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

2 Citations (Scopus)
19 Downloads (Pure)

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.
Original languageEnglish
Pages (from-to)28-43
Number of pages16
JournalIEEE Aerospace and Electronic Systems Magazine
Volume34
Issue number6
DOIs
Publication statusPublished - 2 Aug 2019

Keywords

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

Fingerprint Dive into the research topics of 'Classification of covariance matrix eigenvalues in polarimetric SAR for environmental monitoring applications'. Together they form a unique fingerprint.

  • Cite this