Texture statistics for classification of land use with multitemporal JERS-1 SAR single-look imagery

Texture statistics for classification of land use with multitemporal JERS-1 SAR single-look imagery

Texture statistics are studied using multitemporal JERS-1 synthetic aperture radar (SAR) single-look imagery. A correct autocorrelation function of texture is derived and utilized to calculate textural features. It is demonstrated that a significant improvement in the classification accuracy results...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on geoscience and remote sensing 1999-01, Vol.37 (1), p.227-235
Hauptverfasser: Kurosu, T., Uratsuka, S., Maeno, H., Kozu, T.
Format: Artikel
Sprache:eng
Schlagworte:
Applied geophysics
Autocorrelation
Autocorrelation functions
Azimuth
Classification
Data acquisition
Earth sciences
Earth, ocean, space
Exact sciences and technology
Fading
Image analysis
Image texture analysis
Imagery
Internal geophysics
Mathematical analysis
Remote sensing
Soils
Statistics
Surface layer
Surficial geology
Synthetic aperture radar
Testing
Texture
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Texture statistics are studied using multitemporal JERS-1 synthetic aperture radar (SAR) single-look imagery. A correct autocorrelation function of texture is derived and utilized to calculate textural features. It is demonstrated that a significant improvement in the classification accuracy results if the textural features are used as additional inputs to the classifier.
ISSN:0196-2892
1558-0644
DOI:10.1109/36.739157