Determination of spatial and temporal characteristics as an aid to neural network cloud classification
Determination of spatial and temporal characteristics as an aid to neural network cloud classification
Previous studies of cloud classification from meteorological satellite imagery have shown that artificial neural networks (ANNs) perform as well as, or better than, statistical pattern recognition when multispectral features, supplemented with selected textural features, are used. These features, however, represent only a subset of the full range of features available in this imagery. Spatial characteristics based on the shape of clouds, and temporal characteristics, derived from image sequences, can be more direct pointers to cloud type. In this paper the methods for the determination of such parameters are described, some results are presented, and the effectiveness of the methods are discussed.
899-915
Lewis, H.G.
e9048cd8-c188-49cb-8e2a-45f6b316336a
Cote, S.
ffd99deb-a9e2-4469-9335-fce9b3f477a9
Tatnall, A.R.L.
8b3b9a71-2bc4-459d-8af2-67feb6b984fe
1997
Lewis, H.G.
e9048cd8-c188-49cb-8e2a-45f6b316336a
Cote, S.
ffd99deb-a9e2-4469-9335-fce9b3f477a9
Tatnall, A.R.L.
8b3b9a71-2bc4-459d-8af2-67feb6b984fe
Lewis, H.G., Cote, S. and Tatnall, A.R.L.
(1997)
Determination of spatial and temporal characteristics as an aid to neural network cloud classification.
International Journal of Remote Sensing, 18 (4), .
(doi:10.1080/014311697218827).
Abstract
Previous studies of cloud classification from meteorological satellite imagery have shown that artificial neural networks (ANNs) perform as well as, or better than, statistical pattern recognition when multispectral features, supplemented with selected textural features, are used. These features, however, represent only a subset of the full range of features available in this imagery. Spatial characteristics based on the shape of clouds, and temporal characteristics, derived from image sequences, can be more direct pointers to cloud type. In this paper the methods for the determination of such parameters are described, some results are presented, and the effectiveness of the methods are discussed.
This record has no associated files available for download.
More information
Published date: 1997
Identifiers
Local EPrints ID: 23620
URI: http://eprints.soton.ac.uk/id/eprint/23620
ISSN: 0143-1161
PURE UUID: b8b00187-40d9-4aac-a303-fb05cd4e0c7c
Catalogue record
Date deposited: 31 Jan 2007
Last modified: 26 Jul 2022 01:35
Export record
Altmetrics
Contributors
Author:
S. Cote
Author:
A.R.L. Tatnall
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics