๐ฃ๐ฎ๐๐ฒ๐ฑ ๐ผ๐ฟ ๐๐ป๐ฝ๐ฎ๐๐ฒ๐ฑ? ๐ฃ๏ธ
Accurate road surface information is crucial for emergency responses and route planning. But #OpenStreetMap has comprehensive surface attributes for only 30โ40% of the roads worldwide.
Using state-of-the-art GeoAI methods, we created an openly available ๐๐ผ๐ฟ๐น๐ฑ๐๐ถ๐ฑ๐ฒ ๐ฑ๐ฎ๐๐ฎ๐๐ฒ๐ ๐ผ๐ป ๐ฟ๐ผ๐ฎ๐ฑ ๐๐๐ฟ๐ณ๐ฎ๐ฐ๐ฒ ๐๐๐ฝ๐ฒ๐.
A new paper presents the methods behind the dataset.
โซ๏ธ Studyยดs highlights: https://heigit.org/new-paper-paved-or-unpaved-a-deep-learning-derived-road-surface-global-dataset-from-mapillary-street-view-imagery-2/
โซ๏ธ Full paper: https://www.sciencedirect.com/science/article/pii/S0924271625000784
โซ๏ธ Dataset: https://data.humdata.org/organization/heidelberg-institute-for-geoinformation-technology