The sudden change of vehicle driving environment will reduce the positioning accuracy of single sensor for target vehicle. In this paper, strong tracking unscented Kalman filter (STUKF) algorithm is used to fuse vision and radar sensors to realize multi-sensor fusion positioning of target vehicle and improve positioning accuracy. Firstly, the vehicle motion model is established, and the unscented Kalman filter (UKF) algorithm is studied. In order to improve the robustness of the UKF algorithm, a strong tracking filter (STF) is introduced into the UKF calculation process, and the fading factor is used to correct the prior error covariance in real time to improve the positioning accuracy of the target vehicle. Finally, simulation verifies that the proposed algorithm has good positioning accuracy and robustness under strong transient conditions.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Vision/Radar Sensor Fusion Positioning Algorithm Based on Strong Tracking Filter and Unscented Kalman Filter


    Contributors:
    Qin, Junji (author) / Li, Cong (author) / Jing, Hui (author) / Wang, Gang (author) / Chang, Junyu (author) / Zhong, Guo'An (author)


    Publication date :

    2022-10-12


    Size :

    1599397 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Unscented Schmidt–Kalman Filter Algorithm

    Stauch, Jason / Jah, Moriba | AIAA | 2015


    Sensor Data Fusion using Unscented Kalman Filter for VOR-based Vision Tracking System for Mobile Robots

    ANJUM, MUHAMMAD LATIF / AHMAD, OMAR / BONA, Basilio et al. | BASE | 2014

    Free access

    Vehicle Fusion Tracking Based on Square Root Unscented Kalman Filter

    Ying, C. / Chongzhao, H. | British Library Online Contents | 2005


    Unscented Schmidt-Kalman Filter Algorithm

    Jason Stauch | Online Contents | 2015