Application and performance of convolutional neural networks to SAR

Maxine R. Fox, Ram M. Narayanan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Implementation of convolutional neural networks (CNNs) as classifiers has only recently found application in SAR multi-target classification. Despite the creation of several successful architectures, a general approach to CNN design and training has not been determined. In this paper, the basics of CNN architecture and learning algorithms are discussed. The MSTAR data set is used to demonstrate the effect of individual parameter changes to overall network performance.

Original languageEnglish (US)
Title of host publicationRadar Sensor Technology XXII
EditorsArmin Doerry, Kenneth I. Ranney
PublisherSPIE
ISBN (Electronic)9781510617773
DOIs
StatePublished - Jan 1 2018
EventRadar Sensor Technology XXII 2018 - Orlando, United States
Duration: Apr 16 2018Apr 18 2018

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume10633
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherRadar Sensor Technology XXII 2018
CountryUnited States
CityOrlando
Period4/16/184/18/18

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Application and performance of convolutional neural networks to SAR'. Together they form a unique fingerprint.

  • Cite this

    Fox, M. R., & Narayanan, R. M. (2018). Application and performance of convolutional neural networks to SAR. In A. Doerry, & K. I. Ranney (Eds.), Radar Sensor Technology XXII [1063304] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10633). SPIE. https://doi.org/10.1117/12.2305852