The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B3-2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-201-2020
https://doi.org/10.5194/isprs-archives-XLIII-B3-2020-201-2020
21 Aug 2020
 | 21 Aug 2020

VERY HIGH RESOLUTION LAND COVER MAPPING OF URBAN AREAS AT GLOBAL SCALE WITH CONVOLUTIONAL NEURAL NETWORKS

T. Tilak, A. Braun, D. Chandler, N. David, S. Galopin, A. Lombard, M. Michaud, C. Parisel, M. Porte, and M. Robert

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.