Share Email Print
cover

Proceedings Paper

Deep convolutional neural networks for ATR from SAR imagery
Author(s): David A. E. Morgan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Deep architectures for classification and representation learning have recently attracted significant attention within academia and industry, with many impressive results across a diverse collection of problem sets. In this work we consider the specific application of Automatic Target Recognition (ATR) using Synthetic Aperture Radar (SAR) data from the MSTAR public release data set. The classification performance achieved using a Deep Convolutional Neural Network (CNN) on this data set was found to be competitive with existing methods considered to be state-of-the-art. Unlike most existing algorithms, this approach can learn discriminative feature sets directly from training data instead of requiring pre-specification or pre-selection by a human designer. We show how this property can be exploited to efficiently adapt an existing classifier to recognise a previously unseen target and discuss potential practical applications.

Paper Details

Date Published: 13 May 2015
PDF: 13 pages
Proc. SPIE 9475, Algorithms for Synthetic Aperture Radar Imagery XXII, 94750F (13 May 2015); doi: 10.1117/12.2176558
Show Author Affiliations
David A. E. Morgan, BAE Systems (United Kingdom)


Published in SPIE Proceedings Vol. 9475:
Algorithms for Synthetic Aperture Radar Imagery XXII
Edmund Zelnio; Frederick D. Garber, Editor(s)

© SPIE. Terms of Use
Back to Top