Sciweavers

888 search results - page 33 / 178
» Global pose estimation using non-tree models
Sort
View
CRV
2008
IEEE
295views Robotics» more  CRV 2008»
14 years 2 months ago
3D Human Motion Tracking Using Dynamic Probabilistic Latent Semantic Analysis
We propose a generative statistical approach to human motion modeling and tracking that utilizes probabilistic latent semantic (PLSA) models to describe the mapping of image featu...
Kooksang Moon, Vladimir Pavlovic
ICCV
2005
IEEE
14 years 9 months ago
Beyond Trees: Common-Factor Models for 2D Human Pose Recovery
Tree structured models have been widely used for determining the pose of a human body, from either 2D or 3D data. While such models can effectively represent the kinematic constra...
Xiangyang Lan, Daniel P. Huttenlocher
CIVR
2005
Springer
183views Image Analysis» more  CIVR 2005»
14 years 1 months ago
Automated Image Annotation Using Global Features and Robust Nonparametric Density Estimation
This paper describes a simple framework for automatically annotating images using non-parametric models of distributions of image features. We show that under this framework quite ...
Alexei Yavlinsky, Edward Schofield, Stefan M. R&uu...
ICIP
2004
IEEE
14 years 9 months ago
Unsupervised motion detection using a markovian temporal model with global spatial constraints
In this work, we propose an unsupervised Bayesian model for the detection of moving objects from dynamic scenes. This unsupervised solution is a three-step approach that uses a st...
Pierre-Marc Jodoin, Max Mignotte
ICCV
2009
IEEE
13 years 5 months ago
Complex volume and pose tracking with probabilistic dynamical models and visual hull constraints
We propose a method for estimating the pose of a human body using its approximate 3D volume (visual hull) obtained in real time from synchronized videos. Our method can cope with ...
Norimichi Ukita, Michiro Hirai, Masatsugu Kidode