Rapid image defogging method and device, terminal and storage medium

Abstract

The invention discloses an image rapid defogging method and a device, a terminal and a storage medium, and the method comprises the steps: dividing an original foggy image into a sky region and a non-sky region through a sky region recognition algorithm; performing CLAHE enhancement on the sky region through a CLAHE enhancement algorithm to obtain a defogged image of the sky region; through an improved dark channel theory, firstly performing dark primary color enhancement and CLAHE enhancement on a non-sky area, then taking the mean value of the dark primary color enhancement and the CLAHE enhancement to enhance the contrast ratio and the brightness, and a defogged image of the non-sky area is obtained; and performing defogging restoration processing on the defogged image of the sky area and the defogged image of the non-sky area to obtain a defogged image corresponding to the original foggy image. According to the method, the problem of sky area failure in the prior art can be effectively avoided, the problems of sorting and cyclic traversal in the atmospheric light value calculation process are reduced, implementation of an algorithm on hardware is facilitated, and meanwhile theeffects of appropriate brightness, obvious details, overall image balance and color distortion prevention can be achieved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to a method, device, terminal and storage medium for fast image defogging. Background technique [0002] Fog images exist widely, such as morning fog, sea fog, smog, rain and fog, and so on. Photos taken under foggy conditions usually have the characteristics of low contrast, high brightness, and unclear details. Dehazing techniques are generally divided into two types: non-physical model-based dehazing and physical model-based dehazing. The former is based on non-physical model defogging technology, generally for the purpose of removing noise and improving contrast. Commonly used methods include: histogram equalization, Retinex algorithm, wavelet change and homomorphic filtering. The latter is based on the dehazing technology of the physical model, and establishes a degradation model for the foggy image, so as to reversely restore the fog-free image. The more cla...

AI Technical Summary

Problems solved by technology

[0005] 1) Since the definition of the dark channel prior theory is: In most non-sky local areas, some pixels will always have at least one color channel with a very low value, so the defogging technology based on the dark channel prior theory is ineffective against the sky;

[0006] 2) In the classic dehazing technology based on channel prior theory, the estimation complexity of atmospheric light value is high, which affects the real-time performance of the algorithm;

[0007] 3) After this technology removes fog, the overall brightness of the image is low, and the contrast of details is weak

Images