Leveraging the OSM building data to enhance the localization of an urban vehicle

Abstract - In this paper we present a technique that takes advantage of detected building façades and OpenStreetMaps data to improve the localization of an autonomous vehicle driving in an urban scenario. The proposed approach leverages images from a stereo rig mounted on the vehicle to produce a mathematical representation of the buildings' façades within the field of view. This representation is matched against the outlines of the surrounding buildings as they are available on OpenStreetMaps. The information is then fed into our probabilistic framework, called Road Layout Estimation, in order to produce an accurate lane-level localization of the vehicle. The experiments conducted on the well-known KITTI datasets prove the effectiveness of our approach.

Published in the proceedings of the IEEE Intelligent Transport System Conference, ITSC 2016; ieeexplore link to the paper.

@INPROCEEDINGS{7795618,
author={A. L. Ballardini and D. Cattaneo and S. Fontana and D. G. Sorrenti},
booktitle={2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)},
title={Leveraging the OSM building data to enhance the localization of an urban vehicle},
year={2016},
pages={622-628},
keywords={automatic guided vehicles;control engineering computing;geographic information systems;road vehicles;traffic engineering computing;KITTI datasets;OSM building data;OpenStreetMaps data;autonomous vehicle driving;detected building façades;lane-level localization;mathematical representation;probabilistic framework;road layout estimation;urban scenario;urban vehicle localization;Buildings;Cameras;Context;Roads;Three-dimensional displays;Urban areas;Vehicles},
doi={10.1109/ITSC.2016.7795618},
month={Nov},}