Sciweavers

41 search results - page 3 / 9
» Monocular video foreground segmentation system
Sort
View
HUMO
2007
Springer
14 years 1 months ago
Multi-activity Tracking in LLE Body Pose Space
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
Tobias Jaeggli, Esther Koller-Meier, Luc J. Van Go...
ICIP
2006
IEEE
14 years 9 months ago
Multispectral Object Segmentation and Retrieval in Surveillance Video
This paper describes a system for object segmentation and feature extraction for surveillance video. Segmentation is performed by a dynamic vision system that fuses information fr...
Ciarán O. Conaire, Noel E. O'Connor, Eddie ...
CVPR
2006
IEEE
14 years 9 months ago
Bilayer Segmentation of Live Video
This paper presents an algorithm capable of real-time separation of foreground from background in monocular video sequences. Automatic segmentation of layers from colour/contrast ...
Antonio Criminisi, Geoffrey Cross, Andrew Blake, V...
CVPR
2004
IEEE
14 years 9 months ago
Bayesian Video Matting Using Learnt Image Priors
Video matting, or layer extraction, is a classic inverse problem in computer vision that involves the extraction of foreground objects, and the alpha mattes that describe their op...
Nicholas Apostoloff, Andrew W. Fitzgibbon
VCIP
2003
146views Communications» more  VCIP 2003»
13 years 9 months ago
A segmentation system with model-assisted completion of video objects
This paper presents a new algorithm for video-object segmentation, which combines motion-based segmentation, high-level object-model detection, and spatial segmentation into a sin...
Dirk Farin, Peter H. N. de With, Wolfgang Effelsbe...