Image haze removal method and system based on image layer enhancement

Abstract

The invention discloses an image haze removal method and system based on image layer enhancement. The image haze removal method based on image layer enhancement comprises the steps that S1, the atmosphere optical value A of an original image is estimated; S2, two layers of half-inversion images are constructed according to the atmosphere optical value, and linear contrast enhancement is conducted on the two layers of half-inversion images; S3, the absolute difference values between the original image and the enhanced half-inversion images in an H channel of a CIE LCH space are calculated, the weight distribution of the enhanced half-inversion images are determined according to the absolute difference values, and the two layers of enhanced half-inversion images are fused according to the weight distribution; S4, linear enhancement is further conducted on an image obtained after image infusion, and the image with the haze removed and the increased contrast ratio is obtained finally. By the adoption of the image haze removal method based on image layer enhancement, the situations such as insufficient enhancement or color distortion appearing when a traditional image enhancement algorithm is adopted in the prior art can be effectively avoided, the clear image with the haze removed is obtained, calculation is easy, the applicability is high, and the requirements for real-time processing and application can be met.

Description

technical field [0001] The invention relates to the field of image sharpening processing, in particular to an image defogging method and system based on image layered enhancement. Background technique [0002] Under foggy weather conditions, due to the scattering and absorption of light by a large number of tiny water droplets suspended in the atmosphere and the turbid medium, the visibility of the atmosphere is reduced, resulting in serious degradation of images collected by foggy day imaging sensors, image color and contrast. As a result, visual application systems such as monitoring, tracking, intelligent navigation, and intelligent vehicles based on image feature extraction cannot work normally and stably. Therefore, it is of great practical significance and great application value to study image defogging technology and improve the clarity of degraded images in foggy weather. At the same time, image defogging technology has become a research hotspot in the field of com...

AI Technical Summary

Problems solved by technology

This type of method is relatively simple to calculate, and can effectively improve the contrast of foggy images and highlight the details of the image, but its disadvantage is that it will lose a lot of information and cause unpredictable image distortion, and does not consider the depth information of the scene. For more complex images There will be partial over-enhancement, under-enhancement of some images, and color distortion, etc., and its scope of application is limited to a certain extent.

[0007] For practical applications, the scene changes are complex and the real-time requirements are high, and the above methods cannot achieve the desired effect.

Images