Facebook today released ‘Map with AI’, a map building tool to help the community-based OpenStreetMap organization to create crows-sourced maps easily. Facebook took two years of time to develop these tools, and now it will be available to the OpenStreetMap community members. The tool, RapidID is at the core of this program.
This level of detail means it can spot unpaved roads, as well as alleys and even pedestrian pathways, and distinguish them from visually similar riverbeds or walls. We still have some false positives, of course, and this is where expert human judgment is needed - Danil Kirsanov, Engineering Manager, Facebook
RapidID will render identifying, adding and editing roads into an easy task. RapidID takes satellite images from Maxar, a US-based space tech company. The AI model predicts the presence of roads in a given image and shows them on the map with a magenta overlay, along with existing roads with a white overlay. In order to improve the accuracy of the map, a volunteer can easily choose a road to edit or remove its properties. This model can even detect unpaved roads.
Many rural parts of the world are difficult to map on the ground. As I experienced in my previous work with the Red Cross, the challenges include remote locations, lack of power and internet access, and complicated economic and political environments. Map data gaps can affect everything, including disaster response, community planning, and helping the local econom - Drishtie Patel, Program manager for Maps & Location Infrastructure, Facebook
In order to test out the tools and models, and to predict the accuracy of the tools, Facebook OpenStreetMap Project mapped 300,000 miles’ worth of unmapped road in Thailand. The Facebook AI-powered tool will not only serve Facebook capital wise, but the tools are also released for the greater good of the OpenStreetMap Team to help them out better during natural calamities. This map data can also be very helpful for disaster management response.