Automatic target recognition using enhanced resolution SAR data

Author

Novak, L.M. ; Owirka, G.J. ; Weaver, A.L.

Author_Institution

Lincoln Lab., MIT, Lexington, MA, USA

Volume

35

Issue

1

fYear

1999

fDate

1/1/1999 12:00:00 AM

Firstpage

157

Lastpage

175

Abstract

Using advanced technology, a new automatic target recognition (ATR) system has been developed that provides significantly improved target recognition performance compared with ATR systems that use conventional synthetic aperture radar (SAR) image-processing techniques. This significant improvement in target recognition performance is achieved by using a new superresolution image-processing technique that enhances SAR image resolution (and image quality) prior to performing target recognition. A computationally efficient two-level implementation of a template-based classifier is used to perform target recognition. The improvement in target recognition performance achieved using superresolution image processing in this new ATR system is quantified

Keywords

feature extraction; image classification; image resolution; mean square error methods; object recognition; radar computing; radar imaging; radar resolution; radar target recognition; synthetic aperture radar; MSE classifier; SAR image resolution; automatic target recognition; computationally efficient two-level implementation; depression angle sensitivity; enhanced resolution SAR data; feature extractor; image quality; near real time; recognition performance; robust false alarm mitigation; superresolution image-processing technique; template-based classifier; thresholding; visualization tools; Image processing; Image quality; Image recognition; Image resolution; Laboratories; Real time systems; Robustness; Synthetic aperture radar; Target recognition; US Government;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems, IEEE Transactions on

Publisher

ieee

ISSN

0018-9251

Type

jour

DOI

10.1109/7.745689

Filename

745689