VERY HIGH RESOLUTION LAND COVER MAPPING OF URBAN AREAS AT GLOBAL SCALE WITH CONVOLUTIONAL NEURAL NETWORKS
- 1IGN, Institut National de l’Information Géographique et Forestière, 73, avenue de Paris 94165 Saint-Mandé, France
- 2CEREMA, Centre d'études et d'expertise sur les risques, l'environnement, la mobilité et l'aménagement, 1 avenue du Colonel Roche, 31400 Toulouse, France
Keywords: Land cover map, aerial image, Digital Surface Model, semantic segmentation, U-Net, Deeplab
Abstract. This paper describes a methodology to produce a 7-classes land cover map of urban areas from very high resolution images and limited noisy labeled data. The objective is to make a segmentation map of a large area (a french department) with the following classes: asphalt, bare soil, building, grassland, mineral material (permeable artificialized areas), forest and water from 20cm aerial images and Digital Height Model.
We created a training dataset on a few areas of interest aggregating databases, semi-automatic classification, and manual annotation to get a complete ground truth in each class.
A comparative study of different encoder-decoder architectures (U-Net, U-Net with Resnet encoders, Deeplab v3+) is presented with different loss functions.
The final product is a highly valuable land cover map computed from model predictions stitched together, binarized, and refined before vectorization.