Segmentation of SAR images using textons

Author

Seixas, Francisco ; Silveira, Margarida ; Heleno, Sandra

Author_Institution

Inst. Super. Tecnico, Univ. de Lisboa, Lisbon, Portugal

fYear

2014

fDate

13-18 July 2014

Firstpage

1600

Lastpage

1603

Abstract

In this paper we investigate the use of the well known textons method [1] for the segmentation of SAR images. Two approaches were tested: using the MR8 filter bank and using only the pixel intensities. The K-NN classification algorithm and the SVM algorithm with both Linear and GHI kernels were used as classifiers. Results obtained with real amplitude SAR images for the separation between water and land demonstrate that the texton method is appropriate for the segmentation of SAR images.

Keywords

floods; geophysical image processing; geophysical techniques; image classification; image segmentation; radar imaging; rivers; support vector machines; synthetic aperture radar; GHI kernels; K-NN classification algorithm; MR8 filter bank; SAR image segmentation; SVM algorithm; Spain; floodplain inundation model; linear kernels; lower Tagus River; pixel intensity; real amplitude SAR images; textons method; water-land separation; Histograms; Image segmentation; Kernel; Support vector machines; Synthetic aperture radar; Training; Vectors; Synthetic Aperture Radar; Textons; image segmentation;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2014 IEEE International

Conference_Location

Quebec City, QC

Type

conf

DOI

10.1109/IGARSS.2014.6945952

Filename

6945952