Project Details


An important element of creating more sustainable cities is to promote walking, but it is not enough to create safe walking paths. Citizens and visitors also need to be informed of their walking options through maps. However, the more commonly available maps on e.g. smartphones have a different focus, mainly based on commercial interests. Therefore, several major cities invest in maps of their own. But to create easily readable maps with optimally placed labels requires a large amount of manual labour; to circumvent these high costs, automated map labelling solutions are required. Current automated methods are based on quantification of cartographic rules and optimisation techniques. However, these methods are not good enough for high-quality maps which implies that a substantial part of the map labelling is still made interactively (it is estimated that the labelling takes more than half of the production times of maps).

In this project we use a data-driven approach to automated map labelling. By a cooperation with the Swedish company T-Kartor we have access to around 100,000 unique maps where the final placement of the labels has been performed interactively by a cartographer. These map examples are utilised both for improving the current map labelling algorithms and for selecting candidate solutions. The latter step is performed by training an AI-network. The final step is to distribute an implementation of these methods to the community as open source. The goal is that, by the end of the project, the automation level in cartographic production is increased substantially.
Short titleeSSENCE@LU 7:1
Effective start/end date2021/01/012022/12/31