ORBi: Marée Raphaël - A Machine Learning Approach for Material Detection in Hyperspectral Images

Reference : A Machine Learning Approach for Material Detection in Hyperspectral Images


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/14710

Title :	A Machine Learning Approach for Material Detection in Hyperspectral Images
Language :	English
Author, co-author :	Marée, Raphaël [Université de Liège - ULg > > GIGA-Management : Plateforme bioinformatique >]
	Stevens, Benjamin [PEPITE SA > > > >]
	Geurts, Pierre [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Guern, Yves [ATIS SA > > > >]
	Mack, Philippe [PEPITE SA > > > >]
Publication date :	2009
Main document title :	Proc. 6th IEEE Workshop on Object Tracking and Classification Beyond and in the Visible Spectrum (OTCBVS-CVPR09)
Publisher :	IEEE
On invitation :	No
Audience :	International
Event name :	6th IEEE Workshop on Object Tracking and Classification Beyond and in the Visible Spectrum
Event place (city) :	Miami
Event country :	USA
Keywords :	[en] image ; hyperspectral ; extra-trees
Abstract :	[en] In this paper we propose a machine learning approach for the detection of gaseous traces in thermal infra red hyperspectral images. It exploits both spectral and spatial information by extracting subcubes and by using extremely randomized trees with multiple outputs as a classifier. Promising results are shown on a dataset of more than 60 hypercubes.
Funders :	Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS ; Union Européenne = European Union - UE = EU
Name of the research project :	HAWKEYE SST4-CT-2005-516168
Permalink :	http://hdl.handle.net/2268/14710
Other URL :	http://www.montefiore.ulg.ac.be/services/stochastic/pubs/2009/MSGGM09

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	maree-subcubes-otcbvs-cvpr09.pdf		Author postprint	241.24 kB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5