This chipped training dataset is over Accra and includes high-resolution imagery (.tif format) and corresponding building footprint vector labels (.geojson format) in 256 x 256 pixel tile/label pairs. This dataset is a ramp Tier 1 dataset, meaning it has been thoroughly reviewed and improved. This dataset was used in developing the ramp baseline model and contains 1,330 tiles and 40,786 buildings. The original dataset was sourced from the Open Cities AI Challenge Dataset before the drone imagery was resampled to 30 cm and the labeled data were improved. Dataset keywords: Urban, Dense.
Dataset ID | ramp_accra_ghana |
DOI | 10.34911/rdnt.zyiv7t |
Creator | DevGlobal |
Contact | info@dev.global |
DevGlobal, (2022). ramp Building Footprint Training Dataset - Accra, Ghana, Version 1.0, [Date Accessed]. Radiant MLHub. https://doi.org/10.34911/rdnt.zyiv7t
from radiant_mlhub import Dataset ds = Dataset.fetch('ramp_accra_ghana') for c in ds.collections: print(c.id)
Description | ramp Building Footprint Training Dataset - Accra, Ghana - Source Imagery |
License | CC-BY-SA-4.0 |
Collection ID | ramp_accra_ghana_source |
Download | |
Description | ramp Building Footprint Training Dataset - Accra, Ghana - Labels |
License | CC-BY-SA-4.0 |
Collection ID | ramp_accra_ghana_labels |
Download | |