Sciweavers

2 search results - page 1 / 1
» 4-D Voting for Matching, Densification and Segmentation into...
Sort
View
ICPR
2002
IEEE
14 years 5 months ago
4-D Voting for Matching, Densification and Segmentation into Motion Layers
* We present a novel approach for grouping from motion, based on a 4-D Tensor Voting computational framework. From sparse point tokens in two frames we recover the dense velocity f...
Gérard G. Medioni, Mircea Nicolescu
CVPR
2003
IEEE
1110views Computer Vision» more  CVPR 2003»
14 years 6 months ago
Motion Segmentation with Accurate Boundaries - A Tensor Voting Approach
Producing an accurate motion flow field is very difficult at motion boundaries. We present a novel, noniterative approach for segmentation from image motion, based on two voting p...
Gérard G. Medioni, Mircea Nicolescu