We present a simple yet effective paradigm to accurately predict the future trajectories of observed vehicles in dense city environments. We equipped a large fleet of cars with cameras and performed city-scale structure-from-motion to accurately reconstruct 10M positions of their trajectories spanning over 1000h of driving.We demonstrate that this information can be used as a powerful high-fidelity prior to predict future trajectories of newly observed vehicles in the area without the need for any knowledge of road infrastructure or vehicle motion models. By relating the current position of the observed car to a large dataset of the previously exhibited motion in the area we can directly perform prediction of its future position.We evaluate our method on two large-scale data sets from San Francisco and New York City and demonstrate an order of magnitude improvement compared to a linear-motion based method. We also demonstrate that the performance naturally improves with the amount of data and ultimately yields a system that can accurately predict vehicle motion in challenging situations across extremes in traffic, time, and weather conditions.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Predicting trajectories of vehicles using large-scale motion priors


    Beteiligte:
    Suraj, M S (Autor:in) / Grimmett, Hugo (Autor:in) / Platinsky, Lukas (Autor:in) / Ondruska, Peter (Autor:in)


    Erscheinungsdatum :

    2018-06-01


    Format / Umfang :

    3992347 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    PREDICTING TRAJECTORIES OF VEHICLES USING LARGE-SCALE MOTION PRIORS

    Suraj, M. S. / Grimmett, Hugo / Platinský, Lukáš et al. | British Library Conference Proceedings | 2018


    METHOD AND SYSTEM FOR PREDICTING VEHICLES' MOVING TRAJECTORIES

    PAN JIACHENG / SUN HONGYI / XU KECHENG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    PREDICTING AGENT TRAJECTORIES IN THE PRESENCE OF ACTIVE EMERGENCY VEHICLES

    PARASURAM AISHWARYA / SAXENA ALISHA / SAGAR ANOOSHA et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Method for Using Lateral Motion to Optimize Trajectories for Autonomous Vehicles

    PHILLIPS MICHAEL LEE / BRADLEY DAVID MCALLISTER / EREN UTKU et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Method for using lateral motion to optimize trajectories for autonomous vehicles

    PHILLIPS MICHAEL LEE / BRADLEY DAVID MCALLISTER / EREN UTKU et al. | Europäisches Patentamt | 2022

    Freier Zugriff