Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques

Tiep Vu, Lam Nguyen, Vishal Monga

Research output: Contribution to journalArticle

Abstract

Using low-frequency (UHF to L-band) ultrawideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e.g. bomb or mine, has been successfully demonstrated recently. Despite promising recent progress, a significant open challenge is to distinguish obscured targets from other (natural and manmade) clutter sources in the scene. The problem becomes exacerbated in the presence of noisy responses from rough ground surfaces. In this paper, we present three novel sparsity-driven techniques, which not only exploit the subtle features of raw captured data but also take advantage of the polarization diversity and the aspect angle dependence information from multi-channel SAR data. First, the traditional sparse representation-based classification (SRC) is generalized to exploit shared information of classes and various sparsity structures of tensor coefficients for multichannel data. Corresponding tensor dictionary learning models are consequently proposed to enhance classification accuracy. Lastly, a new tensor sparsity model is proposed to model responses from multiple consecutive looks of objects, which is a unique characteristic of the dataset we consider. Extensive experimental results on a high-fidelity electromagnetic simulated dataset and radar data collected from the U.S. Army Research Laboratory side-looking SAR demonstrate the advantages of proposed tensor sparsity models.

Original languageEnglish (US)
JournalIEEE Transactions on Aerospace and Electronic Systems
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Synthetic aperture radar
Ultra-wideband (UWB)
Tensors
Research laboratories
Glossaries
Radar
Polarization

All Science Journal Classification (ASJC) codes

  • Aerospace Engineering
  • Electrical and Electronic Engineering

Cite this

@article{4d66ef30a8cf4cafa072c334715df0f5,
title = "Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques",
abstract = "Using low-frequency (UHF to L-band) ultrawideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e.g. bomb or mine, has been successfully demonstrated recently. Despite promising recent progress, a significant open challenge is to distinguish obscured targets from other (natural and manmade) clutter sources in the scene. The problem becomes exacerbated in the presence of noisy responses from rough ground surfaces. In this paper, we present three novel sparsity-driven techniques, which not only exploit the subtle features of raw captured data but also take advantage of the polarization diversity and the aspect angle dependence information from multi-channel SAR data. First, the traditional sparse representation-based classification (SRC) is generalized to exploit shared information of classes and various sparsity structures of tensor coefficients for multichannel data. Corresponding tensor dictionary learning models are consequently proposed to enhance classification accuracy. Lastly, a new tensor sparsity model is proposed to model responses from multiple consecutive looks of objects, which is a unique characteristic of the dataset we consider. Extensive experimental results on a high-fidelity electromagnetic simulated dataset and radar data collected from the U.S. Army Research Laboratory side-looking SAR demonstrate the advantages of proposed tensor sparsity models.",
author = "Tiep Vu and Lam Nguyen and Vishal Monga",
year = "2018",
month = "1",
day = "1",
doi = "10.1109/TAES.2018.2875504",
language = "English (US)",
journal = "IEEE Transactions on Aerospace and Electronic Systems",
issn = "0018-9251",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - JOUR

T1 - Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques

AU - Vu, Tiep

AU - Nguyen, Lam

AU - Monga, Vishal

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Using low-frequency (UHF to L-band) ultrawideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e.g. bomb or mine, has been successfully demonstrated recently. Despite promising recent progress, a significant open challenge is to distinguish obscured targets from other (natural and manmade) clutter sources in the scene. The problem becomes exacerbated in the presence of noisy responses from rough ground surfaces. In this paper, we present three novel sparsity-driven techniques, which not only exploit the subtle features of raw captured data but also take advantage of the polarization diversity and the aspect angle dependence information from multi-channel SAR data. First, the traditional sparse representation-based classification (SRC) is generalized to exploit shared information of classes and various sparsity structures of tensor coefficients for multichannel data. Corresponding tensor dictionary learning models are consequently proposed to enhance classification accuracy. Lastly, a new tensor sparsity model is proposed to model responses from multiple consecutive looks of objects, which is a unique characteristic of the dataset we consider. Extensive experimental results on a high-fidelity electromagnetic simulated dataset and radar data collected from the U.S. Army Research Laboratory side-looking SAR demonstrate the advantages of proposed tensor sparsity models.

AB - Using low-frequency (UHF to L-band) ultrawideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e.g. bomb or mine, has been successfully demonstrated recently. Despite promising recent progress, a significant open challenge is to distinguish obscured targets from other (natural and manmade) clutter sources in the scene. The problem becomes exacerbated in the presence of noisy responses from rough ground surfaces. In this paper, we present three novel sparsity-driven techniques, which not only exploit the subtle features of raw captured data but also take advantage of the polarization diversity and the aspect angle dependence information from multi-channel SAR data. First, the traditional sparse representation-based classification (SRC) is generalized to exploit shared information of classes and various sparsity structures of tensor coefficients for multichannel data. Corresponding tensor dictionary learning models are consequently proposed to enhance classification accuracy. Lastly, a new tensor sparsity model is proposed to model responses from multiple consecutive looks of objects, which is a unique characteristic of the dataset we consider. Extensive experimental results on a high-fidelity electromagnetic simulated dataset and radar data collected from the U.S. Army Research Laboratory side-looking SAR demonstrate the advantages of proposed tensor sparsity models.

UR - http://www.scopus.com/inward/record.url?scp=85055027370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85055027370&partnerID=8YFLogxK

U2 - 10.1109/TAES.2018.2875504

DO - 10.1109/TAES.2018.2875504

M3 - Article

AN - SCOPUS:85055027370

JO - IEEE Transactions on Aerospace and Electronic Systems

JF - IEEE Transactions on Aerospace and Electronic Systems

SN - 0018-9251

ER -