Vehicle trajectory prediction is a crucial task in the field of intelligent transportation systems, with applications in traffic management, autonomous driving, and advanced driver assistance systems. In this project, we aim to demonstrate the capabilities of this technology by collecting and analyzing video footage of traffic in Thu Duc District, Ho Chi Minh city. Utilizing YOLOv7 for object detection and DeepSORT for object tracking, we are able to accurately gather the coordinates of vehicles in the scene. Using these coordinates, we then employ various hybrid models such as CNN-LSTM and CNN-GRU to predict the future trajectory of the vehicles. The results are then visualized and superimposed onto the original video footage to showcase the capabilities of these predictive models.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Leverage Deep Learning Methods for Vehicle Trajectory Prediction in Chaotic Traffic


    Additional title:

    Lect. Notes on Data Eng. and Comms.Technol.


    Contributors:

    Conference:

    International Conference on Intelligence of Things ; 2023 ; Ho Chi Minh City, Vietnam October 25, 2023 - October 27, 2023



    Publication date :

    2023-10-20


    Size :

    11 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Network-Wide Vehicle Trajectory Prediction in Urban Traffic Networks using Deep Learning

    Choi, Seongjin / Yeo, Hwasoo / Kim, Jiwon | Transportation Research Record | 2018


    Real-time traffic conflict prediction at signalized intersections using vehicle trajectory data and deep learning

    Zhang, Gongquan / Jin, Jieling / Chang, Fangrong et al. | Elsevier | 2024

    Free access

    Agent Trajectory Prediction in Urban Traffic Environments via Deep Reward Learning

    Saleh, Khaled / Mihaita, Adriana-Simona / Chalup, Stephan | IEEE | 2024


    Trajectory Data-Driven Network Representation for Traffic State Prediction using Deep Learning

    Yasuda, Shohei / Katayama, Hiroki / Nakanishi, Wataru et al. | Springer Verlag | 2024

    Free access

    Traffic density adaptive vehicle trajectory prediction method

    LIU QIANG / LI ZILONG / ZHU JINGLONG et al. | European Patent Office | 2024

    Free access