Skip to main content
placeholder image

Gradual sampling and mutual information maximisation for markerless motion capture

Conference Paper


Abstract


  • The major issue in markerless motion capture is finding the

    global optimum from the multimodal setting where distinctive gestures

    may have similar likelihood values. Instead of only focusing on effective

    searching as many existing works, our approach resolves gesture ambiguity

    by designing a better-behaved observation likelihood. We extend

    Annealed Particle Filtering by a novel gradual sampling scheme that

    allows evaluations to concentrate on large mismatches of the tracking

    subject. Noticing the limitation of silhouettes in resolving gesture ambiguity,

    we incorporate appearance information in an illumination invariant

    way by maximising Mutual Information between an appearance

    model and the observation. This in turn strengthens the effectiveness of

    the better-behaved likelihood. Experiments on the benchmark datasets

    show that our tracking performance is comparable to or higher than the

    state-of-the-art studies, but with simpler setting and higher computational

    efficiency.

Authors


  •   Lu, Yifan (external author)
  •   Wang, Lei
  •   Hartley, Richard (external author)
  •   Li, Hongdong (external author)
  •   Xu, Dan (external author)

Publication Date


  • 2010

Citation


  • Lu, Y., Wang, L., Hartley, R., Li, H. & Xu, D. (2010). Gradual sampling and mutual information maximisation for markerless motion capture. 10th Asian Conference on Computer Vision (ACCV) (pp. 554-565). Berlin Heidelberg: Springer-Verlag.

Scopus Eid


  • 2-s2.0-79952500191

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/528

Start Page


  • 554

End Page


  • 565

Abstract


  • The major issue in markerless motion capture is finding the

    global optimum from the multimodal setting where distinctive gestures

    may have similar likelihood values. Instead of only focusing on effective

    searching as many existing works, our approach resolves gesture ambiguity

    by designing a better-behaved observation likelihood. We extend

    Annealed Particle Filtering by a novel gradual sampling scheme that

    allows evaluations to concentrate on large mismatches of the tracking

    subject. Noticing the limitation of silhouettes in resolving gesture ambiguity,

    we incorporate appearance information in an illumination invariant

    way by maximising Mutual Information between an appearance

    model and the observation. This in turn strengthens the effectiveness of

    the better-behaved likelihood. Experiments on the benchmark datasets

    show that our tracking performance is comparable to or higher than the

    state-of-the-art studies, but with simpler setting and higher computational

    efficiency.

Authors


  •   Lu, Yifan (external author)
  •   Wang, Lei
  •   Hartley, Richard (external author)
  •   Li, Hongdong (external author)
  •   Xu, Dan (external author)

Publication Date


  • 2010

Citation


  • Lu, Y., Wang, L., Hartley, R., Li, H. & Xu, D. (2010). Gradual sampling and mutual information maximisation for markerless motion capture. 10th Asian Conference on Computer Vision (ACCV) (pp. 554-565). Berlin Heidelberg: Springer-Verlag.

Scopus Eid


  • 2-s2.0-79952500191

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/528

Start Page


  • 554

End Page


  • 565