Pseudo-Zernike based multi-pass automatic target recognition from multi-channel SAR

Carmine Clemente, Luca Pallotta, Ian Proudler, Antonio De Maio, John J. Soraghan, Alfonso Farina

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

The capability to exploit multiple sources of information is of fundamental importance in a battlefield scenario. Information obtained from different sources, and separated in space and time, provides the opportunity to exploit diversities to mitigate uncertainty. In this paper, we address the problem of Automatic Target Recognition (ATR) from Synthetic Aperture Radar (SAR) platforms. Our approach exploits both channel (e.g. polarization) and spatial diversity to obtain suitable information for such a critical task. In particular we use the pseudo-Zernike moments (pZm) to extract features representing commercial vehicles to perform target identification. The proposed approach exploits diversities and invariant properties of pZm leading to high confidence ATR, with limited computational complexity and data transfer requirements. The effectiveness of the proposed method is demonstrated using real data from the Gotcha dataset, in different operational configurations and data source availability.
LanguageEnglish
Pages457–466
Number of pages10
JournalIET Radar Sonar and Navigation
Volume9
Issue number4
Early online date4 Dec 2014
DOIs
Publication statusPublished - 2015

Fingerprint

Automatic target recognition
Synthetic aperture radar
Commercial vehicles
Data transfer
Computational complexity
Availability
Polarization
Uncertainty

Keywords

  • automatic target recognition
  • ATR
  • synthetic aperture radar
  • SAR
  • pseudo-Zernike moments
  • pZm

Cite this

Clemente, Carmine ; Pallotta, Luca ; Proudler, Ian ; De Maio, Antonio ; Soraghan, John J. ; Farina, Alfonso. / Pseudo-Zernike based multi-pass automatic target recognition from multi-channel SAR. In: IET Radar Sonar and Navigation. 2015 ; Vol. 9, No. 4. pp. 457–466.
@article{c849d3b5ce66495296dd81b04829c28e,
title = "Pseudo-Zernike based multi-pass automatic target recognition from multi-channel SAR",
abstract = "The capability to exploit multiple sources of information is of fundamental importance in a battlefield scenario. Information obtained from different sources, and separated in space and time, provides the opportunity to exploit diversities to mitigate uncertainty. In this paper, we address the problem of Automatic Target Recognition (ATR) from Synthetic Aperture Radar (SAR) platforms. Our approach exploits both channel (e.g. polarization) and spatial diversity to obtain suitable information for such a critical task. In particular we use the pseudo-Zernike moments (pZm) to extract features representing commercial vehicles to perform target identification. The proposed approach exploits diversities and invariant properties of pZm leading to high confidence ATR, with limited computational complexity and data transfer requirements. The effectiveness of the proposed method is demonstrated using real data from the Gotcha dataset, in different operational configurations and data source availability.",
keywords = "automatic target recognition, ATR, synthetic aperture radar, SAR, pseudo-Zernike moments, pZm",
author = "Carmine Clemente and Luca Pallotta and Ian Proudler and {De Maio}, Antonio and Soraghan, {John J.} and Alfonso Farina",
year = "2015",
doi = "10.1049/iet-rsn.2014.0296",
language = "English",
volume = "9",
pages = "457–466",
journal = "IET Radar Sonar and Navigation",
issn = "1751-8784",
publisher = "Institution of Engineering and Technology",
number = "4",

}

Pseudo-Zernike based multi-pass automatic target recognition from multi-channel SAR. / Clemente, Carmine; Pallotta, Luca; Proudler, Ian ; De Maio, Antonio; Soraghan, John J.; Farina, Alfonso.

In: IET Radar Sonar and Navigation, Vol. 9, No. 4, 2015, p. 457–466.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Pseudo-Zernike based multi-pass automatic target recognition from multi-channel SAR

AU - Clemente, Carmine

AU - Pallotta, Luca

AU - Proudler, Ian

AU - De Maio, Antonio

AU - Soraghan, John J.

AU - Farina, Alfonso

PY - 2015

Y1 - 2015

N2 - The capability to exploit multiple sources of information is of fundamental importance in a battlefield scenario. Information obtained from different sources, and separated in space and time, provides the opportunity to exploit diversities to mitigate uncertainty. In this paper, we address the problem of Automatic Target Recognition (ATR) from Synthetic Aperture Radar (SAR) platforms. Our approach exploits both channel (e.g. polarization) and spatial diversity to obtain suitable information for such a critical task. In particular we use the pseudo-Zernike moments (pZm) to extract features representing commercial vehicles to perform target identification. The proposed approach exploits diversities and invariant properties of pZm leading to high confidence ATR, with limited computational complexity and data transfer requirements. The effectiveness of the proposed method is demonstrated using real data from the Gotcha dataset, in different operational configurations and data source availability.

AB - The capability to exploit multiple sources of information is of fundamental importance in a battlefield scenario. Information obtained from different sources, and separated in space and time, provides the opportunity to exploit diversities to mitigate uncertainty. In this paper, we address the problem of Automatic Target Recognition (ATR) from Synthetic Aperture Radar (SAR) platforms. Our approach exploits both channel (e.g. polarization) and spatial diversity to obtain suitable information for such a critical task. In particular we use the pseudo-Zernike moments (pZm) to extract features representing commercial vehicles to perform target identification. The proposed approach exploits diversities and invariant properties of pZm leading to high confidence ATR, with limited computational complexity and data transfer requirements. The effectiveness of the proposed method is demonstrated using real data from the Gotcha dataset, in different operational configurations and data source availability.

KW - automatic target recognition

KW - ATR

KW - synthetic aperture radar

KW - SAR

KW - pseudo-Zernike moments

KW - pZm

UR - http://digital-library.theiet.org/content/journals/iet-rsn

U2 - 10.1049/iet-rsn.2014.0296

DO - 10.1049/iet-rsn.2014.0296

M3 - Article

VL - 9

SP - 457

EP - 466

JO - IET Radar Sonar and Navigation

T2 - IET Radar Sonar and Navigation

JF - IET Radar Sonar and Navigation

SN - 1751-8784

IS - 4

ER -