293 search results - page 1 / 59 » Object tracking by bidirectional learning with feature selec... |
ICIP
2009
IEEE
13 years 2 months ago
2009
IEEE
This paper proposes a new tracking algorithm which combines object and background information, via building object and background appearance models simultaneously by nonparametric...
ICPR
2008
IEEE
14 years 6 months ago
2008
IEEE
Online Boosting is an effective incremental learning method which can update weak classifiers efficiently according to the object being trackedt. It is a promising technique for o...
CVPR
2007
IEEE
14 years 7 months ago
2007
IEEE
We treat tracking as a matching problem of detected keypoints between successive frames. The novelty of this paper is to learn classifier-based keypoint descriptions allowing to i...
AMFG
2005
IEEE
13 years 10 months ago
2005
IEEE
It has been shown that features can be selected adaptively for object tracking in changing environments [1]. We propose to use the variance of Mutual Information [2] for online fea...
ICIP
2009
IEEE
14 years 6 months ago
2009
IEEE
Most of the state-of-the-art tracking algorithms are prone to error when dealing with occlusions, especially when the involved moving objects are hardly discernible in appearance....