Intelligent Geolocalization in Urban Areas Using Global Positioning Systems, Three-Dimensional Geographic Information Systems, and Vision

Abstract This article tackles the problem of a vehicle's geolocalization in urban areas. For this purpose, Global Positioning System (GPS) receiver is the main sensor. However, the use of GPS alone is not sufficient in many urban environments. GPS has to be helped with dead-reckoned sensors, map data, and cameras. A novel observation of the absolute pose of the vehicle is proposed to back up GPS and the drift of dead-reckoned sensors. This approach uses a new source of information that is a geographical 3-dimensional (3D) model of the environment in which the vehicle navigates. This virtual 3D city model is managed in real time by a 3D geographical information system (3D GIS). This pose's observation is constructed by matching the virtual image provided by the 3D GIS and the real image acquired by an onboard camera. An extended Kalman filter combines the sensors measurements to produce an estimation of the vehicle's pose. Experimental results using data from an odometer, a gyroscope, a GPS receiver, a camera, and an accurate geographical 3D model of the environment illustrate the developed approach. Keywords: 3D GISautonomous navigationdata fusiongeographical 3D model geolocalizationGPSintelligent vehiclevision Notes 1 CitationQuddus, Ochieng, and Noland (2007) proposed a review of map-matching algorithms. CitationQuddus, Ochieng, and Liu (2008) introduced two articles—by CitationSmaili, El Badaoui El Najjar, and Charpillet (2008) and CitationChen, Li, Yu, and Chen (2008)—on the latest research that addresses the map-matching problem.