Microsoft Releases Africa’s 1st Open Building Datasets
The aim of the project is to build a machine learning assisted workflow using HOT’s mapping tool Tasking Manager to enhance map creation of disaster-prone areas.
Microsoft Releases Africa’s 1st Open building datasets
Microsoft owned Bing Maps and the humanitarian arm of OpenStreetMaps, Humanitarian OpenStreetMap Team (HOT), have joined hands under Microsoft’s AI for Humanitarian Action program to utilize the potential of artificial intelligence (AI) in building open maps. The aim of the project is to build a machine learning assisted workflow using HOT’s mapping tool Tasking Manager to enhance map creation of disaster-prone areas.
According to the 2018 world disaster report, over 2 billion people have been affected by disasters in the last 10 years. In 2017 alone, more than 201 million people needed humanitarian assistance and another 18 million were displaced across the world, due to weather-related disasters. Many of these disaster-prone areas had been wiped out of geography, which made it hard for first responders to prepare and deliver relief efforts.
Even today, more than 60% of Africa remains unmapped where the population is still prone to disasters. However, with the initiation of this project, that gap has definitely reduced. In fact, with Tasking Manager, the HOT community has mapped 11 million square kilometres mapped in Africa alone. The initiative focuses on incorporating design updates, integrating machine learning, and bringing new open building datasets into Tasking Manager.
Tasking Manager relies on ML enabler to connect with building datasets through an API. This API-based integration makes it convenient to access not just Africa building footprints, but all open building footprints datasets from Bing Maps through ML enabler, and thus the OpenStreetMap ecosystem. For the project, the team at Bing Maps has been harnessing the power of Computer Vision to identify map features at scale.
Building upon their work in the United States and Canada, Bing Maps is now releasing country-wide open building footprints datasets in Uganda and Tanzania. This will be one of the first open building datasets in Africa and will be available for use within OpenStreetMap (OSM). Moreover, it is making this data open for download free of charge and usable for research, analysis.