Investigation of TERRASAR-X and RADARSAT-2 DATA for river ice classification.

Mermoz, Stéphane; Allain, Sophie; Bernier, Monique et Pottier, Éric (2009). Investigation of TERRASAR-X and RADARSAT-2 DATA for river ice classification. In: IEEE International Geoscience and Remote Sensing Symposium - IGARSS'2009, 13-17 juillet 2009, Cape Town, Afrique du Sud.

Prévisualisation

PDF Télécharger (273kB) | Prévisualisation

Résumé

To date, monitoring of river ice using remote sensing has mainly focused on the use of mono-polarized and multipolarized C-band radar data only. In this paper, Support Vector Machine (SVM) classifications using polarimetric parameters are tested to identify types of river ice. Classification algorithms are validated on the newly available C-band Radarsat-2 and X-band Terrasar-X data to investigate the potential of this new imagery, acquired in winter 2009. An electromagnetic model is improved to simulate the polarimetric response of a river ice cover to understand the interactions of the radar signal with the ice cover. At C-band, using dualpolarized data over mono-polarized data increases by 23.9% the final classification producer accuracy. Furthermore, the best producer accuracy is 91.6% when using dual-pol data at C-band, which stand for a gain of 2.2% compared to dual-pol data at X-band

Type de document:	Document issu d'une conférence ou d'un atelier
Mots-clés libres:	river ice; classification; PolSAR data; electromagnetic model
Centre:	Centre Eau Terre Environnement
Date de dépôt:	09 déc. 2019 21:10
Dernière modification:	20 avr. 2021 14:42
URI:	https://espace.inrs.ca/id/eprint/4763

Gestion Actions (Identification requise)

Modifier la notice