An Adaptive Local Texture Feature Background Model (ALTF-BM) is proposed to resolve the deficiency in current background models, which are easily contaminated by sudden and gradual illumination changes in complex urban traffic scenes. Based on Weber's law, the authors first develop Adaptive Local Texture Feature (ALTF), calculated over a predefined local region around the pixel employing an adaptive distance threshold, and then the background is modelled on the base of sample consensus scheme using the calculated features. Furthermore, to label the foreground pixels, the difference between the background model and input video frames is then directly compared by ALTF encoding. Finally, the model is updated using the random update policy to adapt to the changing illumination and the dynamic background. The experimental results on real-world urban traffic videos and the public Change Detection benchmark of 2014 (CDnet2014) show that the proposed ALTF-BM offers the best performance compared to the other state-of-the-art texture-based methods, and the average F-measures and similarity results of the proposed ALTF-BM are 0.547 and 0.393 higher than benchmarks on the night traffic-light sequence, respectively. The encouraging experimental results demonstrate the efficiency of the proposed ALTF-BM in handling sudden and gradual illumination changes in urban traffic scenes.


    Access

    Access via TIB


    Export, share and cite



    Title :

    Vehicles detection for illumination changes urban traffic scenes employing adaptive local texture feature background model


    Contributors:
    Zhang, Yunsheng (author) / Zhao, Chihang (author) / Shi, Wen (author) / Leng, Kaijun (author)

    Published in:

    Publication date :

    2018-10-02


    Size :

    8 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English





    Background Updating in Illumination-Variant Scenes

    He, Y. / Wang, H. / Zhang, B. et al. | British Library Conference Proceedings | 2003


    Background updating in illumination-variant scenes

    Yinghua He, / Hong Wang, / Bo Zhang, | IEEE | 2003


    Vehicles detection in complex urban traffic scenes using Gaussian mixture model with confidence measurement

    Zhang, Yunsheng / Zhao, Chihang / He, Jie et al. | Wiley | 2016

    Free access

    Vehicles detection in complex urban traffic scenes using Gaussian mixture model with confidence measurement

    Zhang, Yunsheng / Zhao, Chihang / He, Jie et al. | IET | 2016

    Free access