Open Cities AI Challenge Dataset

https://doi.org/10.34911/rdnt.f94cxb

building footprints segmentation

Description

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

Documentation

https://radiant-mlhub.s3-us-west-2.amazonaws.com/open-cities-ai-challenge/documentation.pdf

Citation

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

Created By

Contact

Usage Examples

Tutorials
Tools & Applications
Publications

STAC Collections

  • Description
    Test Source Imagery
    Resource type
    Source Imagery
    Collection ID
    open_cities_ai_challenge_test
    License
    ODbL-1.0
  • Description
    Tier 1 Training Labels
    Resource type
    Labels
    Collection ID
    open_cities_ai_challenge_train_tier_1_labels
    License
    ODbL-1.0
  • Description
    Tier 1 Training Source Imagery
    Resource type
    Source Imagery
    Collection ID
    open_cities_ai_challenge_train_tier_1_source
    License
    ODbL-1.0
  • Description
    Tier 2 Training Labels
    Resource type
    Labels
    Collection ID
    open_cities_ai_challenge_train_tier_2_labels
    License
    ODbL-1.0
  • Description
    Tier 2 Training Source Imagery
    Resource type
    Source Imagery
    Collection ID
    open_cities_ai_challenge_train_tier_2_source
    License
    ODbL-1.0

Edit this dataset entry on GitHub

Home