Analysis of multi- temporal classification techniques for forecasting image time series

Rémi Flamary (1, 2) , Mathieu Fauvel (3) , Mauro Dalla Mura (4) , Silvia Valero (4, 5)

1 OCA - Observatoire de la Côte d'Azur
2 LAGRANGE - Joseph Louis LAGRANGE
3 DYNAFOR - Dynamiques Forestières dans l'Espace Rural
4 GIPSA-SIGMAPHY - GIPSA - Signal Images Physique
5 UPC - Universitat Politècnica de Catalunya = Université polytechnique de Catalogne [Barcelona]

The classification of an annual time series by using data from past years is investigated in this letter. Several classification schemes based on data fusion, sparse learning, and semisupervised learning are proposed to address the problem. Numerical experiments are performed on a Moderate Resolution Imaging Spectroradiometer image time series and show that while several approaches have statistically equivalent performances, a support vector machine with l(1) regularization leads to a better interpretation of the results due to their inherent sparsity in the temporal domain.

Mots clés: classification; satellite image time series; transfer learning

Domaines: Traitement du signal et de l'image [eess.SP]

Rémi Flamary, Mathieu Fauvel, Mauro Dalla Mura, Silvia Valero. Analysis of multi- temporal classification techniques for forecasting image time series. IEEE Geoscience and Remote Sensing Letters, 2015, 12 (5), pp.953-957. ⟨10.1109/LGRS.2014.2368988⟩. ⟨hal-01121476⟩