Improving Estimation for Intensity SAR Data

by Klaus Vasconcellos and Alejandro C. Frery .

Abstract: The performances of three different estimators for the roughness parameter of an important distribution for synthetic aperture radar data analysis are compared: those of a moment estimator, of the maximum likelihood estimator and of the second-order bias-corrected maximum likelihood estimator. A Monte Carlo study is designed to perform this comparison, due to the untractability of the estimators distributions from an analytical point of view. From this study, the use of the second-order bias-corrected maximum likelihood estimator for the roughness parameter is suggested.

Key Words: bias correction, image analysis, maximum likelihood, multiplicative model, SAR data

Authors:
Klaus Vasconcellos, klaus@de.ufpe.br"> klaus@de.ufpe.br">klaus@de.ufpe.br
Alejandro C. Frery, frery@di.ufpe.br

Editor: Dean Foster, foster@hellspark.wharton.upenn.edu

READING THE ARTICLE: You can read the article in portable document (.pdf) format (533112 bytes.)

NOTE: The content of this article is the intellectual property of the authors, who retains all rights to future publication.

This page has been accessed 2481 times since April 1, 2007.


Return to the InterStat Home Page.