There are about four billion people in the world who are living without a physical address. According to a study recently published on the matter, more than half of roads around the world have no adequate street addressing systems resulting many places, particularly in developing countries, having no physical mailing address.
To solve this issue, Facebook and the MIT Media Lab are teaming up to create a solution that will give these people a way of identifying their residence. With the help of machine learning and satellite imagery, the team is building a system that will identify and assign addresses in a cheap and efficient manner, Engadget reported.
To create the solution, the team first trained a deep-learning algorithm to extract the road pixels from satellite images. Another algorithm connected the pixels together into a road network. The system analyzed the density and shape of the roads to segment the network into different communities, and the densest cluster was labeled as the city center. The regions around the city center were divided into north, south, east, and west quadrants, and streets were numbered and lettered according to their orientation and distance from the center.
When they compared their final results with a random sample of un-mapped regions whose streets had been labeled manually, their approach successfully addressed more than 80% of the populated areas, improving coverage compared with Google Maps or OpenStreetMaps.
Other than Facebook, Google too made efforts in the past to solve the issue of unaddressed rural lands. However, identifying addresses is not a problem, but having them adopted widely by the governments and citizens is.
Besides this, a London-based GIS organization, what3words, also solving this issue by generating a unique three-word combination for every 3m x 3m squares on a global grid. It is being used by over 650 businesses, government organisations and NGOs in over 170 countries are using 3 word addresses.
Via ~ Engadget | Source - MIT Technology Review
To solve this issue, Facebook and the MIT Media Lab are teaming up to create a solution that will give these people a way of identifying their residence. With the help of machine learning and satellite imagery, the team is building a system that will identify and assign addresses in a cheap and efficient manner, Engadget reported.
To create the solution, the team first trained a deep-learning algorithm to extract the road pixels from satellite images. Another algorithm connected the pixels together into a road network. The system analyzed the density and shape of the roads to segment the network into different communities, and the densest cluster was labeled as the city center. The regions around the city center were divided into north, south, east, and west quadrants, and streets were numbered and lettered according to their orientation and distance from the center.
When they compared their final results with a random sample of un-mapped regions whose streets had been labeled manually, their approach successfully addressed more than 80% of the populated areas, improving coverage compared with Google Maps or OpenStreetMaps.
Other than Facebook, Google too made efforts in the past to solve the issue of unaddressed rural lands. However, identifying addresses is not a problem, but having them adopted widely by the governments and citizens is.
Besides this, a London-based GIS organization, what3words, also solving this issue by generating a unique three-word combination for every 3m x 3m squares on a global grid. It is being used by over 650 businesses, government organisations and NGOs in over 170 countries are using 3 word addresses.
Via ~ Engadget | Source - MIT Technology Review
Advertisements