Leuven-based technology company GIM deploys AI to map slums in Latin America and Asia

Satellite images have been used for many years to gather information about the earth's surface. Until recently, experts had to rely on software that recognizes and delineates certain spatial patterns. Object Based Image Recognition represented a major step forward in speeding up information processing. The disadvantage is that a relatively large amount of human intervention is still required and that the processing logic has to be set up and tested anew for each project. Moreover, processing the information requires an enormous amount of computing power from the computers used for this purpose.

Belgian know-how deployed worldwide

GIM deployed this technology to demarcate slums in Manila (Philippines), Ho-Chi-Minh City (Vietnam) and Latin America. For Manila and Ho-Chi-Minh City, GIM worked on behalf of the UNDP (United Nations Development Program,) while in Latin America, the Inter-American Development Bank (IDB) coordinates.

The major advantage of the method used is that - once developed - the model can be easily transferred to another region or continent. Thanks to machine learning, the detection of such informal habitation is therefore more accurate, faster and easier. Moreover, an extensive toolbox is provided to users to deploy the software for additional locations or to monitor the evolution over time. Finally, this toolbox is based on open-source tools, which also makes the chosen technology particularly interesting for NGOs that often operate in regions with fewer financial resources.