Sketch map extraction method for polarization SAR image

Abstract

The invention provides a sketch map extraction method for a polarization SAR image. The method comprises the steps that the polarization SAR image to be classified is input, and refined Lee filtering is carried out on the SAR image; a weighted edge filter is constructed to detect the constant false alarm edge of the image processed in the step 1 to acquire a polarization energy map; a weighted gradient filter is constructed to detect the gradient edge of the image processed in the step 1 to acquire a gradient energy map; wavelet transformation is carried out on the polarization energy map and the gradient energy map; different policies are constructed to fuse high frequency and low frequency sub-bands acquired through wavelet transformation; the polarization energy map and the gradient energy map are fused, and non-maximal value suppression is carried out on the fused maps to acquire an edge map; sketch operator tracing is carried out on the edge map to acquire sketch lines; and a statistical hypothesis test method is constructed to select the sketch lines and acquire a polarization sketch map. Polygon and noise-induced pseudo-boundary phenomena are suppressed, and the structure information of the polarization SAR image is accurately characterized.

Description

technical field [0001] The invention belongs to the technical field of image processing and remote sensing, and relates to a method for extracting a sketch of a polarimetric SAR image. Background technique [0002] Polarimetric Synthetic Aperture Radar (Polarimetric Synthetic Aperture Radar, polarimetric SAR) images can provide richer polarization information and better describe the characteristics of ground features. Polarimetric SAR image processing is of great significance to national defense construction and national development. It has become a hotspot of research by more and more scholars. However, due to the various types, scales and structures of polarimetric SAR images, their processing is still a difficult problem. A polarimetric SAR processing method is difficult to apply to various types of ground objects, and structural information can guide the processing of polarimetric SAR images. The place where the SAR image changes is the image structure, which provides e...

AI Technical Summary

Problems solved by technology

[0003] In 2003, Jesper Schou et al. proposed a CFAR detection method based on polarimetric SAR. The calculation of edge energy by Wishart likelihood ratio can effectively suppress speckle noise and achieve better edge results. However, this algorithm is difficult to detect heterogeneous edge information

However, polarimetric SAR images are quite different from natural images in terms of imaging mechanism and scattering characteristics, so the sketch model of natural images is no longer suitable for polarimetric SAR images

[0004] Although the above edge detection method can consider the scattering characteristics and statistical distribution of polarimetric SAR, there are still many defects because it does not consider the visual mechanism and heterogeneous areas: (1) For heterogeneous areas such as urban areas and forests, the regional consistency is difficult to satisfy , the Wishart distribution is no longer suitable for describing such heterogeneous regions, making it difficult to detect the boundaries of bright and dark changes within urban areas

(2) Since the visual cognition mechanism is not considered, the traditional edge detection is prone to disadvantages such as polygons, false edges, and information redundancy.

(3) The sketch model of natural images does not consider the imaging characteristics and scattering mechanism of polarimetric SAR images, so it is difficult to apply to the sketch image extraction of polarimetric SAR images

Therefore, the traditional edge detection is difficult to describe the structural information well, and the sketch model based on the polarimetric SAR image needs to be extracted

[0005] To sum up, there are still some defects in the above-mentioned polarization SAR edge detection methods and natural image sketching models, which are prone to produce polygonal and pseudo-edge phenomena, and it is difficult to effectively describe the structural information of polarization SAR images.

Images