Paper Info
Title
3D object localization using single camera images
Abstract
In this paper we propose a generic 6d object localization approach based on surface normal images and CAD model data. Normal images or “normal maps” can be obtained using only one single camera shot of a simple camera-projector system. The advantages of this sensor setup are very short acquisition times and the exclusive use of consumer hardware, namely a projector and a grey value camera, making it easy and cheap to build up. All computations are analytically tractable and can be computed in the Fourier domain allowing a very effective and fast computation.
Year
Venue
Keywords
2012
Pattern Recognition
CAD,Fourier analysis,cameras,object recognition,optical projectors,pose estimation,3D object localization,6D object localization approach,CAD model data,Fourier domain,camera-projector system,consumer hardware,fast computation,grey value camera,image acquisition,normal images,normal maps,single camera images,surface normal images
Field
DocType
ISSN
Computer vision,Computer graphics (images),Computer science,Normal mapping,Camera auto-calibration,Projector,Fourier transform,Pose,Artificial intelligence,Normal,Cognitive neuroscience of visual object recognition,Computation
Conference
1051-4651
ISBN
Citations 
PageRank 
978-1-4673-2216-4
0
0.34
References 
Authors
8
4
Name
Order
Citations
PageRank
Dirk Buchholz1222.03
Daniel Kubus2489.02
Simon Winkelbach316217.86
Friedrich M. Wahl4794186.93