In this paper, we present an approach for the classification of remote sensing multispectral data, which consists of two sequential stages. The first stage exploits the capabilities of the Support Vector Machines (SVM) approach for density estimation and uses it in a Bayes classification setup. In a typical image, the class of a pixel is highly dependent on the classes of its neighbor pixels. The second stage exploits the dependency of the classes. We incorporate this dependency using stochastic modeling of the context as a Markov Random Field (MRF). The MRF is modeled using Besag model and implemented using the Iterative Conditional Modes (ICM) algorithm. Results show that the stochastic modeling approach enhances the results and provides reasonable smoothness in the classified image.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Two Sequential Stages Classifier for Multispectral Data


    Beteiligte:
    Mohamed, Refaat M (Autor:in) / Farag, Aly A (Autor:in)


    Erscheinungsdatum :

    2003-06-01


    Format / Umfang :

    255844 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Predicting change-points in continuous time-series data using two classifier stages

    HIRADE RYO | Europäisches Patentamt | 2016

    Freier Zugriff


    Airborne multispectral data collection

    Hasell, P. G., Jr. | NTRS | 1974


    A multispectral data simulation technique

    Muasher, M. J. / Swain, P. H. | NTRS | 1980