Skip to main content
placeholder image

Compressive evaluation in human motion tracking

Conference Paper


Download full-text (Open Access)

Abstract


  • The powerful theory of compressive sensing enables an efficient

    way to recover sparse or compressible signals from non-adaptive,

    sub-Nyquist-rate linear measurements. In particular, it has been shown

    that random projections can well approximate an isometry, provided that

    the number of linear measurements is no less than twice of the sparsity

    level of the signal. Inspired by these, we propose a compressive anneal

    particle filter to exploit sparsity existing in image-based human motion

    tracking. Instead of performing full signal recovery, we evaluate the observation

    likelihood directly in the compressive domain of the observed

    images. Moreover, we introduce a progressive multilevel wavelet decomposition

    staged at each anneal layer to accelerate the compressive evaluation

    in a coarse-to-fine fashion. The experiments with the benchmark

    dataset HumanEvaII show that the tracking process can be significantly

    accelerated, and the tracking accuracy is well maintained and comparable

    to the method using original image observations.

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). Compressive evaluation in human motion tracking. 10th Asian Conference on Computer Vision (ACCV) (pp. 1-12). Berlin Heidelberg: Springer-Verlag.

Scopus Eid


  • 2-s2.0-79952531954

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1864&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/858

Has Global Citation Frequency


Start Page


  • 1

End Page


  • 12

Place Of Publication


  • Berlin Heidelberg

Abstract


  • The powerful theory of compressive sensing enables an efficient

    way to recover sparse or compressible signals from non-adaptive,

    sub-Nyquist-rate linear measurements. In particular, it has been shown

    that random projections can well approximate an isometry, provided that

    the number of linear measurements is no less than twice of the sparsity

    level of the signal. Inspired by these, we propose a compressive anneal

    particle filter to exploit sparsity existing in image-based human motion

    tracking. Instead of performing full signal recovery, we evaluate the observation

    likelihood directly in the compressive domain of the observed

    images. Moreover, we introduce a progressive multilevel wavelet decomposition

    staged at each anneal layer to accelerate the compressive evaluation

    in a coarse-to-fine fashion. The experiments with the benchmark

    dataset HumanEvaII show that the tracking process can be significantly

    accelerated, and the tracking accuracy is well maintained and comparable

    to the method using original image observations.

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). Compressive evaluation in human motion tracking. 10th Asian Conference on Computer Vision (ACCV) (pp. 1-12). Berlin Heidelberg: Springer-Verlag.

Scopus Eid


  • 2-s2.0-79952531954

Ro Full-text Url


  • http://ro.uow.edu.au/cgi/viewcontent.cgi?article=1864&context=eispapers

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers/858

Has Global Citation Frequency


Start Page


  • 1

End Page


  • 12

Place Of Publication


  • Berlin Heidelberg