HOT partnered with Microsoft Philanthropies and Bing Maps to produce AI-detected open building datasets for Tanzania and Uganda and to pilot Machine Learning assisted workflows in the Tasking Manager application in order to enhance mapper experience.
The power of volunteer mapping is shown when disaster-affected areas can be mapped in a few days. When thousands of volunteers join together quickly, areas affected by a disaster then have the necessary data for a robust humanitarian response. Through our Missing Maps work, we continue to focus on preparedness mapping for unmapped areas but a challenge still exists to map at a scale and quality for humanitarian use.
Around the world, there are still hundreds of millions of buildings and millions of kilometers of road missing from OpenStreetMap. To meet the challenge of mapping the unmapped areas, the Tasking Manager requires two key improvements to the workflow: an increase in data quality of edits being made, and an increase in mapping and validating efficiency.
There is promising potential for machine/deep/statistical learning assisted mapping - especially for tangible achievements such as image processing. HOT leverages machine power by piloting newly available programming models to improve data quality and mapping experience.
Building upon previous work of the HOT community, in this project we worked with Microsoft’s AI for Humanitarian Action program to build enhanced assisted mapping workflows with machine learning into the Tasking Manager and create an open building dataset in Uganda and Tanzania.
We needed to first improve the general mapping experience, which led to the development of Tasking Manager 4. In addition we implemented a Machine Learning playground with two well-designed use cases around the Tasking Manager. These are focusing on machine learning assisted project creation and task facilitation, and also on AI-assisted mapping.
Photo credit: OpenAerialMap
Recent news from Integrating Deep Learning: AI-Assisted Humanitarian Mapping (View all news)
Team up in the new Tasking Manager
The future is here! A fresh frontend with an integrated ID editor and many new improvements await you.
Tasking Manager gets a makeover
The latest software version 4 of Tasking Manager has just been released with a number of enhancements that will improve users’ experience of collaborative mapping in OpenStreetMap.
Using machine learning to identify the effort and complexity of mapping areas
Testing more machine learning integrations with the Tasking Manager