48 search results - page 4 / 10 » Real-time Body Tracking Using a Gaussian Process Latent Vari... |
CVPR
1999
IEEE
15 years 11 months ago
1999
IEEE
A common method for real-time segmentation of moving regions in image sequences involves "background subtraction," or thresholding the error between an estimate of the i...
ICCV
2005
IEEE
15 years 3 months ago
2005
IEEE
We advocate the use of Scaled Gaussian Process Latent Variable Models (SGPLVM) to learn prior models of 3D human pose for 3D people tracking. The SGPLVM simultaneously optimizes a...
105
click to vote
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human...
BMVC
2001
14 years 12 months ago
2001
A large body of human image processing techniques use skin detection as a first primitive for subsequent feature extraction. Well established methods of colour modelling, such as...
PAMI
2008
14 years 9 months ago
2008
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...