Application and performance of convolutional neural networks to SAR

Maxine R. Fox, Ram Mohan 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

Fingerprint

Neural Networks
Neural networks
Network Performance
Network Architecture
Network Design
Network performance
Network architecture
Learning algorithms
Learning Algorithm
Classifiers
classifiers
Classifier
learning
Target
education
Demonstrate
Architecture
Training

All Science Journal Classification (ASJC) codes

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

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
Fox, Maxine R. ; Narayanan, Ram Mohan. / Application and performance of convolutional neural networks to SAR. Radar Sensor Technology XXII. editor / Armin Doerry ; Kenneth I. Ranney. SPIE, 2018. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{165fae1c0bba4c528efea289c2a7b27e,
title = "Application and performance of convolutional neural networks to SAR",
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.",
author = "Fox, {Maxine R.} and Narayanan, {Ram Mohan}",
year = "2018",
month = "1",
day = "1",
doi = "10.1117/12.2305852",
language = "English (US)",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Armin Doerry and Ranney, {Kenneth I.}",
booktitle = "Radar Sensor Technology XXII",
address = "United States",

}

Fox, MR & Narayanan, RM 2018, Application and performance of convolutional neural networks to SAR. in A Doerry & KI Ranney (eds), Radar Sensor Technology XXII., 1063304, Proceedings of SPIE - The International Society for Optical Engineering, vol. 10633, SPIE, Radar Sensor Technology XXII 2018, Orlando, United States, 4/16/18. https://doi.org/10.1117/12.2305852

Application and performance of convolutional neural networks to SAR. / Fox, Maxine R.; Narayanan, Ram Mohan.

Radar Sensor Technology XXII. ed. / Armin Doerry; Kenneth I. Ranney. SPIE, 2018. 1063304 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 10633).

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

TY - GEN

T1 - Application and performance of convolutional neural networks to SAR

AU - Fox, Maxine R.

AU - Narayanan, Ram Mohan

PY - 2018/1/1

Y1 - 2018/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85050031098&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050031098&partnerID=8YFLogxK

U2 - 10.1117/12.2305852

DO - 10.1117/12.2305852

M3 - Conference contribution

AN - SCOPUS:85050031098

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Radar Sensor Technology XXII

A2 - Doerry, Armin

A2 - Ranney, Kenneth I.

PB - SPIE

ER -

Fox MR, Narayanan RM. Application and performance of convolutional neural networks to SAR. In Doerry A, Ranney KI, editors, Radar Sensor Technology XXII. SPIE. 2018. 1063304. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2305852