) data processing, despite successful first attempts, its huge potential remains locked. In this paper, we provide an introduction to the most relevant deep learning models and concepts, point out possible pitfalls by analyzing special characteristics of SAR data, review the state-of-the-art of deep learning applied to SAR in depth, summarize available benchmarks, and recommend some important future research directions. With this effort, we hope to stimulate more research in this interesting yet under-exploited research field and to pave the way for use of deep learning in big SAR data processing workflows.

show abstract

Section: E Insarmentioning

confidence: 99%

Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives

Zhu

Montazeri

Ali

et al. 2021

IEEE Geosci. Remote Sens. Mag.

215

View full text Add to dashboard Cite

show abstract

“…Because of its problem formulation, this method cannot be employed in true SAR 3-D imaging, i.e., layover separation. An efficient line spectral estimation algorithm based on deep neural networks was proposed in [21] and applied to tackle the TomoSAR inversion. Experiment results in [21] showed that the method can separate overlaid scatterers and achieves moderate reconstruction performance, whereas the super-resolution power of the proposed method was not systematically analyzed.…”

Section: A Related Workmentioning

confidence: 99%

“…An efficient line spectral estimation algorithm based on deep neural networks was proposed in [21] and applied to tackle the TomoSAR inversion. Experiment results in [21] showed that the method can separate overlaid scatterers and achieves moderate reconstruction performance, whereas the super-resolution power of the proposed method was not systematically analyzed. More recently, a novel superresolving TomoSAR imaging framework based on CS and deep neural networks was proposed in [22].…”

Section: A Related Workmentioning

confidence: 99%

γ-Net: Superresolving SAR Tomographic Inversion via Deep Learning

Qian

Wang

Shi

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Synthetic aperture radar tomography (TomoSAR) has been extensively employed in 3-D reconstruction in dense urban areas using high-resolution SAR acquisitions. Compressive sensing (CS)-based algorithms are generally considered as the state of the art in super-resolving TomoSAR, in particular in the single look case. This superior performance comes at the cost of extra computational burdens, because of the sparse reconstruction, which cannot be solved analytically and we need to employ computationally expensive iterative solvers. In this paper, we propose a novel deep learning-based super-resolving TomoSAR inversion approach, γ-Net, to tackle this challenge. γ-Net adopts advanced complex-valued learned iterative shrinkage thresholding algorithm (CV-LISTA) to mimic the iterative optimization step in sparse reconstruction. Simulations show the height estimate from a well-trained γ-Net approaches the Cramér-Rao lower bound while improving the computational efficiency by 1 to 2 orders of magnitude comparing to the first-order CS-based methods. It also shows no degradation in the super-resolution power comparing to the state-of-the-art second-order TomoSAR solvers, which are much more computationally expensive than the first-order methods. Specifically, γ-Net reaches more than 90% detection rate in moderate super-resolving cases at 25 measurements at 6dB SNR. Moreover, simulation at limited baselines demonstrates that the proposed algorithm outperforms the second-order CS-based method by a fair margin. Test on real TanDEM-X data with just 6 interferograms also shows high-quality 3-D reconstruction with high-density detected double scatterers.

show abstract

“…For example, Budillon et al [8] forumulated the TomoSAR inversion problem as a typical classification problem and utilized the neural networks to detect a single scatterer and estimate the corresponding elevation. [9] proposed an efficient line spectral estimation algorithm based on deep neural networks to tackle the TomoSAR inversion, which can distinguish overlaid scatterers and achieve diesirable estimation performance.…”

Section: Introductionmentioning

confidence: 99%

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

Wang¹,

Zhang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving threedimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA algorithm are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications.

show abstract

Fast Super-resolution 3D SAR Imaging Using an Unfolded Deep Network

Cited by 9 publications

References 15 publications

Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives

Deep Learning Meets SAR: Concepts, models, pitfalls, and perspectives

γ-Net: Superresolving SAR Tomographic Inversion via Deep Learning

TomoSAR-ALISTA: Efficient TomoSAR Imaging via Deep Unfolded Network

Contact Info

Product

Resources

About