To improve the effectiveness of pedestrian tracking, the histograms of oriented gradients (HOG) and color histogram characteristics are adopted to track pedestrian based on particle filter. Firstly, the pedestrian is detected using the HOG features to determine the initial target position. Then the target is tracked based on particle filter utilizing color histogram, during which the HOG is used to modify particle heavy weights and particle sampling. Experimental results verify the accurateness and efficiency of the proposed method.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pedestrian Tracking with HOG and Color Histogram Features



    Published in:

    Publication date :

    2012-12-13


    Size :

    4 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Color-histogram-based tracking at 2000 fps

    Ishii, I. / Tatebe, T. / Gu, Q. et al. | British Library Online Contents | 2012



    An EM-Like Algorithm for Color-Histogram-Based Object Tracking

    Zivkovic, Z. / Krose, B. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Efficient Color Histogram Indexing

    Sawhney, H. S. / Hafner, J. L. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994


    Efficient color histogram indexing

    Sawhney, H.S. / Hafner, J.L. | IEEE | 1994