Single image defogging method based on improved non-local prior and medium

Abstract

The invention provides a single image defogging method based on improved non-local prior and a medium, and belongs to the technical field of computer vision and the technical field of image processing. The single image defogging method comprises the following steps: firstly, carrying out atmospheric light estimation by using an improved dark channel prior method, and then processing the whole image by using non-local prior to estimate the initial transmissivity, wherein global information is considered in non-local prior, and the image does not need to be segmented into different blocks, so that the phenomenon of wheel halo can be avoided; secondly, refining the scene transmissivity by adopting context regularization based on a weighted L1 norm to obtain refined scene transmissivity; and finally, correcting the transmissivity by using domain transformation filtering. Evaluation indexes such as peak signal-to-noise ratio, visible edge number, average gradient, saturated pixel point number and the like are improved.

Description

technical field [0001] The invention belongs to the technical fields of computer vision and image defogging, and in particular relates to a single image defogging method based on an improved non-local prior. Background technique [0002] Fog and smog are common natural phenomena, which are formed by the absorption and scattering of light by media such as aerosols and solid particles suspended in the atmosphere. In recent years, frequent smog weather has caused serious degradation of images acquired by outdoor video surveillance equipment, and has had a serious negative impact on the security and stability of intelligent video surveillance systems. Therefore, restoring the true color of foggy images has certain practical application value and research significance. [0003] The existing defogging algorithms mainly include two categories: methods based on image enhancement and methods based on physical models. [0004] a): Image enhancement-based methods. This method does n...

AI Technical Summary

Problems solved by technology

However, the color attenuation prior depends on the color information of the image, and the color information of different depths of field has different effects on this prior, so the color attenuation prior is not suitable for the entire foggy image. For details, see the literature "Zhu Q, Mai J, Fellow, et al.Single Image Haze Removel Using Dark Channel Prior[J].IEEE Transaction on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2341-2353."

[0006] Most of the above methods are based on local pixel blocks for defogging. Not only need to consider the use of multiple block sizes to remove noise interference, but also need to consider the problem of block overlap and the existence of block effects in the defogging results.

Images