It has been claimed that development of an invehicle early warning system is important to maximize collision avoidance capability. This study aims to provide a method that can predict the true ego-vehicle motion long enough so that early warning could be feasible, using a monocular forward-view camera. Based on an observation that severalsecond future position of a vehicle is probabilistic rather than deterministic, our approach utilizes a machine learning algorithm that can probabilistically model human driving behavior from data to predict multiple possible paths, such as going straight, turning left, and turning right. Experimental results on KITTI dataset suggest that our probabilistic learning approach could suffice for 4-second early warning, while an orthodox, deterministic learning approach and a simple motion extrapolation approach do not satisfy the requirement.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning-Based Multiple-Path Prediction for Early Warning


    Beteiligte:
    Sato, Ikuro (Autor:in) / Guoqing, Liu (Autor:in)


    Erscheinungsdatum :

    01.06.2018


    Format / Umfang :

    5903783 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    LEARNING-BASED MULTIPLE-PATH PREDICTION FOR EARLY WARNING

    Sato, Ikuro / Guoqing, Liu | British Library Conference Proceedings | 2018


    Early warning information credibility prediction method based on overspeed early warning and forward collision early warning

    NIU SHIFENG / GUO ZIHAO / HU YANTING et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Intelligent pedestrian path early warning system

    QUAN GUOJUN / JIANG HAI / WU YIMAN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Research on pedestrian vehicle collision warning based on path prediction

    Zhang, Yue / Wang, Xu / Zhuo, Kaimin et al. | IEEE | 2023