GeoDart: A System for Discovering Maps Discrepancies

Abstract

Map service providers are working hard to maintain high-quality maps service to more than three billion digital maps users. As each provider presents its unique routing engine and road network graph (RNG) mapping techniques, inconsistencies in services provided are inevitable. These inconsistencies may be of two types- (1) inconsistencies in RNG, including missing or shifted road segments, missing turn restriction, or mislabeled road attributes; or (2) inconsistencies in routing service arising from the unique routing algorithm (RA). Discovering those inconsistencies would improve the routing services efficiency. This paper presents a system, named GeoDart, that compares publicly available routing data from the APIs of Bing Maps, Google Maps, and OpenStreetMaps (OSM) to automatically discover discrepancies. The system categorizes the detected discrepancies based on (1) routing data such as distance, duration, and route geometry, (2) the attributes of the road segments, and (3) the connectivity and turn restrictions of the RNG. Equipped with an ensemble of Multi-Layer Perception (MLP) and Support Vector Machine Classifiers (SVC), GeoDart can efficiently discover and classify maps discrepancies. Through its graphical interface, the GeoDart system enables users such as professional editors and cartographers to visually inspect, identify, and correct map discrepancies mutually across the three engines.