Unsupervised Deep Basis Pursuit Based Resolution Enhancement for Forward Looking MIMO SAR Imaging

Vijith Varma Kotte; Shahzad Sarwar Gishkori; Mudassir Masood; Tareq Y. Al-Naffouri

doi:10.1109/taes.2023.3317362

Unsupervised Deep Basis Pursuit Based Resolution Enhancement for Forward Looking MIMO SAR Imaging

Vijith Varma Kotte, Shahzad Sarwar Gishkori, Mudassir Masood, Tareq Y. Al-Naffouri

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Nowadays, radar based image reconstruction is becoming important in higher-level automated driving, especially for all weather conditions. In this paper, we present unsupervised deep learning method for forward looking multiple-input multipleoutput synthetic aperture radar (FL-MIMO SAR) to enhance the angular resolution. We present mathematical analysis for the composite antenna pattern generated by FL-MIMO SAR as well as image reconstruction with deep learning for FL-MIMO SAR. We present a computationally efficient deep basis pursuit (DBP) method to solve for convolutional neural network (CNN) with unsupervised learning (i.e. without ground truth) and present modified back projection (MBP) algorithm to reconstruct SAR image with enhanced angular resolution. We present experimental results to verify our proposed methodology and compare the performance with compressed sensing based backprojection algorithm on both simulation and real data.

Original language	English (US)
Pages (from-to)	1-14
Number of pages	14
Journal	IEEE Transactions on Aerospace and Electronic Systems
DOIs	https://doi.org/10.1109/taes.2023.3317362
State	Published - Sep 20 2023

Bibliographical note

KAUST Repository Item: Exported on 2023-09-30
Acknowledged KAUST grant number(s): ORA-CRG2021-4695
Acknowledgements: This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR), under Award No. ORA-CRG2021-4695. The authors would like to thank Jonathan I. Tamir, Assistant Professor of Electrical and Computer Engineering, The University of Texas at Austin, for the useful discussion and explanation on DBP.

ASJC Scopus subject areas

Electrical and Electronic Engineering
Aerospace Engineering

Access to Document

10.1109/taes.2023.3317362

https://repository.kaust.edu.sa/bitstream/10754/694690/1/Unsupervised_Deep_Basis_Pursuit_Based_Resolution_Enhancement_for_Forward_Looking_MIMO_SAR_Imaging.pdf

Cite this

@article{8b241a09b49945cbbc94213c0c324d1e,

title = "Unsupervised Deep Basis Pursuit Based Resolution Enhancement for Forward Looking MIMO SAR Imaging",

abstract = "Nowadays, radar based image reconstruction is becoming important in higher-level automated driving, especially for all weather conditions. In this paper, we present unsupervised deep learning method for forward looking multiple-input multipleoutput synthetic aperture radar (FL-MIMO SAR) to enhance the angular resolution. We present mathematical analysis for the composite antenna pattern generated by FL-MIMO SAR as well as image reconstruction with deep learning for FL-MIMO SAR. We present a computationally efficient deep basis pursuit (DBP) method to solve for convolutional neural network (CNN) with unsupervised learning (i.e. without ground truth) and present modified back projection (MBP) algorithm to reconstruct SAR image with enhanced angular resolution. We present experimental results to verify our proposed methodology and compare the performance with compressed sensing based backprojection algorithm on both simulation and real data.",

author = "Kotte, {Vijith Varma} and Gishkori, {Shahzad Sarwar} and Mudassir Masood and Al-Naffouri, {Tareq Y.}",

note = "KAUST Repository Item: Exported on 2023-09-30 Acknowledged KAUST grant number(s): ORA-CRG2021-4695 Acknowledgements: This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR), under Award No. ORA-CRG2021-4695. The authors would like to thank Jonathan I. Tamir, Assistant Professor of Electrical and Computer Engineering, The University of Texas at Austin, for the useful discussion and explanation on DBP.",

year = "2023",

month = sep,

day = "20",

doi = "10.1109/taes.2023.3317362",

language = "English (US)",

pages = "1--14",

journal = "IEEE Transactions on Aerospace and Electronic Systems",

issn = "0018-9251",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Unsupervised Deep Basis Pursuit Based Resolution Enhancement for Forward Looking MIMO SAR Imaging

AU - Kotte, Vijith Varma

AU - Gishkori, Shahzad Sarwar

AU - Masood, Mudassir

AU - Al-Naffouri, Tareq Y.

N1 - KAUST Repository Item: Exported on 2023-09-30 Acknowledged KAUST grant number(s): ORA-CRG2021-4695 Acknowledgements: This publication is based upon work supported by the King Abdullah University of Science and Technology (KAUST), Office of Sponsored Research (OSR), under Award No. ORA-CRG2021-4695. The authors would like to thank Jonathan I. Tamir, Assistant Professor of Electrical and Computer Engineering, The University of Texas at Austin, for the useful discussion and explanation on DBP.

PY - 2023/9/20

Y1 - 2023/9/20

N2 - Nowadays, radar based image reconstruction is becoming important in higher-level automated driving, especially for all weather conditions. In this paper, we present unsupervised deep learning method for forward looking multiple-input multipleoutput synthetic aperture radar (FL-MIMO SAR) to enhance the angular resolution. We present mathematical analysis for the composite antenna pattern generated by FL-MIMO SAR as well as image reconstruction with deep learning for FL-MIMO SAR. We present a computationally efficient deep basis pursuit (DBP) method to solve for convolutional neural network (CNN) with unsupervised learning (i.e. without ground truth) and present modified back projection (MBP) algorithm to reconstruct SAR image with enhanced angular resolution. We present experimental results to verify our proposed methodology and compare the performance with compressed sensing based backprojection algorithm on both simulation and real data.

AB - Nowadays, radar based image reconstruction is becoming important in higher-level automated driving, especially for all weather conditions. In this paper, we present unsupervised deep learning method for forward looking multiple-input multipleoutput synthetic aperture radar (FL-MIMO SAR) to enhance the angular resolution. We present mathematical analysis for the composite antenna pattern generated by FL-MIMO SAR as well as image reconstruction with deep learning for FL-MIMO SAR. We present a computationally efficient deep basis pursuit (DBP) method to solve for convolutional neural network (CNN) with unsupervised learning (i.e. without ground truth) and present modified back projection (MBP) algorithm to reconstruct SAR image with enhanced angular resolution. We present experimental results to verify our proposed methodology and compare the performance with compressed sensing based backprojection algorithm on both simulation and real data.

UR - http://hdl.handle.net/10754/694690

UR - https://ieeexplore.ieee.org/document/10256073/

U2 - 10.1109/taes.2023.3317362

DO - 10.1109/taes.2023.3317362

M3 - Article

SN - 0018-9251

SP - 1

EP - 14

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

ER -

Unsupervised Deep Basis Pursuit Based Resolution Enhancement for Forward Looking MIMO SAR Imaging

Abstract

Bibliographical note

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this