Obstacles detection and localisation with ...
Document type :
Communication dans un congrès avec actes
Title :
Obstacles detection and localisation with 3D geographical model and monovision
Author(s) :
Cappelle, Cindy [Auteur]
Laboratoire d'Automatique, Génie Informatique et Signal [LAGIS]
El Badaoui El Najjar, Maan [Auteur]
Systèmes Tolérants aux Fautes [STF]
Autonomous intelligent machine [MAIA]
Charpillet, François [Auteur]
Autonomous intelligent machine [MAIA]
Pomorski, Denis [Auteur]
Systèmes Tolérants aux Fautes [STF]
Laboratoire d'Automatique, Génie Informatique et Signal [LAGIS]
El Badaoui El Najjar, Maan [Auteur]

Systèmes Tolérants aux Fautes [STF]
Autonomous intelligent machine [MAIA]
Charpillet, François [Auteur]
Autonomous intelligent machine [MAIA]
Pomorski, Denis [Auteur]

Systèmes Tolérants aux Fautes [STF]
Conference title :
IEEE Intelligent Transportation Systems Conference - ITSC'07
City :
Seattle
Country :
Etats-Unis d'Amérique
Start date of the conference :
2007-09-30
Publication date :
2007
HAL domain(s) :
Informatique [cs]/Robotique [cs.RO]
Informatique [cs]/Automatique
Informatique [cs]/Automatique
English abstract : [en]
In this paper, an obstacle detection approach for downtown environments is developed. This approach exploits a 3D geographical database managed by a 3D-GIS and a monovision-based system. The pose estimated by a LRK GPS is ...
Show more >In this paper, an obstacle detection approach for downtown environments is developed. This approach exploits a 3D geographical database managed by a 3D-GIS and a monovision-based system. The pose estimated by a LRK GPS is used to geo-localise the vehicle. After coordinates system conversion, the vehicle is localised in the 3D geographical database. An image processing module is developed to match synchronized images provided by 3D GIS and an on-board camera. Several kinds of obstacles are then detected and tracked by comparison between real images and virtual images. Finally, the distance between the camera and the obstacles is computed, as well as the geo-position of the detected obstacles. Experimental results with real data are presented in the final section.Show less >
Show more >In this paper, an obstacle detection approach for downtown environments is developed. This approach exploits a 3D geographical database managed by a 3D-GIS and a monovision-based system. The pose estimated by a LRK GPS is used to geo-localise the vehicle. After coordinates system conversion, the vehicle is localised in the 3D geographical database. An image processing module is developed to match synchronized images provided by 3D GIS and an on-board camera. Several kinds of obstacles are then detected and tracked by comparison between real images and virtual images. Finally, the distance between the camera and the obstacles is computed, as well as the geo-position of the detected obstacles. Experimental results with real data are presented in the final section.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Collections :
Source :