Image quick defogging optimized method based on black channel

Abstract

Provided is an image quick defogging optimized method based on a black channel. Edges of an image and non-edge areas of the image are processed through different templates to obtain a transmission picture, and a precise atmosphere light value is obtained by the fact that a sky area or an area with thickest fog is divided. The method greatly reduces consumption, improves the image recovery speed, and improves image recovery effects.

Description

technical field [0001] The invention relates to image processing technology, in particular to a black channel-based fast image defogging optimization method. Background technique [0002] At present, in the existing image defogging methods, using multiple images in the same scene at different shooting angles or under different weather conditions to process the defogging can achieve certain results, but in practical applications, it is difficult in a short time Get multiple images. Using geometric models of known scenes, or using artificially input depth information also limits the practicality of the method. [0003] In recent years, great progress has been made in dehazing with a single image. Tan (R Tan.Visibility in bad weather from a single image[A].Proc of IEEE CVPR[C].Anchorage,Alaska:IEEE Computer Society,2008:1-8.) Observed that images in sunny days are better than images in foggy days There is a higher contrast, and assuming that the neighboring pixels have the s...

AI Technical Summary

Problems solved by technology

Tan (R Tan.Visibility in bad weather from a single image[A].Proc of IEEE CVPR[C].Anchorage,Alaska:IEEE Computer Society,2008:1-8.) Observed that images in sunny days are better than images in foggy days There is a higher contrast, and assuming that the neighboring pixels have the same attenuation, the method of maximizing the local contrast is used to restore the color contrast of the image, which has achieved better results in some scene images, but this method does not conform to the real Physical model, the obtained results are easily distorted

Fattal (R Fattal.Single image dehazing[A].Proc of SIGGRAPH[C].Los Angeles:ACM Transactions on Graphics,2008,27(3):1-9.) assumes that shadow and transmittance are unrelated, using The ICA model estimates the transmittance to obtain the dehazing result, but this method cannot handle dense fog images very well

He (K He, J Sun, X O Tang. Single image haze removal using dark channel prior[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33:1-13.) and others proposed the dark channel priority rule ( Statistical results show that most outdoor photos conform to this rule), using this rule to remove haze can get good results for most outdoor scene haze images, but deviations will appear in some areas where the black channel is not close to 0 , using the same atmospheric light value for the entire image leads to color distortion in the local area of ​​the restoration result, and the soft matting algorithm for optimizing the transmission map will consume a lot of time and memory

Images