Share Email Print

Proceedings Paper

Contextual methods for multisource land cover classification with application to Radarsat and SPOT data
Author(s): Danielle Ducrot; Hugues Sassier; Juste Mombo; Stephane Goze; Jean-Guy Planes
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

For the classification of the radar data, several techniques have been developed, which take the statistical properties of the radar distribution into account and use a priori segmentation to have better contextual information. The introduction of synthetic neo-channels, describing the local texture of radar images, improve the classification process. We also test two different processes to minimize the inter- class confusion caused by the speckle noise: a pixel-by-pixel basis classification which requires a preliminary spatial and/or temporal speckle filtering, or a contextual method without filtering. In the case of the multi-source data classification, we present a fusion algorithm which consists in implementing different statistical rules for radar or optical images.

Paper Details

Date Published: 4 December 1998
PDF: 12 pages
Proc. SPIE 3500, Image and Signal Processing for Remote Sensing IV, (4 December 1998); doi: 10.1117/12.331867
Show Author Affiliations
Danielle Ducrot, Ctr. d'Etude Spatiale de la Biosphere (France)
Hugues Sassier, Ctr. d'Etude Spatiale de la Biosphere and Alcatel Espace (France)
Juste Mombo, Ctr. d'Etude Spatiale de la Biosphere (France)
Stephane Goze, Alcatel Espace (France)
Jean-Guy Planes, Alcatel Espace (France)

Published in SPIE Proceedings Vol. 3500:
Image and Signal Processing for Remote Sensing IV
Sebastiano Bruno Serpico, Editor(s)

© SPIE. Terms of Use
Back to Top