Sciweavers

246 search results - page 41 / 50
» Automatic moving object extraction in MPEG video
Sort
View
ECCV
2006
Springer
14 years 9 months ago
Background Cut
Abstract. In this paper, we introduce background cut, a high quality and realtime foreground layer extraction algorithm. From a single video sequence with a moving foreground objec...
Jian Sun, Weiwei Zhang, Xiaoou Tang, Heung-Yeung S...
CAIP
2007
Springer
101views Image Analysis» more  CAIP 2007»
14 years 1 months ago
Target Positioning with Dominant Feature Elements
We propose a dominant-feature based matching method for capturing a target in a video sequence through the dynamic decomposition of the target template. The target template is segm...
Zhuan Qing Huang, Zhuhan Jiang
ICIP
2005
IEEE
14 years 9 months ago
Visual tracking via efficient kernel discriminant subspace learning
Robustly tracking moving objects in video sequences is one of the key problems in computer vision. In this paper we introduce a computationally efficient nonlinear kernel learning...
Chunhua Shen, Anton van den Hengel, Michael J. Bro...
SPIESR
2003
230views Database» more  SPIESR 2003»
13 years 9 months ago
Bridging the semantic gap in sports
One of the major challenges facing current media management systems and related applications is the so-called ‘‘semantic gap’’ between the rich meaning that a user desires...
Baoxin Li, James H. Errico, Hao Pan, M. Ibrahim Se...
CVPR
2008
IEEE
14 years 9 months ago
Image/video deblurring using a hybrid camera
We propose a novel approach to reduce spatially varying motion blur using a hybrid camera system that simultaneously captures high-resolution video at a low-frame rate together wi...
Yu-Wing Tai, Hao Du, Michael S. Brown, Stephen Lin