Skip to content

hotosm/fAIr

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

HOTOSM Logo

fAIr: AI-assisted Mapping

Open AI-assisted mapping service for Humanitarian

Release Version

CI/CD Backend Build Frontend Build
Tech Stack Django React Docker PostgreSQL TensorFlow PyTorch
Code Style pre-commit Black
Community Slack All Contributors
Submodules fairpredictor Repo fair-utilities Repo
Other Info Roadmap Figma Design Features Plan License

fAIr is an open AI-assisted mapping service developed by the Humanitarian OpenStreetMap Team (HOT) that aims to improve the efficiency and accuracy of mapping efforts for humanitarian purposes. The service uses AI models, specifically computer vision techniques, to detect objects such as buildings, roads, waterways, and trees from satellite and UAV imagery.

The name fAIr is derived from the following terms:

  • f: for freedom and free and open-source software
  • AI: for Artificial Intelligence
  • r: for resilience and our responsibility for our communities and the role we play within humanitarian mapping

Features

  • Intuitive and fair AI-assisted mapping tool
  • Open-source AI models created and trained by local communities
  • Uses open-source satellite and UAV imagery from HOT's OpenAerialMap (OAM) to detect map features and suggest additions to OpenStreetMap (OSM)
  • Constant feedback loop to eliminate model biases and ensure models are relevant to local communities

Unlike other AI data producers, fAIr is a free and open-source AI service that allows OSM community members to create and train their own AI models for mapping in their region of interest and/or humanitarian need. The goal of fAIr is to provide access to AI-assisted mapping across mobile and in-browser editors, using community-created AI models, and to ensure that the models are relevant to the communities where the maps are being created to improve the conditions of the people living there.

To eliminate model biases, fAIr is built to work with the local communities and receive constant feedback on the models, which will result in the progressive intelligence of computer vision models. The AI models suggest detected features to be added to OpenStreetMap (OSM), but mass import into OSM is not planned. Whenever an OSM mapper uses the AI models for assisted mapping and completes corrections, fAIr can take those corrections as feedback to enhance the AI modelโ€™s accuracy.

Product Roadmap (Users' Roadmap)

Status Feature Detailed Description Release
โœ… Adopting YOLOv8 model Improvements to the prediction algorithm v2.0.1+
โœ… New UI/UX redesign to enhance the user experience v2.0.10+
โœ… fAIr evaluation detailed research with Masaryk University & Missing Maps Czechia and Slovakia, welcome to join the efforts, here is the final report
๐Ÿ”„ Handling User Profile Enable users to log in easily and have insights in their user activity, their own models/datasets and submitted trainings
๐Ÿ”„ Notifications features Training status change would trigger a notification on the web/email to let user know training is finished successfully or with a failure
๐Ÿ“… Replicable Models Enable users to run a pre-trained model on new imagery/on a different area of their choice and using different satellite imagery
๐Ÿ“… Offline AI Prediction Enable users to submit requests for prediction using any pre-trained model and any imagery and process it in the background and provide the results back to user.
๐Ÿ“… Post Processing Enhancement Users would get enhanced geometry features (points/polygons) based on the need of the mapping process
๐Ÿ“… fAIrSwipe Enable users to validate fAIR generated features and push them into OSM by integrating fAIr with MapSwipe, more details

|๐Ÿ‘€| You can follow here the details and scope of each of the above features. and you can see and follow the Figma design progress for current in development ๐Ÿ”„ features

A higher level roadmap for 2025 can be found on Github.

General Workflow of fAIr

fAIr1

  1. First We expect there should be a fully mapped and validated task in project Area where model will be trained on
  2. fAIr uses OSM features as labels which are fetched from [Raw Data API] (https://github.com/hotosm/raw-data-api) and Tiles from OpenAerialMap (https://map.openaerialmap.org/)
  3. Once data is ready fAIr supports creation of local model with the input area provided , Publishes model for that area which can be implemented on the rest of the similar area
  4. Feedback is important aspect , If mappers is not satisfied with the prediction that fAIr is making they can submit their feedback and community manager can apply feedback to model so that model will learn

fAIr Architecture

fAIr2

The backend is using library we call it fAIr utilities to handle:

 1. Data preparation for the models
 2. Models trainings
 3. Inference process
 4. Post processing (converting the predicted features to geo data)

Local Installation [DEV]

Checkout Docker Installation docs

Get involved!

Imagery License

Imagery Submission

By submitting imagery link to fAIr for model creation, you:

  1. Grant fAIr permission to download tiles covering your specified area of interest.
  2. Authorize fAIr to use these tiles for training and inference.
  3. Allow fAIr to redistribute the downloaded tiles to anyone who wishes to view or reproduce the dataset used for model training.

Copyright

  • The original copyright remains with the imageryโ€™s source or rights holder.

License Grant

  • You grant fAIr the right to license the downloaded tiles under CC BY 4.0.

Commercial TMS Notice

  • If you are using a commercial TMS (Tile Map Service) with your own token, please be aware that fAIr will download , store and derive information from the tiles for your specified area.
  • These tiles may be published as part of the training process and made available to others.

You must verify that imagery provider's license is compatible with fAIrโ€™s intended use.

Imagery License Compliance

  • When submitting imagery to fAIr, ensure you are not violating the license of the TMS or imagery provider.
  • If you are grabbing imagery from OpenAerialMap, review their legal page for applicable terms.

Extended Use

  • If you plan to use the API or imagery services beyond the scope of the listed license, reach out to [email protected] for further guidance.

image