Sciweavers

11 search results - page 1 / 3
» 3D Skeleton-Based Body Pose Recovery
Sort
View
3DPVT
2006
IEEE
259views Visualization» more  3DPVT 2006»
13 years 9 months ago
3D Skeleton-Based Body Pose Recovery
This paper presents an approach to recover body motions from multiple views using a 3D skeletal model. It takes, as input, foreground silhouette sequences from multiple viewpoints...
Clément Ménier, Edmond Boyer, Bruno ...
PSIVT
2009
Springer
187views Multimedia» more  PSIVT 2009»
13 years 9 months ago
Video-Based Motion Capturing for Skeleton-Based 3D Models
In this paper, a semi-automatic method to capture motion data from a single-camera video is proposed. The input video is first segmented and analyzed, and a 3D character model wit...
Liang-Yu Shih, Bing-Yu Chen, Ja-Ling Wu
CVPR
2009
IEEE
1132views Computer Vision» more  CVPR 2009»
14 years 10 months ago
Observable Subspaces for 3D Human Motion Recovery
The articulated body models used to represent human motion typically have many degrees of freedom, usually expressed as joint angles that are highly correlated. T...
Andrea Fossati (EPFL), Mathieu Salzmann (Universit...
CVPR
2009
IEEE
14 years 10 months ago
Multi-view 3D Human Pose Estimation combining Single-frame Recovery, Temporal Integration and Model Adaptation
We present a system for the estimation of unconstrained 3D human upper body movement from multiple cameras. Its main novelty lies in the integration of three components: single-...
Dariu M. Gavrila, Michael Hofmann
IVC
2007
138views more  IVC 2007»
13 years 3 months ago
Silhouette lookup for monocular 3D pose tracking
Computers should be able to detect and track the articulated 3-D pose of a human being moving through a video sequence. Incremental tracking methods often prove slow and unreliabl...
Nicholas R. Howe