Mapping buildings and roads automatically with remote sensing typically requires high-resolution imagery, which is expensive to obtain and often sparsely available. In this work we demonstrate how multiple 10 m resolution Sentinel-2 images can be used to generate 50 cm resolution building and road segmentation masks. This is done by training a `student' model with access to Sentinel-2 images to reproduce the predictions of a `teacher' model which has access to corresponding high-resolution imagery. While the predictions do not have all the fine detail of the teacher model, we find that we are able to retain much of the performance: for building segmentation we achieve 79.0\% mIoU, compared to the high-resolution teacher model accuracy of 85.5\% mIoU. We also describe two related methods that work on Sentinel-2 imagery: one for counting individual buildings which achieves R2=0.91 against true counts and one for predicting building height with 1.5 meter mean absolute error. This work opens up new possibilities for using freely available Sentinel-2 imagery for a range of tasks that previously could only be done with high-resolution satellite imagery.
@article{arxiv.2310.11622,
title = {High-Resolution Building and Road Detection from Sentinel-2},
author = {Wojciech Sirko and Emmanuel Asiedu Brempong and Juliana T. C. Marcos and Abigail Annkah and Abel Korme and Mohammed Alewi Hassen and Krishna Sapkota and Tomer Shekel and Abdoulaye Diack and Sella Nevo and Jason Hickey and John Quinn},
journal= {arXiv preprint arXiv:2310.11622},
year = {2024}
}