Localisation in urban environment using GPS and INS aided by monocular vision system and 3D geographical model

Cindy Cappelle (1) , Maan El Badaoui El Najjar (2, 3) , Denis Pomorski (3) , François Charpillet (2)

1 LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
2 MAIA - Autonomous intelligent machine
3 STF - Systèmes Tolérants aux Fautes

In this paper, a geo-localisation method was proposed, using GPS, INS, monovision camera and a new geo-information source, which is the 3D cartographical model. A 3D-GIS (Geographical Information System) has been developed to manipulate and navigate in a precise 3D cartographical model database. To have a continuous pose estimation, an EKF has been implemented to fuse GPS and INS. To integrate the 3D cartographical model information, a 3D cartographical observation has been constructed using 2D/3D images matching between real image captured by the embedded camera and virtual images provided by the 3D-GIS. A real data acquisition platform has been developed to test and validate the proposed method.

Mots clés: Automated Vehicles; Information Fusion; Vehicle Environment Perception

Domaines: Automatique; Robotique [cs.RO]

Cindy Cappelle, Maan El Badaoui El Najjar, Denis Pomorski, François Charpillet. Localisation in urban environment using GPS and INS aided by monocular vision system and 3D geographical model. 2007 IEEE Intelligent Vehicles Symposium (IV'07), Jun 2007, Istanbul, Turkey. ⟨inria-00172669⟩