Water Objects Extraction from Polarimetric SAR Imagery Based on Sequential Nonlinear Filtering and Independent Component Analysis

A new method is proposed for speckle noise suppression and water objects extracting from synthetic aperture radar (SAR) imagery based on sequential nonlinear filtering and independent component analysis. The distribution of SAR image data with multiplicative speckle noise is non-Gaussian and its parameters are unknown. Logarithmic Quantification is utilized to transform multiplicative speckle noise to independent additive noise. Speckle noise and image data are separated from multipolarimetric imagery, and the components with the least speckle index are chosen as the object component automatically by means of ICA while the specific distribution of SAR imagery is unnecessary. Water objects are extracted from the separated object component imagery based on sequential nonlinear filtering according to their lightness and region shape features. The experimental results using ENVISAT ASAR polarimetric imagery show that the proposed method can extract water objects rapidly and accurately.

[1]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[2]  Su Zhi-cheng.  Remote Image Classification Based on Independent Component Analysis , 2007 .

[3]  Xiao Peng-feng.  Mathematical Morphological Segmentation of IKONOS Multispectral Data , 2008 .

[4]  Chen Mi.  Classification of Remote Sensing Fused Image Based on Independent Component Analysis and Support Vector Machines , 2007 .

[5]  Y. Peng.  De-noising by modified soft-thresholding , 2000, IEEE APCCAS 2000. 2000 IEEE Asia-Pacific Conference on Circuits and Systems. Electronic Communication Systems. (Cat. No.00EX394).

[6]  Yang Cun.  Extracting the flood extent from SAR imagery on basis of DEM , 2002 .

[7]  Ioannis Pitas.  State of the art of morphological and nonlinear digital image processing , 1993 .

[8]  Li Jing.  Research on Synthetic Aperture Radar Imagery Speckle Filter , 2008 .

[9]  Ruey-Wen Liu,et al.  General approach to blind source separation , 1996, IEEE Trans. Signal Process..

[10]  Zhu Jun-jie.  Water detection with high-resolution SAR image based on texture and imaging knowledge , 2006 .

[11]  Carlos López Martínez,et al.  Polarimetric SAR Speckle Noise Model , 2003 .

[12]  Ju Cun-yong.  Automatic segmentation of high-resolution remote sensing image based on mathematical morphology and maximum likelihood estimate. , 2005 .

[13]  Aapo Hyvärinen,et al.  Independent Component Analysis: A Tutorial , 1999 .

[14]  Xia De-shen.  Remote Image Classification Based on Independent Component Analysis , 2004 .

[15]  S. Intajag,et al.  Speckle Reduction Using Fuzzy Morphological Anisotropic Diffusion , 2005, 2005 5th International Conference on Information Communications & Signal Processing.

[16]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[17]  Ma Songde,et al.  SAR Image De-speckling Based on Modified Frost Filter , 2005 .

[18]  Carlos López-Martínez,et al.  Polarimetric SAR speckle noise model , 2003, IEEE Trans. Geosci. Remote. Sens..

[19]  HU De-yong,et al.  Water and Settlement Area Extraction from Single-band,Single-polarization SAR Images Based on SVM Method , 2008 .