Share Email Print
cover

Proceedings Paper

Multistage analysis of Meteosat images
Author(s): Steven Dewitte; E. Nyssen; Dominique A.H. Crommelynck; Jan P.H. Cornelis
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a methodology for pixel classification applied to METEOSAT images. It will be used as the first step in the derivation of high space/time resolution ERB (Earth Radiation Budget) images. The classification method combines temporal and spatial analysis with fixed prior knowledge (in the form of a surface properties database) to obtain a final robust unsupervised cloud recognition. The different algorithms which are combined in this methodology are time series greyscale morphology, k-means clustering, median filtering and iterative Bayesian clustering based on discriminant analysis using prior probability functions. The combination of these different algorithms realizes a fuzzy combination of complementary data in a multi-stage (gradual) classification-decision-making process. The outputs of the different classification stages can be validated autonomously. Technical novelties in this approach reside as well in the use of the different algorithms as in the way to combine them.

Paper Details

Date Published: 17 November 1995
PDF: 12 pages
Proc. SPIE 2579, Image and Signal Processing for Remote Sensing II, (17 November 1995); doi: 10.1117/12.226831
Show Author Affiliations
Steven Dewitte, Royal Meteorological Institute of Belgium and Vrije Univ. Brussel (Belgium)
E. Nyssen, Vrije Univ. Brussel (Belgium)
Dominique A.H. Crommelynck, Royal Meteorological Institute of Belgium (Belgium)
Jan P.H. Cornelis, Vrije Univ. Brussel (Belgium)


Published in SPIE Proceedings Vol. 2579:
Image and Signal Processing for Remote Sensing II
Jacky Desachy, Editor(s)

© SPIE. Terms of Use
Back to Top