Abstract We address the problem of segmenting an image sequence into rigidly moving 3D objects. An elegant solution to this problem is the multibody factorization approach in which the measurement matrix is factored into lower rank matrices. Despite progress in factorization algorithms, the performance is still far from satisfactory and in scenes with missing data and noise, most existing algorithms fail. In this paper we propose a method for incorporating 2D non-motion cues (such as spatial coherence) into multibody factorization. We formulate the problem in terms of constrained factor analysis and use the EM algorithm to find the segmentation. We show that adding these cues improves performance in real and synthetic sequences.


    Access

    Download


    Export, share and cite



    Title :

    Incorporating Non-motion Cues into 3D Motion Segmentation


    Contributors:
    Gruber, Amit (author) / Weiss, Yair (author)


    Publication date :

    2006-01-01


    Size :

    14 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Incorporating Non-motion Cues into 3D Motion Segmentation

    Gruber, A. / Weiss, Y. | British Library Conference Proceedings | 2006


    Incorporating non-motion cues into 3D motion segmentation

    Gruber, A. / Weiss, Y. | British Library Online Contents | 2007


    Multiscale segmentation by combining motion and intensity cues

    Meirav Galun, / Alexander Apartsin, / Ronen Basri, | IEEE | 2005


    Learning and Incorporating Top-Down Cues in Image Segmentation

    He, X. / Zemel, R. S. / Ray, D. | British Library Conference Proceedings | 2006


    Learning and Incorporating Top-Down Cues in Image Segmentation

    He, Xuming / Zemel, Richard S. / Ray, Debajyoti | Springer Verlag | 2006

    Free access