Sciweavers

790 search results - page 12 / 158
» Gaussian Process Dynamical Models for Human Motion
Sort
View
CRV
2008
IEEE
295views Robotics» more  CRV 2008»
15 years 6 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
PG
2007
IEEE
15 years 6 months ago
Line Drawing as a Dynamic Process
We introduce a novel mechanism for creating line drawings from three-dimensional models, which captures the dynamic nature of the drawing process. The approach takes into account ...
Donald H. House, Mayank Singh
AVSS
2006
IEEE
15 years 5 months ago
Dynamic Control of Adaptive Mixture-of-Gaussians Background Model
We propose a method for create a background model in non-stationary scenes. Each pixel has a dynamic Gaussian mixture model. Our approach can automatically change the number of Ga...
Atsushi Shimada, Daisaku Arita, Rin-ichiro Taniguc...
ICPR
2008
IEEE
16 years 29 days ago
Dual generative models for human motion estimation from an uncalibrated monocular camera
We propose a new approach to estimate gait kinematics from image sequences taken by a monocular uncalibrated camera. This approach involves two generative models for gait represen...
Guoliang Fan, Xin Zhang
ICRA
2003
IEEE
196views Robotics» more  ICRA 2003»
15 years 5 months ago
Generating whole body motions for a biped humanoid robot from captured human dances
— The goal of this study is a system for a robot to imitate human dances. This paper describes the process to generate whole body motions which can be performed by an actual bipe...
Shinichiro Nakaoka, Atsushi Nakazawa, Kazuhito Yok...