Jiayong Zhang, Robert T. Collins, and Yanxi Liu,
"Representation and Matching of Articulated Shapes,"
IEEE Computer Vision and Pattern Recognition,
Washington, DC, June 2004, pp.342-349.
We consider the problem of localizing the articulated and deformable
shape of a walking person in a single view. We represent the non-rigid
2D body contour by a Bayesian graphical model whose nodes correspond
to point positions along the contour. The deformability of the model
is constrained by learned priors corresponding to two basic
mechanisms: local non-rigid deformation, and rotation motion of the
joints. Four types of image cues are combined to relate the model
configuration to the observed image, including edge gradient map,
foreground/background mask, skin color mask, and appearance
consistency constraints. The constructed Bayes network is sparse and
chain-like, enabling efficient spatial inference through Sequential
Monte Carlo sampling methods. We evaluate the performance of the model
on images taken in cluttered, outdoor scenes. The utility of each
image cue is also empirically explored.
Click here for
full paper (1535461 bytes, pdf file).