Clustering-based polarimetric SAR (synthetic aperture radar) image coherence speckle adaptive filtering method

Abstract

The invention belongs to the full-polarimetric SAR (synthetic aperture radar) imaging remote sensing technical field and relates to a clustering-based polarimetric SAR (synthetic aperture radar) image coherence speckle adaptive filtering method. The method includes the following specific steps that: (S1) a polarimetric SAR (synthetic aperture radar) image to be filtered is inputted, and a similarity parameter is calculated according to the polarimetric coherence matrix of the polarimetric SAR image; (S2) the distance measure of the similarity parameter is calculated according to the similarity parameter; (S3) original clustering characteristic parameters are calculated; (S4) the original clustering characteristic parameters are sequenced in an descending order; (S5) the number of clustering categories and a clustering center are determined; (S6) clustering processing is carried out according to the clustering center, so that a clustering category parameter sequence can be obtained; and (S7) a candidate sample pixel set is selected, pixels to be filtered are filtered, each pixel in the polarimetric SAR image is traversed, so that a polarimetric SAR coherence filtering result diagram is obtained. The method of the invention is simple to realize, has good robustness to different surface features and can process polarimetric SAR images of different wave bands and different resolutions.

Description

technical field [0001] The invention belongs to the technical field of full-polarization SAR (Synthetic Aperture Radar, synthetic aperture radar) imaging remote sensing, and relates to a coherent speckle adaptive filtering method based on clustering in polarized SAR images. Background technique [0002] Coherence speckles widely exist in images obtained by coherent imaging systems such as polarimetric SAR. The existence of coherence speckles brings difficulties and challenges to the understanding and interpretation of polarimetric SAR images. When performing processing such as target detection, classification, and recognition, it is usually necessary to perform speckle filtering preprocessing on polarimetric SAR images. Speckle filtering methods with excellent performance require that the details of ground objects should be well preserved while fully suppressing speckle. As a preprocessing of polarimetric SAR images, the performance of coherent speckle filtering directly a...

AI Technical Summary

Problems solved by technology

However, the global threshold cannot always adapt to various texture features in polarimetric SAR images, and the adaptability and accuracy of similar candidate sample pixel selection still need to be improved

Images