Fusion of Evidences in Intensity Channels for Edge Detection in PolSAR Images

Polarimetric synthetic aperture radar (PolSAR) sensors have reached an essential position in remote sensing. The images they provide speckle noise, making their processing and analysis challenging tasks. We discuss edge detection method based on the fusion of evidences obtained intensity channels hh, hv, vv PolSAR multilook images. consists detecting transition points thinnest possible range data that covers two regions using maximum likelihood under Wishart distribution. methods used are: simple average, multiresolution discrete wavelet transform (MR-DWT), principal component (PCA), receiver operating characteristic (ROC) statistics, stationary (MR-SWT), a singular value decomposition (MR-SVD). A quantitative suggests PCA MR-SVD best results.