Registration Method of SAR Image and Visible Light Image Based on Mutual Information of Structural Conditions

Abstract

The invention discloses a SAR image and visible light image registration method based on mutual information of structural conditions, which mainly solves the problems of instability and low registration accuracy in the prior art, and its realization is as follows: 1) Input the reference image and 2) Calculate the phase consistency information of the reference image and the image to be registered through the non-local mean filtering algorithm respectively; 3) Use the phase consistency information of the reference image and the image to be registered to calculate the phase consistency information of the reference image and the image to be registered The phase-consistent edge intensity map and direction map of the image; 4) Calculate the structural condition mutual information between the reference image and the image to be registered according to the phase-consistent edge intensity map and direction map; 5) Under the determined search space, record the structural condition mutual information The corresponding transformation parameter when the information is maximum; 6) transform the image to be registered by using the transformation parameter to obtain the registration result. The invention has stable registration and high registration precision, and can be used for remote sensing image fusion and change detection.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, and further relates to a registration method of a SAR image and a visible light image, which can be used for remote sensing image fusion and change detection. Background technique [0002] Remote sensing image registration is the spatial geometric transformation of two or more images at different times, different fields of view, and different imaging modes, so that each image can be geometrically matched and corresponding. Its main purpose is to reduce or eliminate the geometric deformation between the reference image and the image to be registered, and it has a wide range of applications in remote sensing image fusion and other fields. [0003] S. Suri et al published the paper "Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas" ("IEEE TRANSACTIONS ONGEOSCIENCE AND REMOTE SENSING" article number: 0196-2892 (2010) 48-0939-10 ) uses hist...

AI Technical Summary

Problems solved by technology

[0003] S. Suri et al published the paper "Mutual-information-based registration of TerraSAR-X and Ikonos imagery in urban areas" ("IEEE TRANSACTIONS ONGEOSCIENCE AND REMOTE SENSING" article number: 0196-2892 (2010) 48-0939-10 ) uses histogram segmentation to extract part of the information in the image to calculate the mutual information, without affecting the registration accuracy, it improves the registration speed of large-scale SAR images and visible light images, but this method is more noisy and gray Images with large degree differences cannot obtain stable registration results

[0004] J.P.W.Pluim et al. proposed a gradient-based interactive The image registration method of information, which combines the gradient information of the image as spatial information with mutual information, improves the stability of image registration, but due to the sensitivity of gradient to image noise, this method mainly targets at better quality For SAR image registration involving large noise, the registration result is unstable and the accuracy is low, which affects the effect of subsequent remote sensing image fusion or change detection

Images