Share Email Print
cover

Proceedings Paper

A multispectral spatio-temporal approach for cloud screening of remotely sensed images
Author(s): Paolo Addesso; Roberto Conte; Maurizio Longo; Rocco Restaino; Gemine Vivone
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Information extraction from remotely sensed images acquired in the visible and near-infrared (VNIR) frequency range strongly depends on an accurate cloud pixel screening. Indeed, many remote sensing applications require a preliminary cloud detection phase to obtain profitable results. In this paper we propose to integrate the potential of the MAP-MRF methodology with the multispectral approach for augmenting the capability of the algorithm to detect cloudy pixels. In particular the proposed technique combines information from some SEVIRI sensor channels (in particular the channels 0.64ìm, 1.6ìm, 3.9ìm, 7.3ìm and 10.8ìm) with the classification obtained by the MAP-MRF method in the 0.8ìm channel in order to discriminate between snowy and cloudy pixels. The validation is performed on challenging images of Alps mountains acquired by the SEVIRI sensor during winter months. Results show significant improvements with respect to existing methods. In particular we highlight a more precise classification at the cloud borders and a considerable reduction of unsolicited holes inside the cloud masses.u

Paper Details

Date Published: 26 October 2011
PDF: 11 pages
Proc. SPIE 8177, Remote Sensing of Clouds and the Atmosphere XVI, 81770R (26 October 2011); doi: 10.1117/12.898165
Show Author Affiliations
Paolo Addesso, Univ. degli Studi di Salerno (Italy)
Roberto Conte, Univ. degli Studi di Salerno (Italy)
Maurizio Longo, Univ. degli Studi di Salerno (Italy)
Rocco Restaino, Univ. degli Studi di Salerno (Italy)
Gemine Vivone, Univ. degli Studi di Salerno (Italy)


Published in SPIE Proceedings Vol. 8177:
Remote Sensing of Clouds and the Atmosphere XVI
Evgueni I. Kassianov; Adolfo Comeron; Richard H. Picard; Klaus Schäfer, Editor(s)

© SPIE. Terms of Use
Back to Top