Drift Ice Classification Using SAR Image Data by a Self-Organizing Neural Network

Taketsugu Nagao, Minoru Fukumi, Norio Akamatsu, Yasue Mitsukura

研究成果: Article

抄録

This paper proposes a segmentation method of SAR (Synthetic Aperture Radar) images which uses a SOM(Self-Organizing Map). SAR images are obtained by observation using microwave sensor. They are segmented into the drift ice (thick, thin), and sea regions manually, and then features are extracted from partitioned data. However they are not necessarily effective for neural network learning because they can include incorrectly segmented data. Therefore, in particular, a multi-step SOM is used as a learning method to improve reliability of teacher data, and carries out classification. This process enable us to fix all mistook data and segment the SAR data using just data. The validity of this method was demonstrated by computer simulations using the actual SAR images.

元の言語English
ページ(範囲)800-806
ページ数7
ジャーナルIEEJ Transactions on Electronics, Information and Systems
125
発行部数5
DOI
出版物ステータスPublished - 2005
外部発表Yes

Fingerprint

Synthetic aperture radar
Ice
Neural networks
Self organizing maps
Microwave sensors
Computer simulation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

これを引用

Drift Ice Classification Using SAR Image Data by a Self-Organizing Neural Network. / Nagao, Taketsugu; Fukumi, Minoru; Akamatsu, Norio; Mitsukura, Yasue.

:: IEEJ Transactions on Electronics, Information and Systems, 巻 125, 番号 5, 2005, p. 800-806.

研究成果: Article

@article{8005e1f65d04405fb148d0a91ff26e9c,
title = "Drift Ice Classification Using SAR Image Data by a Self-Organizing Neural Network",
abstract = "This paper proposes a segmentation method of SAR (Synthetic Aperture Radar) images which uses a SOM(Self-Organizing Map). SAR images are obtained by observation using microwave sensor. They are segmented into the drift ice (thick, thin), and sea regions manually, and then features are extracted from partitioned data. However they are not necessarily effective for neural network learning because they can include incorrectly segmented data. Therefore, in particular, a multi-step SOM is used as a learning method to improve reliability of teacher data, and carries out classification. This process enable us to fix all mistook data and segment the SAR data using just data. The validity of this method was demonstrated by computer simulations using the actual SAR images.",
keywords = "Drift Ice, Neural Network, SAR, Self-organizing, SOM",
author = "Taketsugu Nagao and Minoru Fukumi and Norio Akamatsu and Yasue Mitsukura",
year = "2005",
doi = "10.1541/ieejeiss.125.800",
language = "English",
volume = "125",
pages = "800--806",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "5",

}

TY - JOUR

T1 - Drift Ice Classification Using SAR Image Data by a Self-Organizing Neural Network

AU - Nagao, Taketsugu

AU - Fukumi, Minoru

AU - Akamatsu, Norio

AU - Mitsukura, Yasue

PY - 2005

Y1 - 2005

N2 - This paper proposes a segmentation method of SAR (Synthetic Aperture Radar) images which uses a SOM(Self-Organizing Map). SAR images are obtained by observation using microwave sensor. They are segmented into the drift ice (thick, thin), and sea regions manually, and then features are extracted from partitioned data. However they are not necessarily effective for neural network learning because they can include incorrectly segmented data. Therefore, in particular, a multi-step SOM is used as a learning method to improve reliability of teacher data, and carries out classification. This process enable us to fix all mistook data and segment the SAR data using just data. The validity of this method was demonstrated by computer simulations using the actual SAR images.

AB - This paper proposes a segmentation method of SAR (Synthetic Aperture Radar) images which uses a SOM(Self-Organizing Map). SAR images are obtained by observation using microwave sensor. They are segmented into the drift ice (thick, thin), and sea regions manually, and then features are extracted from partitioned data. However they are not necessarily effective for neural network learning because they can include incorrectly segmented data. Therefore, in particular, a multi-step SOM is used as a learning method to improve reliability of teacher data, and carries out classification. This process enable us to fix all mistook data and segment the SAR data using just data. The validity of this method was demonstrated by computer simulations using the actual SAR images.

KW - Drift Ice

KW - Neural Network

KW - SAR

KW - Self-organizing

KW - SOM

UR - http://www.scopus.com/inward/record.url?scp=85024719343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85024719343&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.125.800

DO - 10.1541/ieejeiss.125.800

M3 - Article

AN - SCOPUS:85024719343

VL - 125

SP - 800

EP - 806

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 5

ER -