Object-based SAR image compression using vector quantization

Author

Venkatraman, Mahesh ; Kwon, Heesung ; Nasrabadi, Nasser M.

Author_Institution

Berkeley Concept Res. Corp., CA, USA

Volume

36

Issue

4

fYear

2000

fDate

10/1/2000 12:00:00 AM

Firstpage

1036

Lastpage

1046

Abstract

A simple and elegant algorithm is presented to encode images with rich content, which allows easy access to various objects. An object-plane-based encoding method for compression of synthetic aperture radar (SAR) imagery is developed, with different object planes for target classes and background. A variable-rate residual vector quantization (VQ) algorithm is developed to encode the background information. This algorithm is very powerful as indicated by the experimental results. The proposed coding scheme allows compression matched to the final application of the images, which in this case is target recognition and classification.

Keywords

image coding; neural nets; radar computing; radar imaging; radar target recognition; synthetic aperture radar; vector quantisation; background information; backpropagation; layer segmentation; lossy compression; multiple object planes; nonlinear neural network predictor; object-based SAR image compression; object-plane-based encoding method; software simulation; target classification; target recognition; variable-rate residual VQ algorithm; vector quantization; Bandwidth; Image coding; Laboratories; Object detection; Powders; Pulse modulation; Satellite ground stations; Synthetic aperture radar; Target recognition; Vector quantization;

fLanguage

English

Journal_Title

Aerospace and Electronic Systems, IEEE Transactions on

Publisher

ieee

ISSN

0018-9251

Type

jour

DOI

10.1109/7.892656

Filename

892656