Stochastic configuration network-based SAR image target classification approach
Synthetic aperture radar (SAR) image interpretation is a great scientific application challenge. The classification of SAR image targets has become one of the main research directions for SAR image interpretation. Therefore, achieving fast and accurate SAR image target classification has always been...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-09-01
|
Series: | The Journal of Engineering |
Subjects: | |
Online Access: | https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0683 |
id |
doaj-a7996c697aec47d1a1e9c6e5e6abea59 |
---|---|
record_format |
Article |
spelling |
doaj-a7996c697aec47d1a1e9c6e5e6abea592021-04-02T11:15:52ZengWileyThe Journal of Engineering2051-33052019-09-0110.1049/joe.2019.0683JOE.2019.0683Stochastic configuration network-based SAR image target classification approachYan P. Wang0Yi B. Zhang1Yuan Zhang2Jun Fan3Hong Q. Qu4North China University of TechnologyNorth China University of TechnologyNorth China University of TechnologyArmy aviation Research InstituteNorth China University of TechnologySynthetic aperture radar (SAR) image interpretation is a great scientific application challenge. The classification of SAR image targets has become one of the main research directions for SAR image interpretation. Therefore, achieving fast and accurate SAR image target classification has always been a research hotspot in this field. Here, the authors propose a classification method based on a regularised stochastic configuration network (SCN), which randomly assigns the input weights and biases with constraint and finds out the output weights all together by solving a global least squares problem. Experimental results on the moving and stationary target acquisition and recognition benchmark dataset illustrate that the regularised SCN classifies ten-class targets to achieve an accuracy of 94.6%. It is significantly superior to the traditional SCN model and effectively improves the generalisation ability of the network.https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0683synthetic aperture radarpattern classificationradar imagingimage classificationstochastic configuration network-based sar image target classification approachsynthetic aperture radar image interpretationten-class targetsrecognition benchmark datasetstationary target acquisitionregularised stochastic configuration networkclassification methodaccurate sar image target classificationsar image interpretationmain research directionssar image targetsgreat scientific application challenge |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yan P. Wang Yi B. Zhang Yuan Zhang Jun Fan Hong Q. Qu |
spellingShingle |
Yan P. Wang Yi B. Zhang Yuan Zhang Jun Fan Hong Q. Qu Stochastic configuration network-based SAR image target classification approach The Journal of Engineering synthetic aperture radar pattern classification radar imaging image classification stochastic configuration network-based sar image target classification approach synthetic aperture radar image interpretation ten-class targets recognition benchmark dataset stationary target acquisition regularised stochastic configuration network classification method accurate sar image target classification sar image interpretation main research directions sar image targets great scientific application challenge |
author_facet |
Yan P. Wang Yi B. Zhang Yuan Zhang Jun Fan Hong Q. Qu |
author_sort |
Yan P. Wang |
title |
Stochastic configuration network-based SAR image target classification approach |
title_short |
Stochastic configuration network-based SAR image target classification approach |
title_full |
Stochastic configuration network-based SAR image target classification approach |
title_fullStr |
Stochastic configuration network-based SAR image target classification approach |
title_full_unstemmed |
Stochastic configuration network-based SAR image target classification approach |
title_sort |
stochastic configuration network-based sar image target classification approach |
publisher |
Wiley |
series |
The Journal of Engineering |
issn |
2051-3305 |
publishDate |
2019-09-01 |
description |
Synthetic aperture radar (SAR) image interpretation is a great scientific application challenge. The classification of SAR image targets has become one of the main research directions for SAR image interpretation. Therefore, achieving fast and accurate SAR image target classification has always been a research hotspot in this field. Here, the authors propose a classification method based on a regularised stochastic configuration network (SCN), which randomly assigns the input weights and biases with constraint and finds out the output weights all together by solving a global least squares problem. Experimental results on the moving and stationary target acquisition and recognition benchmark dataset illustrate that the regularised SCN classifies ten-class targets to achieve an accuracy of 94.6%. It is significantly superior to the traditional SCN model and effectively improves the generalisation ability of the network. |
topic |
synthetic aperture radar pattern classification radar imaging image classification stochastic configuration network-based sar image target classification approach synthetic aperture radar image interpretation ten-class targets recognition benchmark dataset stationary target acquisition regularised stochastic configuration network classification method accurate sar image target classification sar image interpretation main research directions sar image targets great scientific application challenge |
url |
https://digital-library.theiet.org/content/journals/10.1049/joe.2019.0683 |
work_keys_str_mv |
AT yanpwang stochasticconfigurationnetworkbasedsarimagetargetclassificationapproach AT yibzhang stochasticconfigurationnetworkbasedsarimagetargetclassificationapproach AT yuanzhang stochasticconfigurationnetworkbasedsarimagetargetclassificationapproach AT junfan stochasticconfigurationnetworkbasedsarimagetargetclassificationapproach AT hongqqu stochasticconfigurationnetworkbasedsarimagetargetclassificationapproach |
_version_ |
1724165267736494080 |