SAR image and visible light image matching method based on improved feature extraction and game theory hypergraphs

Abstract

The invention discloses an SAR (Synthetic Aperture Radar) image and visible light image matching method based on improved feature extraction and game theory hypergraph, which comprises the following steps: firstly, preprocessing an SAR image, extracting the contour of the SAR image, and extracting CSS (Coordinated Square Square) angular points on the contour as feature points; for the visible light image, carrying out image sharpening preprocessing on the image in advance, extracting a contour, and extracting CSS angular points on the contour at the same time; then, matching the angular pointswith contour points around the angular points by using a CPD algorithm, converting a matching problem into a probability density estimation problem, carrying out consistent drifting motion on featurepoints of the two images, respectively constructing hypergraph models for matching points of each image, and respectively establishing hyperedge adjacent tensors for the two hypergraph models; and finally, converting a matching problem into a game problem by using a game theory-based hypergraph matching algorithm, calculating to reach a Nash equilibrium point, and eliminating wrong matching pointpairs.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method for matching SAR images and visible light images based on improved feature extraction and game theory hypergraphs. Background technique [0002] Since the development of Synthetic Aperture Radar (SAR) technology, it has been attracting attention from all walks of life. Because of its strong penetrating ability and all-weather and all-weather advantages, SAR has been widely used in military reconnaissance, weather forecasting, aerospace and other fields. . Since SAR is sensitive to metal objects and the surface, there will be obvious texture features when imaging, which can be used to explore mineral resources and detect terrain changes. In addition to detecting objects above the ground, SAR images can also penetrate the surface to detect objects underground. However, there are many defects in SAR images. The lack of spectrum leads to the lack of image color. A...

AI Technical Summary

Problems solved by technology

And because of the different imaging principles of SAR images and visible light images, there is a big difference in grayscale and resolution, and SAR images are often affected by coherent speckle noise, so the images are not clear enough

Images