Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information

Seiichiro Kamata, Eiji Kawaguchi

研究成果: Conference contribution

5 引用 (Scopus)

抄録

The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spatial information. In this paper, we apply the NN approach to the classification of multi-temporal LANDSAT TM images in order to investigate the robustness of two normalization methods using spectral and spatial information. From our experiments, we confirmed that the NN approach with the preprocess is more effective for the classification than the original NN approach even if the test data is taken at the different time.

元の言語English
ホスト出版物のタイトルProceedings of the International Joint Conference on Neural Networks
出版場所Piscataway, NJ, United States
出版者Publ by IEEE
ページ2199-2202
ページ数4
3
ISBN(印刷物)0780314212, 9780780314214
出版物ステータスPublished - 1993
外部発表Yes
イベントProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
継続期間: 1993 10 251993 10 29

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
Nagoya, Jpn
期間93/10/2593/10/29

Fingerprint

Classifiers
Neural networks
Statistical methods
Experiments

ASJC Scopus subject areas

  • Engineering(all)

これを引用

Kamata, S., & Kawaguchi, E. (1993). Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information. : Proceedings of the International Joint Conference on Neural Networks (巻 3, pp. 2199-2202). Piscataway, NJ, United States: Publ by IEEE.

Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information. / Kamata, Seiichiro; Kawaguchi, Eiji.

Proceedings of the International Joint Conference on Neural Networks. 巻 3 Piscataway, NJ, United States : Publ by IEEE, 1993. p. 2199-2202.

研究成果: Conference contribution

Kamata, S & Kawaguchi, E 1993, Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information. : Proceedings of the International Joint Conference on Neural Networks. 巻. 3, Publ by IEEE, Piscataway, NJ, United States, pp. 2199-2202, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 93/10/25.
Kamata S, Kawaguchi E. Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information. : Proceedings of the International Joint Conference on Neural Networks. 巻 3. Piscataway, NJ, United States: Publ by IEEE. 1993. p. 2199-2202
Kamata, Seiichiro ; Kawaguchi, Eiji. / Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information. Proceedings of the International Joint Conference on Neural Networks. 巻 3 Piscataway, NJ, United States : Publ by IEEE, 1993. pp. 2199-2202
@inproceedings{964835c1db1b465289364d5f5b685da7,
title = "Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information",
abstract = "The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spatial information. In this paper, we apply the NN approach to the classification of multi-temporal LANDSAT TM images in order to investigate the robustness of two normalization methods using spectral and spatial information. From our experiments, we confirmed that the NN approach with the preprocess is more effective for the classification than the original NN approach even if the test data is taken at the different time.",
author = "Seiichiro Kamata and Eiji Kawaguchi",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "3",
pages = "2199--2202",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Neural net classifier for multi-temporal LANDSAT images using spacial and spectral information

AU - Kamata, Seiichiro

AU - Kawaguchi, Eiji

PY - 1993

Y1 - 1993

N2 - The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spatial information. In this paper, we apply the NN approach to the classification of multi-temporal LANDSAT TM images in order to investigate the robustness of two normalization methods using spectral and spatial information. From our experiments, we confirmed that the NN approach with the preprocess is more effective for the classification than the original NN approach even if the test data is taken at the different time.

AB - The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. We have proposed an NN model to combine the spectral and spatial information. In this paper, we apply the NN approach to the classification of multi-temporal LANDSAT TM images in order to investigate the robustness of two normalization methods using spectral and spatial information. From our experiments, we confirmed that the NN approach with the preprocess is more effective for the classification than the original NN approach even if the test data is taken at the different time.

UR - http://www.scopus.com/inward/record.url?scp=0027797757&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027797757&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027797757

SN - 0780314212

SN - 9780780314214

VL - 3

SP - 2199

EP - 2202

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -