This chipped training dataset is over Dhaka 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 fine-tune Dhaka Model and contains 11,905 tiles and 189,057 individual buildings. The satellite imagery resolution is 30 cm and sourced from Maxar ODP (BG_Dhaka_19Q3_V0_R6C3, ...R6C4, ...R3C2, ...R2C3, ...R3C4). Dataset keywords: Very Dense Urban, Rural, Agricultural, Forested.
DevGlobal, (2022). ramp Building Footprint Training Dataset - Dhaka, Bangladesh, Version 1.0, [Date Accessed]. Radiant MLHub. https://doi.org/10.34911/rdnt.848og9
from radiant_mlhub import Dataset ds = Dataset.fetch('ramp_dhaka_bangladesh') for c in ds.collections: print(c.id)
ramp Building Footprint Training Dataset - Dhaka, Bangladesh - Source Imagery
ramp Building Footprint Training Dataset - Dhaka, Bangladesh - Labels