A new framework dealing with motion estimation in transparent images is presented. It relies on a block-oriented estimation involving an efficient multiresolution minimization. A downhill simplex method provides an appropriate initialization to this scheme. The estimated velocity vectors are greatly improved by an original postprocessing stage which performs a single motion estimation on differences of warped images. Finally, a regularization step is carried out. It is demonstrated on a large set of simulations that a quarter-pixel accuracy can be attained on noise-free images. The case of noisy images is also addressed and provides satisfactory results, even in the case of low-contrasted medical images. An example on real clinical images is also reported with promising results.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multiresolution parametric estimation of transparent motions


    Contributors:
    Auvray, V. (author) / Bouthemy, P. (author) / Lienard, J. (author)


    Publication date :

    2005-01-01


    Size :

    232312 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multiresolution Parametric Estimation of Transparent Motions

    Auvray, V. / Bouthemy, P. / Lienard, J. | British Library Conference Proceedings | 2005


    Computing Occluding and Transparent Motions

    Irani, M. / Rousso, B. / Peleg, S. | British Library Online Contents | 1994


    Multiresolution motion estimation and target detection

    Karlsen, R.E. / Gorsich, D.J. / Gerhart, G.R. | Tema Archive | 1998


    Multiresolution-based motion estimation [3062-32]

    Gorsich, D. / Karlsen, R. E. / Gerhart, G. R. et al. | British Library Conference Proceedings | 1997


    The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow Fields

    Black, M. J. / Anandan, P. | British Library Online Contents | 1996