A Neural Net Classifier for Multi-Temporal LANDSAT TM Images

Sei-ichiro KAMATA; Eiji KAWAGUCHI

A Neural Net Classifier for Multi-Temporal LANDSAT TM Images

Sei-ichiro KAMATA, Eiji KAWAGUCHI

Full Text Views

0

Cite this

Summary :

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 spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.

Publication: IEICE TRANSACTIONS on Information Vol.E78-D No.10 pp.1295-1300

Publication Date: 1995/10/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Processing, Computer Graphics and Pattern Recognition

Cite this

Copy

Sei-ichiro KAMATA, Eiji KAWAGUCHI, "A Neural Net Classifier for Multi-Temporal LANDSAT TM Images" in IEICE TRANSACTIONS on Information, vol. E78-D, no. 10, pp. 1295-1300, October 1995, doi: .
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 spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.
URL: https://global.ieice.org/en_transactions/information/10.1587/e78-d_10_1295/_p

Copy

@ARTICLE{e78-d_10_1295,
author={Sei-ichiro KAMATA, Eiji KAWAGUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={A Neural Net Classifier for Multi-Temporal LANDSAT TM Images},
year={1995},
volume={E78-D},
number={10},
pages={1295-1300},
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 spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.},
keywords={},
doi={},
ISSN={},
month={October},}

Copy

TY - JOUR
TI - A Neural Net Classifier for Multi-Temporal LANDSAT TM Images
T2 - IEICE TRANSACTIONS on Information
SP - 1295
EP - 1300
AU - Sei-ichiro KAMATA
AU - Eiji KAWAGUCHI
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E78-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 1995
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 spacial information of a LANDSAT TM image. In this paper, we apply the NN approach with a normalization method to classify multi-temporal LANDSAT TM images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN approach and maximum likelihood approach.
ER -