Comparison between co-occurrence and wavelet features for characterization of urban environments by SAR data

Author

Rangsanseri, Y.

Author_Institution

Dept. of Telecommun. Eng., King Mongkut´´s Inst. of Technol., Bangkok, Thailand

fYear

2000

fDate

2000

Firstpage

330

Lastpage

332

Abstract

It is well known that co-occurrence matrix related measures have already shown to be effective in remote sensing. While wavelet analysis, even if widely applied to texture classification problems, has not been evaluated in the context of urban environment classification. In this paper we present a comparative study between these two textural features for characterization of urban environments by SAR data. We found that the correct classification rates are slightly superior by using wavelet features

Keywords

image classification; image texture; matrix algebra; radar imaging; remote sensing by radar; synthetic aperture radar; wavelet transforms; SAR data; co-occurrence features; co-occurrence matrix related measures; environment characterization; remote sensing; texture classification; urban environment classification; urban environments; wavelet analysis; wavelet features; Data engineering; Energy measurement; Frequency; Image analysis; Pixel; Quantization; Remote sensing; Symmetric matrices; Wavelet analysis; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Microwave Conference, 2000 Asia-Pacific

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-6435-X

Type

conf

DOI

10.1109/APMC.2000.925804

Filename

925804