000017745 001__ 17745 000017745 005__ 20200702121611.0 000017745 0247_ $$2DOI$$a10.1016/j.cageo.2011.05.012 000017745 0247_ $$2WOS$$aWOS:000298524100012 000017745 037__ $$aPreJuSER-17745 000017745 041__ $$aeng 000017745 082__ $$a550 000017745 084__ $$2WoS$$aComputer Science, Interdisciplinary Applications 000017745 084__ $$2WoS$$aGeosciences, Multidisciplinary 000017745 1001_ $$0P:(DE-Juel1)VDB4989$$aCanty, M. J.$$b0$$uFZJ 000017745 245__ $$aLinear and Kernel Methods for Multivariate Change Detection 000017745 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2012 000017745 300__ $$a107 - 114 000017745 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article 000017745 3367_ $$2DataCite$$aOutput Types/Journal article 000017745 3367_ $$00$$2EndNote$$aJournal Article 000017745 3367_ $$2BibTeX$$aARTICLE 000017745 3367_ $$2ORCID$$aJOURNAL_ARTICLE 000017745 3367_ $$2DRIVER$$aarticle 000017745 440_0 $$019264$$aComputers & Geosciences$$v38$$x0098-3004 000017745 500__ $$3POF3_Assignment on 2016-02-29 000017745 500__ $$aRecord converted from VDB: 12.11.2012 000017745 520__ $$aThe iteratively reweighted multivariate alteration detection (IR-MAD) algorithm may be used both for unsupervised change detection in multi- and hyperspectral remote sensing imagery and for automatic radiometric normalization of multitemporal image sequences. Principal components analysis (PCA), as well as maximum autocorrelation factor (MAF) and minimum noise fraction (MNF) analyses of IR-MAD images, both linear and kernel-based (nonlinear), may further enhance change signals relative to no-change background. IDL (Interactive Data Language) implementations of IR-MAD, automatic radiometric normalization, and kernel PCA/MAF/MNF transformations are presented that function as transparent and fully integrated extensions of the ENVI remote sensing image analysis environment. The train/test approach to kernel PCA is evaluated against a Hebbian learning procedure. Matlab code is also available that allows fast data exploration and experimentation with smaller datasets. New, multiresolution versions of IR-MAD that accelerate convergence and that further reduce no-change background noise are introduced. Computationally expensive matrix diagonalization and kernel image projections are programmed to run on massively parallel CUDA-enabled graphics processors, when available, giving an order of magnitude enhancement in computational speed. The software is available from the authors' Web sites. (C) 2011 Elsevier Ltd. All rights reserved. 000017745 536__ $$0G:(DE-Juel1)FUEK407$$2G:(DE-HGF)$$aTerrestrische Umwelt$$cP24$$x0 000017745 588__ $$aDataset connected to Web of Science 000017745 650_7 $$2WoSType$$aJ 000017745 65320 $$2Author$$aCUDA 000017745 65320 $$2Author$$aENVI 000017745 65320 $$2Author$$aIDL 000017745 65320 $$2Author$$aIR-MAD 000017745 65320 $$2Author$$aiMAD 000017745 65320 $$2Author$$aKernel methods 000017745 65320 $$2Author$$aMatlab 000017745 65320 $$2Author$$aRadiometric normalization 000017745 65320 $$2Author$$aRemote sensing 000017745 65320 $$2Author$$aMultiresolution 000017745 7001_ $$0P:(DE-HGF)0$$aNielsen, A.A.$$b1 000017745 773__ $$0PERI:(DE-600)1499977-8$$a10.1016/j.cageo.2011.05.012$$gVol. 38, p. 107 - 114$$p107 - 114$$q38<107 - 114$$tComputers & geosciences$$v38$$x0098-3004$$y2012 000017745 8567_ $$uhttp://dx.doi.org/10.1016/j.cageo.2011.05.012 000017745 909CO $$ooai:juser.fz-juelich.de:17745$$pVDB$$pVDB:Earth_Environment 000017745 9131_ $$0G:(DE-Juel1)FUEK407$$1G:(DE-HGF)POF2-240$$2G:(DE-HGF)POF2-200$$bErde und Umwelt$$kP24$$lTerrestrische Umwelt$$vTerrestrische Umwelt$$x0 000017745 9132_ $$0G:(DE-HGF)POF3-259H$$1G:(DE-HGF)POF3-250$$2G:(DE-HGF)POF3-200$$aDE-HGF$$bMarine, Küsten- und Polare Systeme$$lTerrestrische Umwelt$$vAddenda$$x0 000017745 9141_ $$y2012 000017745 915__ $$0StatID:(DE-HGF)0010$$2StatID$$aJCR/ISI refereed 000017745 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR 000017745 915__ $$0StatID:(DE-HGF)0110$$2StatID$$aWoS$$bScience Citation Index 000017745 915__ $$0StatID:(DE-HGF)0111$$2StatID$$aWoS$$bScience Citation Index Expanded 000017745 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection 000017745 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bThomson Reuters Master Journal List 000017745 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS 000017745 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline 000017745 915__ $$0StatID:(DE-HGF)0420$$2StatID$$aNationallizenz 000017745 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record 000017745 9201_ $$0I:(DE-Juel1)IBG-3-20101118$$gIBG$$kIBG-3$$lAgrosphäre$$x0 000017745 970__ $$aVDB:(DE-Juel1)132310 000017745 980__ $$aVDB 000017745 980__ $$aConvertedRecord 000017745 980__ $$ajournal 000017745 980__ $$aI:(DE-Juel1)IBG-3-20101118 000017745 980__ $$aUNRESTRICTED