Image defogging transmittivity optimization method based on dark channel prior

Abstract

The invention discloses an image defogging transmittivity optimization method based on dark channel prior. The method comprises the following steps that firstly, rough transmissivity is solved according to the dark channel prior theory, a foggy image is subjected to rough defogging, and an intermediate defogging result is obtained; secondly, the transmissivity is optimized through the intermediate defogging result so that the transmissivity can be more approximate to a true transmissivity value, and then steering filtering is used for refining the optimized transmissivity to eliminate the blocking effect. According to the method, the transmissivity is optimized, the optimized transmissivity is more approximate to the true value of a scene, and the color cast phenomenon appearing in some special areas through a traditional dark channel prior algorithm is relieved. The improving method aims at optimizing the transmissivity and is quite simple and effective, details of the restored image are greatly enhanced, the overall brightness is improved, the visual effect is better, and the defogged image is more lifelike.

Description

technical field [0001] The invention relates to the technical field of digital image processing and image defogging, in particular to an image defogging transmittance optimization method based on dark channel prior. Background technique [0002] In recent years, smog has appeared more and more frequently in major cities in my country, and some places are even shrouded in smog for most of the year. In 2013, only 5 days in Beijing were not smog days; in January of this year, 30 provinces and cities were enveloped in smog four times. When the smog is large, the visibility is reduced, which seriously affects the clarity of the pictures taken. [0003] Images taken in hazy weather will be seriously degraded due to the influence of atmospheric light, doped with a large amount of fog components, the overall image is grayish white, with less edge information, and the detectability is greatly reduced. Especially for images taken in dense fog, the loss of detail information is large...

AI Technical Summary

Problems solved by technology

This algorithm can effectively avoid the halo phenomenon, but for the color cast phenomenon that will appear in the sky area, especially the hazy and fog-free images

Article [7] (Cui Bingqi, Xie Zhendong, Li Hong, Improvement of Image Dehazing Method Based on Dark Channel Prior, Information Communication (A), 1673-1131(2013) 06-0060-02) proposes the method of extracting images by wavelet transform For low-frequency information and high-frequency information, only the low-frequency part is subjected to dark channel prior defogging, and then reconstructed with high-frequency information to restore a clear image without fog. This method has a poor effect on restoring image details. There is not much difference before, and the wavelet transform method is time-consuming. Although it is shorter than the soft matting method, it has a high time complexity compared with the guided filtering method, so it has great limitations in practical engineering applications.

[0008] Patent CN105631829A adopts the method of inverting the image for defogging, which improves the defect of the original dark channel algorithm in low-light conditions such as night, but the algorithm cannot adapt to the scene with high light to defog, and in fact the brightness of the fog image Usually higher, the recovery effect of defogging is poor under low illumination conditions

Images