IMCLASS – A USER-TAILORED MACHINE LEARNING IMAGE CLASSIFICATION CHAIN FOR CHANGE DETECTION OR LANDCOVER MAPPING

• Published in: International archives of the photogrammetry, remote sensing and spatial information sciences. Vol. XLIII-B3-2020; pp. 677 - 683
• Main Authors: Déprez, A., Puissant, A., Malet, J.-P., Michéa, D.
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Gottingen Copernicus GmbH 01.01.2020; Copernicus GmbH (Copernicus Publications); Copernicus Publications
• Subjects: Chains; Change detection; Classification; Construction; Detection; Disasters; Exploitation; Geological hazards; Ill posed problems; Image classification; Imagery; Landslides; Landslides & mudslides; Machine learning; Mapping; Microprocessors; Object recognition; Radar; Radar imaging; Satellite imagery; Sciences of the Universe; Spaceborne remote sensing; Urban areas; Vineyards
• ISSN: 2194-9034; 1682-1750; 2194-9034
• DOI: 10.5194/isprs-archives-XLIII-B3-2020-677-2020

With the increasing availability of satellite imagery at several spatial, spectral and temporal resolutions, the choice of the best image and the most appropriate method for object detection and classification of a broad range of land surface classes or processes is still a difficult task for many users. In order to guide the users, we proposed a user-tailored machine learning method (IMage CLASSification - ImCLASS) to detect and classifiy specific landcover classes.The method assumes a mono-class approach taking several ill-posed problems (e.g. class imbalance, high diversity inside the studied class, similarities with the adjacent samples…) as use cases (landslides, construction works in urban areas, burnt areas, vegetation classes…). It is a generalization of the ALADIM processor already validated in the context of landslide mapping and available as a service on the ESA GeoHazards Exploitation Platform (GEP). The proposed chain is able to combine optical and radar images, uses open source libraries, and is optimized for rapid calculation on HPC environments. The ImCLASS processor is presented and its performance is evaluated on three use cases: landslide detection and mapping after disasters in different regions of the World, urban classes change detection with a focus on construction works in Strasbourg, and crop mapping (vineyard) in the Grand-Est region. First results using either bi-dates or mono-date imagery are presented.