Today, Google launched Kartta Labs, an open source system that is scalable to Google Cloud and Kubernetes and uses historical maps and photos to reconstruct what cities looked like in the past. Available as a suite of tools, Kartta creates a map with an explorable timeline that allows users to populate data with historically accurate information.
Kartta Labs was first introduced last year during the International Workshop on AI for the Discovery of Geographic Knowledge. According to the makers, the motivation is to organize the historical maps of the world while making them accessible and useful. Historical maps, with the help of which cultural and social trends can be identified, are of inestimable value not only for citizen research, but also for planning and public relations work. Over a decade ago, former Vice President Al Gore used historical images from Google Earth to show the melting of the polar ice caps.
There are other efforts to collect historical maps in digital archives, but Kartta goes beyond simply collecting data to register the maps in space and time. A temporary map server shows how maps change over time, while a crowdsourcing platform allows users to upload historical maps of cities and match them with real-world coordinates. Another platform runs on maps to create a 3D experience by using AI to reconstruct buildings.
The entry point is Warper, a web app that allows users to “georectify” uploaded images by finding points on a historical map and corresponding points on a base map. Once a user uploads a map, the best way for Warper to guess the map’s geolocation is to extract textual information from the map. This initial guess is used to place the map in approximate position and to allow the user to georeference the map pixels. After manually placing the control point pairs on the historical map and a reference map, the app uses the georeferenced points to distort the image so that it matches the reference map well.
The editor complements Warper. The tool supports the time dimension and integrates with the other apps in the Kartta suite so that users can load the georectified historical maps and track geographic features such as creating footprints and roads in vector format. In the front end of the temporary map, Kartta visualizes the vector tiles so that users can navigate in historical maps in space and time.
The Kartta frontend works like Google Maps, but with a time slider that selects the map year. Moving the time slider shows how features on the map change over time. According to Google, an upcoming module – aptly called 3D models – will reconstruct the detailed full 3D structures of historical buildings, link images with map data, organize these 3D models in a repository and render them on the maps.
“We developed the tools described above to facilitate crowdsourcing and address the main challenge of insufficient historical data,” wrote Raimondas Kiveris, senior software engineer at Google Research, in a blog post. “We hope that Kartta Labs will act as a nexus for an active community of developers, map enthusiasts and casual users who not only use our historical data sets and open source code, but actively contribute to both.”