Application of neural network approach to classify multi-temporal Landsat images

Seiichiro Kamata, Eiji Kawaguchi

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

2 Citations (Scopus)

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 use the spectral and spacial 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 a normalization method. From our experiments, we confirmed that the NN approach with the preprocessing is more effective for the classification than the original NN approach even if the test data is taken at the different time.

Original languageEnglish
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
EditorsSadao Fujimura
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages716-718
Number of pages3
Volume2
ISBN (Print)0780312406
Publication statusPublished - 1993
Externally publishedYes
EventProceedings of the 13th Annual International Geoscience and Remote Sensing Symposium - Tokyo, Jpn
Duration: 1993 Aug 181993 Aug 21

Other

OtherProceedings of the 13th Annual International Geoscience and Remote Sensing Symposium
CityTokyo, Jpn
Period93/8/1893/8/21

Fingerprint

Landsat
Neural networks
Statistical methods
experiment
method
Experiments

ASJC Scopus subject areas

  • Software
  • Geology

Cite this

Kamata, S., & Kawaguchi, E. (1993). Application of neural network approach to classify multi-temporal Landsat images. In S. Fujimura (Ed.), International Geoscience and Remote Sensing Symposium (IGARSS) (Vol. 2, pp. 716-718). Piscataway, NJ, United States: Publ by IEEE.

Application of neural network approach to classify multi-temporal Landsat images. / Kamata, Seiichiro; Kawaguchi, Eiji.

International Geoscience and Remote Sensing Symposium (IGARSS). ed. / Sadao Fujimura. Vol. 2 Piscataway, NJ, United States : Publ by IEEE, 1993. p. 716-718.

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

Kamata, S & Kawaguchi, E 1993, Application of neural network approach to classify multi-temporal Landsat images. in S Fujimura (ed.), International Geoscience and Remote Sensing Symposium (IGARSS). vol. 2, Publ by IEEE, Piscataway, NJ, United States, pp. 716-718, Proceedings of the 13th Annual International Geoscience and Remote Sensing Symposium, Tokyo, Jpn, 93/8/18.
Kamata S, Kawaguchi E. Application of neural network approach to classify multi-temporal Landsat images. In Fujimura S, editor, International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 2. Piscataway, NJ, United States: Publ by IEEE. 1993. p. 716-718
Kamata, Seiichiro ; Kawaguchi, Eiji. / Application of neural network approach to classify multi-temporal Landsat images. International Geoscience and Remote Sensing Symposium (IGARSS). editor / Sadao Fujimura. Vol. 2 Piscataway, NJ, United States : Publ by IEEE, 1993. pp. 716-718
@inproceedings{683f70d207834ec9a5550c72563ca216,
title = "Application of neural network approach to classify multi-temporal Landsat images",
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 use the spectral and spacial 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 a normalization method. From our experiments, we confirmed that the NN approach with the preprocessing 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 = "0780312406",
volume = "2",
pages = "716--718",
editor = "Sadao Fujimura",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Application of neural network approach to classify multi-temporal Landsat images

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 use the spectral and spacial 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 a normalization method. From our experiments, we confirmed that the NN approach with the preprocessing 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 use the spectral and spacial 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 a normalization method. From our experiments, we confirmed that the NN approach with the preprocessing 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=0027871840&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027871840&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780312406

VL - 2

SP - 716

EP - 718

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

A2 - Fujimura, Sadao

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -