Classification of covariance matrix eigenvalues in polarimetric SAR for environmental monitoring applications

Pia Addabbo, Filippo Biondi, Carmine Clemente, Danilo Orlando, Luca Pallotta

Research output: Contribution to journalArticle

Abstract

In this paper, we describe novel techniques for automatic classification of the dominant scattering mechanisms associated with the pixels of polarimetric SAR images. Specifically, we investigate two operating scenarios. In the first scenario, it is assumed that the polarimetric image pixels locally share the same covariance (homogeneous environment), whereas the second scenario considers polarimetric pixels with different power levels and the same covariance structure (heterogeneous environment). In the second case, we invoke the Principle of Invariance to get rid of the dependence on the power levels. For both scenarios, we formulate the classification problem in terms of multiple hypothesis tests which is addressed by applying the model order selection rules. The performance analysis is conducted on both simulated and measured data and demonstrates the effectiveness of the proposed approach.
LanguageEnglish
Pages28-43
Number of pages16
JournalIEEE Aerospace and Electronic Systems Magazine
Volume34
Issue number6
DOIs
Publication statusPublished - 2 Aug 2019

Fingerprint

environmental monitoring
eigenvalue
Covariance matrix
pixel
synthetic aperture radar
eigenvalues
Pixels
pixels
matrix
Monitoring
Invariance
invariance
scattering
Scattering

Keywords

  • covariance matrix
  • eigenvalues decomposition
  • model order selection rules
  • polarimetric SAR image classification

Cite this

@article{172f963716164a56ba70e81c0fb5cfec,
title = "Classification of covariance matrix eigenvalues in polarimetric SAR for environmental monitoring applications",
abstract = "In this paper, we describe novel techniques for automatic classification of the dominant scattering mechanisms associated with the pixels of polarimetric SAR images. Specifically, we investigate two operating scenarios. In the first scenario, it is assumed that the polarimetric image pixels locally share the same covariance (homogeneous environment), whereas the second scenario considers polarimetric pixels with different power levels and the same covariance structure (heterogeneous environment). In the second case, we invoke the Principle of Invariance to get rid of the dependence on the power levels. For both scenarios, we formulate the classification problem in terms of multiple hypothesis tests which is addressed by applying the model order selection rules. The performance analysis is conducted on both simulated and measured data and demonstrates the effectiveness of the proposed approach.",
keywords = "covariance matrix, eigenvalues decomposition, model order selection rules, polarimetric SAR image classification",
author = "Pia Addabbo and Filippo Biondi and Carmine Clemente and Danilo Orlando and Luca Pallotta",
note = "{\circledC} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2019",
month = "8",
day = "2",
doi = "10.1109/MAES.2019.2905924",
language = "English",
volume = "34",
pages = "28--43",
journal = "IEEE Aerospace and Electronic Systems Magazine",
issn = "0885-8985",
number = "6",

}

Classification of covariance matrix eigenvalues in polarimetric SAR for environmental monitoring applications. / Addabbo, Pia; Biondi, Filippo; Clemente, Carmine; Orlando, Danilo; Pallotta, Luca.

In: IEEE Aerospace and Electronic Systems Magazine, Vol. 34, No. 6, 02.08.2019, p. 28-43.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification of covariance matrix eigenvalues in polarimetric SAR for environmental monitoring applications

AU - Addabbo, Pia

AU - Biondi, Filippo

AU - Clemente, Carmine

AU - Orlando, Danilo

AU - Pallotta, Luca

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/8/2

Y1 - 2019/8/2

N2 - In this paper, we describe novel techniques for automatic classification of the dominant scattering mechanisms associated with the pixels of polarimetric SAR images. Specifically, we investigate two operating scenarios. In the first scenario, it is assumed that the polarimetric image pixels locally share the same covariance (homogeneous environment), whereas the second scenario considers polarimetric pixels with different power levels and the same covariance structure (heterogeneous environment). In the second case, we invoke the Principle of Invariance to get rid of the dependence on the power levels. For both scenarios, we formulate the classification problem in terms of multiple hypothesis tests which is addressed by applying the model order selection rules. The performance analysis is conducted on both simulated and measured data and demonstrates the effectiveness of the proposed approach.

AB - In this paper, we describe novel techniques for automatic classification of the dominant scattering mechanisms associated with the pixels of polarimetric SAR images. Specifically, we investigate two operating scenarios. In the first scenario, it is assumed that the polarimetric image pixels locally share the same covariance (homogeneous environment), whereas the second scenario considers polarimetric pixels with different power levels and the same covariance structure (heterogeneous environment). In the second case, we invoke the Principle of Invariance to get rid of the dependence on the power levels. For both scenarios, we formulate the classification problem in terms of multiple hypothesis tests which is addressed by applying the model order selection rules. The performance analysis is conducted on both simulated and measured data and demonstrates the effectiveness of the proposed approach.

KW - covariance matrix

KW - eigenvalues decomposition

KW - model order selection rules

KW - polarimetric SAR image classification

UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=62

U2 - 10.1109/MAES.2019.2905924

DO - 10.1109/MAES.2019.2905924

M3 - Article

VL - 34

SP - 28

EP - 43

JO - IEEE Aerospace and Electronic Systems Magazine

T2 - IEEE Aerospace and Electronic Systems Magazine

JF - IEEE Aerospace and Electronic Systems Magazine

SN - 0885-8985

IS - 6

ER -