Hostname: page-component-6bf8c574d5-mggfc Total loading time: 0 Render date: 2025-02-16T17:47:50.896Z Has data issue: false hasContentIssue false
  • English
  • Français

Physical model-driven deep networks for through-the-wall radar imaging

Published online by Cambridge University Press:  03 February 2022

Yuhao Wang ,
Yue Zhang Open the ORCID record for Yue Zhang [Opens in a new window] ,
Mingcheng Xiao ,
Huilin Zhou ,
Qiegen Liu  and
Jianfei Gao
Yuhao Wang*
Affiliation:
School of Information Engineering, Nanchang University, 999 Xuefu Avenue, Honggutan New District, Nanchang, Jiangxi, China
Yue Zhang
Affiliation:
School of Information Engineering, Nanchang University, 999 Xuefu Avenue, Honggutan New District, Nanchang, Jiangxi, China
Mingcheng Xiao
Affiliation:
School of Information Engineering, Nanchang University, 999 Xuefu Avenue, Honggutan New District, Nanchang, Jiangxi, China
Huilin Zhou
Affiliation:
School of Information Engineering, Nanchang University, 999 Xuefu Avenue, Honggutan New District, Nanchang, Jiangxi, China
Qiegen Liu
Affiliation:
School of Information Engineering, Nanchang University, 999 Xuefu Avenue, Honggutan New District, Nanchang, Jiangxi, China
Jianfei Gao
Affiliation:
School of Information Engineering, Nanchang University, 999 Xuefu Avenue, Honggutan New District, Nanchang, Jiangxi, China
*
Author for correspondence: Yuhao Wang, E-mail: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

In order to merge the advantages of the traditional compressed sensing (CS) methodology and the data-driven deep network scheme, this paper proposes a physical model-driven deep network, termed CS-Net, for solving target image reconstruction problems in through-the-wall radar imaging. The proposed method consists of two consequent steps. First, a learned convolutional neural network prior is introduced to replace the regularization term in the traditional iterative CS-based method to capture the redundancy of the radar echo signal. Moreover, the physical model of the radar signal is used in the data consistency layer to encourage consistency with the measurements. Second, the iterative CS optimization is unrolled to yield a deep learning network, where the weight, regularization parameter, and the other parameters are learnable. A quantity of training data enables the network to extract high-dimensional characteristics of the radar echo signal to reconstruct the spatial target image. Simulation results demonstrated that the proposed method can achieve accurate target image reconstruction and was superior to the traditional CS method, in terms of mean squared error and the target texture details.

Keywords

Compressed sensingdeep learningimage reconstructionTWRIunrolling network
Type
Radar
Information
International Journal of Microwave and Wireless Technologies , Volume 15 , Special Issue 1: EuCAP 2021 Special Issue , February 2023 , pp. 82 - 89
Check for updates
Copyright
Copyright © The Author(s), 2022. Published by Cambridge University Press in association with the European Microwave Association

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Muqaibel, AH (2015) Improved compressive sensing with antenna directivity for TWRI. in Symposium on Antennas and Propagation & USNC/URSI National Radio Science Meeting, 402–403.CrossRefGoogle Scholar
Sun, HB (2019) Through-the-wall human motion sensing based on forward scattering. in 2019 IEEE Radar Conference, 1–5.CrossRefGoogle Scholar
Laviada, J, Arboleya, A, Lopez-Gayarre, F and Las-Heras, F (2021) Broadband synthetic aperture scanning system for three-dimensional through-the-wall inspection. IEEE Geoscience and Remote Sensing Letters, 13, 97–101.CrossRefGoogle Scholar
Tang, VH, Bouzerdoum, A and Phung, SL (2020) Compressive radar imaging of stationary indoor targets with low-rank plus jointly sparse and total variation regularizations. IEEE Transactions on Image Processing, 29, 4598–4613.CrossRefGoogle Scholar
Tivive, FHC, Bouzerdoum, A and Amin, MG (2015) A subspace projection approach for wall clutter mitigation in through-the-wall radar imaging. IEEE Transactions on Geoscience and Remote Sensing, 53, 2108–2122.CrossRefGoogle Scholar
Yoon, YS and Amin, MG (2009) Spatial filtering for wall-clutter mitigation in through-the-wall radar imaging. IEEE Transactions on Geoscience and Remote Sensing, 47, 3192–3208.CrossRefGoogle Scholar
Zhang, Y and Xia, T (2016) In-wall clutter suppression based on low-rank and sparse representation for through-the-wall radar. IEEE Geoscience and Remote Sensing Letters, 13, 671–675.CrossRefGoogle Scholar
Zhang, Q, Chen, YJ, Chen, YG, Chi, L and Wu, Y (2015) A cognitive signals reconstruction algorithm based on compressed sensing. in 2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar, 724–727.CrossRefGoogle Scholar
Lei, L, Huang, JJ and Sun, Y (2016) Compressed sensing MIMO radar waveform optimization without signal recovery. 2016 CIE International Conference on Radar, 1–4.CrossRefGoogle Scholar
Yan, HC, Xu, J and Zhang, XD (2015) Compressed sensing radar imaging of off-grid sparse targets. 2015 IEEE Radar Conference, 0690–0693.CrossRefGoogle Scholar
Unser, M, Fageot, J and Gupta, H (2016) Representer theorems for sparsity-promoting $\ell _1$ regularization. IEEE Transactions on Information Theory, 62, 5167–5180.CrossRefGoogle Scholar
Hosseini, MS and Plataniotis, KN (2014) High-accuracy total variation with application to compressed video sensing. IEEE Transactions on Image Processing, 23, 3869–3884.CrossRefGoogle ScholarPubMed
Jin, T (2017) Autofocus compressed sensing imaging based on nonlinear conjugate gradient. in 2017 XXXIInd General Assembly and Scientific Symposium of the International Union of Radio Science, 1–4.CrossRefGoogle Scholar
Aggarwal, HK, Mani, MP and Jacob, M (2019) MoDL: model-based deep learning architecture for inverse problems. IEEE Transactions on Medical Imaging, 38, 394–405.CrossRefGoogle ScholarPubMed
Sanghvi, Y, Kalepu, Y and Khankhoje, UK (2020) Embedding deep learning in inverse scattering problems. IEEE Transactions on Computational Imaging, 6, 46–56.CrossRefGoogle Scholar
Chen, XD, Wei, Z, Li, MK and Rocca, P (2020) A review of deep learning approaches for inverse scattering problems. Progress in Electromagnetics Research, 167, 67–81.CrossRefGoogle Scholar
Zheng, ZJ, Pan, J, Ni, ZK, Shi, C, Ye, SB and Fang, GY (2021) Human posture reconstruction for through-the-wall radar imaging using convolutional neural networks. IEEE Geoscience and Remote Sensing Letters, 19.Google Scholar
Zhang, HY, Song, RY, Chen, SY, Wang, G, Jia, Y and Yan, C (2019) Target Imaging Based on Generative Adversarial Nets in Through-wall Radar Imaging. in International Conference on Control, Automation and Information Sciences (ICCAIS), 1–6.CrossRefGoogle Scholar
Li, HQ, Cui, GL, Guo, SS, Kong, LJ and Yang, XB (2021) Human target detection based on FCN for through-the-wall radar imaging. IEEE Geoscience and Remote Sensing Letters, 18, 1565–1569.CrossRefGoogle Scholar
Tivive, FHC and Bouzerdoum, A (2021) Clutter removal in through-the-wall radar imaging using sparse autoencoder with low-rank projection. IEEE Transactions on Geoscience and Remote Sensing, 59, 1118–1129.CrossRefGoogle Scholar
Li, MC, Xi, XL, Zhang, XH and Liu, GH (2021) Joint compressed sensing and spread spectrum through-the-wall radar imaging. IEEE Access, 9, 6259–6267.CrossRefGoogle Scholar