Paper Info
Title
Combination of foveal and peripheral vision for object recognition and pose estimation
Abstract
In this paper, we present a real-time vision system that integrates a number of algorithms using monocular and binocular cues to achieve robustness in realistic settings, for tasks such as object recognition, tracking and pose estimation. The system consists of two sets of binocular cameras; a peripheral set for disparity based attention and a foveal one for higher level processes. Thus the conflicting requirements of a wide field of view and high resolution can be overcome. One important property of the system is that the step from task specification through object recognition to pose estimation is completely automatic, combining both appearance and geometric models. Experimental evaluation is performed in a realistic indoor environment with occlusions, clutter, changing lighting and background conditions.
Year
DOI
Venue
2004
10.1109/ROBOT.2004.1302532
Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference
Keywords
Field
DocType
real time systems,image segmentation,machine vision,layout,robustness,peripheral vision,solid modeling,computer vision,object recognition,geometric model,high resolution,image recognition,field of view,pose estimation
Computer vision,3D single-object recognition,Computer science,3D pose estimation,Pose,Peripheral vision,Foveal,Artificial intelligence,Depth perception,Articulated body pose estimation,Cognitive neuroscience of visual object recognition
Conference
Volume
ISSN
ISBN
5
1050-4729
0-7803-8232-3
Citations 
PageRank 
References 
20
0.96
14
Authors
2
Name
Order
Citations
PageRank
Mårten Björkman120213.90
Danica Kragic22070142.17