Image defogging method based on dark and bright primary color prior and adaptive parameter optimization

Abstract

The invention discloses an image defogging method based on dark and bright primary color prior and adaptive parameter optimization, and proposes a bright primary color prior theory according to the characteristic that the pixel values ​​in white areas are generally higher, and combines the theory with the dark primary color prior theory , which effectively solves the problem of defogging the white area in the foggy image, and performs adaptive weighting processing on the pixel value of the sky-like area and the maximum dark channel value, so that the obtained atmospheric light value is more robust, and then through the automatic The image defogging algorithm adapted to weight optimization can better realize the optimized processing of the defogged image. Through the self-adaptive scale guided filtering algorithm, the size of the original fog image can be adaptively adjusted to the filter scale, so that after filtering The effect is better, so as to realize the effective defogging of the image. This method not only effectively solves the problems that the original algorithm is not suitable for large white areas and the image is dark after defogging, but also the visual effect of the image after defogging is more real and natural.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an image dehazing method based on a priori of dark and bright primary colors and adaptive parameter optimization. Background technique [0002] The information revolution is regarded as the fourth industrial revolution, and its importance is self-evident, and one of the important sources of information is digital image information. Clear images can be used in various fields and play a vital role. Therefore, it is very important to obtain a clear image. However, in real life, due to various reasons, the obtained image quality is not high, especially in bad weather, the obtained image quality is often poor, which greatly reduces the application of the image. value, among which smog is one of the common bad weather. [0003] In 2009, a dehazing method based on dark primary color prior was proposed. The method obtained the prior knowledge that each area always h...

AI Technical Summary

Problems solved by technology

[0004] 1) For large white areas, such as sky, dense fog, etc., there are few dark channels, and this method is difficult to apply;

[0005] 2) When there are white areas, it is easy to overestimate the atmospheric light;

[0006] 3) The defogging parameters are too fixed and single, and after defogging, the image is prone to darker adverse effects;

[0007] 4) The soft matting algorithm is too complicated and the amount of calculation is too large

[0013] Aiming at the problems existing in the defogging method based on the dark channel prior, experts and scholars at home and abroad have done a lot of research and improvement. Although a lot of achievements have been made, there are still various problems. So far, there is no A person can come up with an improvement method that has both aspects

Images