Image de-fogging method based on average saturation priori treatment

A saturation and image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of lack of accuracy, inability to deal with foggy images in non-homogeneous atmosphere, achieve good dehazing effect and solve uncertainties Effects of Sexual Problems

Active Publication Date: 2017-09-01
NANJING COLLEGE OF INFORMATION TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The technical problem solved by the present invention is: the existing image defogging method can only deal with foggy images with homogeneous atmosphere, but cannot deal with foggy images under non-homogeneous atmospheric conditions, and the scattering coefficient is set according to manual experience, which lacks accuracy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image de-fogging method based on average saturation priori treatment
  • Image de-fogging method based on average saturation priori treatment
  • Image de-fogging method based on average saturation priori treatment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention proposes an image defogging method based on the average saturation prior, such as figure 1 shown, including the following steps:

[0037] S1, calculate the atmospheric light value based on the foggy image, including:

[0038] S101. Find the minimum intensity value in the R channel, G channel and B channel of each pixel of the foggy image to obtain the minimum channel image, and then set multiple windows centered on each pixel, and perform minimum on each window value filtering to obtain a dark channel image.

[0039] Specifically, the minimum intensity value corresponding to each pixel in the hazy image is found according to the following equation to form a dark channel image:

[0040]

[0041] Where Ω(x, y) represents a local pixel block centered on any pixel (x, y) in the foggy image, preferably the size of the local pixel block is 15×15, I c (a,b) represents the intensity value of any pixel (a,b) in the local pixel block Ω(x,y), I dark (...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention proposes an image de-fogging method based on average saturation priori treatment. The image de-fogging method comprises: calculating an atmospheric light value according to a fogged image; calculating a depth value of each pixel in the fogged image; obtaining lots of sunny images and calculating an average saturation value of each sunny image; carrying out statistics of average saturation values of all sunny images to obtain average saturation probability distribution of the sunny images, and calculating an expected value as an average saturation priori value; constructing an optimal model of a scattering coefficient by using the average saturation priori value; calculating a scattering coefficient optimization model to obtain a scattering coefficient of each pixel in the fogged image; calculating a scene albedo of each pixel in the fogged image; and calculating an intensity value of each pixel in the fogged image to form a de-fogged image. With the method provided by the invention, defogging can be carried out on an atmospheric non-homogeneous fogged image effectively; and a good defogging effect can be obtained when the atmospheric homogeneous fogged image is processed.

Description

technical field [0001] The invention specifically relates to an image defogging method based on average saturation prior, which is used for colorless defogging of color images, and belongs to the technical field of digital image processing. Background technique [0002] In the foggy environment, due to the influence of suspended particles in the atmosphere, the images collected by imaging equipment have poor visibility, low saturation, and serious lack of clarity. Therefore, it is of great practical significance to sharpen the degraded image in foggy weather. [0003] In the field of computer vision, the atmospheric scattering model is commonly used to describe the imaging process under foggy weather conditions. The process of image dehazing is to restore the intensity value of each pixel in the foggy image according to the atmospheric scattering model. Intensity value for each pixel. Most of the existing image dehazing methods use the atmospheric scattering model describe...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00
CPCG06T2207/20024G06T2207/10024G06T5/90G06T5/73
Inventor 顾振飞鞠铭烨袁小燕李秋张钰
Owner NANJING COLLEGE OF INFORMATION TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap