Reconstructing 3D scenes with independently moving objects from uncalibrated monocular image sequences still poses serious challenges. One important problem is to find the relative scales between these different reconstructed objects. The perspective reconstruction of a single object can only be known up to a certain scale which results in a one-parameter family of relative scales and trajectories per moving object. The paper formulates this ambiguity and proposes solutions in the vein of "non-accidentalness". Two instantiations of its use are analyzed: planar motion and the 'heading constraint'.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Reconstructing 3D independent motions using non-accidentalness


    Contributors:
    Ozden, K.E. (author) / Cornelis, K. (author) / Van Eycken, L. (author) / Van Gool, L. (author)


    Publication date :

    2004-01-01


    Size :

    811493 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Reconstructing 3D Independent Motions Using Non-Accidentalness

    Ozden, K. / Cornelis, K. / Van Eycken, L. et al. | British Library Conference Proceedings | 2004


    Estimating Multiple Independent Motions in Segmented Images Using Parametric Models with Local Deformations

    Black, M. J. / Jepson, A. / IEEE et al. | British Library Conference Proceedings | 1994


    Reconstructing Trajectories

    P. Santini | NTIS | 1969


    Reconstructing locomotives

    Brown, Francis R.F. | Engineering Index Backfile | 1898


    Reconstructing surfaces using anisotropic basis functions

    Huong Quynh Dinh, / Turk, G. / Slabaugh, G. | IEEE | 2001