Water objects extraction from polarimetric SAR imagery based on blind source separation and morphological reconstruction

Author

Wang, Dong ; Zhou, Weifeng ; Fan, Wei ; Jiang, Xingwei ; Qin, Ping

Author_Institution

Key & Open Lab. of Remote Sensing & Inf. Technol. Applic. in Fishing Resource, China Acad. of Fishery Sci., Shanghai, China

Volume

3

fYear

2010

fDate

16-18 Oct. 2010

Firstpage

1028

Lastpage

1032

Abstract

The SOMMR nonlinear blind source separation (BSS) method is proposed for speckle noise suppression and water objects extracting from synthetic aperture radar (SAR) imagery based on self-organizing maps (SOM) neural networks and morphological reconstruction (MR). The multiplicative speckle noise and image data are separated from multipolarimetric imagery by means of SOM neural networks. Morphological reconstruction is employed to remove the residual noise. The experimental results using ENVISAT ASAR polarimetric imagery show that the proposed method can extract water objects accurately, and the speckle noise index is better than ICA and SOM method.

Keywords

blind source separation; feature extraction; image denoising; image reconstruction; radar imaging; radar polarimetry; self-organising feature maps; synthetic aperture radar; SOMMR nonlinear blind source separation; morphological reconstruction; neural networks; polarimetric synthetic aperture radar imagery; self-organizing maps; speckle noise index; speckle noise suppression; water objects extraction; Artificial neural networks; Blind source separation; Image reconstruction; Indexes; Noise; Speckle; Synthetic aperture radar; blind source separation; morphological reconstruction; self-organizing maps neural networks; synthetic aperture radar; target extraction;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2010 3rd International Congress on

Conference_Location

Yantai

Print_ISBN

978-1-4244-6513-2

Type

conf

DOI

10.1109/CISP.2010.5647013

Filename

5647013