Spatio-Temporal Mining of PolSAR Satellite Image Time Series - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2010

Spatio-Temporal Mining of PolSAR Satellite Image Time Series

Gabriel Vasile
Michel Gay

Résumé

This paper presents an original data mining approach for describing Satellite Image Time Series (SITS) spa- tially and temporally. It relies on pixel-based evolution and sub-evolution extraction. These evolutions, namely the frequent grouped sequential patterns, are required to cover a minimum surface and to affect pixels that are sufficiently connected. These spatial constraints are ac- tively used to face large data volumes and to select evolu- tions making sense for end-users. In this paper, a specific application to fully polarimetric SAR image time series is presented. Preliminary experiments performed on a RADARSAT-2 SITS covering the Chamonix Mont-Blanc test-site are used to illustrate the proposed approach.
Fichier non déposé

Dates et versions

hal-00504655 , version 1 (21-07-2010)

Identifiants

  • HAL Id : hal-00504655 , version 1

Citer

Andreea Julea, Nicolas Méger, Emmanuel Trouvé, Philippe Bolon, Christophe Rigotti, et al.. Spatio-Temporal Mining of PolSAR Satellite Image Time Series. The 2010 European Space Agency Living Planet Symposium, Jun 2010, Bergen, Norway. pp.6. ⟨hal-00504655⟩
570 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More