title   
  

Parameter selection in sparsity-driven SAR imaging

Batu, Özge and Çetin, Müjdat (2010) Parameter selection in sparsity-driven SAR imaging. (Accepted/In Press)

WarningThere is a more recent version of this item available.

[img]
Preview
PDF (This is a RoMEO green publisher -- author can archive pre-print (ie pre-refereeing)) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
781Kb

Abstract

We consider a recently developed sparsity-driven synthetic aperture radar (SAR) imaging approach which can produce superresolution, feature-enhanced images. However, this regularization-based approach requires the selection of a hyper-parameter in order to generate such high-quality images. In this paper we present a number of techniques for automatically selecting the hyper-parameter involved in this problem. In particular, we propose and develop numerical procedures for the use of Stein’s unbiased risk estimation, generalized cross-validation, and L-curve techniques for automatic parameter choice. We demonstrate and compare the effectiveness of these procedures through experiments based on both simple synthetic scenes, as well as electromagnetically simulated realistic data. Our results suggest that sparsity-driven SAR imaging coupled with the proposed automatic parameter choice procedures offers significant improvements over conventional SAR imaging.

Item Type:Article
Uncontrolled Keywords:parameter selection, synthetic aperture radar, sparse signal representation, non-quadratic regularization, generalized cross-validation, Stein’s unbiased risk estimator, L-curve.
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
ID Code:16150
Deposited By:Müjdat Çetin
Deposited On:15 Dec 2010 09:17
Last Modified:02 Jan 2012 22:34

Repository Staff Only: item control page