Image defogging method and device, storage medium, electronic equipment

Abstract

The present disclosure relates to the field of image processing technology, and in particular, to an image defogging method and device, storage media, and electronic equipment. The method may include: segmenting the sky area in the image to be dehazed according to the brightness information, saturation information and gradient information of the image to be dehazed; calculating the first global atmospheric light component based on all pixels in the sky area, and dividing the sky area into The transmittance of all pixels is set to the first transmittance; the second transmittance of each pixel in the non-sky area in the image to be dehazed is calculated according to the first global atmospheric light component; according to the first global atmospheric light component, The first transmittance and the second transmittance of each pixel in the non-sky area are combined with an atmospheric scattering model to calculate a dehazed image of the image to be dehazed. The present disclosure improves the accuracy of sky area segmentation, avoids color distortion in the sky area, and retains more detailed information in non-sky areas, making the dehazed image clearer and more natural.

Description

technical field [0001] The present disclosure relates to the technical field of image processing, and in particular to an image defogging method and device, a storage medium, and electronic equipment. Background technique [0002] In smoggy weather, there are a large number of suspended particles floating in the atmosphere, and these suspended particles have the effect of absorbing and scattering light. Therefore, in the foggy environment, especially in the case of heavy fog, the image captured by the visible light imaging system will have low contrast, color distortion, blurring and other degradation phenomena. This not only affects people's visual effects, but also brings serious security risks to various outdoor video surveillance, such as traffic surveillance. Therefore, how to obtain a clear defogged image has great application value. [0003] At present, image defogging methods can be roughly divided into two categories: one is based on traditional image enhancement ...

AI Technical Summary

Problems solved by technology

However, when there is a sky region in the image, since the sky region does not meet the prior conditions, the sky region in the defogged image obtained by this method will appear color distortion

In addition, the current image defogging method also includes using gradient information to segment the sky area, but when the concentration of fog is high, this method may misclassify the area similar to the sky area into the sky area, for example, in the concentration of fog When it is large, a large area of ​​field may be wrongly divided into sky regions. Therefore, only using gradient information to segment the sky region cannot achieve the desired effect

In addition, most of the current defogging methods are good for light fog images, but poor for dense fog images, and will produce obvious halo effects in places where the depth of the scene changes rapidly.

Images