Guided filter parameter automatic adjustment-based remote sensing image fusion method

Abstract

The invention provides a guided filter parameter automatic adjustment-based remote sensing image fusion method, and aims to improve the resolution of a fused image. The method is implemented by the steps of obtaining to-be-fused remote sensing images; performing multi-scale transformation on the to-be-fused remote sensing images; obtaining low-frequency weight graphs of the to-be-fused remote sensing images; obtaining high-frequency weight graphs of the to-be-fused remote sensing images; setting guided filter adjustment parameters, and calculating an iterative frequency of a window radius of aguided filter; obtaining redefined low-frequency weight graphs of the to-be-fused remote sensing images; performing weighted fusion on corresponding low-frequency coefficients by utilizing the redefined low-frequency weight graphs of the to-be-fused remote sensing images; obtaining redefined high-frequency weight graphs of the to-be-fused remote sensing images; performing weighted fusion on corresponding high-frequency coefficients by utilizing the redefined high-frequency weight graphs of the to-be-fused remote sensing images; obtaining the fused remote sensing image; and obtaining the optimal fused remote sensing image. The method can be used for image analysis and processing in the fields of geology, weather and the like.

Description

technical field [0001] The invention belongs to the technical field of image processing, and relates to a remote sensing image fusion method, in particular to a remote sensing image fusion method based on automatic adjustment of guiding filter parameters, which can be used for image analysis and processing of geological, meteorological and other aspects. Background technique [0002] With the rapid development of sensor technology, more and more remote sensing satellite platforms have been launched one after another, and the same scene can obtain multi-space and multi-spectral image information. However, due to the limitations of the sensor's own design, it is often impossible to obtain high spatial resolution when high spectral resolution is satisfied. To solve this problem, remote sensing image fusion algorithm has become a research hotspot. [0003] According to the processing level of data during image fusion, the fusion algorithm can be divided into pixel-level fusion,...

AI Technical Summary

Problems solved by technology

However, in the process of guided filtering, the selected guiding filter parameters are fixed values, which cannot be adjusted according to the properties of remote sensing fusion images, resulting in low resolution of the fusion result image, loss of some color information, and image distortion.

Images