Unlock instant, AI-driven research and patent intelligence for your innovation.

A method of image haze removal based on non-local mean filter

A non-local average and image technology, which is applied in image enhancement, image analysis, image data processing, etc., can solve the problems of overall dark image, haze image blur, low contrast, etc., to achieve simple calculation, retain edge details, remove noise effect

Active Publication Date: 2019-02-15
BEIHANG UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The problem solved by the technology of the present invention is: to overcome the deficiencies of the prior art, aiming at the blurring, low contrast and overall darkening of the image with haze, a method for removing haze based on non-local mean filtering is provided. The combination of non-local mean filtering algorithm and dark channel prior algorithm can effectively remove haze and improve the visual effect of the image

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
  • A method of image haze removal based on non-local mean filter
  • A method of image haze removal based on non-local mean filter
  • A method of image haze removal based on non-local mean filter

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be described in detail below in conjunction with the accompanying drawings and embodiments.

[0032] Such as figure 1 Shown, the specific implementation steps of the present invention are as follows (below taking the airborne pod TV image as an example to illustrate the specific implementation of the method):

[0033] 1. For the original image acquired in the outdoor scene, the RGB color space and the YCrCb color space are converted, and the R, G, B, components are converted into brightness and chrominance components. where the conversion function looks like this:

[0034] Y=0.257×R+0.504×G+0.098×B

[0035] Cb=-0.148×R-0.291×G+0.439×B

[0036] Cr=0.439×R-0.368×G-0.071×B

[0037] Among them, R, G, and B are the original pixel values ​​in RGB space, and Y, Cb, and Cr are the pixel values ​​in YCbCr space, respectively.

[0038] 2. Use the histogram to count the brightness component pixel values ​​in the YCrCb color space, and calculate the ...

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 relates to an image dehazing method based on non-local mean filtering. The method includes the following steps of firstly, converting an RGB color space and a YCrCb color space for an obtained original image to obtain a brightness component of the original image; secondly, counting pixel values of the brightness component through a histogram to obtain the average value of all the pixel values of the brightness component; thirdly, judging the magnitude of the average value of the pixel values of the brightness component, considering that the original image contains haze if the average value is larger than 150, otherwise considering that the image does not contain haze; fourthly, obtaining an image dark primary color for the input original image; fifthly, selecting the positionof 0.1% of pixels with the highest brightness value in the image dark primary color, and making the brightness maximum value in the position as the atmosphere light value; sixthly, roughly estimatingthe spreading rate of an atmosphere scattering model according to a dark primary color calculating formula; seventhly, refining the spreading rate through a non-local mean filtering method; eighthly,substituting the atmosphere light value and the refined spreading rate into an atmosphere scattering model, and restoring a dehazed image.

Description

technical field [0001] The invention relates to an image desmog method based on non-local mean value filtering, which is suitable for providing clear and highly recognizable real-time images for outdoor video monitoring, remote sensing navigation, aircraft TV electronic imaging and other systems in haze weather . Background technique [0002] In recent years, due to the expansion of my country's industrial production scale and the improvement of living standards, severe smog has occurred in many places. Under foggy weather conditions, tiny particles in the atmosphere will absorb and scatter visible light, causing the reflected light on the surface of the object to attenuate during transmission, resulting in reduced visibility of the target object; in addition, when sunlight passes through the tiny particles , a certain degree of scattering will also occur, and part of the light energy will be enhanced during the scattering process; when the two work together, the image qual...

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 Patents(China)
IPC IPC(8): G06T5/40G06T5/10G06T7/90
CPCG06T5/10G06T5/40G06T7/90G06T2207/20032
Inventor 张弘李岩杨一帆
Owner BEIHANG UNIV