Skip to main content
placeholder image

Fast multi-labelling for stereo matching

Conference Paper


Abstract


  • We describe a new fast algorithm for multi-labelling problems.

    In general, a multi-labelling problem is NP-hard.Widely used algorithms

    like α-expansion can reach a suboptimal result in a time linear in

    the number of the labels. In this paper, we propose an algorithm which

    can obtain results of comparable quality polynomially faster. We use the

    Divide and Conquer paradigm to separate the complexities induced by

    the label set and the variable set, and deal with each of them respectively.

    Such a mechanism improves the solution speed without depleting

    the memory resource, hence it is particularly valuable for applications

    where the variable set and the label set are both huge. Another merit of

    the proposed method is that the trade-off between quality and time efficiency

    can be varied through using different parameters. The advantage

    of our method is validated by experiments.

Authors


  •   Zhang, Yuhang (external author)
  •   Hartley, Richard (external author)
  •   Wang, Lei

Publication Date


  • 2010

Citation


  • Zhang, Y., Hartley, R. & Wang, L. (2010). Fast multi-labelling for stereo matching. 11th European Conference on Computer Vision (ECCV) (pp. 524-537). Heldermann Verlag: Springer-Verlag.

Scopus Eid


  • 2-s2.0-78149329131

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/531

Start Page


  • 524

End Page


  • 537

Abstract


  • We describe a new fast algorithm for multi-labelling problems.

    In general, a multi-labelling problem is NP-hard.Widely used algorithms

    like α-expansion can reach a suboptimal result in a time linear in

    the number of the labels. In this paper, we propose an algorithm which

    can obtain results of comparable quality polynomially faster. We use the

    Divide and Conquer paradigm to separate the complexities induced by

    the label set and the variable set, and deal with each of them respectively.

    Such a mechanism improves the solution speed without depleting

    the memory resource, hence it is particularly valuable for applications

    where the variable set and the label set are both huge. Another merit of

    the proposed method is that the trade-off between quality and time efficiency

    can be varied through using different parameters. The advantage

    of our method is validated by experiments.

Authors


  •   Zhang, Yuhang (external author)
  •   Hartley, Richard (external author)
  •   Wang, Lei

Publication Date


  • 2010

Citation


  • Zhang, Y., Hartley, R. & Wang, L. (2010). Fast multi-labelling for stereo matching. 11th European Conference on Computer Vision (ECCV) (pp. 524-537). Heldermann Verlag: Springer-Verlag.

Scopus Eid


  • 2-s2.0-78149329131

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/531

Start Page


  • 524

End Page


  • 537