VERY HIGH RESOLUTION LAND COVER MAPPING OF URBAN AREAS AT GLOBAL SCALE WITH CONVOLUTIONAL NEURAL NETWORKS
| Autor: | T. Tilak, A. Braun, D. Chandler, N. David, S. Galopin, A. Lombard, M. Michaud, C. Parisel, M. Porte, M. Robert |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XLIII-B3-2020, Pp 201-208 (2020) |
| Druh dokumentu: | article |
| ISSN: | 1682-1750 2194-9034 |
| DOI: | 10.5194/isprs-archives-XLIII-B3-2020-201-2020 |
| Popis: | 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. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|