Unsupervised classification of changes in multispectral satellite imagery

Morton J. Canty, Allan A. Nielsen

AbstractThe statistical techniques of multivariate alteration detection, maximum autocorrelation factor transformation, expectation maximization, fuzzy maximum likelihood estimation and probabilistic label relaxation are combined in a unified scheme to classify changes in multispectral satellite data. An example involving bitemporal LANDSAT TM imagery is given.
Keywordschange detection; clustering
TypeConference paper [With referee]
ConferenceProceedings of SPIE, Image and Signal Processing for Remote Sensing X
EditorsLorenzo Bruzzone
Year2004    Month September    Vol. 5573    pp. 356-363
AddressMaspalomas, Gran Canaria, Spain
SeriesTechnical University of Denmark
Electronic version(s)[pdf]
BibTeX data [bibtex]
IMM Group(s)Image Analysis & Computer Graphics, Geoinformatics