A remotely sensed image denoising method based on incremental dictionary learning

Abstract

The invention discloses a remotely sensed image denoising method based on incremental dictionary learning. The pixel intensity of pixel blocks extracted from a target image and pixel blocks extractedfrom a reference image has a linear relationship to utilize the similarity of edge features, and finally the coefficients are obtained as a restriction condition for solving a final objective function. Based on the local incremental dictionary learning, the noise in the remote sensing image is removed by using the similarity of the edge features, which can keep the characteristics of the target image while effectively suppressing the noise.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image denoising method based on incremental dictionary learning. Background technique [0002] Many studies showed that in order to better remove the noise in remote sensing images, some reference information needs to be introduced. Compared with the method of denoising only using the information of the noisy remote sensing image itself, the denoising method of introducing reference information can use more information to denoise, so as to achieve a better denoising effect. The prior information can be introduced through the relationship between the pixel distribution of the target image and the pixel distribution of the reference image, and the prior information can also be introduced into the noise removal process in the wavelet domain. For multi-source remote sensing images, prior information can also be introduced in the gradient doma...

AI Technical Summary

Problems solved by technology

All these methods make use of the relationship between the reference image and the target image, but how to improve the noise removal effect of remote sensing images by introducing prior information is still a relatively open problem.

Images