Introduction
The data received from weather satellites are used in weather forecasting
and long-term prediction by the Finnish Meteorological Institute.
The main motivation for the present study was the need for automatic
methods to interpretate satellite images.
This has been studied in Laboratory of Computer and Information Science in
Helsinki University of Technology
since 1991. The main interest has been
the classification of clouds from satellite images.
As a result a cloud classifier is implemented.
The classifier is a multispectral, vector-based classifier.
The classification of a satellite image is done in two phases.
In the first phase clouds are separated from surface
and in the second phase the cloudy regions are classified into ten cloud types.
The classifier is fully automatic, and it can be adapted to changing
situations with new examples.
|
 |
