Sciweavers

81 search results - page 14 / 17
» Robust Key Frame Extraction for 3D Reconstruction from Video...
Sort
View
CVPR
2005
IEEE
14 years 10 months ago
Full Body Tracking from Multiple Views Using Stochastic Sampling
We present a novel approach for full body pose tracking using stochastic sampling. A volumetric reconstruction of a person is extracted from silhouettes in multiple video images. ...
Roland Kehl, Matthieu Bray, Luc J. Van Gool
PCM
2001
Springer
195views Multimedia» more  PCM 2001»
14 years 25 days ago
A Motion Activity Descriptor and Its Extraction in Compressed Domain
A novel motion activity descriptor and its extraction from a compressed MPEG (MPEG-1/2) video stream are presented. The descriptor consists of two parts, a temporal descriptor and ...
Xinding Sun, Ajay Divakaran, B. S. Manjunath
ICRA
2010
IEEE
116views Robotics» more  ICRA 2010»
13 years 7 months ago
Learning visibility of landmarks for vision-based localization
— We aim to perform robust and fast vision-based localization using a pre-existing large map of the scene. A key step in localization is associating the features extracted from t...
Pablo Fernández Alcantarilla, Sang Min Oh, ...
ICCV
2005
IEEE
14 years 2 months ago
Spherical Matching for Temporal Correspondence of Non-Rigid Surfaces
This paper introduces spherical matching to estimate dense temporal correspondence of non-rigid surfaces with genus-zero topology. The spherical domain gives a consistent 2D param...
Jonathan Starck, Adrian Hilton
SIGGRAPH
2000
ACM
14 years 23 days ago
Video textures
This paper introduces a new type of medium, called a video texture, which has qualities somewhere between those of a photograph and a video. A video texture provides a continuous ...
Arno Schödl, Richard Szeliski, David Salesin,...