Land cover classification using SAR: a comparison of the segmentation and filtering approaches

Author

Caves, Ronald G. ; Quegan, Shaun

Author_Institution

Centre for Earth Obs. Sci., Sheffield Univ., UK

Volume

2

fYear

34881

fDate

10-14 Jul1995

Firstpage

907

Abstract

Two approaches to reducing speckle in synthetic aperture radar (SAR) images are compared using, the gamma maximum a posteriori filter and a segmentation algorithm based on an iterative process of multi-scale edge detection and segment growing. The two methods are applied to an ERS-1 SAR image of an agricultural scene. The smoothed images and edge maps are compared for the degree and homogeneity of smoothing, and for feature preservation

Keywords

agriculture; digital filters; geophysical signal processing; geophysical techniques; image classification; image segmentation; radar applications; radar imaging; remote sensing by radar; spaceborne radar; speckle; synthetic aperture radar; SAR image classification; agricultural land; crops; edge map; feature preservation; filtering; gamma maximum a posteriori filter; geophysical measurement technique; image segmentation; iterative process; land surface; multi-scale edge detection; remote sensing; segment growing; smoothed image; speckle reduction; synthetic aperture radar; terrain mapping; vegetation mapping; Filtering; Filters; Image edge detection; Image segmentation; Iterative algorithms; Iterative methods; Layout; Pixel; Smoothing methods; Spaceborne radar; Speckle; Synthetic aperture radar;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1995. IGARSS '95. 'Quantitative Remote Sensing for Science and Applications', International

Conference_Location

Firenze

Print_ISBN

0-7803-2567-2

Type

conf

DOI

10.1109/IGARSS.1995.521093

Filename

521093