AI Enabled Fast Global Mapping as Surprise Most of the World is Still Not Mapped

Facebook, OpenStreetMap, and Map with AI are creating tools that will enable vastly faster mapping of unmapped roads and other unmapped feature. Artificial intelligence to predict features on high-resolution satellite imagery; these features are then populated in our RapiD map editing tool. When combined with global-scale humanitarian efforts, they hope RapiD can help realize our vision of a more connected world.

Artificial intelligence applied to satellite data presents a high level view of where potential unmapped and missing roads are on a global scale.

For those of us who live in places where driving directions are available at our fingertips, it might be surprising to learn that millions of miles of roads around the world have yet to be mapped. For more than 10 years, volunteers with the OpenStreetMap (OSM) project have worked to address that gap by meticulously adding data on the ground and reviewing public satellite images by hand and annotating features like roads, highways, and bridges. It’s a painstaking manual task. But, thanks to AI, there is now an easier way to cover more areas in less time.

How AI-powered maps help improve vaccination campaigns and rural electrification

With assistance from Map With AI (a new service that Facebook AI researchers and engineers created) a team of Facebook mappers has recently cataloged all the missing roads in Thailand and more than 90 percent of missing roads in Indonesia. Map With AI enabled them to map more than 300,000 miles of roads in Thailand in only 18 months, going from a road network that covered 280,000 miles before they began to 600,000 miles after. Doing it the traditional way — without AI — would have taken another three to five years, estimates Xiaoming Gao, a Facebook research scientist who helped lead the project.

Starting today, anyone will be able to use the Map With AI service, which includes access to AI-generated road mappings in Afghanistan, Bangladesh, Indonesia, Mexico, Nigeria, Tanzania, and Uganda, with more countries rolling out.

The road network around Mount Muria, Indonesia. (Satellite image courtesy of Maxar.)

Using AI to help experts map faster and better

Map With AI uses a subfield of artificial intelligence called computer vision, whereby machines learn to spot complex patterns in images so they can analyze the same type of satellite imagery that OSM volunteers have worked with for years. The AI system has been trained to identify possible roads and highlight them in the mapping tool. The OSM volunteers use their expertise to review and then confirm or modify the AI system’s suggestions.

In this case, the computer vision system is what’s called a deep neural network (DNN) segmentation model. The actual output from the tool is an enhanced satellite image giving the probability that each pixel is part of a road. Bright magenta means there is high confidence of the pixel being a road, and transparent means there is low confidence.

7 thoughts on “AI Enabled Fast Global Mapping as Surprise Most of the World is Still Not Mapped”

  1. Open street maps provides GPS navigation system apps that can navigate through places like China where your Google maps will not work.

    I’m not sure of the date, but my Strava maps, which use the Google maps database, was working ok (though with a clear offset from reality) in Beijing in February, but was completely blocked by May. OSM maps still work.

  2. Boarding planes, nailing boards, etc. Mental confusion, too much reliance on spellcheckers and auto-correct, and just not knowing the difference.

  3. Only if we are all in the same place at the same time. Time to get out of this gravity well I am thinking.

  4. There is a difference between public, military, utility, and private roads. And that won’t necessarily be obvious from a satellite image.

    It also may aid crime, as they can find ways to cross boarders more easily…though, I suppose the satellite images are already available.

    There are also many roads that are not visible because of tree canopy.

    The grade of roads is not necessarily obvious either.

    And the names of the roads will not be necessarily identifiable either.

    There are of course all the positives already mentioned. And I would add that it may help statisticians to more accurately gauge the number of miles of each kind of road and rail. They don’t have to rely on likely inaccurate to dishonest figures. This can be important for loans and humanitarian efforts.

    It should also be possible to count the number of road vehicles, trains, aircraft, homes, factories, etc.

Comments are closed.