Sciweavers

521 search results - page 89 / 105
» Foreground Object Detection Using Two Successive Images
Sort
View
CVPR
2008
IEEE
15 years 11 months ago
Global pose estimation using non-tree models
We propose a novel global pose estimation method to detect body parts of articulated objects in images based on non-tree graph models. There are two kinds of edges defined in the ...
Hao Jiang, David R. Martin
138
Voted
CAPTECH
1998
Springer
15 years 1 months ago
3D Part Recognition Method for Human Motion Analysis
A method for matching sequences from two perspective views of a moving person silhouette is presented. Regular (approximate uniform thickness) parts are detected on an image and a ...
Carlos Yániz, Jairo Rocha, Francisco J. Per...
MCAM
2007
Springer
238views Multimedia» more  MCAM 2007»
15 years 3 months ago
A Three-Level Scheme for Real-Time Ball Tracking
A three-level method is proposed to achieve robust and real-time ball tracking in soccer videos. It includes object-, intra-trajectory-, and intertrajectory-level processing. Due t...
Xiaofeng Tong, Tao Wang, Wenlong Li, Yimin Zhang, ...
CVPR
2000
IEEE
15 years 11 months ago
Reliable Feature Matching across Widely Separated Views
In this paper we present a robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints. Un...
Adam Baumberg
CVPR
2004
IEEE
15 years 11 months ago
Bayesian Fusion of Camera Metadata Cues in Semantic Scene Classification
Semantic scene classification based only on low-level vision cues has had limited success on unconstrained image sets. On the other hand, camera metadata related to capture condit...
Matthew R. Boutell, Jiebo Luo