Sciweavers

327 search results - page 46 / 66
» Disambiguating the recognition of 3D objects
Sort
View
CVPR
2011
IEEE
13 years 5 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...
RSS
2007
145views Robotics» more  RSS 2007»
13 years 11 months ago
Semantic Modeling of Places using Objects
— While robot mapping has seen massive strides , higher level abstractions in map representation are still not widespread. Maps containing semantic concepts such as objects and l...
Ananth Ranganathan, Frank Dellaert
IROS
2009
IEEE
161views Robotics» more  IROS 2009»
14 years 4 months ago
Accurate shape-based 6-DoF pose estimation of single-colored objects
— The problem of accurate 6-DoF pose estimation of 3D objects based on their shape has so far been solved only for specific object geometries. Edge-based recognition and trackin...
Pedram Azad, Tamim Asfour, Rüdiger Dillmann
ICCV
2007
IEEE
14 years 11 months ago
Depth-From-Recognition: Inferring Meta-data by Cognitive Feedback
Thanks to recent progress in category-level object recognition, we have now come to a point where these techniques have gained sufficient maturity and accuracy to succesfully feed...
Alexander Thomas, Vittorio Ferrari, Bastian Leibe,...
ACCV
2006
Springer
14 years 3 months ago
Probabilistic Modeling for Structural Change Inference
We view the task of change detection as a problem of object recognition from learning. The object is defined in a 3D space where the time is the 3rd dimension. We propose two com...
Wei Liu, Véronique Prinet