We present a novel algorithm for optimally segmenting dynamic scenes containing multiple rigidly moving objects. We cast the motion segmentation problem as a constrained nonlinear least squares problem, which minimizes the reprojection error subject to all multibody epipolar constraints. By converting this constrained problem into an unconstrained one, we obtain an objective function that depends on the motion parameters only (fundamental matrices), but is independent on the segmentation of the image features. Therefore, our algorithm does not iterate between feature segmentation and single body motion estimation. Instead, it uses standard nonlinear optimization techniques to simultaneously recover all the fundamental matrices, without prior segmentation. We test our approach on a real sequence.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optimal segmentation of dynamic scenes from two perspective views


    Contributors:
    Vidal, R. (author) / Sastry, S. (author)


    Publication date :

    2003-01-01


    Size :

    370635 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Optimal Segmentation of Dynamic Scenes from Two Perspective Views

    Vidal, R. / Sastry, S. / IEEE | British Library Conference Proceedings | 2003


    Dynamic Segmentation of Traffic Scenes

    Giachetti, A. / Torre, V. / Cappello, M. et al. | British Library Conference Proceedings | 1995


    Segmentation of dynamic scenes from image intensities

    Vidal, R. / Sastry, S. | IEEE | 2002


    Two-body segmentation from two perspective views

    Wolf, L. / Shashua, A. | IEEE | 2001


    Two-Body Segmentation from Two Perspective Views

    Wolf, L. / Shashua, A. / IEEE | British Library Conference Proceedings | 2001