A Semi-Automated System for Exploring and Fixing OSM Connectivity

As an open license project, Open Street Map (OSM) aims to make the collectively produced geographic data freely available to be used for various purposes. Routing engines frequently take advantage of this data set. Nonetheless, providing routing services on top of OSM requires the full connectivity of the OSM road network graph in the interest area. This connectivity needs to be achieved individually at every level of the road network graph: the motorway, trunk, primary, secondary, tertiary, and residential roads. However, due to its open-editing nature, the OSM data often contains faults attributed to issues like missing road network connections or mistakenly attributed road segments. In this paper, we demonstrate a system we have developed that helps the end-user (i.e., cartographer) discover and fix the connectivity errors in an OSM road network graph. More specifically, the system aims to achieve full connectivity in the overall road network graph, which in turn requires full connectivity at each road level. The system automatically detects the connectivity errors that would otherwise remain undetected or need a lengthy manual process to discover. It can accept hints from the editor through its easy to use graphical user interface to investigate errors further, improve the detection process, and subsequently fix them. Based on our pilot runs in New Zealand with the supervision of professional cartographers and a team from Microsoft Geospatial, we were able to detect more than 300 incorrect connections and to achieve connectivity across different road levels.