MAYUR: Map conflAtion using earlY prUning and Rank join

OpenStreetMap (OSM) is a collaborative good quality crowd-sourced geospatial database (GDB). The quality of OSM is generally very good, it lacks good coverage in many parts of the world. A natural approach for extending its coverage is to conflate missing spatial features from other GDBs into OSM, but this is laborious and time-consuming. We propose a system MAYUR solving road network conflation between two vector GDBs, representing the GDBs as a graph of road intersections (vertices) and road segments (edges). MAYUR is based on a novel map matching framework that adapts the classic Rank Join in databases, where each edge of the reference GDB is modeled as a relation. Our algorithm finds the best matching between a reference and target GDB, respecting the connectivity of the road network. While classic Rank Join in databases gets quickly inefficient on instances with more than 10 relations, MAYUR's enhanced Rank Join incorporates three optimizations that boost the algorithm's efficiency, making it scale to our problem setting featuring hundreds to thousands of relations. Our manual evaluation of MAYUR conflation results on sidewalks in OSM and Boston Open Data shows an impressive 98.65% precision and 99.55% recall.