Modern approaches in deep learning for SAR ATR

Michael Wilmanski; Chris Kreucher; Jim Lauer

doi:10.1117/12.2220290

14 May 2016 Modern approaches in deep learning for SAR ATR

Michael Wilmanski, Chris Kreucher, Jim Lauer

Proceedings Volume 9843, Algorithms for Synthetic Aperture Radar Imagery XXIII; 98430N (2016) https://doi.org/10.1117/12.2220290
Event: SPIE Defense + Security, 2016, Baltimore, MD, United States

Abstract

Recent breakthroughs in computational capabilities and optimization algorithms have enabled a new class of signal processing approaches based on deep neural networks (DNNs). These algorithms have been extremely successful in the classification of natural images, audio, and text data. In particular, a special type of DNNs, called convolutional neural networks (CNNs) have recently shown superior performance for object recognition in image processing applications. This paper discusses modern training approaches adopted from the image processing literature and shows how those approaches enable significantly improved performance for synthetic aperture radar (SAR) automatic target recognition (ATR). In particular, we show how a set of novel enhancements to the learning algorithm, based on new stochastic gradient descent approaches, generate significant classification improvement over previously published results on a standard dataset called MSTAR.

Citation Download Citation

Michael Wilmanski, Chris Kreucher, and Jim Lauer "Modern approaches in deep learning for SAR ATR", Proc. SPIE 9843, Algorithms for Synthetic Aperture Radar Imagery XXIII, 98430N (14 May 2016); https://doi.org/10.1117/12.2220290

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available