ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume V-3-2021
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 101–107, 2021
https://doi.org/10.5194/isprs-annals-V-3-2021-101-2021
ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., V-3-2021, 101–107, 2021
https://doi.org/10.5194/isprs-annals-V-3-2021-101-2021

  17 Jun 2021

17 Jun 2021

MARRYING DEEP LEARNING AND DATA FUSION FOR ACCURATE SEMANTIC LABELING OF SENTINEL-2 IMAGES

G. Fonteix1, M. Swaine2, M. Leras1, Y. Tarabalka1, S. Tripodi1, F. Trastour1, A. Giraud1, L. Laurore1, and J. Hyland2 G. Fonteix et al.
  • 1LuxCarta Technology, Mouans Sartoux, France
  • 2LuxCarta South Africa, Cape Town, South Africa

Keywords: deep learning, time-series, optical satellite images, semantic segmentation, U-net, confidence maps

Abstract. The understanding of the Earth through global land monitoring from satellite images paves the way towards many applications including flight simulations, urban management and telecommunications. The twin satellites from the Sentinel-2 mission developed by the European Space Agency (ESA) provide 13 spectral bands with a high observation frequency worldwide. In this paper, we present a novel multi-temporal approach for land-cover classification of Sentinel-2 images whereby a time-series of images is classified using fully convolutional network U-Net models and then coupled by a developed probabilistic algorithm. The proposed pipeline further includes an automatic quality control and correction step whereby an external source can be introduced in order to validate and correct the deep learning classification. The final step consists of adjusting the combined predictions to the cloud-free mosaic built from Sentinel-2 L2A images in order for the classification to more closely match the reference mosaic image.