3-D SAR Data-Driven Imaging via Learned Low-Rank and Sparse Priors

In the research topic of three-dimensional (3-D) synthetic aperture radar (SAR) imaging, the sparsity-enforcing techniques offer promise in shortening the sensing time and improving the reconstruction accuracy. However, many of them only explore the sparse prior of 3-D SAR images, which leads to bia...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 17
Main Authors: Wang, Mou, Wei, Shunjun, Zhou, Zichen, Shi, Jun, Zhang, Xiaoling, Guo, Yongxin
Format: Journal Article
Language:English
Published: New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
3-D synthetic aperture radar (SAR) imaging
Algorithms
Computational modeling
deep unfolding
Echoes
fast iterative shrinkage/thresholding algorithm (FISTA)
Image reconstruction
Imaging
Imaging techniques
Independent variables
low-rank
matrix completion
millimeter-wave (mmW)
Optimization
Radar imaging
Radar polarimetry
SAR (radar)
Scattering
Synthetic aperture radar
Three-dimensional displays
ISSN:0196-2892, 1558-0644
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In the research topic of three-dimensional (3-D) synthetic aperture radar (SAR) imaging, the sparsity-enforcing techniques offer promise in shortening the sensing time and improving the reconstruction accuracy. However, many of them only explore the sparse prior of 3-D SAR images, which leads to biased estimations in cases of non-sparse scenarios. To remedy this problem, we propose a new network with learned low-rank and sparse priors, i.e., LLRS-Net, to obtain improved reconstructions from sparsely sampled 3-D SAR echoes. In our scheme, a two-stage reconstruction algorithmic framework (LSRA) is derived based on sparse and low-rank priors, wherein the first stage recovers the measurements from their limited observations by exploring the low-rank prior, while the second estimates the final 3-D SAR images with a fast iterative optimization. Theoretically inspired by LRSA, the LLRS-Net is designed into a cascaded network structure. In LLRS-Net, the trainable weights serve as independent variables and control the algorithmic hyperparameters via regularizing functions, ensuring a well-conditioned updating tendency. By end-to-end training, the network weights are updated automatically under the guidance of a compound loss function constraining both the outputs of two stages. Finally, the methodology is validated on simulations and measured experiments. These results show that the proposed framework outperforms many state-of-the-art imaging algorithms in recovering 3-D SAR images from incomplete echo data.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2022.3175486