Method and device of image dehazing

Abstract

The invention discloses a method and a device of image dehazing, wherein the method comprises calculating a dark primary color image I (x, y) according to a primary image and obtaining airglow A corresponding to the dark primary color image; estimating the dark primary color image and accordingly obtain a first transmission diagram of an atmospheric scattering module, and adopting Gaussian filtering to conduct edge thinning on the first transmission diagram and accordingly obtain a second transmission diagram; and conducting recovery operations on the a primary image I (x, y) according to the second transmission diagram and the airglow and accordingly obtain a fog-free image. By adopting the method and the device of image dehazing, an outdoor video system can normally work even on heavy fog scenes, and relatively clear images can be acquired.

Description

technical field [0001] The invention relates to the technical field of computer image processing, in particular to an image defogging method and device. Background technique [0002] In the case of foggy weather, due to the reduced visibility of the scene, the contrast and color of the target in the image will be attenuated, resulting in the failure of the outdoor video system to work normally. Therefore, it is necessary to eliminate the influence of haze on the scene image in the video image. Image dehazing has always been an important content in the field of computer vision research. Since the imaging process of foggy objects is very complex, it is difficult to accurately describe quantitatively, and the degree of image degradation in foggy weather is proportional to the depth of the object, so obtaining the depth information of the scene object from a single image itself is a pathological problem. [0003] That is to say, in the prior art, the way of obtaining the depth ...

AI Technical Summary

Problems solved by technology

Since the imaging process of the target in foggy weather is very complicated, it is difficult to accurately describe it quantitatively, and the degree of image degradation in foggy weather is proportional to the depth of the target, so obtaining the depth information of the scene target from a single image is itself a pathological problem.

[0003] That is to say, in the prior art, the method of obtaining the depth information of the scene target by using a single image cannot eliminate the problem that the smog affects the work of the external video system, and no effective technical solution has been proposed yet.

Images