Stochastic Tracking of 3D Human Figures Using 2D Image Motion

DMCA

Stochastic Tracking of 3D Human Figures Using 2D Image Motion (2000)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Hedvig Sidenbladh , Michael J. Black , D. J. Fleet

Venue:	In European Conference on Computer Vision
Citations:	383 - 33 self

BibTeX

@INPROCEEDINGS{Sidenbladh00stochastictracking,
    author = {Hedvig Sidenbladh and Michael J. Black and D. J. Fleet},
    title = {Stochastic Tracking of 3D Human Figures Using 2D Image Motion},
    booktitle = {In European Conference on Computer Vision},
    year = {2000},
    pages = {702--718}
}

OpenURL

Abstract

. A probabilistic method for tracking 3D articulated human gures in monocular image sequences is presented. Within a Bayesian framework, we de ne a generative model of image appearance, a robust likelihood function based on image graylevel dierences, and a prior probability distribution over pose and joint angles that models how humans move. The posterior probability distribution over model parameters is represented using a discrete set of samples and is propagated over time using particle ltering. The approach extends previous work on parameterized optical ow estimation to exploit a complex 3D articulated motion model. It also extends previous work on human motion tracking by including a perspective camera model, by modeling limb self occlusion, and by recovering 3D motion from a monocular sequence. The explicit posterior probability distribution represents ambiguities due to image matching, model singularities, and perspective projection. The method relies only on a...

Keyphrases

human figure stochastic tracking image motion previous work perspective projection generative model image appearance monocular sequence motion model limb self occlusion parameterized optical ow estimation robust likelihood function model parameter probabilistic method discrete set human motion tracking explicit posterior probability distribution image matching posterior probability distribution monocular image sequence particle ltering articulated human gures prior probability distribution perspective camera model bayesian framework image graylevel dierences joint angle model singularity

DMCA