Statistical target behaviour in SAR images

Author

Blacknell, D.

Author_Institution

Defence Evaluation & Res. Agency, Malvern, UK

Volume

147

Issue

3

fYear

2000

fDate

6/1/2000 12:00:00 AM

Firstpage

143

Lastpage

148

Abstract

The paper discusses the statistical behaviour of targets in synthetic aperture radar (SAR) images and demonstrates how this information can be exploited for automatic SAR target classification and recognition. It describes a target-smoothing algorithm for estimating the underlying radar cross-section, which can be used with an appropriate noise model to generate many target realisations for a given imaging configuration. This allows a statistical analysis of target features to be performed that can be used to enhance feature-based classification, as is demonstrated by a simple classification experiment using real targets

Keywords

image classification; image recognition; image resolution; noise; radar cross-sections; radar imaging; radar target recognition; smoothing methods; statistical analysis; synthetic aperture radar; RCS estimation; SAR images; automatic SAR target classification; automatic SAR target recognition; classification experiment; feature-based classification; high-resolution radar; imaging configuration; military surveillance tasks; noise model; radar cross-section; real targets; statistical analysis; statistical behaviour; statistical target behaviour; synthetic aperture radar; target features; target-smoothing algorithm;

fLanguage

English

Journal_Title

Radar, Sonar and Navigation, IEE Proceedings -

Publisher

iet

ISSN

1350-2395

Type

jour

DOI

10.1049/ip-rsn:20000321

Filename

850810