Remote sensing image color enhancing method based on multi-scale image segmentation and color transferring

Abstract

The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image color enhancing method based on multi-scale image segmentation and color transferring. The method comprises steps: S1, conducting wavelet denoising preprocessing for a target gray level image; S2, according to a multi-scale normalized segmentation method, conducting segmentation of the target gray level image after preprocessed; S3, combining a reference image, and conducting brightness matching for all sub-domains of the target gray level image; and S4, selecting a sub-domain with the similar property to conduct mapping and color transferring. Aesthetic measure and target recognized degree of a result image are obviously enhanced, under the condition that image registering is not needed, the method can achieve full-automatic color enhancing for a remote sensing image which is relatively simple in texture structure and big in brightness contrast just through a color reference image which is similar in character and style, and therefore, the remote sensing image color enhancing method provides strong technical support for remote sensing image processing.

Description

technical field [0001] The invention relates to the technical field of remote sensing image processing, in particular to a remote sensing image color enhancement method based on multi-scale image segmentation and color transfer. Background technique [0002] In a grayscale image, the human eye can only distinguish more than 20 gray levels from black to white, while the human eye can distinguish hundreds or even thousands of colors. If the original grayscale image is colorized, the human visual system can have a richer understanding of the details of the image, thereby greatly improving the readability of the image and making it easier to extract the required information. [0003] In the prior art, there are roughly two types of processing methods to solve image colorization: one is to use human-computer interaction, represented by software BlackMagic and colorization using optimization, and the other is non-interactive It is represented by pseudo-colorization (pse udo-color...

AI Technical Summary

Problems solved by technology

However, this method also has its own defects that are difficult to overcome: (1) data from different data sources, different sensors, and data of different periods often have contradictions in image registration; It is not the real color of the scene, so the color of the fusion image is often unnatural, which will produce sensory confusion and distortion

Although a lot of research work has been carried out in image registration at home and abroad, there are still many difficult problems to solve, mainly including: (1) Registration accuracy directly affects the fusion results, but in actual operation due to noise and other factors It is difficult to achieve high-precision image registration, which will affect the accuracy of the results; (2) For sensor images with completely different properties, or between images with large differences in bands, resolutions, and scene features, and the presence of In the case of large scale change, rotation or translation, large image nonlinear distortion, or serious geometric correction residual error, it is difficult or impossible to perform image registration; (3) manual interaction is required, and it is difficult to achieve automatic registration ; (4) The current processing speed of image registration still cannot meet the fast and real-time requirements

[0007] In summary, there is no method in the prior art that can quickly and effectively realize fully automatic color enhancement of remote sensing images

Images