Lightweight FISTA-Inspired Sparse Reconstruction Network for mmW 3-D Holography

Integrating compressed sensing (CS) with millimeter-wave (mmW) holography has shown great potential to achieve lightweight onboard hardware, low sampling ratio, and high-speed sensing. However, conventional CS-driven algorithms are always limited by nontrivial adjusting of parameters and excessive c...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 20
Main Authors: Wang, Mou, Wei, Shunjun, Liang, Jiadian, Liu, Shan, Shi, Jun, Zhang, Xiaoling
Format: Journal Article
Language:English
Published: New York IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
3-D holography
Algorithms
Artificial neural networks
Azimuth
Coefficients
compressed sensing (CS)
Computer applications
Computer networks
Computing costs
Deep learning
deep unfolding
fast iterative shrinkage-thresholding algorithm (FISTA)
Holography
Image reconstruction
Imaging
Imaging techniques
Iterative methods
Kernels
Machine learning
Millimeter waves
millimeter-wave (mmW) imaging
Momentum
near-field
Neural networks
Parameters
Radar
Radar imaging
Radar polarimetry
Sensors
sparse reconstruction
Synthetic aperture radar
ISSN:0196-2892, 1558-0644
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Integrating compressed sensing (CS) with millimeter-wave (mmW) holography has shown great potential to achieve lightweight onboard hardware, low sampling ratio, and high-speed sensing. However, conventional CS-driven algorithms are always limited by nontrivial adjusting of parameters and excessive computational cost caused by plenty of iterations. To address this problem, we propose a lightweight model-based deep learning framework (LFIST-Net) for mmW 3-D holography, by combining the interpretability of fast iterative shrinkage-thresholding algorithm (FISTA) and tuning-free merit of data-driven deep neural network. First, the single-frequency (SF) holographic imaging technique is integrated into FISTA, which serves as the sensing kernels, to avoid large-scale matrix multiplications. Subsequently, the kernel-based FISTA (KFISTA) is mapped into layer-fixed and parameter-learnable LFIST-Net, whose weights are relaxed to be layer-varied. The updating of key parameters in LFIST-Net, including step sizes, thresholds, and momentum coefficients, are regularized by soft-plus function to ensure the non-negativity and monotonicity. As for 3-D holography implementation, the "1-D + 2-D" scheme is adopted, where the matched filtering (MF) and well-trained LFIST-Net are used for range focusing and reconstructions of azimuth slices. Without losing efficiency, the range-focused subechoes are processed parallelly in 3-D cube form. Experiments, including both simulated and measured tests based on a commercial mmW radar, prove that LFIST-Net is capable of reconstructing the imaging scene precisely. In particular, in near-field mmW 3-D holography tests, both numerical and visual results demonstrate LFIST-Net yields compelling reconstruction performance while maintaining high computational speed compared with MF-based, conventional CS-driven, and network-based methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2021.3093307