Visualization and unsupervised classification of changes in multispectral satellite imagery

Morton J. Canty, Allan Aasbjerg Nielsen

    Research output: Contribution to journalJournal articleResearchpeer-review


    The statistical techniques of multivariate alteration detection, minimum/maximum autocorrelation factors transformation, expectation maximization and probabilistic label relaxation are combined in a unified scheme to visualize and to classify changes in multispectral satellite data. The methods are demonstrated with an example involving bitemporal LANDSAT TM imagery.
    Original languageEnglish
    JournalInternational Journal of Remote Sensing
    Issue number18
    Pages (from-to)3961-3975
    Publication statusPublished - 2006

    Cite this