At the Humanitarian OpenStreetMap Team (HOT), we are working on a group of free and open source tools for community creation of maps. Following a process that involves aerial imagery gathering with UAVs, remote volunteer mapping, community in-the-field data collection, AI assisted remote sensing, and finally, downloading and using the map in disasters and humanitarian work. This is an end-to-end (E2E) solution that benefits everyone, from a small community to a big organization. We want to tell the story about how we’re creating and using these tools and what could be the future of humanitarian and disaster mapping from an open tech and data perspective.

We hope that you leave this talk inspired and excited about becoming part of the end to end mapping journey!

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. However currently focused on buildings only .

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

In this talk we will talk about the recent developments in fAIr , Our experiment with Yolo model and RAMP model for community mapping and couple of test results . fAIr recently made public version deployment : https://fair.hotosm.org/