Sciweavers

145 search results - page 21 / 29
» On improving point-based 3D recognition
Sort
View
ICCV
2003
IEEE
14 years 9 months ago
View-invariant Alignment and Matching of Video Sequences
In this paper, we propose a novel method to establish temporal correspondence between the frames of two videos. 3D epipolar geometry is used to eliminate the distortion generated ...
Cen Rao, Alexei Gritai, Mubarak Shah, Tanveer Fath...
IBPRIA
2007
Springer
14 years 1 months ago
Improving Piecewise-Linear Registration Through Mesh Optimization
Abstract. Piecewise-linear methods accomplish the registration by dividing the images in corresponding triangular patches, which are individually mapped through affine transformati...
Vicente Arévalo, Javier González
AIPR
2000
IEEE
14 years 2 days ago
Autonomous Video Registration Using Sensor Model Parameter Adjustments
Recently, airborne video surveillance platforms have gained greater acceptance for use in a variety of DoD missions due to their utility, affordability and autonomy. While a varie...
Richard W. Cannata, Steven G. Blask, John A. Van W...
ICRA
2010
IEEE
226views Robotics» more  ICRA 2010»
13 years 6 months ago
Indoor scene recognition through object detection
Abstract— Scene recognition is a highly valuable perceptual ability for an indoor mobile robot, however, current approaches for scene recognition present a significant drop in p...
Pablo Espinace, Thomas Kollar, Alvaro Soto, Nichol...
ICPR
2006
IEEE
14 years 8 months ago
Automatic Texture Synthesis for Face Recognition from Single Views
One possible solution for pose- and illuminationinvariant face recognition is to employ appearancebased approaches, which rely greatly on correct facial textures. However, existin...
Maylor K. H. Leung, Xiaozheng Zhang, Yongsheng Gao