Weighted least square filtering-based single image defogging method

Abstract

The invention designs a weighted least square filtering-based image defogging method, and research is carried out according to an existing single image defogging algorithm. The method comprises the specific implementation steps of firstly improving estimation of an atmospheric light value by utilizing super-pixel processing and quadtree segmentation methods; secondly according to dark channel prior knowledge and an image space conversion thought, performing multi-time fusion by utilizing weighted least square filtering, thereby obtaining accurate atmospheric curtain parameters; thirdly performing inverse conversion through the obtained atmospheric curtain parameters to obtain an atmospheric transmission function; and finally substituting the obtained atmospheric light value and the atmospheric transmission function into a model for performing restoration processing on a foggy image. According to the method, the atmospheric light value can be accurately estimated, the transmission function can be indirectly obtained, the definition, contrast and detail information of the image can be effectively improved, and especially the processing effect on a close shot is better.

Description

technical field [0001] The invention belongs to the field of image processing and relates to a method for defogging a single image. Background technique [0002] Smog is the result of the interaction between specific climate conditions and human activities, and has evolved into a very serious social problem in recent years. Under the special conditions of fog and haze, the quality of the collected images is severely degraded, and the contrast is significantly reduced. Therefore, applications based on outdoor scene images, such as remote sensing, intelligent transportation, object recognition, and monitoring facilities, are greatly disturbed. This not only affects the observer's vision, but also is not conducive to the extraction of effective information. Therefore, the clear processing of images collected under haze weather has attracted the attention of many scholars. [0003] There are two main types of existing image defogging methods: the first type is based on image e...

AI Technical Summary

Problems solved by technology

The above dehazing method has high computational complexity and relies on prior knowledge

Document 2 "He KM, Sun J, and Tang X O.Single image haze removal using dark channel prior, IEEEConference on Computer Vision and Pattern Recognition (CVPR), 2009:1956-1963." proposed based on dark channel prior knowledge ( Dark Channel Prior (DCP) single image defogging method, this method roughly estimates the medium propagation function, and then refines the medium propagation function with the help of the matting algorithm, and directly selects the brightest pixel as the atmospheric light value, and the large Image processing of area sky prone to distortion

Images