195 search results - page 14 / 39 » Robust Computer Vision through Kernel Density Estimation |
BMVC
2001
15 years 2 days ago
2001
This paper introduces a new method of registering point sets. The registration error is directly minimized using general-purpose non-linear optimization (the Levenberg–Marquardt...
FGR
2006
IEEE
15 years 1 months ago
2006
IEEE
Non-linear subspaces derived using kernel methods have been found to be superior compared to linear subspaces in modeling or classification tasks of several visual phenomena. Such...
ECCV
2002
Springer
15 years 11 months ago
2002
Springer
Abstract. In many vision problems, the observed data lies in a nonlinear manifold in a high-dimensional space. This paper presents a generic modelling scheme to characterize the no...
114
click to vote
CVPR
2010
IEEE
15 years 5 months ago
2010
IEEE
Motion blur due to camera shake is a annoying problem in low-light photography. In this paper, we propose a novel method to recover a sharp image from a pair of motion blurred and ...
ACIVS
2009
Springer
15 years 4 months ago
2009
Springer
Abstract. In this paper, we present a fully automatic approach to multiple human detection and tracking in high density crowds in the presence of extreme occlusion. Human detection...