Image defogging processing method and device and computer storage medium

Abstract

The invention provides an image defogging processing method and device, and a computer storage medium, and the method comprises the steps: carrying out the negation of each pixel value corresponding to each pixel point in a target channel of a to-be-processed foggy image, and obtaining a dark channel image of the foggy image, the method comprises the following steps: acquiring a foggy image, sequentially acquiring a global ambient light value and each transmissivity value corresponding to each pixel point according to a dark channel image of the foggy image, and acquiring a defogged image of the foggy image according to each transmissivity value corresponding to each pixel point, each initial pixel value corresponding to each pixel point in the foggy image and the global ambient light value. According to the invention, a good image defogging effect can be achieved.

Description

Technical field [0001] The present application embodiment relates to image processing techniques, particularly an image deiffal treatment method, device, and computer storage medium. Background technique [0002] In the environment in foggy days, haze or sandstorms, the image captured by the visible light imaging system will often present the degradation of low contrast, fuzzy, and color distortion. Therefore, the image degenerate is becoming an increasingly important Image processing technology, which reduces the fog, the low-energy imaging environment on the image on the degradation of the image, and improves image subjective visual quality. [0003] In general, the image denger method can be divided into an image enhanced method and a method based on the physical model. Among them, the degradation method based on the physical model is analyzed by analyzing the degradation mechanism of the fog day image, and the atmospheric scattering model is constructed, and the clear image i...

AI Technical Summary

Problems solved by technology

[0004] At present, in the research on the dehazing method based on the physical model, the dehazing method based on the dark channel prior principle is the representative, which is more suitable for most foggy images, but because this method is in the process of optimizing the transmittance In , the soft matting algorithm is used, which will generate a large memory overhead and cause the algorithm to run too slowly

[0005] In order to solve the above-mentioned problem of too slow running speed, relevant researchers proposed a single image defogging method based on physical model and dark channel prior. This method improves the running efficiency to a certain extent, but the processing result is not smooth. problem; in addition, there is a local atmospheric light defogging algorithm, although this algorithm can achieve fast defogging, but it still cannot achieve the ideal restoration effect for large areas of the sky

[0006] In addition, some researchers have proposed a dark channel image defogging method based on sky recognition, which mainly uses the sky recognition algorithm to divide the foggy image into the sky part and the non-sky part, and then process them separately. However, this The limitation of the method is that the edge connection between the sky part and the non-sky part is not smooth enough after defogging, and halos and artifacts are prone to occur.

[0007] According to the above research, it can be found that the current image defogging methods based on the dark channel prior principle mainly have the following problems: First, for foggy images containing large areas of sky or white objects, most methods have poor defogging effects; Second, in the area where the depth of field of the image changes greatly, the edge details of the image cannot be well preserved, causing halos to appear in the restored image

Images