Sciweavers

727 search results - page 42 / 146
» 3D Motion Reconstruction for Real-World Camera Motion
Sort
View
CVIU
2006
110views more  CVIU 2006»
13 years 8 months ago
Viewpoint invariant exemplar-based 3D human tracking
This paper proposes a clustered exemplar-based model for performing viewpoint invariant tracking of the 3D motion of a human subject from a single camera. Each exemplar is associa...
Eng-Jon Ong, Antonio S. Micilotta, Richard Bowden,...
CVPR
2006
IEEE
14 years 2 months ago
Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference
We present an algorithm for jointly learning a consistent bidirectional generative-recognition model that combines top-down and bottom-up processing for monocular 3d human motion ...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
BMVC
2010
13 years 6 months ago
Live Feature Clustering in Video Using Appearance and 3D Geometry
We present a method for live grouping of feature points into persistent 3D clusters as a single camera browses a static scene, with no additional assumptions, training or infrastr...
Adrien Angeli, Andrew Davison
ICRA
2010
IEEE
225views Robotics» more  ICRA 2010»
13 years 6 months ago
3D reconstruction of fish schooling kinematics from underwater video
This paper describes a probabilistic framework to estimate the shape and position of multiple fish in a school. We model the fish shape as an ellipsoid with a curvature coefficient...
Sachit Butail, Derek A. Paley
SIBGRAPI
2009
IEEE
14 years 3 months ago
Scale-Space for Union of 3D Balls
Shape discretization through union of weighted points or balls appears as a common representation in different fields of computer graphics and geometric modeling. Among others, it...
Alex Laier Bordignon, Betina Vath, Thales Vieira, ...