SAR automatic target recognition based on convolutional neural networks

Date published

2018-05-28

Free to read from

Supervisor/s

Journal Title

Journal ISSN

Volume Title

Publisher

IEEE

Department

Type

Conference paper

ISSN

Format

Citation

O Kechagias-Stamatis, N Aouf and CDL Belloni. SAR automatic target recognition based on convolutional neural networks. In: IET International Conference on Radar Systems (Radar 2017), Belfast, 23-26 October 2017

Abstract

We propose a multi-modal multi-discipline strategy appropriate for Automatic Target Recognition (ATR) on Synthetic Aperture Radar (SAR) imagery. Our architecture relies on a pre-trained, in the RGB domain, Convolutional Neural Network that is innovatively applied on SAR imagery, and is combined with multiclass Support Vector Machine classification. The multi-modal aspect of our architecture enforces the generalisation capabilities of our proposal, while the multi-discipline aspect bridges the modality gap. Even though our technique is trained in a single depression angle of 17°, average performance on the MSTAR database over a 10-class target classification problem in 15°, 30° and 45° depression is 97.8%. This multi-target and multi-depression ATR capability has not been reported yet in the MSTAR database literature.

Description

Software Description

Software Language

Github

Keywords

Automatic Target recognition, Convolutional Neural Networks, Deep Learning, Support Vector Machine, Synthetic Aperture Radar

DOI

Rights

Attribution-NonCommercial 4.0 International

Relationships

Relationships

Supplements

Funder/s