Sciweavers

84 search results - page 3 / 17
» Multiple Cues used in Model-Based Human Motion Capture
Sort
View
CVPR
2005
IEEE
15 years 11 months ago
Hybrid Models for Human Motion Recognition
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the h...
Claudio Fanti, Lihi Zelnik-Manor, Pietro Perona
ICCV
2007
IEEE
15 years 11 months ago
Real-Time Marker-free Motion Capture from multiple cameras
We present a fully-automated method for real-time and marker-free 3D human motion capture. The system computes the 3D shape of the person filmed from a synchronized camera set. We...
Brice Michoud, Erwan Guillou, Héctor M. Bri...
CVPR
2003
IEEE
15 years 11 months ago
Shape-From-Silhouette of Articulated Objects and its Use for Human Body Kinematics Estimation and Motion Capture
Shape-From-Silhouette (SFS), also known as Visual Hull (VH) construction, is a popular 3D reconstruction method which estimates the shape of an object from multiple silhouette ima...
German K. M. Cheung, Simon Baker, Takeo Kanade
CVPR
2011
IEEE
14 years 6 months ago
Functional Categorization of Objects using Real-time Markerless Motion Capture
Unsupervised categorization of objects is a fundamental problem in computer vision. While appearance-based methods have become popular recently, other important cues like function...
Juergen Gall, Andrea Fossati, Luc VanGool
ICCV
2003
IEEE
15 years 11 months ago
Model-Based Multiple View Reconstruction of People
This paper presents a framework to reconstruct a scene captured in multiple camera views based on a prior model of the scene geometry. The framework is applied to the capture of a...
Jonathan Starck, Adrian Hilton