Attribute profiles for satellite image time series

Caglayan Tuna (1) , François Merciol (1) , Sébastien Lefèvre (1)

1 OBELIX - Observation de l’environnement par imagerie complexe

Morphological attribute profiles have been one of the most effective image features for spatial-spectral classification of remote sensing images during the last decade. The motivation of this paper is to extend attribute profiles to satellite image time series, i.e. taking into account the temporal information. We introduce different approaches and report their performances for land cover mapping. Experiments are conducted on a Sentinel-2 dataset considering well-established supervised classification methods that are Random Forest and Support Vector Machines.

Mots clés: Index Terms-Attribute profiles; Satellite Image Time Series; Multiscale representation; Land cover mapping

Domaines: Traitement des images [eess.IV]

Caglayan Tuna, François Merciol, Sébastien Lefèvre. Attribute profiles for satellite image time series. IEEE International Geosciences and Remote Sensing Symposium (IGARSS), 2019, Yokohama, Japan. ⟨hal-02343965⟩