Title :
PolSAR image filtering based on feature detection using the wavelet transform
Author :
Farage, Grégory ; Foucher, Samuel ; Bénié, Goze B.
Author_Institution :
Univ. of Sherbrooke, Sherbrooke
Abstract :
This paper elucidates a new approach for speckle reduction in polarimetric synthetic aperture radar ("PolSAR") images based on the stationary wavelet transform. Noisy wavelet coefficients are thresholded using an entropic thresholding technique. Principal Component Analysis and Sum of Squared Coefficients methods are used to detect significant coefficients based on the entire polarimetric covariance matrix.
Keywords :
covariance matrices; feature extraction; geophysical techniques; image denoising; principal component analysis; radar polarimetry; synthetic aperture radar; wavelet transforms; PolSAR image filtering; Principal Component Analysis; Sum of Squared Coefficients methods; entropic thresholding technique; feature detection; noisy wavelet coefficients; polarimetric covariance matrix; polarimetric synthetic aperture radar images; speckle reduction; wavelet transform; Computer vision; Covariance matrix; Filtering; Filters; Image edge detection; Multiresolution analysis; Principal component analysis; Wavelet analysis; Wavelet coefficients; Wavelet transforms; PolSAR; entropic thresholding; speckle filtering; wavelet;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 2007. IGARSS 2007. IEEE International
Conference_Location :
Barcelona
Print_ISBN :
978-1-4244-1211-2
Electronic_ISBN :
978-1-4244-1212-9
DOI :
10.1109/IGARSS.2007.4423389
