CN107977941A - A kind of bright areas color fidelity and the image defogging method of contrast enhancing - Google Patents
A kind of bright areas color fidelity and the image defogging method of contrast enhancing Download PDFInfo
- Publication number
- CN107977941A CN107977941A CN201711261135.3A CN201711261135A CN107977941A CN 107977941 A CN107977941 A CN 107977941A CN 201711261135 A CN201711261135 A CN 201711261135A CN 107977941 A CN107977941 A CN 107977941A
- Authority
- CN
- China
- Prior art keywords
- image
- bright areas
- mrow
- value
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000002708 enhancing effect Effects 0.000 title claims abstract description 19
- 239000003595 mist Substances 0.000 claims abstract description 18
- 230000008030 elimination Effects 0.000 claims abstract description 11
- 238000003379 elimination reaction Methods 0.000 claims abstract description 11
- 238000004422 calculation algorithm Methods 0.000 claims description 23
- 238000002834 transmittance Methods 0.000 claims description 23
- 238000001914 filtration Methods 0.000 claims description 12
- 230000033228 biological regulation Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 6
- 238000000205 computational method Methods 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 238000003384 imaging method Methods 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012937 correction Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000009738 saturating Methods 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 1
- 238000000889 atomisation Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention discloses the image defogging method that a kind of bright areas color fidelity and contrast strengthen, atmospherical scattering model is selected as physical model, air light value is estimated according to dark primary figure, by judging image-region pixel, pixel to being determined as non-bright areas, transmissivity is calculated with the method plotted against in color priori, pixel to being determined as bright areas, the transmissivity of bright areas is corrected, brightness and contrast's enhancing is carried out to revised mist elimination image by Gauss histogram specification method.Solution route is provided for bright areas color distortion after dark primary defogging, and for picture after defogging is partially dark, contrast problem, there is provided adaptive enhancements.
Description
Technical field
The present invention relates to a kind of digital image processing method, and in particular to a kind of bright areas color fidelity and contrast increase
Strong image defogging method.
Background technology
In recent years, haze weather increases so that the imaging definition of outdoor Visible imaging system reduces, image appearance pair
, brightness lower than degree is partially dark and phenomena such as details lacks, and influences the processing of later image.This is because during haze weather, in air
Steam and the aerosol that is combined into of a large amount of suspended particulates light is absorbed and scattered, cause from imaging system obtain can
See light image quality degradation.
Image defogging algorithm is broadly divided into the defogging algorithm of no priori and the defogging algorithm based on priori.Without elder generation
Testing the image defogging algorithm of knowledge mainly has color histogram equalization algorithm, local histogram equalization algorithm and contrast to draw
Algorithm etc. is stretched, such algorithm mainly strengthens image by lifting picture contrast, without certain priori to instruct,
The distortion of image is easily caused, therefore the image defogging algorithm based on priori is the emphasis studied at present.
Defogging algorithm based on priori is to carry out statistical analysis to the haze image being down to, and finds experience rule therein
Rule, recovers fogless image, the difficult point of such method is the excavation to priori in conjunction with the solution by physical model
And the accurate estimation of model parameter, dark primary prior image defogging algorithm is the Typical Representative of such algorithm.
The content of the invention
The present invention is to solve the above-mentioned problems, it is proposed that a kind of bright areas color fidelity and the image of contrast enhancing are gone
Mist method, the present invention realize bright areas defogging by new transmissivity method for solving and Gauss histogram specification method
Color correction and the lifting of mist elimination image contrast, solve the problems, such as that the image after mist is overall partially dark.
To achieve these goals, the present invention adopts the following technical scheme that：
A kind of bright areas color fidelity and the image defogging method of contrast enhancing, select atmospherical scattering model as thing
Model is managed, air light value is estimated according to dark primary figure, by judging image-region pixel, to being determined as non-bright areas
Pixel, calculate transmissivity with the method plotted against in color priori, the pixel to being determined as bright areas, corrects bright areas
Transmissivity, by Gauss histogram specification method to revised mist elimination image carry out brightness and contrast's enhancing.
A kind of bright areas color fidelity and the image defogging method of contrast enhancing, specifically include following steps：
(1) using atmospherical scattering model as physical model, air light intensity value is estimated using dark channel diagram；
(2) according to the ratio of foggy image brightness value and air light intensity value, by image-region be divided into bright areas with
Non- bright areas；
(3) for the non-bright areas of division, using dark primary priori computation transmittance figure, for bright areas, use
Modified transmissivity method calculates transmittance figure；
(4) using guiding filtering algorithm refinement transmittance figure, mist elimination image is obtained；
(5) the histogram specification method based on Gaussian function is used, adjusts the histogram of image after defogging.
Further, in the step (1), using the atmospherical scattering model of McCarney, its input picture light intensity
Non- light projection ratio with it is fogless when scenery light intensity product, and one subtract the value of light transmittance and atmosphere light component
The sum of product.
Further, in the step (1), image defogging target be exactly recovered by known foggy image it is fogless
Image is, it is necessary to estimate air luminous intensity and light transmittance.
In the step (1), air light value estimation, specifically includes：
(a) a certain proportion of pixel of brightness maximum is taken from the dark channel diagram containing mist；
(b) location of pixels obtained in corresponding (a), finds the value of maximum brightness point as atmosphere light in original image
Value.
Further, in the step (2), the specific steps of region division：According to foggy image brightness value I and air
Whether the ratio in judgement pixel of light intensity value A belongs to bright areas, setting ratio threshold alpha, if I/A ＞ α, judge pixel
Belong to bright areas；Conversely, belong to normal region, i.e., non-bright areas.
Further, it is saturating using the computational methods of dark primary priori, light for non-bright areas in the step (3)
The computational methods for penetrating rate are：One and the region in the minimum value of coloured image RGB channel and atmosphere light component ratio be multiplied by ratio
The difference of coefficient.
Further, proportionality coefficient is adjusted according to the concentration of mist.
Further, in the step (3), for bright areas, the calculation formula of transmissivity is modified, after modification
Formula be：
Using the form of exponential function, after setting, pixel brightness value is more close with air light value, then transmittance values are got over
Greatly, transmissivity is made to realize dynamic regulation, Ω (x) represents one piece of regional area centered on pixel x, IcRepresent coloured image
C-th of channel value in RGB channel, β are coefficient, AcRepresent the air light value of estimation.
In the step (4), guiding filtering algorithm assumes to be oriented to image and there is local line between filtering output image
Sexual intercourse, filtered image is obtained by linear regression method according to input picture.
In the step (5), the histogram using the histogram specification method based on Gaussian function to image after defogging
It is adjusted, achievees the purpose that image enhancement.
In the step (5), set using Gaussian function come the histogram of regulation output image, the mathematical expectation of image
For k times of the average gray of mist elimination image, the variance of Gaussian function is set as mist elimination image variance, and k is constant, use
SML Mapping implementation histogram specifications.
Compared with prior art, beneficial effects of the present invention are：
The image defogging method of the present invention has that bright areas can keep true after defogging for atomization image
Real color, and the partially dark situation of image after defogging, the brightness and contrast for improving image can be directed to.
Brief description of the drawings
The accompanying drawings which form a part of this application are used for providing further understanding of the present application, and the application's shows
Meaning property embodiment and its explanation are used to explain the application, do not form the improper restriction to the application.
Fig. 1 is the flow chart of the specific embodiment of the invention.
Fig. 2 (a) is classified as foggy image experimental result, and Fig. 2 (b) is classified as dark primary priori defogging as a result, Fig. 2 (c) is classified as this
Invention defogging result.
Embodiment：
The invention will be further described with embodiment below in conjunction with the accompanying drawings.
It is noted that described further below is all illustrative, it is intended to provides further instruction to the application.It is unless another
Indicate, all technical and scientific terms used herein has usual with the application person of an ordinary skill in the technical field
The identical meanings of understanding.
It should be noted that term used herein above is merely to describe embodiment, and be not intended to restricted root
According to the illustrative embodiments of the application.As used herein, unless the context clearly indicates otherwise, otherwise singulative
It is also intended to include plural form, additionally, it should be understood that, when in the present specification using term "comprising" and/or " bag
Include " when, it indicates existing characteristics, step, operation, device, component and/or combinations thereof.
In the present invention, term as " on ", " under ", "left", "right", "front", "rear", " vertical ", " level ", " side ",
The orientation or position relationship of instructions such as " bottoms " are based on orientation shown in the drawings or position relationship, only to facilitate describing this hair
Bright each component or component structure relation and definite relative, not refer in particular to either component or element in the present invention, it is impossible to understand
For limitation of the present invention.
In the present invention, term such as " affixed ", " connected ", " connection " should be interpreted broadly, and expression can be fixedly connected,
Can also be integrally connected or be detachably connected；It can be directly connected, can also be indirectly connected by intermediary.For
The related scientific research of this area or technical staff, can determine the concrete meaning of above-mentioned term in the present invention as the case may be,
It is not considered as limiting the invention.
As background technology is introduced, dark primary elder generation checking method exists in the prior art after image bright areas defogging
The deficiency of color distortion occurs, in order to solve technical problem as above, present applicant proposes a kind of bright areas color fidelity
And the image defogging method of contrast enhancing, it is real by new transmissivity method for solving and Gauss histogram specification method
Existing bright areas defogging color correction and mist elimination image contrast lifting.
The image defogging method of the present invention is for the saturating of the estimation of the bright areas dark primary priori defogging algorithm such as on high
Penetrate that rate is relatively low, so as to cause the image after processing color distortion occur；And the image after defogging is overall partially dark, and contrast is relatively low
The problems such as, and a kind of image defogging algorithm suitable for bright areas designed, and pass through Gauss histogram specification method solution
Certainly overall partially dark, the relatively low problem of contrast of image, the specific implementation process of this method are as follows after defogging：
The present invention uses the atmospherical scattering model of McCarney, which has in visual light imaging field widely should
With.
I (x)=t (x) J (x)+(1-t (x)) A
Wherein：I (x) is input picture light intensity, and t (x) refers to light transmittance, and A is atmosphere light component, and J (x) is fogless
When scenery light intensity.
Image defogging target is exactly to recover fogless image J, it is necessary to estimate atmosphere light by known foggy image I
Intensity A and light transmittance t.
(1) air light value is estimated
The present invention estimates air light value using dark channel diagram, and specific method is：
(a) 0.1% pixel of brightness maximum is taken from the dark channel diagram containing mist；
(b) location of pixels obtained in corresponding (a), finds the value of maximum brightness point as atmosphere light in original image
Value.
(2) image-region is divided
Whether the present invention belongs to bright district according to the ratio in judgement pixel of foggy image brightness value and air light intensity value
Domain, because the brightness value I of foggy image pixel is more close with air light intensity value A, then the pixel is more possible to belong in image
In bright areas, specific decision method is that what a proportion threshold value α set in advance, if I/A ＞ α, judges that pixel belongs to
Bright areas；Conversely, belong to normal region, i.e., non-bright areas.
(3) transmittance figure is calculated
The present invention determines image bright areas in (2) with the basis of non-bright areas, carrying out the calculating of transmissivity.It is right
It is as follows using the computational methods of dark primary priori, formula in non-bright areas：
In above formula, Ω (x) represents one piece of regional area centered on pixel x；IcRepresent in coloured image RGB channel
C-th of channel value, ω represent image defogging degree.When fog is denseer, the value of ω should obtain it is larger because dense
Greasy weather gas, light transmittance decline more serious；Conversely, under misty, the value of ω should be less than normal.
When the value very little of light transmittance t (x), the value of the image J (x) of recovery can be caused bigger than normal, so that image
It is overall excessive to white field.By setting a threshold value t0, when less than when, make t (x)=t0, present invention specific implementation season t0For 0.1.
When solving transmissivity with dark primary method for bright areas, the transmissivity calculated can be relatively low, causes to recover
Bright areas color distortion because dark primary priori theoretical be built upon dark primary channel value usually level off to 0 this system
Count in rule, but it is generally more average for the value on tri- passages of bright areas RGB, there is no dark primary, thus it is dark former
Color algorithm is not suitable for bright areas.The present invention is directed to the problem of bright areas transmissivity is less than normal, calculating of the present invention to transmissivity
Formula is modified, and amended formula is：
Above-mentioned formula employs the form of exponential function, and after setting, pixel brightness value is more close with air light value, then
Transmittance values are bigger, in this way, transmissivity can be made to realize dynamic regulation, the present invention in the specific implementation, makes β=2.
(4) transmittance figure is refined
There is obvious blocking effect in the image that coarse transmissivity can to restore, and the present invention uses guiding filtering algorithm,
Refine transmittance figure, guiding filtering be it is a kind of quick protect side algorithm, similar to bilateral filtering, can the spatial information of image and
Codomain information is combined together, and reaches the effect for protecting side denoising.Guiding filtering algorithm assumes to be oriented to image and filtering output image
Between there is local linear relationship, can be represented by the formula：
For I to be oriented to image, q is filtered output image.wkIt is the square window centered on a pixel,
(ak,bk) it is in window wkIn constant linear coefficient.
If p is input picture, can be obtained by linear regression method：
Wherein, μkWithIt is to be oriented to image I in window wkIn average value and variance, | w | be in window wkIn pixel
Sum,It is the average value of input picture p pixels in window wk.
For the present invention using the coarse transmittance figure previously obtained as the input picture for guiding filtering, foggy image is guiding
Image, the transmittance figure that can be refined after filtered.
(5) brightness of image and contrast are strengthened
The fog free images that dark primary elder generation checking method recovers are partially dark on the whole, contrast is relatively low, the histogram of partially dark image
General grayscale dynamic range is relatively narrow, its histogram can be handled, common method have histogram equalization method and
Histogram specification method, but the specific enhancing effect of histogram equalization method is difficult to control, and is easily lost the details of image,
Traditional histogram specification method adaptivity difference is, it is necessary to repeatedly attempt just obtain satisfied effect.The present invention is by right
Traditional histogram specification algorithm is improved, using the histogram specification method based on Gaussian function to image after defogging
Histogram be adjusted, achieve the purpose that image enhancement.
One width number of greyscale levels is the original input picture of s, its grey level probability density function is represented by p (ri), wherein 1≤
i≤s,riTo correspond to gray value during i, then average gray μ and variances sigma can be defined with following formula：
For Gaussian function, can be represented by the formula:
Wherein m represents the mathematical expectation of Gaussian function, and n represents the variance of Gaussian function.
The present invention is set as defogging figure using Gaussian function come the histogram of regulation output image, the mathematical expectation of image
K times of the average gray of picture, the variance of Gaussian function are set as mist elimination image variance, and the present invention is when it is implemented, make k=2.
The SML Mapping implementation histogram specifications that the present invention uses, comprise the following steps that：
(1) accumulation histogram of original image is solved
Wherein psFor the histogram of original image.
(2) Gaussian function accumulation histogram is solved
Wherein ulFor goal histogram.
(3) SML maps
SML mappings are carried out from original accumulation histogram to target accumulated histogram, find first make the k of following formula minimum with
l。
Then by ps(si) correspond to pu(uj) up.
The foregoing is merely the preferred embodiment of the application, the application is not limited to, for the skill of this area
For art personnel, the application can have various modifications and variations.It is all within spirit herein and principle, made any repair
Change, equivalent substitution, improvement etc., should be included within the protection domain of the application.
Although above-mentioned be described the embodiment of the present invention with reference to attached drawing, model not is protected to the present invention
The limitation enclosed, those skilled in the art should understand that, on the basis of technical scheme, those skilled in the art are not
Need to make the creative labor the various modifications that can be made or deformation still within protection scope of the present invention.
Claims (10)
1. a kind of bright areas color fidelity and the image defogging method of contrast enhancing, it is characterized in that：Select atmospheric scattering mould
Type estimates air light value as physical model according to dark primary figure, non-to being determined as by judging image-region pixel
The pixel of bright areas, calculates transmissivity, the pixel to being determined as bright areas, is corrected with the method plotted against in color priori
The transmissivity of bright areas, brightness and contrast's increasing is carried out by Gauss histogram specification method to revised mist elimination image
By force.
2. a kind of bright areas color fidelity and the image defogging method of contrast enhancing, it is characterized in that：Specifically include following step
Suddenly：
(1) using atmospherical scattering model as physical model, air light intensity value is estimated using dark channel diagram；
(2) according to the ratio of foggy image brightness value and air light intensity value, by image-region be divided into bright areas with it is non-bright
Bright area；
(3) for the non-bright areas of division, using dark primary priori computation transmittance figure, for bright areas, using amendment
Transmissivity method calculate transmittance figure；
(4) using guiding filtering algorithm refinement transmittance figure, mist elimination image is obtained；
(5) the histogram specification method based on Gaussian function is used, adjusts the histogram of image after defogging.
3. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (1), using the atmospherical scattering model of McCarney, the non-light projection ratio of its input picture light intensity with
The product of the light intensity of scenery when fogless, and one subtract the value of light transmittance and atmosphere light component product and.
4. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (1), image defogging target is exactly to recover fogless image by known foggy image, it is necessary to estimate
Go out air luminous intensity and light transmittance.
5. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (1), air light value estimation, specifically includes：
(a) a certain proportion of pixel of brightness maximum is taken from the dark channel diagram containing mist；
(b) location of pixels obtained in corresponding (a), finds the value of maximum brightness point as air light value in original image.
6. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (2), the specific steps of region division：According to foggy image brightness value I and the ratio of air light intensity value A
Value judges whether pixel belongs to bright areas, and setting ratio threshold alpha, if I/A ＞ α, judges that pixel belongs to bright areas；
Conversely, belong to normal region, i.e., non-bright areas.
7. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (3), for non-bright areas, using the computational methods of dark primary priori, the computational methods of light transmittance
For：One and the region in the minimum value of coloured image RGB channel and atmosphere light component ratio be multiplied by the difference of proportionality coefficient.
8. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (3), for bright areas, the calculation formula of transmissivity is modified, and amended formula is：
<mrow>
<mi>t</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msup>
<mi>e</mi>
<mrow>
<mi>&beta;</mi>
<mrow>
<mo>(</mo>
<munder>
<mi>min</mi>
<mrow>
<mi>y</mi>
<mo>&Element;</mo>
<mi>&Omega;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
</mrow>
</munder>
<mo>(</mo>
<mrow>
<munder>
<mi>min</mi>
<mi>c</mi>
</munder>
<mfrac>
<mrow>
<msup>
<mi>I</mi>
<mi>c</mi>
</msup>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
<msup>
<mi>A</mi>
<mi>c</mi>
</msup>
</mfrac>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</msup>
</mrow>
Using the form of exponential function, after setting, pixel brightness value is more close with air light value, then transmittance values are bigger,
Transmissivity is set to realize dynamic regulation, Ω (x) represents one piece of regional area centered on pixel x, IcRepresent that coloured image RGB leads to
C-th of channel value in road, β are coefficient, AcRepresent the air light value of estimation.
9. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (4), guiding filtering algorithm assumes to be oriented to image and there is local linear pass between filtering output image
System, filtered image is obtained by linear regression method according to input picture.
10. a kind of bright areas color fidelity as claimed in claim 2 and the image defogging method of contrast enhancing, its feature
It is：In the step (5), it is set as using Gaussian function come the histogram of regulation output image, the mathematical expectation of image
K times of the average gray of mist image, the variance of Gaussian function are set as mist elimination image variance, and k is constant, and the SML of use reflects
Penetrate and realize histogram specification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711261135.3A CN107977941B (en) | 2017-12-04 | 2017-12-04 | Image defogging method for color fidelity and contrast enhancement of bright area |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711261135.3A CN107977941B (en) | 2017-12-04 | 2017-12-04 | Image defogging method for color fidelity and contrast enhancement of bright area |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107977941A true CN107977941A (en) | 2018-05-01 |
| CN107977941B CN107977941B (en) | 2021-04-20 |
Family
ID=62009135
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711261135.3A Active CN107977941B (en) | 2017-12-04 | 2017-12-04 | Image defogging method for color fidelity and contrast enhancement of bright area |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107977941B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765316A (en) * | 2018-05-07 | 2018-11-06 | 珠海全志科技股份有限公司 | Fog concentration self-adapting judgment method |
| CN109146815A (en) * | 2018-08-20 | 2019-01-04 | 深圳创维－Rgb电子有限公司 | Picture contrast method of adjustment, device and computer equipment |
| CN110175967A (en) * | 2019-06-05 | 2019-08-27 | 海南大学 | Image defogging processing method, system, computer equipment and storage medium |
| CN112561906A (en) * | 2020-12-24 | 2021-03-26 | 百果园技术(新加坡)有限公司 | Image processing method, device, equipment and medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663694A (en) * | 2012-03-30 | 2012-09-12 | 大连理工大学 | Digital fog effect filter method based on dark primary color channel prior principle |
| CN102750674A (en) * | 2012-04-26 | 2012-10-24 | 长春理工大学 | Video image defogging method based on self-adapting allowance |
| CN105096272A (en) * | 2015-08-19 | 2015-11-25 | 常州工学院 | De-hazing method based on dual-tree complex wavelet |
| CN105279746A (en) * | 2014-05-30 | 2016-01-27 | 西安电子科技大学 | Multi-exposure image integration method based on bilateral filtering |
| CN105678712A (en) * | 2016-01-29 | 2016-06-15 | 陕西师范大学 | Improved Criminisi image restoration method with self-adaptive gradient block division and equilong transformation |
| CN105787904A (en) * | 2016-03-25 | 2016-07-20 | 桂林航天工业学院 | Adaptive global dark channel prior image dehazing method for bright area |
| CN106846253A (en) * | 2017-02-14 | 2017-06-13 | 深圳市唯特视科技有限公司 | A kind of image super-resolution rebuilding method based on reverse transmittance nerve network |
| US20170316551A1 (en) * | 2016-04-29 | 2017-11-02 | Industry Foundation Of Chonnam National University | System for image dehazing by modifying lower bound of transmission rate and method therefor |
-
2017
- 2017-12-04 CN CN201711261135.3A patent/CN107977941B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663694A (en) * | 2012-03-30 | 2012-09-12 | 大连理工大学 | Digital fog effect filter method based on dark primary color channel prior principle |
| CN102750674A (en) * | 2012-04-26 | 2012-10-24 | 长春理工大学 | Video image defogging method based on self-adapting allowance |
| CN105279746A (en) * | 2014-05-30 | 2016-01-27 | 西安电子科技大学 | Multi-exposure image integration method based on bilateral filtering |
| CN105096272A (en) * | 2015-08-19 | 2015-11-25 | 常州工学院 | De-hazing method based on dual-tree complex wavelet |
| CN105678712A (en) * | 2016-01-29 | 2016-06-15 | 陕西师范大学 | Improved Criminisi image restoration method with self-adaptive gradient block division and equilong transformation |
| CN105787904A (en) * | 2016-03-25 | 2016-07-20 | 桂林航天工业学院 | Adaptive global dark channel prior image dehazing method for bright area |
| US20170316551A1 (en) * | 2016-04-29 | 2017-11-02 | Industry Foundation Of Chonnam National University | System for image dehazing by modifying lower bound of transmission rate and method therefor |
| CN106846253A (en) * | 2017-02-14 | 2017-06-13 | 深圳市唯特视科技有限公司 | A kind of image super-resolution rebuilding method based on reverse transmittance nerve network |
Non-Patent Citations (9)
| Title |
|---|
| WENCHENG WANG ET AL: "Fast Image Dehazing Method Based on Linear Transformation", 《IEEE TRANSACTIONS ON MULTIMEDIA》 * |
| YU LINAN ET AL: "Video Defogging Based on Adaptive Tolerance", 《TELKOMNIKA》 * |
| 刘业妃等: "改进的Criminisi图像修复算法", 《小型微型计算机***》 * |
| 周军其等: "《遥感原理与应用》", 30 November 2014 * |
| 尹承添等: "一种改进的图像增强算法及其在铸坯图像增强中的应用", 《连铸》 * |
| 崔宝侠: "明亮区域的暗原色先验算法", 《沈阳工业大学学报》 * |
| 方雯等: "反馈调节机制的暗通道去雾算法", 《计算机应用》 * |
| 王万国等: "基于直方图规定化的图像去雾算法", 《计算机技术与发展》 * |
| 麦嘉铭等: "特征学习的单幅图像去雾算法", 《中国图象图形学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108765316A (en) * | 2018-05-07 | 2018-11-06 | 珠海全志科技股份有限公司 | Fog concentration self-adapting judgment method |
| CN108765316B (en) * | 2018-05-07 | 2021-11-16 | 珠海全志科技股份有限公司 | Mist concentration self-adaptive judgment method |
| CN109146815A (en) * | 2018-08-20 | 2019-01-04 | 深圳创维－Rgb电子有限公司 | Picture contrast method of adjustment, device and computer equipment |
| CN110175967A (en) * | 2019-06-05 | 2019-08-27 | 海南大学 | Image defogging processing method, system, computer equipment and storage medium |
| CN112561906A (en) * | 2020-12-24 | 2021-03-26 | 百果园技术(新加坡)有限公司 | Image processing method, device, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107977941B (en) | 2021-04-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106251300B (en) | A kind of quick night Misty Image restored method based on Retinex | |
| CN107301623B (en) | Traffic image defogging method and system based on dark channel and image segmentation | |
| CN102831591B (en) | Gaussian filter-based real-time defogging method for single image | |
| CN103218778B (en) | The disposal route of a kind of image and video and device | |
| CN104253930B (en) | A kind of real-time video defogging method | |
| CN102750674B (en) | Video image defogging method based on self-adapting allowance | |
| CN106846263A (en) | The image defogging method being immunized based on fusion passage and to sky | |
| CN104036466B (en) | A kind of video defogging method and system | |
| CN107103591A (en) | A kind of single image to the fog method based on image haze concentration sealing | |
| CN107977941A (en) | A kind of bright areas color fidelity and the image defogging method of contrast enhancing | |
| CN110570360B (en) | Retinex-based robust and comprehensive low-quality illumination image enhancement method | |
| CN107767354A (en) | A kind of image defogging algorithm based on dark primary priori | |
| CN109087254B (en) | Unmanned aerial vehicle aerial image haze sky and white area self-adaptive processing method | |
| CN104867121B (en) | Image Quick demisting method based on dark primary priori and Retinex theories | |
| CN105631829A (en) | Night haze image defogging method based on dark channel prior and color correction | |
| CN103049888A (en) | Image/video demisting method based on combination of dark primary color of atmospheric scattered light | |
| CN109255759A (en) | Image defogging method based on sky segmentation and transmissivity adaptive correction | |
| CN105913390B (en) | A kind of image defogging method and system | |
| CN103985091A (en) | Single image defogging method based on luminance dark priori method and bilateral filtering | |
| CN105959510B (en) | A kind of video rapid defogging method | |
| CN107451966A (en) | A kind of real-time video defogging method realized using gray-scale map guiding filtering | |
| Pei et al. | Effective image haze removal using dark channel prior and post-processing | |
| CN106548461A (en) | Image defogging method | |
| CN103345733A (en) | Rapid low-illumination image enhancing method based on improved dark channel prior | |
| WO2024060576A1 (en) | Image dehazing method based on dark channel prior |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Ji'nan City, Shandong Province Wang Yue Road 250003 No. 2000 Applicant after: Electric Power Research Institute of State Grid Shandong Electric Power Company Applicant after: National Network Intelligent Technology Co., Ltd. Applicant after: State Grid Corporation of China Address before: Ji'nan City, Shandong Province Wang Yue Road 250003 No. 2000 Applicant before: Electric Power Research Institute of State Grid Shandong Electric Power Company Applicant before: Shandong Luneng Intelligent Technology Co., Ltd. Applicant before: State Grid Corporation of China |
|
| CB02 | Change of applicant information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20201030 Address after: 250101 Electric Power Intelligent Robot Production Project 101 in Jinan City, Shandong Province, South of Feiyue Avenue and East of No. 26 Road (ICT Industrial Park) Applicant after: National Network Intelligent Technology Co.,Ltd. Address before: Ji'nan City, Shandong Province Wang Yue Road 250003 No. 2000 Applicant before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Applicant before: National Network Intelligent Technology Co.,Ltd. Applicant before: STATE GRID CORPORATION OF CHINA |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |