In this paper we present the development of a framework for vehicle localization refinement based on the detection of traffic road signs. Leveraging on the detection capabilities of deep neural networks, the proposed architecture relies on the recognition of traffic signs to navigate a graph, in order to spatially localize the vehicle on the road. Knowing the internal camera parameters and the size of the road signals it is possible to refine the localization accuracy and propagate the information over time thanks to the application of a Kalman filter. The implemented solution demonstrates that the trajectory of the vehicle is more accurate, reducing the error when comparing the standard GPS information and the RTK positioning system.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Exploitation of road signalling for localization refinement of autonomous vehicles


    Contributors:


    Publication date :

    2018-07-01


    Size :

    2411887 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    ROAD DNA BASED LOCALIZATION FOR AUTONOMOUS VEHICLES

    Li, Liang / Yang, Ming / Wang, Chunxiang et al. | British Library Conference Proceedings | 2016


    Indoor Localization of Autonomous Vehicles

    BALLARD BENJAMIN DAVID / PUCHALSKI MATTHEW / LORD DALE HUMBERT et al. | European Patent Office | 2022

    Free access

    Autonomous Vehicles and Road Safety

    Michałowska, Maria / Ogłoziński, Mariusz | British Library Conference Proceedings | 2017


    Autonomous Vehicles and Road Safety

    Michałowska, Maria / Ogłoziński, Mariusz | Springer Verlag | 2017


    Vision-based Autonomous Road Vehicles

    Graefe, Volker / Kuhnert, Klaus-Dieter | Springer Verlag | 1992