Sciweavers

445 search results - page 50 / 89
» Shape-based object recognition in videos using 3D synthetic ...
Sort
View
ICCV
1995
IEEE
13 years 11 months ago
Alignment by Maximization of Mutual Information
A new information-theoretic approach is presented for finding the pose of an object in an image. The technique does not require information about the surface properties of the ob...
Paul A. Viola, William M. Wells III
ECCV
2006
Springer
14 years 9 months ago
Feature Harvesting for Tracking-by-Detection
We propose a fast approach to 3?D object detection and pose estimation that owes its robustness to a training phase during which the target object slowly moves with respect to the ...
Mustafa Özuysal, Vincent Lepetit, Franç...
CVPR
2011
IEEE
13 years 3 months ago
Real-time Human Pose Recognition in Parts from Single Depth Images
We propose a new method to quickly and accurately predict 3D positions of body joints from a single depth image, using no temporal information. We take an object recognition appro...
Jamie Shotton, Andrew Fitzgibbon, Mat Cook, Andrew...
ECCV
2004
Springer
14 years 9 months ago
Shape and View Independent Reflectance Map from Multiple Views
We consider the problem of estimating the 3D shape and reflectance properties of an object made of a single material from a calibrated set of multiple views. To model reflectance, ...
Tianli Yu, Ning Xu, Narendra Ahuja
DAGM
2003
Springer
14 years 1 months ago
Real-Time Recognition of 3D-Pointing Gestures for Human-Machine-Interaction
We present a system capable of visually detecting pointing gestures and estimating the 3D pointing direction in real-time. We use Hidden Markov Models (HMMs) trained on different ...
Kai Nickel, Rainer Stiefelhagen