In this paper we address the problem of multiple 3D rigid body motion estimation from the optical flow. We use the differential epipolar constraint to measure the consistency of the local flow estimates with 3D rigid body motion and employ a probabilistic interpretation of the overall flowfield in terms of mixture models. The estimation of 3D motion parameters as well as the refinement of the initial motion segmentation is carried out using an Expectation-Maximization (EM) algorithm. The algorithm is guaranteed to improve the overall likelihood of the data. The proposed technique is a step towards estimation of 3D motion of independently moving objects in the presence of egomotion.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Experiments in estimation of independent 3D motion using EM


    Contributors:
    Kosecka, J. (author)


    Publication date :

    2001-01-01


    Size :

    545350 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Experiments in Estimation of Independent 3-D Motion Using EM

    Kosecka, J. | British Library Conference Proceedings | 2001


    Detection of Independent Motion Using Directional Motion Estimation

    Fejes, S. / Davis, L. S. | British Library Online Contents | 1999



    Real-Time Detection of Independent Motion using Stereo

    Agrawal, Motilal / Konolige, Kurt / Iocchi, Luca | IEEE | 2005


    Computing Egomotion and Detecting Independent Motion from Image Motion Using Collinear Points

    Da Vitoria Lobo, N. / Tsotsos, J. K. | British Library Online Contents | 1996