In this paper, an automatic classification approach for polarimetric covariance structure is derived and assessed. It extends the framework of Pallotta et al. "Detecting Covariance Symmetries in Polarimetric SAR Images" to the heterogeneous environment, where the pixels of the polarimetric image share the same covariance structure but different power levels. The Principle of Invariance is exploited to replace the original data with a suitable statistic whose distribution is independent of the scale factors. Then, the classification problem is formulated in terms of a multiple hypotheses test and solved by means of model order selection rules. The behavior of the newly devised classifiers is first assessed over simulated data also in comparison with the analogous counterparts for a homogeneous environment. Next, the classification performances are evaluated on real measured data corroborating the satisfactory results highlighted in the simulations.

Pallotta, L., De Maio, A., Orlando, D. (2019). A Robust Framework for Covariance Classification in Heterogeneous Polarimetric SAR Images and Its Application to L-Band Data. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 57(1), 104-119 [10.1109/TGRS.2018.2852559].

A Robust Framework for Covariance Classification in Heterogeneous Polarimetric SAR Images and Its Application to L-Band Data

Pallotta L.;
2019-01-01

Abstract

In this paper, an automatic classification approach for polarimetric covariance structure is derived and assessed. It extends the framework of Pallotta et al. "Detecting Covariance Symmetries in Polarimetric SAR Images" to the heterogeneous environment, where the pixels of the polarimetric image share the same covariance structure but different power levels. The Principle of Invariance is exploited to replace the original data with a suitable statistic whose distribution is independent of the scale factors. Then, the classification problem is formulated in terms of a multiple hypotheses test and solved by means of model order selection rules. The behavior of the newly devised classifiers is first assessed over simulated data also in comparison with the analogous counterparts for a homogeneous environment. Next, the classification performances are evaluated on real measured data corroborating the satisfactory results highlighted in the simulations.
2019
Pallotta, L., De Maio, A., Orlando, D. (2019). A Robust Framework for Covariance Classification in Heterogeneous Polarimetric SAR Images and Its Application to L-Band Data. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 57(1), 104-119 [10.1109/TGRS.2018.2852559].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11590/356224
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 25
  • ???jsp.display-item.citation.isi??? 23
social impact