EDST

 

 

 

 

Thèses Soutenues

 

	Titre de la thèse	Vehicle geo-localization based on GPS, Vision and 3D virtual model
	Auteur(s)	Maya Dawood
	Laboratoires
	Thèse en cotutelle	University of Sciences and Technology of Lille Ecole Doctorale des Matériaux et UNIVERSITE LIBANAISE Ecole Doctorale des Sciences et de Technologie
		thesis maya1.pdf
	Titre
	Titre en englais	Vehicle geo-localization based on GPS, Vision and 3D virtual model
	Date de soutenance	01 Mars 2013
	Résumé
	Résumé en anglais	Vehicle geo-localization remains a challenging problems in urban areas. For this purpose, GPS receiver is usually the main sensor. But, the use of GPS alone is not sufficient in many urban environments due to wave multi-path. In order to provide accurate and robust localization, GPS has to be helped with other sensors like dead-reckoned sensors, map data, cameras or LIDAR. In this thesis, a new observation of the absolute pose of the vehicle is proposed to back up GPS measurements. The proposed approach exploits virtual 3D city model managed by a 3D Geographical Information System (3D GIS) and a video camera. Vehicle geo-localization uses several sources of information: a GPS receiver, proprioceptive sensors (odometers and gyrometer), a video camera and a virtual 3D city model. The proprioceptive sensors allow to continuously estimating the dead-reckoning position and orientation of the vehicle. This deadreckoning estimation of the pose is corrected by GPS measurements. Moreover, a 3D geographical observation is constructed to compensate the drift of the dead-reckoning localization when GPS measurements are unavailable. The 3D geographical observation is based on the matching between the virtual 3D city model and the images acquired by the camera. For that, two images have to be matched: the real image and the virtual image. The real image is acquired by the on board camera and provides the real view of the scene viewed by the vehicle. The virtual image is provided by the 3D GIS. The developed method is composed of three parts. The first part consists in detecting and matching the feature points of the real image and of the virtual image. Three methods: SURF, SIFT and Harris corner detector are compared. The second part concerns the position computation using POSIT algorithm and the previously matched features set. The third part concerns the data fusion using IMM-UKF. The proposed approach has been tested on a real sequence and the obtained results proved the feasibility and robustness of the proposed approach.
	Organisme de delivrance	University of Sciences and Technology of Lille et UNIVERSITE LIBANAISE
	Ecole doctorale
	Langue	Englais
	Directeur de thèse
	Composition du Jury	Président: J. CHARARA, Membres: M. KHALIL, M. B- NAJJAR, V.BERGES –         CHERFAOUI, B. DAYA, D.POMORSKI, C. CAPELLE
	Mots clés
	Mots clés en anglais