In this study a Bayesian Hierarchical Model for predicting the accident lane using the average section speed and density data obtained from a sensor or GPS was developed. With the assumption that speed and density values are normally distributed in an accident situation depending on the lane the accident has occurred, we have modelled the related parameters and predicted the probability of occurrence for each lane. This method can be used in real time traffic services where accidents are recorded by users or detected by other algorithms in order to alert the drivers about the lane of the accident. The awareness to the accident lane can ease the channeling of vehicles to the non-accident lanes and can help prevent the secondary accidents.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Accident Lane Prediction Using Probabilistic Inference


    Contributors:


    Publication date :

    2019-06-01


    Size :

    3561071 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Accident Prediction Models for Two-Lane Rural Highways

    K. R. Kalokota / P. N. Seneviratne | NTIS | 1994


    Probabilistic Lane Change Prediction using Gaussian Process Neural Networks

    Kruger, Martin / Novo, Anne Stockem / Nattermann, Till et al. | IEEE | 2019


    Probabilistic time-to-lane-change prediction on highways

    Wissing, Christian / Nattermann, Till / Glander, Karl-Heinz et al. | IEEE | 2017


    Run-off-road Accident Prediction Model for Two-lane Highway

    Gao, Hai-long / Kan, Wei-sheng / Li, Chang-cheng et al. | ASCE | 2008


    Probabilistic Time-To-Lane-Change Prediction on Highways

    Wissing, Christian / Nattermann, Till / Glander, Karl-Heinz et al. | British Library Conference Proceedings | 2017