CN105118027B - A kind of defogging method of image - Google Patents
A kind of defogging method of image Download PDFInfo
- Publication number
- CN105118027B CN105118027B CN201510450993.7A CN201510450993A CN105118027B CN 105118027 B CN105118027 B CN 105118027B CN 201510450993 A CN201510450993 A CN 201510450993A CN 105118027 B CN105118027 B CN 105118027B
- Authority
- CN
- China
- Prior art keywords
- mrow
- image
- color channel
- amendment
- transmissivity
- 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.)
- Active
Links
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a kind of defogging method of image, applied to the image comprising fog, methods described includes:The dark of described image is obtained by the Color Channel of described image;The transmissivity of air light intensity and described image is obtained by the dark;The Color Channel is modified according to the transmissivity and obtains correcting Color Channel;Amendment air light intensity is obtained by the amendment Color Channel and transmissivity is corrected;Mist elimination image is obtained according to the amendment Color Channel, amendment air light intensity and amendment transmissivity.The present invention is modified to the Color Channel of image, air light intensity and transmissivity, can eliminate the fog of image, the problems such as eliminating blocky effect to greatest extent according to the characteristics of image itself.
Description
Technical field
The invention belongs to technical field of image processing, more particularly to a kind of defogging method of image.
Background technology
As a kind of important means of security protection, video monitoring plays particularly important effect.However, video monitoring
System is larger by such environmental effects when obtaining image.For example, under the conditions of haze, the image matter that optical sensor is captured
Amount degradation, picture contrast bottom, loss of detail is serious, is that follow-up image procossing and analysis work bring and is greatly stranded
Difficulty, therefore the efficiently feasible defogging algorithm of research has highly important theoretical and researching value.
Domestic and foreign scholars are broadly divided into two classes for the research of defogging method:Defogging algorithm based on air photon diffusion models
With the defogging algorithm based on image enhancement technique.Defogging algorithm based on air photon diffusion models mainly includes:Based on dark
The defogging algorithm of priori and fuzzy defogging algorithm etc.;Defogging algorithm based on image enhancement technique includes:Based on Retinex images
The defogging algorithm of enhancing technology, based on pixel color diversity defogging algorithm etc..Dark is based in these existing algorithms
The defogging algorithm of priori is acknowledged as a kind of most effective and most general algorithm.The algorithm is to be based on dark channel prior information structure
Defogging model is built, the priori is thought in three Color Channels of image local area, the pixel value of at least one Color Channel
Than relatively low or close to zero, dark is defined as.By defining dark, it is estimated that mist in foggy image into
Point, so as to realize the purpose for recovering original image from foggy image, method flow diagram is as shown in Figure 1.What existing method was obtained
Image after defogging has large area light color or the partially image of white region, and the value of dark is generally also higher so that pending
Image not exclusively meets dark channel prior theory, and obtained mist elimination image be present.
The content of the invention
In view of this, the embodiment of the present invention is expected to provide a kind of defogging method of image, can at least solve existing defogging side
The technical problems such as the blocky effect that method is present.
What the technical scheme of the embodiment of the present invention was realized in:
The embodiments of the invention provide a kind of defogging method of image, applied to the image comprising fog, methods described bag
Include:
The dark of described image is obtained by the Color Channel of described image;
The transmissivity of air light intensity and described image is obtained by the dark;
The Color Channel is modified according to the transmissivity and obtains correcting Color Channel;
Amendment air light intensity is obtained by the amendment Color Channel and transmissivity is corrected;
Mist elimination image is obtained according to the amendment Color Channel, amendment air light intensity and amendment transmissivity.
In such scheme, the dark that the Color Channel by described image obtains described image includes:
Channel decomposition is carried out to described image, each Color Channel of image is obtained;
Described image is divided into setting image block, by the Color Channel that the corresponding gray value of described image block is minimum
It is set as described image block dark.
In such scheme, the process of asking for of the air light intensity is:
Obtain the brightness highest pixel point set in the dark;
The pixel for concentrating selection setting ratio from the pixel is used as reference image vegetarian refreshments;
Calculate the gray value of reference image vegetarian refreshments corresponding pixel in described image;
The intermediate value of the gray value is set as air light intensity.
In such scheme, described be modified according to the transmissivity to the Color Channel obtains correcting Color Channel bag
Include:
Normalized is done to the transmissivity in described image block dark and obtains normalized transmittance;
Calculate weight of the Color Channel in described image block dark in the corresponding Color Channel of described image;
Pass through the normalized transmittance and weight calculation amendment Color Channel.
It is described that defogging is obtained according to the amendment Color Channel, amendment air light intensity and amendment transmissivity in such scheme
Image includes:
The defogging color for obtaining described image by the amendment Color Channel, amendment air light intensity and amendment transmissivity is led to
Road;
The mist elimination image for obtaining correspondence described image is weighted to the defogging Color Channel.
In such scheme, the calculating process of described image block dark is:
Wherein, Jdark(y) it is image block dark, is represented with matrix;R, g, b represent red, green and blueness respectively;c
One of for r, g, tri- kinds of colors of b;Y is the set of the local cell domain composition centered on the space coordinate x of described image, and Ω is
Set symbol, is expressed as y ∈ Ω (x);Jc(y) for image block regional area Color Channel any one.
In such scheme, the calculating process of the transmissivity is:
Wherein, t (y) is transmissivity;Ic(y) it is the corresponding Color Channels of color c;AcFor Color Channel Ic(y) it is corresponding big
Gas light intensity.
In such scheme, the calculating process of the amendment Color Channel is:
Wherein, Ic' (y) amendment Color Channel for being, represented with matrix;Tck(y) it is normalized transmittance;Gck(y) it is power
Weight;Ick(y) it is Color Channel I of the foggy image in image block kc(y) value on.
In such scheme, the calculating process of the defogging Color Channel is:
Wherein,For the Color Channel of mist elimination image, represented with matrix;Ic' (y) be revised Color Channel;For amendment air light intensity;For amendment transmissivity.
In such scheme, the calculating process of the mist elimination image is:
Wherein, J (y) is mist elimination image, is represented with matrix;N is weights, and n value is identical with the quantity of Color Channel.
The defogging method for the image that the embodiment of the present invention is provided, Color Channel, air light intensity and transmissivity to image
It is modified, the fog of image, the problems such as eliminating blocky effect can be eliminated to greatest extent according to the characteristics of image itself.
Brief description of the drawings
Fig. 1 is the flow chart of existing defogging method;
Fig. 2 is the flow chart of the defogging method of the image of embodiment 1;
Fig. 3 is the image defog effect comparison diagram of embodiment 2.
In order to be able to clearly realize the structure of embodiments of the invention, certain size, structure and device are labelled with figure,
But it is only for illustrating needs, is not intended to limit the invention in the specific dimensions, structure, device and environment, according to specific
Need, these devices and environment can be adjusted or changed by one of ordinary skill in the art, the adjustment that is carried out or
Person's modification is still included in the scope of appended claims.
Embodiment
In the following description, multiple different aspects of the present invention will be described, however, for common skill in the art
For art personnel, the present invention can be implemented just with some or all structures or flow of the present invention.In order to explain
Definition for, elaborate specific number, configuration and order, however, it will be apparent that in the situation without these specific details
Under can also implement the present invention.In other cases, will no longer for some well-known features in order to not obscure the present invention
It is described in detail.
Embodiment 1
In order to solve the technical problems such as the blocky effect that existing defogging method is present, the embodiments of the invention provide one kind figure
The defogging method of picture, applied to the image comprising fog, as shown in Fig. 2 the described method comprises the following steps:
Step S101:The dark of described image is obtained by the Color Channel of described image;
Image described in the present embodiment refers to obtain by digital imaging apparatus (such as mobile phone, video camera, digital camera)
The image for including fog, the image is also referred to as colour cast image.The contrast bottom of colour cast image, loss of detail are serious, while can produce
Fog situation, is that follow-up image procossing and analysis work bring great difficulty.
The present embodiment by method of the image by channel decomposition, obtain each pixel of image RGB (Red- is red,
Green- is green, Blue- is blue) pixel value on passage, and represented with the form of matrix, i.e. Color Channel;Asked according to Color Channel
Obtain dark.
Step S102:The transmissivity of air light intensity and described image is obtained by the dark;
The air light intensity of image and the transmissivity of described image are obtained based on dark so that the air light intensity and described
Transmissivity more meets present image.
Step S103:The Color Channel is modified according to the transmissivity and obtains correcting Color Channel;
Generally, there are the different depth of field in image, and the corresponding transmissivity of the different depth of field is also different;Therefore, according to transmission
Rate is modified to Color Channel, fog can be removed for the depth of field feature of present image itself.
Step S104:Amendment air light intensity is obtained by the amendment Color Channel and transmissivity is corrected;
Obtain after amendment Color Channel, air light intensity and transmissivity are modified again, present image is further conformed to
Defogging need.
Step S105:Mist elimination image is obtained according to the amendment Color Channel, amendment air light intensity and amendment transmissivity.
Image when Color Channel, amendment air light intensity and amendment transmissivity are applied to this implementation beginning will be corrected, must
To corresponding mist elimination image.
The present embodiment method is modified to the Color Channel of image, air light intensity and transmissivity, can be according to image itself
The characteristics of eliminate the fog of image, the problems such as eliminating blocky effect to greatest extent.
Specifically, step S101 includes:
Step S1011:Channel decomposition is carried out to described image, Color Channel is obtained;
Channel decomposition is carried out to described image by tri- passages of RGB, red channel, green channel and blueness is respectively obtained
Passage.
Step S1012:Described image is divided into setting image block, by the institute that the corresponding gray value of described image block is minimum
State the dark that Color Channel is set as described image block.
Different images, the depth of field is also different.According to the characteristics of image itself, setting image block is divided the image into;Then
Dark block is individually asked for each image block, the dark of all images block is combined into the dark of correspondence described image
Image.
The calculating process of described image block dark is:
Wherein, Jdark(y) it is image block dark, is represented with matrix;R, g, b represent red, green and blueness respectively;c
One of for r, g, tri- kinds of colors of b;Y is the set of the local cell domain composition centered on the space coordinate x of described image, and Ω is
Set symbol, is expressed as y ∈ Ω (x);Jc(y) for image block regional area Color Channel any one.
The process of asking for of air light intensity described in step S102 is:
Step S1021:Obtain the brightness highest pixel point set in the dark;
Step S1022:The pixel for concentrating selection setting ratio from the pixel is used as reference image vegetarian refreshments;
Step S1023:Calculate the gray value of reference image vegetarian refreshments corresponding pixel in described image;
Step S1024:The intermediate value of the gray value is set as air light intensity.
In addition, the calculating process of transmissivity is described in step S102:
Wherein, t (y) is transmissivity;Ic(y) it is the corresponding Color Channels of color c;AcFor Color Channel Ic(y) it is corresponding big
Gas light intensity.
The step S103 is specifically included:
Step S1031:Normalized is done to the transmissivity in described image block dark and obtains normalized transmittance;
Step S1032:Calculate the weight of the Color Channel on the image in described image block dark;
Step S1033:Pass through the normalized transmittance and weight calculation amendment Color Channel.The amendment Color Channel
Calculating process be:
Wherein, Ic' (y) for amendment Color Channel, represented with matrix;Tck(y) it is normalized transmittance;Gck(y) it is weight;
Ick(y) it is Color Channel I of the foggy image in image block kc(y) value on;
The step S105 is specifically included:
Step S1051:Described image is obtained by the amendment Color Channel, amendment air light intensity and amendment transmissivity
Defogging Color Channel;The calculating process of the defogging Color Channel is:
Wherein,For the Color Channel of mist elimination image, represented with matrix;Ic' (y) be revised Color Channel;For amendment air light intensity;For amendment transmissivity.
Step S1052:The mist elimination image for obtaining correspondence described image is weighted to the defogging Color Channel.It is described to go
The calculating process of mist image is:
Wherein, J (y) is mist elimination image, is represented with matrix;N is weights, and n value is identical with the quantity of Color Channel.
The present embodiment method shows the image block Color Channel of image with weight, and assigns different images block simultaneously
The different weighted value of Color Channel, be based on transmissivity optimization cost function in dark channel prior algorithm with original and be combined, fit
There is " halation ", block effect for there is large area light color or the partially image of white region, and image after processing can be significantly improved
The problem of answering.
Embodiment 2
The present invention is described in detail according to the scene of a reality for the present embodiment.
The present embodiment method comprises the following steps:
(1) Color Channel of image is obtained
The foggy image obtained by digital camera, the first-class digital imaging apparatus of cell-phone camera is input in computer,
Image is indicated in RGB color;
Colour cast image is obtained by digital imaging apparatus (such as digital camera, cell-phone camera is first-class).In haze condition
Under, the picture quality degradation that digital imaging apparatus optical sensor is captured, picture contrast bottom, loss of detail is serious,
Atomization image is produced, is that follow-up image procossing and analysis work bring great difficulty,.The image of atomization is read into meter
In calculation machine, and pixel value of each pixel of image in tri- passages of R, G, B is obtained by channel decomposition, so as to obtain image
Data message, these data messages be carry out defogging basis, use formula as follows:
Wherein, I (x) is represented to treat mist elimination image with matrix;Ir(x) it is the red color passage of image;Ig(x) it is image
Green color channel;Ib(x) it is the blue color channels of image.In order to represent convenient, I is usedc(x) I is representedr(x)、Ig(x) and
Ib(x) any one Color Channel in.
(2) image dark channel is calculated
This step includes:
A, divides the image into image block, the quantity of specific image block is according to actual image setting;
B, calculates the dark of each image block, and dark solution formula is:
Wherein, Jc(y) it is the Color Channel of fog free images, herein with the dark of the equations foggy image, formula
It is deformed into:
Wherein, Idark(y) it is to have mist to attack the dark of that suddenly;Ic(y) it is foggy image.
(3) air light intensity is estimated
Generally, air light intensity chooses the concentration highest of mist in image, brightness highest pixel.Choose in dark
Then these pixels in foggy image are averaged, as air light intensity by pixel highest point again.The present embodiment
In, 0.1% pixel of brightest pixel quantity is first chosen from dark, the ash of these pixels in original input image is then chosen
Maximum gray value (is taken this as the standard) as air light intensity value in angle value.
(4) transmissivity is calculated
Assuming that the overall air light intensity of each image block is all identical and known in foggy image, it is assumed that transmissivity is each
All it is constant in image block, just slightly transmissivity is asked in estimation, then greasy weather air illumination model is:
I (x)=J (x) t (x)+A (1-t (x))
Wherein, I (x) is foggy image, is represented with matrix;J (x) is the image after I (x) defoggings, is represented with matrix;t(x)
For transmissivity;A is air light intensity;X is the space coordinate of image.
Because defogging process is carried out respectively in the regional area of each tri- Color Channels of region R, G, B, above formula
It is represented by:
Ic(y)=Jc(y)t(y)+Ac(1-t(y))
Due to set of the y for the local cell domain composition centered on the space coordinate x of described image, corresponding, t (y)
To represent the projection ratio in regional area, J is similarly generalized tocAnd I (y)c(y)。
Above formula is filtered using minimum, can be obtained:
Above formula with divided by AcHave:
Minimum value is taken to have on three Color Channels:
From the foregoing,And air light intensity AcActual value very
Greatly, then have:
And then obtain transmissivity:
(5) Color Channel is modified
A, calculates the normalized transmittance of image block:
Wherein, Tck(y) the Color Channel I for being image block kc(y) normalized transmittance;tck(y) color for being image block k
Passage Ic(y) transmissivity;U (y) is image block k Color Channel Ic(y) average of transmissivity,S
(y) the Color Channel I for being image block kc(y) standard deviation of transmissivity,ωkFor image
Block k sum;ω is the ω image block.
B, calculates weight of the Color Channel of image block in image respective color passage:
Wherein, ωcFor the Color Channel I of imagec(y) pixel count;Ick(y) it is Color Channel I of the image in image block kc
(y) value on;Gck(y) for image in image block Ic(y) weight on.
C, corrects Color Channel:
Wherein, Ick(y) it is Color Channel I of the image in image block kc(y) value on
(6) air light intensity and transmissivity are modified
The amendment Color Channel obtained in (5) is brought into step (2) to (4), air light intensity and transmissivity is modified,
Obtain correcting air light intensityWith amendment transmissivity(when the transmittance values difference after adjacent two suboptimization is less than 0.15
Stop optimization process;Stop optimization process when the transmissivity intensity values difference after adjacent two suboptimization is less than 0.15).
(7) mist elimination image is exported
A, calculates defogging Color Channel
According to Ic(y)=Jc(y)t(y)+Ac(1-t (y)) can be obtainedIt is then corresponding to go
Mist Color Channel is:
Wherein,For the Color Channel of mist elimination image.
B, calculates mist elimination image
The design sketch handled by existing method and the present embodiment method piece image is as shown in Figure 3.Wherein, scheme
3a is original image;Fig. 3 b are the mist elimination image after existing method is handled;Fig. 3 c are the defogging figure after the present embodiment method is handled
Picture., it is apparent that the image after the present embodiment method defogging is higher than existing method in methods such as definition from Fig. 3.
The method that the present invention is weighted using Color Channel carries out the defogging processing of atomization image, on the basis of dark channel prior
On, the data message included in image is made full use of, the correlation deeply excavated between each Color Channel pixel value of image is examined
Consider influence of the regional area Color Channel weighted value for defogging result.Image after this method defogging, more conforms to people
Eye visual experience, with preferable defog effect;Pass through zoning (image block) transmissivity and different zones Color Channel
Weighted value construction amendment weights, so as to realize the amendment to dark numerical value, improve the scope of application of algorithm, even if in image
In the presence of light color or inclined white region, algorithm still has higher accuracy;By the way of Color Channel weighting output, after processing
Image in blocky effect and halation phenomenon be improved significantly, while the depth information of different scenery can be embodied;Adopt
With relatively simple calculation formula and algorithm flow, time complexity is smaller, speed is performed, with higher efficiency, energy
Enough meet requirement of real-time.The inventive method is available for taken by logarithmic code camera, the first-class digital imaging apparatus of cell-phone camera
Image carry out accurately and efficiently defogging handle, with wide application value and market prospects.
, can be by it in several embodiments provided herein, it should be understood that disclosed apparatus and method
Its mode is realized.Apparatus embodiments described above are only schematical, for example, the division of the unit, is only
A kind of division of logic function, can have other dividing mode, such as when actually realizing:Multiple units or component can be combined, or
Another system is desirably integrated into, or some features can be ignored, or do not perform.In addition, shown or discussed each composition portion
Coupling point each other or direct-coupling or communication connection can be the INDIRECT COUPLINGs of equipment or unit by some interfaces
Or communication connection, can be electrical, machinery or other forms.
The above-mentioned unit illustrated as separating component can be or may not be it is physically separate, it is aobvious as unit
The part shown can be or may not be physical location, you can positioned at a place, can also be distributed to multiple network lists
In member;Part or all of unit therein can be selected to realize the purpose of this embodiment scheme according to the actual needs.
In addition, each functional unit in various embodiments of the present invention can be fully integrated into a processing module, also may be used
Be each unit individually as a unit, can also two or more units it is integrated in a unit;It is above-mentioned
Integrated unit can both be realized in the form of hardware, it would however also be possible to employ hardware adds the form of SFU software functional unit to realize.
One of ordinary skill in the art will appreciate that:Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in a computer read/write memory medium, the program
Upon execution, the step of including above method embodiment is performed;And foregoing storage medium includes:It is movable storage device, read-only
Memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disc or
Person's CD etc. is various can be with the medium of store program codes.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (9)
1. a kind of defogging method of image, applied to the image comprising fog, it is characterised in that methods described includes:
The dark of described image is obtained by the Color Channel of described image;
The transmissivity of air light intensity and described image is obtained by the dark;
The Color Channel is modified according to the transmissivity and obtains correcting Color Channel;Specifically include:To described image
Transmissivity in block dark does normalized and obtains normalized transmittance;Calculate the face in described image block dark
Weight of the chrominance channel in the corresponding Color Channel of described image;It is logical by the normalized transmittance and weight calculation amendment color
Road;
Amendment air light intensity is obtained by the amendment Color Channel and transmissivity is corrected;
Mist elimination image is obtained according to the amendment Color Channel, amendment air light intensity and amendment transmissivity.
2. a kind of defogging method of image according to claim 1, it is characterised in that the color by described image
The dark that passage obtains described image includes:
Channel decomposition is carried out to described image, each Color Channel of image is obtained;
Described image is divided into setting image block, the minimum Color Channel of the corresponding gray value of described image block is set
For described image block dark.
3. a kind of defogging method of image according to claim 1, it is characterised in that the air light intensity asks for process
For:
Obtain the brightness highest pixel point set in the dark;
The pixel for concentrating selection setting ratio from the pixel is used as reference image vegetarian refreshments;
Calculate the gray value of reference image vegetarian refreshments corresponding pixel in described image;
The intermediate value of the gray value is set as air light intensity.
4. the defogging method of a kind of image according to claim 2, it is characterised in that described to be led to according to the amendment color
Road, amendment air light intensity and amendment transmissivity obtain mist elimination image and included:
The defogging Color Channel of described image is obtained by the amendment Color Channel, amendment air light intensity and amendment transmissivity;
The mist elimination image for obtaining correspondence described image is weighted to the defogging Color Channel.
5. a kind of defogging method of image according to claim 2, it is characterised in that the calculating of described image block dark
Process is:
<mrow>
<msup>
<mi>J</mi>
<mrow>
<mi>d</mi>
<mi>a</mi>
<mi>r</mi>
<mi>k</mi>
</mrow>
</msup>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munder>
<mi>min</mi>
<mrow>
<mi>c</mi>
<mo>&Element;</mo>
<mo>{</mo>
<mi>r</mi>
<mo>,</mo>
<mi>g</mi>
<mo>,</mo>
<mi>b</mi>
<mo>}</mo>
</mrow>
</munder>
<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>
<msup>
<mi>J</mi>
<mi>c</mi>
</msup>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>0</mn>
</mrow>
Wherein, Jdark(y) it is image block dark, is represented with matrix;R, g, b represent red, green and blueness respectively;C is r, g,
One of tri- kinds of colors of b;Y is the set of the local cell domain composition centered on the space coordinate x of described image, and Ω is set symbol
Number, it is expressed as y ∈ Ω (x);Jc(y) for image block regional area Color Channel any one.
6. a kind of defogging method of image according to claim 1, it is characterised in that the calculating process of the transmissivity
For:
<mrow>
<mi>t</mi>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<munder>
<mi>min</mi>
<mi>c</mi>
</munder>
<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>
<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>
<mo>)</mo>
<mo>)</mo>
</mrow>
</mrow>
Wherein, t (y) is transmissivity;Ic(y) it is the corresponding Color Channels of color c;AcFor Color Channel Ic(y) corresponding atmosphere light
By force.
7. a kind of defogging method of image according to claim 2, it is characterised in that the calculating of the amendment Color Channel
Process is:
<mrow>
<msubsup>
<mi>I</mi>
<mi>c</mi>
<mo>&prime;</mo>
</msubsup>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>k</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msub>
<mi>T</mi>
<mrow>
<mi>c</mi>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>G</mi>
<mrow>
<mi>c</mi>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>I</mi>
<mrow>
<mi>c</mi>
<mi>k</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein, I'c(y) it is amendment Color Channel, is represented with matrix;Tck(y) it is normalized transmittance;Gck(y) it is weight;Ick
(y) it is Color Channel I of the foggy image in image block kc(y) value on.
8. a kind of defogging method of image according to claim 7, it is characterised in that the calculating of the defogging Color Channel
Process is:
<mrow>
<msup>
<mover>
<mi>J</mi>
<mo>~</mo>
</mover>
<mi>c</mi>
</msup>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mi>I</mi>
<mi>c</mi>
<mo>&prime;</mo>
</msubsup>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msup>
<mover>
<mi>A</mi>
<mo>~</mo>
</mover>
<mi>c</mi>
</msup>
</mrow>
<mrow>
<mover>
<mi>t</mi>
<mo>~</mo>
</mover>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
</mfrac>
<mo>+</mo>
<msup>
<mover>
<mi>A</mi>
<mo>~</mo>
</mover>
<mi>c</mi>
</msup>
</mrow>
Wherein,For the Color Channel of mist elimination image, represented with matrix;I'c(y) it is revised Color Channel;To repair
Positive air light intensity;For amendment transmissivity.
9. a kind of defogging method of image according to claim 4, it is characterised in that the calculating process of the mist elimination image
For:
<mrow>
<mi>J</mi>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mrow>
<munder>
<mo>&Sigma;</mo>
<mrow>
<mi>c</mi>
<mo>&Element;</mo>
<mo>{</mo>
<mi>r</mi>
<mo>,</mo>
<mi>g</mi>
<mo>,</mo>
<mi>b</mi>
<mo>}</mo>
</mrow>
</munder>
<msup>
<mover>
<mi>J</mi>
<mo>~</mo>
</mover>
<mi>c</mi>
</msup>
<mrow>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
</mrow>
</mrow>
<mi>n</mi>
</mfrac>
</mrow>
Wherein, J (y) is mist elimination image, is represented with matrix;N is weights, and n value is identical with the quantity of Color Channel.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510450993.7A CN105118027B (en) | 2015-07-28 | 2015-07-28 | A kind of defogging method of image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510450993.7A CN105118027B (en) | 2015-07-28 | 2015-07-28 | A kind of defogging method of image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105118027A CN105118027A (en) | 2015-12-02 |
CN105118027B true CN105118027B (en) | 2017-10-27 |
Family
ID=54666002
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510450993.7A Active CN105118027B (en) | 2015-07-28 | 2015-07-28 | A kind of defogging method of image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105118027B (en) |
Families Citing this family (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105913391B (en) * | 2016-04-07 | 2018-12-07 | 西安交通大学 | A kind of defogging method can be changed Morphological Reconstruction based on shape |
CN105976337B (en) * | 2016-05-10 | 2018-12-18 | 长安大学 | A kind of image defogging method based on intermediate value guiding filtering |
CN106651822A (en) * | 2016-12-20 | 2017-05-10 | 宇龙计算机通信科技(深圳)有限公司 | Picture recovery method and apparatus |
CN106657948A (en) * | 2017-01-18 | 2017-05-10 | 聚龙智瞳科技有限公司 | low illumination level Bayer image enhancing method and enhancing device |
CN106960421B (en) * | 2017-03-16 | 2020-04-17 | 天津大学 | Night image defogging method based on statistical characteristics and brightness estimation |
CN107203981B (en) * | 2017-06-16 | 2019-10-01 | 南京信息职业技术学院 | A kind of image defogging method based on fog concentration feature |
CN108416742B (en) * | 2018-01-23 | 2021-09-17 | 浙江工商大学 | Sand and dust degraded image enhancement method based on color cast correction and information loss constraint |
CN108961206B (en) * | 2018-04-20 | 2021-05-11 | 北京航空航天大学 | Non-reference objective evaluation method for defogging effect |
CN110175967B (en) * | 2019-06-05 | 2020-07-17 | 邓诗雨 | Image defogging processing method, system, computer device and storage medium |
CN110675340A (en) * | 2019-09-16 | 2020-01-10 | 重庆邮电大学 | Single image defogging method and medium based on improved non-local prior |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102968772B (en) * | 2012-12-04 | 2016-01-13 | 电子科技大学 | A kind of image defogging method capable based on dark channel information |
CN103279931B (en) * | 2013-06-03 | 2016-07-13 | 中国人民解放军国防科学技术大学 | Mist elimination image denoising method based on absorbance |
-
2015
- 2015-07-28 CN CN201510450993.7A patent/CN105118027B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN105118027A (en) | 2015-12-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105118027B (en) | A kind of defogging method of image | |
CN103606182B (en) | Method and device for image rendering | |
CN102693532B (en) | The automatic local directed complete set of image shadow and highlight | |
CN105874506B (en) | With the image blurring of details reservation | |
CN101360250B (en) | Immersion method and system, factor dominating method, content analysis method and parameter prediction method | |
CN109361910A (en) | Self-adapted white balance correction method and device | |
CN106920221A (en) | Take into account the exposure fusion method that Luminance Distribution and details are presented | |
CN110544213A (en) | Image defogging method based on global and local feature fusion | |
CN103886565A (en) | Nighttime color image enhancement method based on purpose optimization and histogram equalization | |
CN107077830A (en) | Screen brightness regulation method and unmanned aerial vehicle (UAV) control end suitable for unmanned aerial vehicle (UAV) control end | |
CN105681775A (en) | White balance method and device | |
CN107763808A (en) | Equipment adjusting method and related product | |
CN110223251A (en) | Suitable for manually with the convolutional neural networks underwater image restoration method of lamp | |
US20230074060A1 (en) | Artificial-intelligence-based image processing method and apparatus, electronic device, computer-readable storage medium, and computer program product | |
CN109803172A (en) | A kind of processing method of live video, device and electronic equipment | |
CN105809643A (en) | Image enhancing method based on self-adaptive block channel stretching | |
CN103034983A (en) | Defogging method based on anisotropic filtering | |
CN103702116A (en) | Wide dynamic compressing method and device for image | |
CN108875759A (en) | A kind of image processing method, device and server | |
CN104331867A (en) | Image defogging method and device and mobile terminal | |
CN105574819A (en) | Real-time image defogging method and apparatus | |
CN110807735A (en) | Image processing method, image processing device, terminal equipment and computer readable storage medium | |
CN117274107B (en) | End-to-end color and detail enhancement method, device and equipment under low-illumination scene | |
CN103824250B (en) | image tone mapping method based on GPU | |
CN112489144A (en) | Image processing method, image processing apparatus, terminal device, and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |