Sciweavers

47 search results - page 7 / 10
» The Role of Total Least Squares in Motion Analysis
Sort
View
ICCV
2001
IEEE
14 years 9 months ago
Robust Principal Component Analysis for Computer Vision
Principal Component Analysis (PCA) has been widely used for the representation of shape, appearance, and motion. One drawback of typical PCA methods is that they are least squares...
Fernando De la Torre, Michael J. Black
ICMCS
1999
IEEE
234views Multimedia» more  ICMCS 1999»
13 years 11 months ago
Spatiotemporal Segmentation and Tracking of Objects for Visualization of Videoconference Image Sequences
Abstract--In this paper, a procedure is described for the segmentation, content-based coding, and visualization of videoconference image sequences. First, image sequence analysis i...
Ioannis Kompatsiaris, Michael G. Strintzis
FGR
2002
IEEE
197views Biometrics» more  FGR 2002»
14 years 10 days ago
Robust Full-Motion Recovery of Head by Dynamic Templates and Re-Registration Techniques
This paper presents a method to recover the full-motion (3 rotations and 3 translations) of the head from an input video using a cylindrical head model. Given an initial reference...
Jing Xiao, Takeo Kanade, Jeffrey F. Cohn
CVPR
2008
IEEE
14 years 9 months ago
On errors-in-variables regression with arbitrary covariance and its application to optical flow estimation
Linear inverse problems in computer vision, including motion estimation, shape fitting and image reconstruction, give rise to parameter estimation problems with highly correlated ...
Björn Andres, Claudia Kondermann, Daniel Kond...
SIP
2007
13 years 8 months ago
Mosaic-based figure-ground segmentation along with static segmentation by mean shift
This work deals with the problem of backgroundforeground segmentation in video scenes. We propose an approach that makes use of feature extraction and matching, robust estimation,...
J. Sole, Yu Huang, Joan Llach