Single image defogging method based on luminance dark priori method and bilateral filtering

Abstract

The invention discloses a single image defogging method based on a luminance dark priori method and bilateral filtering. A new image priori method, the luminance dark priori method, is used for estimating the fog concentration and restoring an image, the priori method is based on the statistical law of fog-free image HSI color space luminance components, and according to the statistical law, some pixels exist in local areas of most fog-free images, and the strength value of the luminance components I of the pixels is low and approaches to zero. Based on the priori method, the image is firstly transformed to the HSI color space to obtain the luminance components, a dark priori image is calculated, then atmosphere light and transmissivity are estimated through the luminance dark priori method, the transmissivity is refined through the bilateral filtering, and finally restoration is carried out according to an atmosphere scattering model to obtain the fog-free images. According to the method, the contrast ratio of the image is enhanced obviously, grain details in the images are restored, the visual effect of the image is obviously improved, and the good algorithm performance is achieved.

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 brightness-dark prior and bilateral filtering. Background technique [0002] With the development of computer vision and image processing technology, outdoor vision systems have been widely used in transportation, security defense, terrain detection and other fields. However, under foggy conditions, due to the scattering effect of atmospheric particles, the images acquired by the outdoor vision system have quality degradation problems such as reduced contrast, color distortion, and blurring, resulting in feature extraction, target discrimination, and target tracking. Therefore, it has important practical application value to study the dehazing technology of degraded images in foggy weather. [0003] The scene depth information of the degraded image is an important clue to restore the foggy image. According to w...

AI Technical Summary

Problems solved by technology

[0006] The object of the present invention is to provide a single image defogging method based on luminance dark prior and bilateral filtering, which solves the problem that the dark channel prior defogging method fails to defog in severe haze conditions, and effectively reduces the time complexity

Images