Identification and characterization of agricultural winter land-use based on Alos-2 and Radarsat-2 polarimetric SAR time-series images

Conference: EUSAR 2018 - 12th European Conference on Synthetic Aperture Radar
06/04/2018 - 06/07/2018 at Aachen, Germany

Proceedings: EUSAR 2018

Pages: 5Language: englishTyp: PDF

Personal VDE Members are entitled to a 10% discount on this title

Authors:
Denize, Julien (University of Rennes & IETR UMR 6164, France)
Hubert-Moy, Laurence; Corgne, Samuel (University of Rennes & LETG UMR 6554, France)
Betbeder, Julie (Cirad UPR 105 Forests & Sociéties, Montpellier, France)
Pottier, Eric (University of Rennes & IETR UMR 6164, France,)

Abstract:
Land cover and land use monitoring, particularly during winter season, is still a major environmental challenge. Indeed, the presence of a vegetation cover, the dates of sowing, the length of the catch crops period, and land use types have an impact on pollutant transport to water bodies. The objective of this study was to evaluate the potential of C- and L-SAR times series to improve the identification and characterization of vegetation cover during winter season. Alos-2 and Radar-sat-2 time-series were classified on a 130km2 site using SVM and RF algorithms. Land-use was classified with an OA of ~ 80 from Radarsat-2 polarimetric images acquired between August 2016 and May 2017 using RF classifier.