Background modeling is an important component of many vision systems. Existing work in the area has mostly addressed scenes that consist of static or quasi-static structures. When the scene exhibits a persistent dynamic behavior in time, such an assumption is violated and detection performance deteriorates. In this paper, we propose a new method for the modeling and subtraction of such scenes. Towards the modeling of the dynamic characteristics, optical flow is computed and utilized as a feature in a higher dimensional space. Inherent ambiguities in the computation of features are addressed by using a data-dependent bandwidth for density estimation using kernels. Extensive experiments demonstrate the utility and performance of the proposed approach.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Motion-based background subtraction using adaptive kernel density estimation


    Beteiligte:
    Mittal, A. (Autor:in) / Paragios, N. (Autor:in)


    Erscheinungsdatum :

    2004-01-01


    Format / Umfang :

    706064 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Motion-Based Background Subtraction Using Adaptive Kernel Density Estimation

    Mittal, A. / Paragios, N. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Object Tracking Using Background Subtraction and Motion Estimation in MPEG Videos

    Aggarwal, Ashwani / Biswas, Susmit / Singh, Sandeep et al. | Springer Verlag | 2006


    Object Tracking Using Background Subtraction and Motion Estimation in MPEG Videos

    Aggarwal, A. / Biswas, S. / Singh, S. et al. | British Library Conference Proceedings | 2006


    Motion based Object Detection based on Background Subtraction: A Review

    Baral, Ayush / Gupta, Deepa / Sharma, Lavanya | IEEE | 2019


    Adaptive maintenance scheme for codebook-based dynamic background subtraction

    Zeng, Zhi / Jia, Jianyuan / Zhu, Zhaofei et al. | British Library Online Contents | 2016