Sciweavers

880 search results - page 12 / 176
» Integrating Multiple Model Views for Object Recognition
Sort
View
ICCV
2003
IEEE
14 years 9 months ago
Surface Reconstruction by Integrating 3D and 2D Data of Multiple Views
Surface representation is needed for almost all modeling and visualization applications, but unfortunately, 3D data from a passive vision system are often insufficient for a tradi...
Maxime Lhuillier, Long Quan
AMFG
2003
IEEE
163views Biometrics» more  AMFG 2003»
14 years 29 days ago
Pose Estimation using 3D View-Based Eigenspaces
In this paper we present a method for estimating the absolute pose of a rigid object based on intensity and depth viewbased eigenspaces, built across multiple views of example obj...
Louis-Philippe Morency, Patrik Sundberg, Trevor Da...
IVC
2010
289views more  IVC 2010»
13 years 6 months ago
Automatic 3D object segmentation in multiple views using volumetric graph-cuts
We propose an algorithm for automatically obtaining a segmentation of a rigid object in a sequence of images that are calibrated for camera pose and intrinsic parameters. Until re...
Neill D. F. Campbell, George Vogiatzis, Carlos Her...
CVPR
2011
IEEE
13 years 3 months ago
Cross-View Action Recognition via View Knowledge Transfer
In this paper, we present a novel approach to recognizing human actions from different views by view knowledge transfer. An action is originally modelled as a bag of visual-words ...
Jingen Liu
BMVC
2010
13 years 5 months ago
A general boosting-based framework for active object recognition
We propose a novel general framework with a boosting algorithm to achieve active object classification by view selection. The proposed framework actively decides the next best vie...
Zhaoyin Jia, Yao-Jen Chang, Tsuhan Chen