Per city-block, density estimation at build-up areas from aerial RGB imagery with deep learning
Résumé
Estimating the density of the 'urban fabric' land cover classes is of major importance for various urban and regional planning activities. However, the generation of such maps is still challenging requiring significant time and labor costs for the per city-block analysis of very high resolution remote sensing data. In this paper, we propose a supervised classification approach based on deep learning towards the accurate density estimation of build-up areas. In particular, for the training procedure we exploit information both from maps (open street, google, etc) and from very high resolution RGB google image mosaics. A patch-based, deep learning model was trained against five land cover classes. During the prediction phase the per city-block classification procedure delivered the locations and percentages of impervious, soil and green regions. Experimental results and validation at two European cities i.e., Athens and Bilbao, indicated overall accuracy rates of 95%. Results, also, highly match with the corresponding layers from the Copernicus Urban Atlas product.