<link rel="stylesheet" href="/res/styles.39be4579664c3a48.css">
Artículo

Fisher Information Matrix and Texture Parameter Estimator for the Polarimetric SAR $\mathcal{G}_{p}^{0}$ Data Model

Fernández Michelli, Juan Ignacio Icon; Muravchik, Carlos Horacio

Otros responsables

Fecha

01/2026

Editorial

Institute of Electrical and Electronics Engineers

Revista

Ieee Transactions On Geoscience And Remote Sensing

Título del libro

Nombre del evento

Fecha del evento

Institución organizadora

ISSN

0196-2892

eISSN

ISBN

Idioma

Inglés

Tipo del evento

Resumen

The product model is widely used to describe PolSAR data. When the scalar variable that models the texture is assigned an inverse gamma model γ −1 and the polarimetric speckle is assigned a scaled complex Wishart model (sWC), the matrix variate representing the PolSAR return follows a G 0 p distribution. This model can adequately describe areas with a wide range of texture levels while maintaining a reasonable mathematical tractability. In this paper, the Fisher information matrix (FIM) of the G 0 p model is analytically computed and a closed-form texture parameter estimator is proposed which does not rely on optimization algorithms. The related Cramer- ´ Rao lower bound (CRLB) is also presented and a performance comparison with well-known texture estimators is made for simulated and real data. For the latter, a goodness-of-fit test based on the method of matrix log-cumulants (MoMLCs) was used to evaluate the fitting accuracy of the estimates to the G 0 p model.

Colecciones

Aprobación

Revisión

Complementado por

Referenciado por

Licencia Creative Commons

Excepto donde se indique lo contrario, la licencia de este ítem se describe como by-nc-sa