Quantifying the performance of SAR segmentation algorithms

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

1434

Abstract

Objective methods for analysing the performance of SAR segmentation algorithms, in terms of segment homogeneity, are discussed. Tests are based on the segmentations generated by two algorithms, RWSEG and ANNEAL, of an ERS-1 image of an agricultural scene. Homogeneity is assessed using the coefficient of variation of segments and the ratio of the original and segmented images. The relation between these approaches and the effect of segment size are discussed. The measures of homogeneity which are derived correspond to the results of a visual comparison

Keywords

geophysical signal processing; geophysical techniques; image segmentation; radar imaging; remote sensing by radar; spaceborne radar; synthetic aperture radar; ANNEAL; ERS-1; RWSEG; SAR imaging; agriculture; geophysical measurement technique; image segmentation algorithm; land surface; performance; radar remote sensing; segment homogeneity; synthetic aperture radar; terrain mapping; vegetation mapping; Algorithm design and analysis; Annealing; Change detection algorithms; Image edge detection; Image segmentation; Iterative algorithms; Layout; Performance analysis; Pixel; Speckle; Testing;

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.1995.521772

Filename

521772