Drift ice recognition using remote sensing data by neural networks

T. Nagao, Yasue Mitsukura, M. Fukumi, N. Akamatsu

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

2 Citations (Scopus)

Abstract

In recent years, observation of a wide variety in the Earth's surface can be done by improvement of remote sensing technology. The purpose of the paper is to recognize a drift ice as thick ice, thin ice, and sea using synthetic aperture radar (SAR) images. The recognition of the drift ice is achieved by using neural networks (NN). The neural network applies two methods, a BP trained neural network and a self-organizing map. Training data are image features extracted from SAR images. There are three methods for extracting the features: Fourier transform, high-order autocorrelation function (HACF), and image features based on a run length method. We carry out a comparative experiment, and demonstrate their effectiveness by means of computer simulation.

Original languageEnglish
Title of host publicationICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages645-649
Number of pages5
Volume2
ISBN (Print)9810475241, 9789810475246
DOIs
Publication statusPublished - 2002
Externally publishedYes
Event9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore
Duration: 2002 Nov 182002 Nov 22

Other

Other9th International Conference on Neural Information Processing, ICONIP 2002
CountrySingapore
CitySingapore
Period02/11/1802/11/22

Fingerprint

Ice
Remote sensing
Neural networks
Synthetic aperture radar
Self organizing maps
Autocorrelation
Fourier transforms
Earth (planet)
Computer simulation
Experiments

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems
  • Signal Processing

Cite this

Nagao, T., Mitsukura, Y., Fukumi, M., & Akamatsu, N. (2002). Drift ice recognition using remote sensing data by neural networks. In ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (Vol. 2, pp. 645-649). [1198137] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1198137

Drift ice recognition using remote sensing data by neural networks. / Nagao, T.; Mitsukura, Yasue; Fukumi, M.; Akamatsu, N.

ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2002. p. 645-649 1198137.

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

Nagao, T, Mitsukura, Y, Fukumi, M & Akamatsu, N 2002, Drift ice recognition using remote sensing data by neural networks. in ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. vol. 2, 1198137, Institute of Electrical and Electronics Engineers Inc., pp. 645-649, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 02/11/18. https://doi.org/10.1109/ICONIP.2002.1198137
Nagao T, Mitsukura Y, Fukumi M, Akamatsu N. Drift ice recognition using remote sensing data by neural networks. In ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Vol. 2. Institute of Electrical and Electronics Engineers Inc. 2002. p. 645-649. 1198137 https://doi.org/10.1109/ICONIP.2002.1198137
Nagao, T. ; Mitsukura, Yasue ; Fukumi, M. ; Akamatsu, N. / Drift ice recognition using remote sensing data by neural networks. ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 2002. pp. 645-649
@inproceedings{a1574607ea1044a1a9c62b40b07e2f72,
title = "Drift ice recognition using remote sensing data by neural networks",
abstract = "In recent years, observation of a wide variety in the Earth's surface can be done by improvement of remote sensing technology. The purpose of the paper is to recognize a drift ice as thick ice, thin ice, and sea using synthetic aperture radar (SAR) images. The recognition of the drift ice is achieved by using neural networks (NN). The neural network applies two methods, a BP trained neural network and a self-organizing map. Training data are image features extracted from SAR images. There are three methods for extracting the features: Fourier transform, high-order autocorrelation function (HACF), and image features based on a run length method. We carry out a comparative experiment, and demonstrate their effectiveness by means of computer simulation.",
author = "T. Nagao and Yasue Mitsukura and M. Fukumi and N. Akamatsu",
year = "2002",
doi = "10.1109/ICONIP.2002.1198137",
language = "English",
isbn = "9810475241",
volume = "2",
pages = "645--649",
booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Drift ice recognition using remote sensing data by neural networks

AU - Nagao, T.

AU - Mitsukura, Yasue

AU - Fukumi, M.

AU - Akamatsu, N.

PY - 2002

Y1 - 2002

N2 - In recent years, observation of a wide variety in the Earth's surface can be done by improvement of remote sensing technology. The purpose of the paper is to recognize a drift ice as thick ice, thin ice, and sea using synthetic aperture radar (SAR) images. The recognition of the drift ice is achieved by using neural networks (NN). The neural network applies two methods, a BP trained neural network and a self-organizing map. Training data are image features extracted from SAR images. There are three methods for extracting the features: Fourier transform, high-order autocorrelation function (HACF), and image features based on a run length method. We carry out a comparative experiment, and demonstrate their effectiveness by means of computer simulation.

AB - In recent years, observation of a wide variety in the Earth's surface can be done by improvement of remote sensing technology. The purpose of the paper is to recognize a drift ice as thick ice, thin ice, and sea using synthetic aperture radar (SAR) images. The recognition of the drift ice is achieved by using neural networks (NN). The neural network applies two methods, a BP trained neural network and a self-organizing map. Training data are image features extracted from SAR images. There are three methods for extracting the features: Fourier transform, high-order autocorrelation function (HACF), and image features based on a run length method. We carry out a comparative experiment, and demonstrate their effectiveness by means of computer simulation.

UR - http://www.scopus.com/inward/record.url?scp=84964443413&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964443413&partnerID=8YFLogxK

U2 - 10.1109/ICONIP.2002.1198137

DO - 10.1109/ICONIP.2002.1198137

M3 - Conference contribution

AN - SCOPUS:84964443413

SN - 9810475241

SN - 9789810475246

VL - 2

SP - 645

EP - 649

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

PB - Institute of Electrical and Electronics Engineers Inc.

ER -