Header logo is ps

Stochastic tracking of {3D} human figures using {2D} image motion


Conference Paper


A probabilistic method for tracking 3D articulated human figures in monocular image sequences is presented. Within a Bayesian framework, we define a generative model of image appearance, a robust likelihood function based on image gray level differences, 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 filtering. The approach extends previous work on parameterized optical flow 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 frame-to-frame assumption of brightness constancy and hence is able to track people under changing viewpoints, in grayscale image sequences, and with complex unknown backgrounds.

Award: (Winner of the 2010 Koenderink Prize for Fundamental Contributions in Computer Vision)
Author(s): Sidenbladh, H. and Black, M. J. and and Fleet, D.J.
Book Title: European Conference on Computer Vision, ECCV
Pages: 702-718
Year: 2000
Month: June
Series: LNCS 1843
Publisher: Springer Verlag

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Dublin, Ireland
Award Paper: Winner of the 2010 Koenderink Prize for Fundamental Contributions in Computer Vision

Links: pdf


  title = {Stochastic tracking of {3D} human figures using {2D} image motion},
  author = {Sidenbladh, H. and Black, M. J. and and Fleet, D.J.},
  booktitle = {European Conference on Computer Vision, ECCV},
  pages = {702-718},
  series = {LNCS 1843},
  publisher = {Springer Verlag},
  address = {Dublin, Ireland},
  month = jun,
  year = {2000},
  month_numeric = {6}