DocumentCode :
2886201
Title :
A new semi-supervised approach for hyperspectral image classification with different active learning strategies
Author :
Dopido, Inmaculada ; Jun Li ; Plaza, Antonio ; Bioucas-Dias, Jose M.
Author_Institution :
Dept. of Technol. of Comput. & Commun., Univ. of Extremadura, Caceres, Spain
fYear :
2012
fDate :
4-7 June 2012
Firstpage :
1
Lastpage :
4
Abstract :
Supervised hyperspectral image classification is a difficult task due to the unbalance between the high dimensionality of the data and the limited availability of labeled training samples in real analysis scenarios. While the collection of labeled samples is generally difficult, expensive and time-consuming, unlabeled samples can be generated in a much easier way. This observation has fostered the idea of adopting semi-supervised learning (SSL) techniques in hyperspectral image classification. The main assumption of such techniques is that the new (unlabeled) training samples can be obtained from a (limited) set of available labeled samples without significant effort/cost. In this paper, we develop a new framework for SSL which exploits active learning (AL) for unlabeled sample selection. Specifically, we use AL to select the most informative unlabeled training samples and further evaluate two different strategies for active sample selection. In this work, the proposed approach is illustrated with the sparse multinomial logistic regression (SMLR) classifier learned with the MLR via variable splitting and augmented Lagrangian (LORSAL) algorithm. Our experimental results with a real hyperspectral image collected by the NASA Jet Propulsion Laboratory´s Airborne Visible Infra-Red Imaging Spectrometer (AVIRIS) indicate that the use of AL for unlabeled sample selection represents an effective and promising strategy in the context of semi-supervised hyperspectral data classification.
Keywords :
geophysical image processing; hyperspectral imaging; image classification; learning (artificial intelligence); regression analysis; remote sensing; AL; AVIRIS; LORSAL algorithm; MLR; NASA jet propulsion laboratory airborne visible infrared imaging spectrometer; SMLR classifier; SSL techniques; active learning strategy; augmented Lagrangian algorithm; high data dimensionality; informative unlabeled training samples; labeled sample collection; real hyperspectral image; semisupervised hyperspectral data classification; semisupervised learning approach; sparse multinomial logistic regression classifier; supervised hyperspectral image classification; unlabeled sample selection; variable splitting algorithm; Abstracts; Decision support systems; Hyperspectral imaging; Imaging; Spatial resolution; Vectors; Hyperspectral image classification; active learning; semi-supervised learning; sparse multinomial logistic regression;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2012 4th Workshop on
Conference_Location :
Shanghai
Print_ISBN :
978-1-4799-3405-8
Type :
conf
DOI :
10.1109/WHISPERS.2012.6874225
Filename :
6874225
Link To Document :
بازگشت