Abstract Missing values in the vehicle trajectory data undermine its application in traffic modelling and simulation. Traditional methods for missing data imputation rely on neighbor points of the missing/distorted data point and consequently can hardly handle trajectory with consecutive data loss. To fill in this research gap, external data with latent information should be considered to enhance the imputation. Hence, the primary objective of this study is to find an effective approach to impute consecutive missing data in the vehicle trajectory making use of leading vehicle trajectory. We proposed a novel imputation adversarial convolutional neural network (IACNN) by extending the CNN model with a multi‐objective loss function and adversarial learning framework for vehicle trajectory data imputation. Performance of the model is evaluated on the commonly used trajectory dataset NGSIM with comparison to other baseline models. It turns out that the proposed IACNN outperforms other baseline models in most data loss scenarios, especially with consecutive data loss.


    Access

    Download


    Export, share and cite



    Title :

    Car‐following trajectory data imputation with adversarial convolutional neural network


    Contributors:
    De Zhao (author) / Yan Zhang (author) / Wei Wang (author) / Xuedong Hua (author) / Min Yang (author)


    Publication date :

    2023




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    Unknown




    Car‐following trajectory data imputation with adversarial convolutional neural network

    Zhao, De / Zhang, Yan / Wang, Wei et al. | Wiley | 2023

    Free access

    Innovative method for traffic data imputation based on convolutional neural network

    Zhuang, Yifan / Ke, Ruimin / Wang, Yinhai | IET | 2018

    Free access

    Innovative method for traffic data imputation based on convolutional neural network

    Zhuang, Yifan / Ke, Ruimin / Wang, Yinhai | Wiley | 2019

    Free access

    Deep convolutional generative adversarial networks for traffic data imputation encoding time series as images

    Tongge Huang / Pranamesh Chakraborty / Anuj Sharma | DOAJ | 2023

    Free access

    Traffic Data Imputation with Ensemble Convolutional Autoencoder

    Ye, Yongchao / Zhang, Shuyu / Yu, James J.Q. | IEEE | 2021