Image defogging method based on blue channel correction

Abstract

The invention discloses an image defogging method based on blue channel correction, which is applied to the technical field of computer vision and image processing, and aims at solving the problems ofpoor defogging effect and large algorithm limitation of the existing histogram equalization algorithm, multi-scale Retinex (MSR) algorithm, dark channel prior defogging algorithm and the like. The method comprises the following steps: firstly, extracting information of red, green and blue channels, combining and sorting the information to obtain depth and transmissivity information, then respectively calculating the red, green and blue channels of an image to obtain a defogged image of each channel, and finally combining the images to obtain a final defogged image. The method has the advantages of few calculation parameters, simple and rapid calculation, good effect and no color cast, and is very suitable for processing outdoor fog images.

Description

technical field [0001] The invention belongs to the technical field of computer vision and image processing, in particular to an image defogging technology. Background technique [0002] Images taken under better natural conditions often have higher contrast and saturation. In foggy weather, natural light is scattered by atmospheric particles, resulting in reduced image contrast, brightness, and saturation. For example, the same lawn will appear green with high saturation when the weather is good (clear and fog-free), but it will appear green with low saturation in foggy weather, and the overall image is gray and the details are blurred. The images obtained in this way will cause great interference during image analysis, so it is extremely important to correct the images obtained under foggy weather. [0003] Representative dehazing algorithms include histogram equalization algorithm, multi-scale Retinex (MSR) algorithm and dark channel prior dehazing algorithm, etc. Amon...

AI Technical Summary

Problems solved by technology

This method is not very effective in the sky area with high brightness, and the sky area is prone to color cast

In addition, in recent years, more and more deep learning-based dehazing algorithms have achieved good results, but they require a large number of images with real reference data for model training, but foggy images generally cannot be trained accordingly Sample images, making the limitations of this type of method relatively large

Images