AI to Detect Buildings in Under-Mapped Areas
A new AI tracking map, developed by Google and the United Nations (UN), enhances visibility in under-mapped regions, offering insights into building footprints and population distribution in the Global South.
A revolutionary AI satellite image map has been launched to increase visibility in under-mapped parts of the world, particularly in Africa and the Global South, to increase visibility. Designed by Google and the United Nations, the new tool features insights into the building footprint area and height, captured between 2016 and 2023.
Large swaths of the areas had been mapped earlier with low-resolution images, making it difficult to monitor and analyze how settlements have been changing over time and understand where people live.
AI Tracking Details
AI based satellite image analysis extracts crucial building data from images, even those of low quality.
The new map uses satellite image AI to extract building details from images taken every five days by satellites. This breakthrough is particularly significant for areas where mapping effort has been minimal. The AI tracking technology understands the satellite data and reveals outlines and heights of all buildings, as well as in temporary settlements – the refugee camps.
“Not knowing where buildings are is a big problem for lots of practical reasons,” said John Quinn, a Google researcher. “If you’re creating services or vaccination campaigns or rescuing people after an emergency, this is a problem.”
The project opens this information to help bridge the gap between the global South and the global North, enabling policymakers in under-resourced regions to make decisions on an even playing field. Abdoulaye Diack, programme manager and contributor to the project added, “We want people in the global South making policy decisions to have the same tools available as the global North.”
Limitations of the AI Mapping Tool
Although this AI tracking driven map is a big leap in the human headcount, there are certain shortcomings it carries. The makeshift shelters and tents are hardly detected by this system, besides the fact that the system works in clear weather conditions only. Cloud cover and rain reduce the reliability of the map in those places.
All this is especially important in a sparsely populated country torn apart by war. In such traditional censuses, quite often it is difficult to conduct and thus estimate how many people may live there. “Understanding where people live is vital for making sure that resources are distributed fairly and that no one is left behind in delivering services like healthcare,” said Professor Andrew Tatem, head of the WorldPop team.
This can be a gold mine for resource distribution, humanitarian aid, and policy planning across a number of the most underserved regions in the world. Though the AI tracking technology has its challenges, it greatly promises to bring out a clearer view of life in areas that were formerly under-mapped, a step forward supported by UN AI initiatives.
Inside Telecom provides you with an extensive list of content covering all aspects of the tech industry. Keep an eye on our Intelligent Tech sections to stay informed and up-to-date with our daily articles.