This paper presents a method for classifying the direction of movement and for segmenting objects simultaneously using features of space-time patches. Our approach uses vector quantization to classify the direction of movement of an object and to estimate its centroid by referring to a codebook of the space-time patch feature, which is generated from multiple learning samples. We segmented the objects’ regions based on the probability calculated from the mask images of the learning samples by using the estimated centroid of the object. Even though occlusions occur when multiple objects overlap in different directions of movement, our method detects objects individually because their direction of movement is classified. Experimental results show that object detection is more accurate with our method than with the conventional method, which is only based on appearance features.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Combined Object Detection and Segmentation by Using Space-Time Patches


    Contributors:

    Conference:

    Asian Conference on Computer Vision ; 2007 ; Tokyo, Japan November 18, 2007 - November 22, 2007


    Published in:

    Computer Vision – ACCV 2007 ; Chapter : 87 ; 915-924


    Publication date :

    2007-01-01


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Segmentation of Range Data into Rigid Subsets using Surface Patches

    Ashbrook, A. P. / Fisher, R. B. / Robertson, C. et al. | British Library Conference Proceedings | 1998



    Discriminative training for object recognition using image patches

    Deselaers, T. / Keysers, D. / Ney, H. | IEEE | 2005


    Video Denoising via Empirical Bayesian Estimation of Space-Time Patches

    Arias, P. | British Library Online Contents | 2018


    Patches

    Online Contents | 2000