Radiant MLHub

Open Cities AI Challenge Dataset

satellite

This dataset was developed as part of a challenge to segment building footprints from aerial imagery. The goal of the challenge was to accelerate the development of more accurate, relevant, and usable open-source AI models to support mapping for disaster risk management in African cities [Read more about the challenge]. The data consists of drone imagery from 10 different cities and regions across Africa

Dataset ID

open_cities_ai_challenge

DOI

10.34911/rdnt.f94cxb

Creator

Global Facility for Disaster Reduction and Recovery (GFDRR)

Contact

njones@worldbankgroup.org

Documentation

Citation

GFDRR Labs (2020). "Open Cities AI Challenge Dataset", Version 1.0, Radiant MLHub. [Date Accessed] https://doi.org/10.34911/rdnt.f94cxb

Python Client example

from radiant_mlhub import Dataset

ds = Dataset.fetch('open_cities_ai_challenge')
for c in ds.collections:
    print(c.id)

Python Client quick-start guide

Source Imagery Collections

Description

Open Cities AI Challenge Test Dataset

License

CC-BY-4.0

Collection ID

open_cities_ai_challenge_test

Download

Description

Open Cities AI Challenge Train Tier 1 Source Imagery

License

CC-BY-4.0

Collection ID

open_cities_ai_challenge_train_tier_1_source

Download

Description

Open Cities AI Challenge Train Tier 2 Source Imagery

License

CC-BY-4.0

Collection ID

open_cities_ai_challenge_train_tier_2_source

Download

Labels Collections

Description

Open Cities AI Challenge Train Tier 1 Labels

License

ODbL-1.0

Collection ID

open_cities_ai_challenge_train_tier_1_labels

Download

Description

Open Cities AI Challenge Train Tier 2 Labels

License

ODbL-1.0

Collection ID

open_cities_ai_challenge_train_tier_2_labels

Download