8 search results - page 1 / 2 » Recovering Motion Fields: An Evaluation of Eight Optical Flo... |
BMVC
1998
13 years 6 months ago
1998
Evaluating the performance of optical flow algorithms has been difficult because of the lack of ground-truth data sets for complex scenes. We describe a simple modification to a r...
ICCV
2007
IEEE
14 years 6 months ago
2007
IEEE
This paper presents a method for scene flow estimation from a calibrated stereo image sequence. The scene flow contains the 3-D displacement field of scene points, so that the 2-D...
ICPR
2008
IEEE
13 years 11 months ago
2008
IEEE
Video footage of real crowded scenes still poses severe challenges for automated surveillance. This paper evaluates clustering methods for finding independent dominant motion fi...
ICCV
2009
IEEE
14 years 9 months ago
2009
IEEE
The accurate estimation of motion in image sequences is
of central importance to numerous computer vision applications.
Most competitive algorithms compute flow fields
by minimi...
ICCV
2003
IEEE
14 years 6 months ago
2003
IEEE
A novel procedure is presented to construct image-domain filters (receptive fields) that directly recover local motion and shape parameters. These receptive fields are derived fro...