Background modeling plays an important role for video surveillance, object tracking, and object counting. In this paper, we propose a novel deep background modeling approach utilizing fully convolutional network. In the network block constructing the deep background model, three atrous convolution branches with different dilate are used to extract spatial information from different neighborhoods of pixels, which breaks the limitation that extracting spatial information of the pixel from fixed pixel neighborhood. Furthermore, we sample multiple frames from original sequential images with increasing interval, in order to capture more temporal information and reduce the computation. Compared with classical background modeling approaches, our approach outperforms the state-of-art approaches both in indoor and outdoor scenes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Deep Background Modeling Using Fully Convolutional Network


    Contributors:
    Yang, Lu (author) / Li, Jing (author) / Luo, Yuansheng (author) / Zhao, Yang (author) / Cheng, Hong (author) / Li, Jun (author)


    Publication date :

    2018-01-01


    Size :

    2617708 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Fast Vehicle Detection in Satellite Images Using Fully Convolutional Network

    Hu, Jingao / Xu, Tingbing / Zhang, Jixiang et al. | British Library Conference Proceedings | 2016


    TUNING A FULLY CONVOLUTIONAL NETWORK FOR VELOCITY MODEL ESTIMATION

    Campos, L. R. / Nogueira, P. / Nascimento, E. | TIBKAT | 2020


    Emergency Vehicle Detection Using Deep Convolutional Neural Network

    Haque, Samiul / Sharmin, Shayla / Deb, Kaushik | Springer Verlag | 2022



    Employing a fully convolutional neural network for road marking detection

    Horita, Luiz Ricardo T. / Grassi, Valdir | IEEE | 2017