Flood detection in time series of optical and sar images

Clément Rambour (1, 2) , Nicolas Audebert (2) , E. Koeniguer (1) , B. Le Saux (1) , M. Crucianu (2) , Mihai Datcu (2, 3)

1 DTIS, ONERA, Université Paris Saclay [Palaiseau]
2 CEDRIC - VERTIGO - CEDRIC. Données complexes, apprentissage et représentations
3 DLR - Deutsches Zentrum für Luft- und Raumfahrt [Oberpfaffenhofen-Wessling]

These last decades, Earth Observation brought a number of new perspectives from geosciences to human activity monitoring. As more data became available, Artificial Intelligence (AI) techniques led to very successful results for understanding remote sensing data. Moreover, various acquisition techniques such as Synthetic Aperture Radar (SAR) can also be used for problems that could not be tackled only through optical images. This is the case for weather-related disasters such as floods or hurricanes, which are generally associated with large clouds cover. Yet, machine learning on SAR data is still considered challenging due to the lack of available labeled data. To help the community go forward, we introduce a new dataset composed of co-registered optical and SAR images time series for the detection of flood events and new neural network approaches to leverage these two modalities. Figure 1. The SEN12-FLOOD dataset is composed of SAR and optical time series in which a flood event may occur.

Domaines: Intelligence artificielle [cs.AI]; Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Réseau de neurones [cs.NE]

Clément Rambour, Nicolas Audebert, E. Koeniguer, B. Le Saux, M. Crucianu, et al.. Flood detection in time series of optical and sar images. ISPRS International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2020, XLIII-B2-2020, pp.1343-1346. ⟨10.5194/isprs-archives-XLIII-B2-2020-1343-2020⟩. ⟨hal-02924220⟩