Multi-scale structure feature enhanced NSST intra-domain multimode image fusion method

Abstract

The invention discloses a multi-scale structure feature enhanced multi-mode image fusion method in an NSST domain, and mainly solves the problems of geometric structure information loss and spectral information distortion in a fusion result of an SAR image and a panchromatic optical image. The method comprises the following steps: 1) inputting an SAR image and a panchromatic optical image; 2) performing multi-scale decomposition on the two input images to respectively obtain a high-frequency component and a low-frequency component; 3) fusing the low-frequency components of the two images by adopting an improved Laplacian operator fusion strategy; 4) fusing the high-frequency components of the two images by adopting an absolute value maximum method fusion strategy; 5) extracting edge structure information in the SAR image by adopting an exponential weighted mean ratio operator, and injecting the edge structure information into a high-frequency decomposition component of the SAR image through guided filtering; and 6) performing inverse NSST on the low-frequency component and the high-frequency component of the fused image to obtain a final fused image. The structural characteristics of the fused image are improved by 2.4%, the spectral information is improved by 4.3%, and the influence of speckle noise on the fusion result is effectively inhibited.

Description

technical field [0001] The present invention relates to the technical field of image fusion, in particular, the present invention relates to a multi-mode image fusion method in NSST domain enhanced by multi-scale structural features. Background technique [0002] With the vigorous development of the number of remote sensing satellites in orbit at home and abroad, a large number of multi-mode remote sensing images have been accumulated. Among them, SAR data and panchromatic optical image data are the two main types of data of the satellite remote sensing platform, therefore, the fusion of the two image data is becoming more and more important. [0003] The fusion of SAR images and panchromatic optical images can combine the advantages of the two images, not only maintaining the spectral information of panchromatic optical images, but also highlighting the expressiveness of SAR images on ground details and improving the interpretability of images. For the fusion of SAR images...

AI Technical Summary

Problems solved by technology

[0004] The present invention proposes a multi-mode image fusion method in the NSST domain with multi-scale structural feature enhancement, to solve the problems of loss of important geometric structure information and inconspicuous spectral information in the fusion results of SAR images and panchromatic optical images

Images