4284 search results - page 619 / 857 » Useful Computer Vision Techniques for Human-Robot Interactio... |
192
click to vote
ACIVS
2006
Springer
2006
Springer
Constrained Region-Growing and Edge Enhancement Towards Automated Semantic Video Object Segmentation
15 years 10 months ago
Most existing object segmentation algorithms suffer from a so-called under-segmentation problem, where parts of the segmented object are missing and holes often occur inside the ob...
179
click to vote
ECCV
2006
Springer
15 years 10 months ago
2006
Springer
A scene containing multiple independently moving, possibly occluding, rigid objects is considered under the weak perspective camera model. We obtain a set of feature points tracke...
199
click to vote
ICPR
2000
IEEE
15 years 10 months ago
2000
IEEE
Traditional techniques for tracking non-rigid objects such as optical flow, correlation, active contours or color, can not deal with situations where image changes are not due to ...
193
click to vote
CVPR
2010
IEEE
15 years 10 months ago
2010
IEEE
Depth-map merging is one typical technique category for multi-view stereo (MVS) reconstruction. To guarantee accuracy, existing algorithms usually require either sub-pixel level s...
160
click to vote
BMVC
2000
15 years 8 months ago
2000
This paper addresses the problem of reconstructing surface models of indoor scenes from sparse 3D scene structure captured from N camera views. Sparse 3D measurements of real scen...