The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 1529–1535, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1529-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 1529–1535, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-1529-2020

  14 Aug 2020

14 Aug 2020

DEEP NEURAL NETWORKS FOR AUTOMATIC EXTRACTION OF FEATURES IN TIME SERIES OPTICAL SATELLITE IMAGES

G. Kamdem De Teyou1,2,3, Y. Tarabalka2, I. Manighetti1, R. Almar3, and S. Tripodi2 G. Kamdem De Teyou et al.
  • 1Géoazur, Université Côte d’Azur, Observatoire de la Côte d’Azur, IRD, CNRS, Sophia, France
  • 2Luxcarta Technology, 460 Avenue de la Quiera, 06370 Mouans-Sartoux, France
  • 3LEGOS, IRD, 14 Avenue Edouard Belin, 31400 Toulouse, France

Keywords: Deep Learning, U-Net, ConvLSTM, CNN, Remote optical images, Time Series, Earth observation, Anthropogenic and natural features

Abstract. Many Earth observation programs such as Landsat, Sentinel, SPOT, and Pleiades produce huge volume of medium to high resolution multi-spectral images every day that can be organized in time series. These time series are a great opportunity to detect and measure the space and time changes of anthropogenic and natural features. In this work, we thus exploit both temporal and spatial information provided by these images to generate land cover maps. For this purpose, we combine a fully convolutional neural network with a convolutional long short-term memory. Implementation details of the proposed spatio-temporal neural network architecture are provided. Experimental results show that the temporal information provided by time series images allows increasing the accuracy of land cover classification, thus producing up-to-date maps that can help in identifying changes on earth in both time and space.