In this paper we discuss a hybrid technique for piecewise-smooth optical flow estimation. We first pose optical flow estimation as a gradient-based local regression problem and solve it under a high-breakdown robust criterion. Then taking the output from the first step as the initial guess, we recast the problem in a robust matching-based global optimization framework. We have developed novel fast-converging deterministic algorithms for both optimization problems and incorporated a hierarchical scheme to handle large motions. This technique inherits the good subpixel accuracy from the local gradient approach and the insensitivity to local perturbation and derivative quality from the global matching approach, and it overcomes the limitations of both. Significant advantages over competing techniques are demonstrated on various standard synthetic and real image sequences.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Local gradient, global matching, piecewise-smooth optical flow


    Contributors:
    Ye, M. (author) / Haralick, R.A. (author)


    Publication date :

    2001-01-01


    Size :

    1025679 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Local Gradient, Global Matching, Piecewise-Smooth Optical Flow

    Ye, M. / Haralick, R. M. / IEEE | British Library Conference Proceedings | 2001


    Piecewise-Smooth Dense Optical Flow via Level Sets

    Amiaz, T. / Kiryati, N. | British Library Online Contents | 2006


    Tomographic Reconstruction of Piecewise Smooth Images

    Alvino, C. / Yezzi, A. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Tomographic reconstruction of piecewise smooth images

    Alvino, C.V. / Yezzi, A.J. | IEEE | 2004


    Low-dimensional maps for piecewise smooth oscillators

    Pavlovskaia, Ekaterina | Online Contents | 2007