RGB-D Multi-View System Calibration for Full 3D Scene Reconstruction

Afzal, Hassan; Aouada, Djamila; Fofi, David; Mirbach, Bruno; Ottersten, Björn

Reference : RGB-D Multi-View System Calibration for Full 3D Scene Reconstruction


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/10993/17042

Title :	RGB-D Multi-View System Calibration for Full 3D Scene Reconstruction
Language :	English
Author, co-author :	Afzal, Hassan [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Aouada, Djamila [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Fofi, David [Universite de Bourgogne]
	Mirbach, Bruno []
	Ottersten, Björn [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Publication date :	2014
Main document title :	22nd International Conference on Pattern Recognition (ICPR'14)
Peer reviewed :	Yes
Audience :	International
Event name :	22nd International Conference on Pattern Recognition
Event date :	from 24-08-2014 to 28-08-2014
Abstract :	[en] One of the most crucial requirements for building a multi-view system is the estimation of relative poses of all cameras. An approach tailored for a RGB-D cameras based multi-view system is missing. We propose BAICP+ which combines Bundle Adjustment (BA) and Iterative Closest Point (ICP) algorithms to take into account both 2D visual and 3D shape information in one minimization formulation to estimate relative pose parameters of each camera. BAICP+ is generic enough to take different types of visual features into account and can be easily adapted to varying quality of 2D and 3D data. We perform experiments on real and simulated data. Results show that with the right weighting factor BAICP+ has an optimal performance when compared to BA and ICP used independently or sequentially.
Funders :	Fonds National de la Recherche - FnR
Name of the research project :	I2R-DIR-PFN-11FAVE > C11/IS/1204105 : FAVE > 01/01/2012 - 31/12/2014 > OTTERSTEN Björn
Permalink :	http://hdl.handle.net/10993/17042

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	RGB-D Multi-View System Calibration for Full 3D Scene Reconstruction.pdf		Author preprint	3.78 MB	Request a copy

All documents in ORBi^lu are protected by a user license.

University of Luxembourg Library | Feedback | Legal notices