Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Transactions on Geoscience and Remote Sensing Year : 2021

Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series

Abstract

Recent satellite missions have led to a huge amount of earth observation data, most of them being freely available. In such a context, satellite image time series have been used to study land use and land cover information. However, optical time series, like Sentinel-2 or Landsat ones, are provided with an irregular time sampling for different spatial locations, and images may contain clouds and shadows. Thus, pre-processing techniques are usually required to properly classify such data. The proposed approach is able to deal with irregular temporal sampling and missing data directly in the classification process. It is based on Gaussian processes and allows to perform jointly the classification of the pixel labels as well as the reconstruction of the pixel time series. The method complexity scales linearly with the number of pixels, making it amenable in large scale scenarios. Experimental classification and reconstruction results show that the method does not compete yet with state of the art classifiers but yields reconstructions that are robust with respect to the presence of undetected clouds or shadows and does not require any temporal preprocessing.
Fichier principal
Vignette du fichier
main.pdf (2.7 Mo) Télécharger le fichier
supplementary_material.pdf (18.29 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02997573 , version 1 (10-11-2020)
hal-02997573 , version 2 (03-03-2021)
hal-02997573 , version 3 (21-04-2021)

Identifiers

Cite

Alexandre Constantin, Mathieu Fauvel, Stéphane Girard. Joint Supervised Classification and Reconstruction of Irregularly Sampled Satellite Image Times Series. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60, pp.4403913. ⟨10.1109/TGRS.2021.3076667⟩. ⟨hal-02997573v3⟩
460 View
588 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More