 |
|
|
|
|
|
|
ICCV 2001
International Conference on Computing Vision
Vancouver,
Canada,
July 9- July 12 2001
|
|
| |
|
|
| |
Plan-view
Trajectory Estimation with Dense Stereo Background Models
T. Darrell, D. Demirdjian, N. Checka, P.Felzenszwalb
Vision Interface Group
MIT Artificial Intelligence Laboratory
200 Technology Square, Cambridge, MA 02139 USA
{trevor,demirdji,nealc,pff}@ai.mit.edu
|
|
| |
|
|
| |
ABSTRACT
|
|
| |
|
|
| |
In a known environment,
objects may be tracked in multiple views using a set of
background models. Stereo-based models can be illumination-invariant,
but often have undefined values which inevitably lead to
foreground classification errors. We derive dense stereo
models for object tracking using long-term, extended dynamic-range
imagery, and by detecting and interpolating uniform but
unoccluded planar regions. Foreground points are detected
quickly in new images using pruned disparity search. We
adopt a "late segmentation" strategy, using an
integrated plan-view density representation. Foreground
points are segmented into object regions only when a trajectory
is finally estimated, using dynamic programming-based method.
Object entry and exit are optimally determined and are not
restricted to special spatial zones.
|
|
| |
|
|
|
|
|
|
