Sciweavers

1066 search results - page 106 / 214
» Robotic Grasping of Novel Objects using Vision
Sort
View
CORR
2010
Springer
237views Education» more  CORR 2010»
13 years 6 months ago
Featureless 2D-3D Pose Estimation by Minimising an Illumination-Invariant Loss
The problem of identifying the 3D pose of a known object from a given 2D image has important applications in Computer Vision ranging from robotic vision to image analysis. Our pro...
Srimal Jayawardena, Marcus Hutter, Nathan Brewer
ICRA
2003
IEEE
210views Robotics» more  ICRA 2003»
14 years 2 months ago
A truncated least squares approach to the detection of specular highlights in color images
— One of the most difficult aspects of dealing with illumination effects in computer vision is accounting for specularity in the images of real objects. The specular regions in ...
Jae Byung Park, Avinash C. Kak
CVPR
2004
IEEE
14 years 20 days ago
Parts-Based 3D Object Classification
This paper presents a parts-based method for classifying scenes of 3D objects into a set of pre-determined object classes. Working at the part level, as opposed to the whole objec...
Daniel F. Huber, Anuj Kapuria, Raghavendra Donamuk...
CVPR
2009
IEEE
14 years 3 months ago
Disambiguating the recognition of 3D objects
We propose novel algorithms for the detection, segmentation, recognition, and pose estimation of threedimensional objects. Our approach initially infers geometric primitives to de...
Gutemberg Guerra-Filho
ECCV
2000
Springer
14 years 10 months ago
Learning to Recognize 3D Objects with SNoW
This paper describes a novel view-based learning algorithm for 3D object recognition from 2D images using a network of linear units. The SNoW learning architecture is a sparse netw...
Ming-Hsuan Yang, Dan Roth, Narendra Ahuja