A main difficulty for estimating camera and scene geometry from a set of point correspondences is caused by the presence of false matches and independently moving objects. Given two images, after obtaining the matching points, they are usually filtered by an outlier rejection step before being used to solve for epipolar geometry and 3D structure estimation. In the presence of moving objects, image registration becomes a more challenging problem, as the matching and registration phases become interdependent. We propose a novel approach that decouples the above operations, allowing for explicit and separate handling of matching, outlier rejection, grouping, and recovery of camera and scene structure. The method is based on a voting-based computational framework for motion analysis; it determines an accurate representation, in terms of dense velocities, segmented motion regions and boundaries, by using only the smoothness of image motion, followed by the extraction of scene and camera 3D geometry.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Voting-based grouping and interpretation of visual motion


    Contributors:
    Nicolescu, M. (author) / Medioni, G. (author)


    Publication date :

    2004-01-01


    Size :

    433778 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A voting strategy for visual ego-motion from stereo

    Obdržálek, Štĕpán / Matas, J | IEEE | 2010


    Aerial image interpretation via perceptual grouping

    Cosby, S.J. / Thomas, R. | Tema Archive | 1990


    Direct Bayesian Interpretation of Visual Motion

    Laganiere, R. / Mitiche, A. / IEEE et al. | British Library Conference Proceedings | 1994



    Visual Grouping and Object Recognition

    Malik, J. / IEEE | British Library Conference Proceedings | 2001