The major contribution of this paper concerns vehicle geo-localization in urban environment by integrating a new source of information that is a virtual 3D city model. The 3D model provides a realistic representation of the vehicle's navigation environment. To optimize the performance of vehicle geo-localization system, several sources of information are used for their complementarity and redundancy: a GPS receiver, proprioceptive sensors (odometers and gyrometer), exteroceptive sensors (video camera or laser scanner) and a virtual 3D city model as a priori information. The proprioceptive sensors allow to continuously estimate the dead-reckoning position and orientation of the vehicle. Moreover, two concepts based on 3D virtual model and exteroceptive sensors could be envisaged to compensate the drift of the dead-reckoning localization when GPS measurements are unavailable for a long time. The first proposed approach is based on the matching between the virtual image extracted from the 3D city model and the real image acquired by the camera. This observation construction is composed of two major parts. The first part consists in detecting and matching the feature points of the real and virtual images. Three features are compared: Harris corner, SIFT (Scale Invariant Feature Transform) and SURF (Speed Up Robust Features). The second part is the pose computation using POSIT algorithm and the previously matched features set. The second approach uses an on-board horizontal laser scanner which provides a set of distances. This set of distances (real laser scan data) is matched with depth information of virtual laser scan data obtained using the virtual 3D city model which is managed in real-time by a 3D Geographical Information System (3D-GIS). GPS measurements, proprioceptive sensors based pose estimation, and camera/3D model based pose estimation are integrated in IMM UKF data fusion formalism. The developed approaches have been tested on a real sequence and the obtained results proved the feasibility of the approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicle geo-localization using IMM-UKF multi-sensor data fusion based on virtual 3D city model as a priori information


    Beteiligte:
    Dawood, Maya (Autor:in) / El Najjar, Maan E. (Autor:in) / Cappelle, Cindy (Autor:in) / Peng, Jing (Autor:in) / Khalil, Mohamad (Autor:in) / Pomorski, Denis (Autor:in)


    Erscheinungsdatum :

    2012-07-01


    Format / Umfang :

    1407339 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Virtual 3D city model as a priori information source for vehicle localization system

    Dawood, Maya / Cappelle, Cindy / El Najjar, Maan E. et al. | Elsevier | 2015



    Multi-sensor data fusion for land vehicle localization using /sup RT/MAPS

    Abuhadrous, I. / Nashashibi, F. / Laurgeau, C. et al. | IEEE | 2003


    Multi-Sensor Fusion Localization

    Zhang, Xinyu / Li, Jun / Li, Zhiwei et al. | Springer Verlag | 2023