Establishing spatially continuous patterns in a non-supervised way

Author

Garcia-Consuegra, J. ; Cisneros, G. ; Martinez, A.

Author_Institution

Dept. Inf., Univ. de Castilla-La Mancha, Spain

Volume

2

fYear

1999

fDate

6/21/1905 12:00:00 AM

Firstpage

726

Abstract

In the authors´ previous work (1998), the advantages of a continuous pattern approach versus a discrete pattern (homogeneous zones) were shown. In that paper, the training fields were introduced in a supervised way. This paper carries this research line further, developing a non-supervised version. Their aim is to extract the spectral classes and their spatial pattern. The test bed consisted of images acquired by the Thematic Mapper (TM) sensor on board the Landsat V satellite

Keywords

geophysical signal processing; geophysical techniques; image classification; image processing; multidimensional signal processing; remote sensing; terrain mapping; Landsat; Thematic Mapper; geophysical measurement technique; image classification; land surface; multispectral method; non-supervised way; optical imaging; remote sensing; spatial pattern; spatially continuous pattern; spectral class; terrain mapping; training; unsupervised method; Data mining; Image sampling; Image sensors; Remote sensing; Satellites; Scattering; Sensor phenomena and characterization; Spatial resolution; Telecommunications; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1999. IGARSS '99 Proceedings. IEEE 1999 International

Print_ISBN

0-7803-5207-6

Type

conf

DOI

10.1109/IGARSS.1999.774420

Filename

774420