An eigenvalue-based approach for structure classification in polarimetric SAR images

Filippo Biondi, Carmine Clemente, Danilo Orlando

Research output: Contribution to journalLetter

Abstract

In this paper, we design a novel unsupervised architecture for automatic classification of the dominant polarization in polarimetric SAR images. To this end, we leverage the ideas developed in [1] and suitably exploit them to build a decision logic capable of recognizing the dominant scattering mechanism which characterizes the pixel under test. Specifically, we combine the original data to generate three different sets of reduced-size vectors, which feed a dominant eigenvalues classifier based upon the Model Order Selection rules. Then, the outputs of the latter classification schemes are exploited to infer, according to a specific criterion, the dominant polarization. The performance analysis is conducted on measured data and points out the effectiveness of the newly proposed classification architecture also showing that information about the dominant polarization canbe representative of the type of structure which gives raise to the dominant backscattering mechanism.
LanguageEnglish
Pages1-5
Number of pages5
JournalIEEE Geoscience and Remote Sensing Letters
DOIs
Publication statusAccepted/In press - 4 Sep 2019

Fingerprint

eigenvalue
synthetic aperture radar
polarization
Polarization
Backscattering
pixel
Classifiers
Pixels
scattering
Scattering

Keywords

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

Cite this

@article{41914ab58477464c979a9ce7ed7b36ad,
title = "An eigenvalue-based approach for structure classification in polarimetric SAR images",
abstract = "In this paper, we design a novel unsupervised architecture for automatic classification of the dominant polarization in polarimetric SAR images. To this end, we leverage the ideas developed in [1] and suitably exploit them to build a decision logic capable of recognizing the dominant scattering mechanism which characterizes the pixel under test. Specifically, we combine the original data to generate three different sets of reduced-size vectors, which feed a dominant eigenvalues classifier based upon the Model Order Selection rules. Then, the outputs of the latter classification schemes are exploited to infer, according to a specific criterion, the dominant polarization. The performance analysis is conducted on measured data and points out the effectiveness of the newly proposed classification architecture also showing that information about the dominant polarization canbe representative of the type of structure which gives raise to the dominant backscattering mechanism.",
keywords = "covariance matrix, eigenvalues decomposition, model order selection rules, polarimetric SAR image classification, structure classification",
author = "Filippo Biondi and Carmine Clemente and Danilo Orlando",
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 = "9",
day = "4",
doi = "10.1109/LGRS.2019.2940420",
language = "English",
pages = "1--5",
journal = "IEEE Geoscience and Remote Sensing Letters",
issn = "1545-598X",
publisher = "IEEE",

}

An eigenvalue-based approach for structure classification in polarimetric SAR images. / Biondi, Filippo; Clemente, Carmine; Orlando, Danilo.

In: IEEE Geoscience and Remote Sensing Letters, 04.09.2019, p. 1-5.

Research output: Contribution to journalLetter

TY - JOUR

T1 - An eigenvalue-based approach for structure classification in polarimetric SAR images

AU - Biondi, Filippo

AU - Clemente, Carmine

AU - Orlando, Danilo

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 - 2019/9/4

Y1 - 2019/9/4

N2 - In this paper, we design a novel unsupervised architecture for automatic classification of the dominant polarization in polarimetric SAR images. To this end, we leverage the ideas developed in [1] and suitably exploit them to build a decision logic capable of recognizing the dominant scattering mechanism which characterizes the pixel under test. Specifically, we combine the original data to generate three different sets of reduced-size vectors, which feed a dominant eigenvalues classifier based upon the Model Order Selection rules. Then, the outputs of the latter classification schemes are exploited to infer, according to a specific criterion, the dominant polarization. The performance analysis is conducted on measured data and points out the effectiveness of the newly proposed classification architecture also showing that information about the dominant polarization canbe representative of the type of structure which gives raise to the dominant backscattering mechanism.

AB - In this paper, we design a novel unsupervised architecture for automatic classification of the dominant polarization in polarimetric SAR images. To this end, we leverage the ideas developed in [1] and suitably exploit them to build a decision logic capable of recognizing the dominant scattering mechanism which characterizes the pixel under test. Specifically, we combine the original data to generate three different sets of reduced-size vectors, which feed a dominant eigenvalues classifier based upon the Model Order Selection rules. Then, the outputs of the latter classification schemes are exploited to infer, according to a specific criterion, the dominant polarization. The performance analysis is conducted on measured data and points out the effectiveness of the newly proposed classification architecture also showing that information about the dominant polarization canbe representative of the type of structure which gives raise to the dominant backscattering mechanism.

KW - covariance matrix

KW - eigenvalues decomposition

KW - model order selection rules

KW - polarimetric SAR image classification

KW - structure classification

UR - https://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=8859

U2 - 10.1109/LGRS.2019.2940420

DO - 10.1109/LGRS.2019.2940420

M3 - Letter

SP - 1

EP - 5

JO - IEEE Geoscience and Remote Sensing Letters

T2 - IEEE Geoscience and Remote Sensing Letters

JF - IEEE Geoscience and Remote Sensing Letters

SN - 1545-598X

ER -