Prior art in traffic incident detection relies on high sensor coverage and is primarily based on decision-tree and random forest models that have limited representation capacity and, as a result, cannot detect incidents with high accuracy. This paper presents IncidentNet - a novel approach for classifying, localizing, and estimating the severity of traffic incidents using deep learning models trained on data captured from sparsely placed sensors in urban environments. Our model works on microscopic traffic data that can be collected using cameras installed at traffic intersections. Due to the unavailability of datasets that provide microscopic traffic details and traffic incident details simultaneously, we also present a methodology to generate a synthetic microscopic traffic dataset that matches given macroscopic traffic data. IncidentNet11https://github.com/MPSLab-ASU/IncidentNet achieves a traffic incident detection rate of 98%, with false alarm rates of less than 7% in 197 seconds on average in urban environments with cameras on less than 20% of the traffic intersections.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing




    Publication date :

    2024-09-24


    Size :

    730044 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    IncidentNet: Traffic Incident Detection, Localization and Severity Estimation with Sparse Sensing

    Peddiraju, Sai Shashank / Harapanahalli, Kaustubh / Andert, Edward et al. | ArXiv | 2024

    Free access

    Sparse road traffic incident air ground combination detection method

    LIU XIAOFENG / GUAN ZHIWEI / SONG YUQING et al. | European Patent Office | 2015

    Free access

    Traffic congestion incident detection

    Bowers..., D. J. | TIBKAT | 1996


    A Dempster-Shafer Sensor Fusion Approach for Traffic Incident Detection and Localization

    Mehrannia, Pouya / Moghadam, Aida Arman / Basir, Otman A. | IEEE | 2018


    Multiple Model Particle Filter for Traffic Estimation and Incident Detection

    Wang, Ren / Work, Daniel B. / Sowers, Richard | IEEE | 2016