Small sample sizes and imbalanced datasets have been two difficulties in previous traffic incident detection-related studies. Moreover, real-time characteristics of incident detection models must be improved to satisfy the needs of traffic management. In this study, a hybrid model is proposed to address the above problems. In the proposed model, a generative adversarial network (GAN) is used to expand the sample size and balance datasets, and a temporal and spatially stacked autoencoder (TSSAE) is used to extract temporal and spatial correlations of traffic flow and detect incidents. Using a real-world dataset, the model is evaluated from different aspects. The results show that the proposed model, considering both temporal and spatial variables, outperforms some benchmark models. The model can both increase the incident sample size and balance the dataset. Furthermore, the sample selection method improves the real-time capacity of the detection.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Real-time traffic incident detection based on a hybrid deep learning model


    Contributors:
    Li, Linchao (author) / Lin, Yi (author) / Du, Bowen (author) / Yang, Fan (author) / Ran, Bin (author)

    Published in:

    Publication date :

    2022-03-04


    Size :

    21 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Real-time Traffic Incident Detection Using an Autoencoder Model

    Yang, Huan / Wang, Yu / Zhao, Han et al. | IEEE | 2020


    Real-Time Traffic Incident Detection with Classification Methods

    Li, Linchao / Zhang, Jian / Zheng, Yuan et al. | Springer Verlag | 2017


    Real-Time Traffic Incident Detection with Classification Methods

    Li, Linchao / Zhang, Jian / Zheng, Yuan et al. | British Library Conference Proceedings | 2018


    Real-time visual traffic monitoring and automatic incident detection

    Ali, A.T. / Dagless, E.L. | Tema Archive | 1992