Single image defogging method for generating adversarial network based on priori knowledge guide condition

Abstract

The invention discloses a single image defogging method based on a priori knowledge guide condition generative adversarial network. The method comprises the steps of 1, establishing an atomized image training set; 2, performing preliminary defogging on a single random foggy image; 3, performing defogging training on the preliminary defogged image; 4, calculating true and false values of the defogging training image of the reference true value image and the preliminary defogging image; 5, calculating an image loss objective function; 6, updating the weight parameter set; 7, calling a new single random foggy image, and repeating the step 2 to the step 6 until the true and false values reach a set value; and 8, defogging a single actual foggy image. According to the invention, priori knowledge is utilized to guide a coding network to generate a fog-free result. A part of useful information obtained through priori knowledge is utilized. Meanwhile, the feature modeling capability of the deep neural network is utilized to make up for the deficiency of the priori knowledge, it is not needed to display and establish an atmospheric scattering model in the deep neural network, but the atmospheric scattering model is regarded as condition generation of an image, and the defogging effect is good.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method for defogging a single image based on a priori knowledge-guided conditional generative confrontation network. Background technique [0002] Images collected under severe weather such as fog and haze will suffer from quality degradation due to atmospheric scattering, which will make the image color off-white, reduce the contrast, and make it difficult to identify object features. It can also lead to biased understanding of image content. Image defogging refers to the use of specific methods and means to reduce or even eliminate the adverse effects of suspended particles in the air on images. Single image defogging refers to dehazing to obtain a clear image under the condition of only one foggy image. [0003] At present, single image defogging methods are mainly divided into three categories: the first category is based on image enhancement methods,...

AI Technical Summary

Problems solved by technology

However, this method is very dependent on data due to the lack of comparison of real scenes.

Images