Sciweavers

636 search results - page 42 / 128
» Deep Structure from a Geometric Point of View
Sort
View
ICPR
2008
IEEE
14 years 10 months ago
Multiple view based 3D object classification using ensemble learning of local subspaces
Multiple observation improves the performance of 3D object classification. However, since the distribution of feature vectors obtained from multiple view points have strong nonlin...
Jianing Wu, Kazuhiro Fukui
DCG
2002
106views more  DCG 2002»
13 years 8 months ago
Perpendicular Dissections of Space
For each pair (Qi, Qj) of reference points and each real number r there is a unique hyperplane h QiQj such that d(P, Qi)2 - d(P, Qj)2 = r for points P in h. Take n reference point...
Thomas Zaslavsky
PRICAI
2004
Springer
14 years 2 months ago
Shape Matching for Robot Mapping
We present a novel geometric model for robot mapping based on shape. Shape similarity measure and matching techniques originating from computer vision are specially redesigned for ...
Diedrich Wolter, Longin Jan Latecki
APVIS
2009
13 years 6 months ago
Contextual picking of volumetric structures
This paper presents a novel method for the interactive identification of contextual interest points within volumetric data by picking on a direct volume rendered image. In clinica...
Peter Kohlmann, Stefan Bruckner, Armin Kanitsar, M...
CISST
2004
181views Hardware» more  CISST 2004»
13 years 10 months ago
Intrinsic Camera Calibration Based on Radical Center Estimation
Camera calibration is an important step in obtaining 3D information from 2D images. Generally camera parameters can be obtained by using traditional methods if a calibration object...
Dong Hoon Lee, Kyung Ho Jang, Soon Ki Jung