CN109993705A - A kind of defogging self-adaptation control method and system - Google Patents
A kind of defogging self-adaptation control method and system Download PDFInfo
- Publication number
- CN109993705A CN109993705A CN201711497617.9A CN201711497617A CN109993705A CN 109993705 A CN109993705 A CN 109993705A CN 201711497617 A CN201711497617 A CN 201711497617A CN 109993705 A CN109993705 A CN 109993705A
- Authority
- CN
- China
- Prior art keywords
- defogging
- weight factor
- dark
- estimated value
- image
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 230000005540 biological transmission Effects 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000003044 adaptive effect Effects 0.000 claims abstract description 12
- 238000002834 transmittance Methods 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 8
- 239000003595 mist Substances 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 15
- 238000004422 calculation algorithm Methods 0.000 abstract description 9
- 238000011084 recovery Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000001151 other effect Effects 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 1
- 235000007926 Craterellus fallax Nutrition 0.000 description 1
- 240000007175 Datura inoxia Species 0.000 description 1
- VAYOSLLFUXYJDT-RDTXWAMCSA-N Lysergic acid diethylamide Chemical compound C1=CC(C=2[C@H](N(C)C[C@@H](C=2)C(=O)N(CC)CC)C2)=C3C2=CNC3=C1 VAYOSLLFUXYJDT-RDTXWAMCSA-N 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000009828 non-uniform distribution Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/14—Picture signal circuitry for video frequency region
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The present invention provides a kind of defogging self-adaptation control method and system, which comprises obtains the image information of input picture；The dark estimated value DC of calculating input image；Defogging weight factor ω is determined by image information, dark estimated value DC；Transmission plot is calculated according to the defogging weight factor, dark estimated value and the atmosphere light estimated value determined by dark estimated value, and defogging processing is carried out to input picture based on the transmission plot, image information and atmosphere light estimated value.The present invention can be realized based on image information, dark estimated value DC carries out self adaptive control to the defogging weight factor, and the relevant operation of defogging is targetedly adjusted according to the relevant information obtained in the image information of original input picture and image processing process, and then the defog effect of rich image, optimize the defogging algorithm.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of defogging self-adaptation control method and systems
Background technique
The bad weathers such as haze had been to be concerned by more and more people in recent years, how in severe natural environment obtain compared with
Become the emphasis that many people study concern for ideal visual effect.Substantially divide for the research of defogging method related fields at present
For three classes.The first kind is restored based on image, passes through multiple or single image recovery technology realization defog effect.Second class is based on
The technology of image enhancement related fields realizes defog effect.Third class is by combining the image information obtained in different wavelength range
Realize defog effect.The algorithm of images above processing is relatively easy, general for the defog effect of complex scene.
It is by image itself carrying out image defogging based on DCP (dark primary priori: Dark channel prior)
DC (dark: Dark channel) information, and be all made of in approximate processing in the estimation of transmission plot, still, usually
Mist information and non-uniform Distribution in most of scenes, it is especially existing when handling sky or part has compared with the scene of intense light source
Method be not it is highly desirable, lead to the problem of can not further realizing abundant defog effect only with information single in image.
Summary of the invention
Defogging self-adaptation control method provided by the invention and system can be based on image information, dark estimated value DC
It realizes and self adaptive control is carried out to the defogging weight factor, and according to the image information and image procossing of original input picture
The relevant information obtained in the process targetedly adjusts the relevant operation of defogging, and then the defog effect of rich image, optimizes institute
State defogging algorithm.
In a first aspect, the present invention provides a kind of defogging self-adaptation control method, comprising:
Obtain the image information of input picture；
The dark estimated value DC of calculating input image；
Defogging weight factor ω is determined by image information, dark estimated value DC；
Estimate according to the defogging weight factor, dark estimated value and by the atmosphere light that dark estimated value determines
Transmission plot is calculated in value, and is carried out at defogging based on the transmission plot, image information and atmosphere light estimated value to input picture
Reason.
Optionally, described image information includes colour difference information, and/or luminance information.
Optionally, described to determine that defogging weight factor includes: by image information, dark estimated value DC
First defogging weight factor ω is determined by dark estimated value DC1, wherein the dark estimated value DC and first
Defogging weight factor ω1It is corresponding；
Second defogging weight factor ω is determined by the colour difference information in image information2, wherein the colour difference information and second
Defogging weight factor ω2It is corresponding；
Third defogging weight factor ω is determined by the luminance information in image information3, wherein the luminance information and third
Defogging weight factor ω3It is corresponding.
Optionally, the dark estimated value DC and the first defogging weight factor ω1It is directly proportional；Wherein,
The first defogging weight factor ω1Between first threshold and second threshold with dark estimated value DC increase and
Increase.
Optionally, the colour difference information and the second defogging weight factor ω2It is directly proportional；Wherein,
The second defogging weight factor ω2Between third threshold value and the 4th threshold value with colour difference information difference increase and
Increase.
Optionally, the third defogging weight factor ω3With in luminance information between the 5th threshold value and the 6th threshold value
Brightness increases and first increases and reduce afterwards.
Optionally, the method also includes:
According to the first defogging weight factor ω1, the second defogging weight factor ω2, third defogging weight factor ω3Really
Determine defogging weight factor ω.
Optionally, described that input picture is carried out at defogging based on the transmission plot, image information and atmosphere light estimated value
Reason includes:
Transmission plot is optimized, and restored image is obtained by the transmission plot after optimizing；
The image pixel intensity value after restoring is calculated according to each channel numerical value of the RGB of restored image；
The image pixel intensity value after recovery is mapped to obtain according to the corresponding relationship of luminance information in image information
Map intensity values；
The number ratios between the image pixel intensity value after mapping obtains map intensity values and restores are calculated, and according to number
Value ratio, which calculates separately, obtains each channel numerical value of final RGB.
Second aspect, the present invention provide a kind of defogging adaptive control system, comprising:
Module is obtained, for obtaining the image information of input picture；
Computing module, the dark estimated value DC for calculating input image；
Weight module, for determining defogging weight factor ω by image information, dark estimated value DC；
Transmittance calculation module, for according to the first defogging weight factor ω1, dark estimated value and by dark
Transmission plot is calculated in the atmosphere light estimated value that channel estimated value determines,
Defogging processing unit, for carrying out defogging processing to input picture based on the transmission plot and atmosphere light estimated value.
Optionally, the weight module further include:
First weight factor determines submodule, for determining the first defogging weight factor ω by dark estimated value DC1；Its
In, the dark estimated value DC and defogging weight factor ω1It is corresponding；
Second weight factor determines submodule, for determining the second defogging weight factor ω by acquired colour difference information2,
Wherein, the colour difference information and the second defogging weight factor ω2It is corresponding.
Third weight factor determines submodule, for determining third defogging weight factor ω by acquired luminance information3,
Wherein, the luminance information and third defogging weight factor ω3It is corresponding.
Defogging self-adaptation control method provided in an embodiment of the present invention and system, since the dark of calculating input image is estimated
EvaluationWhen using approximate processing method, i.e. dark pixel value very little
(close to 0), finally according to being approximately equal to 0 processing, but when there is no the natural scene picture especially color of haze signal in actual conditions
Color gorgeous picture, dark numerical value is close to 0.But because there is the presence of the scattered signals such as haze, the dark of acquisition is not
It can be approximately 0 and numerical value is larger, numerical values recited depends on the thickness of haze, then the location of pixels has numerical value.Therefore, originally
Embodiment the method presses formula by carrying out the amendment of defogging weight to transmittance calculation item in transmittance values finding processTransmission plot is sought, transmittance figure is on the one hand avoidedThe deviation and image of value are also
Former pixel value deviation；Meanwhile the defogging weight factor is to adjust the weight factor of defogging intensity, based on image information, secretly
Channel estimated value DC, which is realized, carries out self adaptive control to the defogging weight factor, can be believed according to the image of original input picture
The relevant information obtained in breath and image processing process targetedly adjusts the relevant operation of defogging, and then realizes more horn of plenty
Defog effect, optimize the defogging algorithm.
In conclusion the present embodiment the method is by combining the image information of input picture to different zones defogging intensity
And image caused by defogging is dimmed and other effects has carried out further improvement and optimization, improves the defog effect of image.
Detailed description of the invention
Fig. 1 is the flow chart of one embodiment of the invention defogging self-adaptation control method；
Fig. 2 is the flow chart of another embodiment of the present invention defogging self-adaptation control method；
Fig. 3 is another embodiment of the present invention dark estimated value and the first defogging weight factor ω1Controlling curve；
Fig. 4 is another embodiment of the present invention colour difference information and the second defogging weight factor ω2Controlling curve；
Fig. 5 is another embodiment of the present invention luminance information and third defogging weight factor ω3Controlling curve；
Fig. 6 is the mapping curve of one embodiment of the invention brightness value Y and map intensity values Y '；
Fig. 7 is the structural schematic diagram of one embodiment of the invention defogging adaptive controller；
Fig. 8 is the structural schematic diagram of another embodiment of the present invention defogging adaptive controller.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
It is only a part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill
Personnel's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
The embodiment of the present invention provides a kind of defogging self-adaptation control method, as shown in Figure 1, which comprises
S11, the image information for obtaining input picture；
The dark estimated value DC of S12, calculating input image；
S13, defogging weight factor ω is determined by image information, dark estimated value DC；
S14, according to the defogging weight factor, dark estimated value and the atmosphere light determined by dark estimated value
Transmission plot is calculated in estimated value, and is gone based on the transmission plot, image information and atmosphere light estimated value to input picture
Mist processing.
Defogging self-adaptation control method provided in an embodiment of the present invention, due to the dark estimated value of calculating input imageWhen using approximate processing method, i.e. dark pixel value very little (connects
It is nearly 0), finally according to being approximately equal to 0 processing, but when there is no the natural scene picture especially color of haze signal in actual conditions
Color gorgeous picture, dark numerical value is close to 0.But because there is the presence of the scattered signals such as haze, the dark of acquisition is not
It can be approximately 0 and numerical value is larger, numerical values recited depends on the thickness of haze, then the location of pixels has numerical value.Therefore, originally
Embodiment the method presses formula by carrying out the amendment of defogging weight to transmittance calculation item in transmittance values finding processTransmission plot is sought, transmittance figure is on the one hand avoidedThe deviation and image restoring of value
Pixel value deviation；Meanwhile the defogging weight factor is to adjust the weight factor of defogging intensity, based on image information, is helped secretly
Road estimated value DC, which is realized, carries out self adaptive control to the defogging weight factor, can be according to the image information of original input picture
And the relevant information obtained in image processing process targetedly adjusts the relevant operation of defogging, and then realizes more abundant
Defog effect optimizes the defogging algorithm.
In conclusion the present embodiment the method is by combining the image information of input picture to different zones defogging intensity
And image caused by defogging is dimmed and other effects has carried out further improvement and optimization, improves the defog effect of image.
Optionally, as shown in Fig. 2, described image information includes colour difference information, and/or luminance information.
Optionally, described to determine that defogging weight factor includes: by image information, dark estimated value DC
First defogging weight factor ω is determined by dark estimated value DC1, wherein the dark estimated value DC and first
Defogging weight factor ω1It is corresponding；
Second defogging weight factor ω is determined by the colour difference information in image information2, wherein the colour difference information and second
Defogging weight factor ω2It is corresponding；
Third defogging weight factor ω is determined by the luminance information in image information3, wherein the luminance information and third
Defogging weight factor ω3It is corresponding.
Specifically, as shown in figure 3, the present embodiment the method is on the one hand since there are the associated intermediaries such as mist, scapes in air
It (can be approximately more rich than erlang fixed that object, which reflects signal intensity in transmission successively decreases with propagation distance during through the media such as haze,
Rule), along with the signal that atmosphere light is scattered by medium, so that the color of scenery becomes region muted color, it is especially beautiful in colour
Scenery become no longer so beautiful in colour.Since scattered signal R, G, B component are all very close to tend to muted color, by original
The signal difference quilt between each channel RGB that final image sensor obtains after the gorgeous biggish Signal averaging of scene RGB difference
It reduces, being reacted to the final effect obtained on picture is exactly that region beautiful in colour levels off to neutral color.Since light is in mist
The Propagation of equal particles or drop, which is roughlyd abide by, wins law than erlang, i.e. the degree of transmission of scenery and apart from directly proportional,
And show the trend of exponential damping.The RGB component difference for being presented on final image apart from remoter scenery is smaller and helps secretly
Road value is bigger.Therefore, it can may determine that the thickness of mist by the size of dark channel value DC, wherein dark channel information corresponds to haze
The power of signal, the stronger region of haze signal, dark numerical value are bigger.The then number that the present embodiment the method passes through dark
Value information adjusts different zones the first defogging weight factor ω1, wherein when dark DC value shows that mist is thicker more greatly, then increase
Add the first defogging weight factor ω1；When dark DC value is smaller shows that mist is thinner, then reduce the first defogging weight factor ω1,
In order to avoid the too strong defect brought on image procossing of defogging.
Second aspect, in image, there are at the region of muted color by the colour difference information of input picture for the method
Reason, as shown in the graph in fig. 4, the bigger region of color difference is more suitable to use dark defogging method, it is possible to appropriate enhancing
Defogging intensity, the smaller region dark validity of color difference is poorer, more not applicable this method, so it is strong suitably to weaken defogging
Degree, in order to avoid therefore, when the value of chromatism in each channel RGB is smaller, assigned lesser after introducing processing the defects of bring noise
Second defogging weight factor ω2, as the value of chromatism in each channel RGB tends to increase, it is gradually increased the second defogging weight factor
ω2。
The third aspect, in the present embodiment in addition to difference, the colour difference information in each channel RGB defogging result can be generated it is certain
Influence except, in the excessively bright region of brightness, such as sky or light source position should reduce defogging intensity, in order to avoid cause the area
Domain, which does not plan a successor, waits flaws, simultaneously as the valuable image information of sky areas physical presence is less, therefore the method will
Sky is carried out to reduce defogging weight.Pass through the curve synoptic diagram of brightness self adaptive control as shown in Figure 5.By to different bright
Spend the corresponding defogging weight third defogging weight factor ω of Region Matching3。
In conclusion method described in the present embodiment, according to colour difference information, dark channel value DC and luminance information are corresponding
Mapping curve calculates defogging weight factor ω.The method is by introducing colour difference information, luminance information and dark conduct
Each pixel defogging intensity reference.Wherein, the colour difference information reacts fog signal power size, the luminance information with dark
Having reacted regional area needs degree to be protected, and overly bright region carries out the defects of defogging easily causes color and image quality is caused to damage
It loses.Therefore, the present embodiment the method can not only take full advantage of the image information and input picture processing of input picture
The information obtained in the process provides more abundant information for the realization of algorithm, so that algorithm is to different scenes and Same Scene
The processing of middle different zones is more flexible.It is final image recuperation that the data in image processing process, which can also be taken full advantage of,
It provides reference frame and improves algorithm according to these information and realize the problem of bring image overall brightness reduces.
Optionally, as shown in figure 3, the dark estimated value DC and the first defogging weight factor ω1It is directly proportional；Wherein,
The first defogging weight factor ω1Between first threshold and second threshold with dark estimated value DC increase and
Increase.
Optionally, as shown in figure 4, the colour difference information and the second defogging weight factor ω2It is directly proportional；Wherein,
The second defogging weight factor ω2Between third threshold value and the 4th threshold value with colour difference information difference increase and
Increase.
Optionally, as shown in figure 5, the third defogging weight factor ω3With bright between the 5th threshold value and the 6th threshold value
Brightness in degree information increases and first increases and reduce afterwards.
Optionally, the method also includes:
According to the first defogging weight factor ω1, the second defogging weight factor ω2, third defogging weight factor ω3Really
Determine defogging weight factor ω.
Optionally, described that input picture is carried out at defogging based on the transmission plot, image information and atmosphere light estimated value
Reason includes:
S141, transmission plot is optimized, and restored image is obtained by the transmission plot after optimizing；
S142, the image pixel intensity value after restoring is calculated according to each channel numerical value of RGB of restored image；
S143, the image pixel intensity value after recovery is mapped according to the corresponding relationship of luminance information in image information
Obtain map intensity values；
S144, the number ratios mapped between the image pixel intensity value after obtaining map intensity values and restoring are calculated, and
It is calculated separately according to number ratios and obtains each channel numerical value of final RGB.
Specifically, the present embodiment the method passes through following formula first obtains restored image J (x),
I (x)=J (x) e-βd(x)+A(1-e-βd(x))
T (x)=e-βd(x)
Then formula Y=0.2126*R+0.7152*G+0.0722* is pressed by each channel numerical value of RGB according to restored image
The image pixel intensity value Y after restoring is calculated in B；And according to mapping relations in image information as shown in Figure 6 to recovery after
Image pixel intensity value is mapped to obtain map intensity values Y ', wherein Y '=0.2126*R '+0.7152*G '+0.0722*B '；
And then the image pixel after mapping obtains map intensity values and restores is calculated according to formula Luma_Ratio=Y '/Y
Number ratios LR between brightness value, and it is each logical according to number ratios LR final RGB to be calculated according to following formula respectively
Road numerical value.
R '=R*Luma_Ratio
G '=G*Luma_Ratio
B '=B*Luma_Ratio
The embodiment of the present invention also provides a kind of defogging adaptive control system, as shown in fig. 7, the system comprises:
Module is obtained, for obtaining the image information of input picture；
Computing module, the dark estimated value DC for calculating input image；
Weight module, for determining defogging weight factor ω by image information, dark estimated value DC；
Transmittance calculation module, for according to the first defogging weight factor ω1, dark estimated value and by dark
Transmission plot is calculated in the atmosphere light estimated value that channel estimated value determines,
Defogging processing unit, for carrying out defogging processing to input picture based on the transmission plot and atmosphere light estimated value.
Defogging adaptive control system provided in an embodiment of the present invention, due to the dark of computing module calculating input image
Estimated valueWhen using approximate processing method, i.e. dark pixel value very little
(close to 0), finally according to being approximately equal to 0 processing, but when there is no the natural scene picture especially color of haze signal in actual conditions
Color gorgeous picture, dark numerical value is close to 0.But because there is the presence of the scattered signals such as haze, the dark of acquisition is not
It can be approximately 0 and numerical value is larger, numerical values recited depends on the thickness of haze, then the location of pixels has numerical value.Therefore, originally
Embodiment the method carries out defogging power to transmittance calculation item in transmittance values finding process by transmittance calculation module
Reconditioning just, that is, presses formulaTransmission plot is sought, transmittance figure is on the one hand avoidedValue
Deviation and image restoring pixel value deviation；Meanwhile the defogging weight factor is to adjust the weight factor of defogging intensity, base
It is realized in image information, dark estimated value DC and self adaptive control is carried out to the defogging weight factor, it can be according to original defeated
Enter the relevant operation that the relevant information obtained in the image information and image processing process of image targetedly adjusts defogging, into
And realize more abundant defog effect, optimize the defogging algorithm.
In conclusion system described in the present embodiment is by combining the image information of input picture to different zones defogging intensity
And image caused by defogging is dimmed and other effects has carried out further improvement and optimization, improves the defog effect of image.
Optionally, as shown in figure 8, the weight module further include:
First weight factor determines submodule, for determining the first defogging weight factor ω by dark estimated value DC1；Its
In, the dark estimated value DC and defogging weight factor ω1It is corresponding；
Second weight factor determines submodule, for determining the second defogging weight factor ω by acquired colour difference information2,
Wherein, the colour difference information and the second defogging weight factor ω2It is corresponding.
Third weight factor determines submodule, for determining third defogging weight factor ω by acquired luminance information3,
Wherein, the luminance information and third defogging weight factor ω3It is corresponding.
The system of the present embodiment can be used for executing the technical solution of above method embodiment, realization principle and technology
Effect is similar, and details are not described herein again.
Those of ordinary skill in the art will appreciate that realizing all or part of the process in above-described embodiment method, being can be with
Relevant hardware is instructed to complete by computer program, the program can be stored in a computer-readable storage medium
In, the program is when being executed, it may include such as the process of the embodiment of above-mentioned each method.Wherein, the storage medium can be magnetic
Dish, CD, read-only memory (Read-Only Memory, ROM) or random access memory (Random Access
Memory, RAM) etc..
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers
It is included within the scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.
Claims (10)
1. a kind of defogging self-adaptation control method characterized by comprising
Obtain the image information of input picture；
The dark estimated value DC of calculating input image；
Defogging weight factor ω is determined by image information, dark estimated value DC；
According to the defogging weight factor, dark estimated value and the atmosphere light estimated value meter determined by dark estimated value
Calculation obtains transmission plot, and carries out defogging processing to input picture based on the transmission plot, image information and atmosphere light estimated value.
2. the method according to claim 1, wherein described image information includes colour difference information, and/or brightness letter
Breath.
3. according to the method described in claim 2, it is characterized in that, described determined by image information, dark estimated value DC
Mist weight factor includes:
First defogging weight factor ω is determined by dark estimated value DC1, wherein the dark estimated value DC and the first defogging
Weight factor ω1It is corresponding；
Second defogging weight factor ω is determined by the colour difference information in image information2, wherein the colour difference information and the second defogging
Weight factor ω2It is corresponding；
Third defogging weight factor ω is determined by the luminance information in image information3, wherein the luminance information and third defogging
Weight factor ω3It is corresponding.
4. according to the method described in claim 3, it is characterized in that, the dark estimated value DC and the first defogging weight factor
ω1It is directly proportional；Wherein,
The first defogging weight factor ω1Increase between first threshold and second threshold with dark estimated value DC and increases.
5. according to the method described in claim 3, it is characterized in that, the colour difference information and the second defogging weight factor ω2Cheng Zheng
Than；Wherein,
The second defogging weight factor ω2Increase between third threshold value and the 4th threshold value with the difference of colour difference information and increases.
6. according to the method described in claim 3, it is characterized in that, the third defogging weight factor ω3In the 5th threshold value and
Increase between six threshold values with the brightness in luminance information and first increases and reduce afterwards.
7. according to any method of claim 3-6, which is characterized in that the method also includes:
According to the first defogging weight factor ω1, the second defogging weight factor ω2, third defogging weight factor ω3Determination is gone
Mist weight factor ω.
8. according to any method of claim 2-7, which is characterized in that it is described based on the transmission plot, image information and
Atmosphere light estimated value carries out defogging processing to input picture
Transmission plot is optimized, and restored image is obtained by the transmission plot after optimizing；
The image pixel intensity value after restoring is calculated according to each channel numerical value of the RGB of image restoration；
It is mapped and is reflected to by the image pixel intensity value after restoring according to the corresponding relationship of luminance information in image information
Penetrate brightness value；
The number ratios between the image pixel intensity value after mapping obtains map intensity values and restores are calculated, and according to numeric ratio
Example, which calculates separately, obtains each channel numerical value of final RGB.
9. a kind of defogging adaptive control system characterized by comprising
Module is obtained, for obtaining the image information of input picture；
Computing module, the dark estimated value DC for calculating input image；
Weight module, for determining defogging weight factor ω by image information, dark estimated value DC；
Transmittance calculation module, for according to the first defogging weight factor ω1, dark estimated value and estimated by dark
Transmission plot is calculated in the atmosphere light estimated value that evaluation determines,
Defogging processing unit, for carrying out defogging processing to input picture based on the transmission plot and atmosphere light estimated value.
10. system according to claim 9, which is characterized in that the weight module further include:
First weight factor determines submodule, for determining the first defogging weight factor ω by dark estimated value DC1；Wherein, institute
State dark estimated value DC and defogging weight factor ω1It is corresponding；
Second weight factor determines submodule, for determining the second defogging weight factor ω by acquired colour difference information2, wherein
The colour difference information and the second defogging weight factor ω2It is corresponding.
Third weight factor determines submodule, for determining third defogging weight factor ω by acquired luminance information3, wherein
The luminance information and third defogging weight factor ω3It is corresponding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711497617.9A CN109993705A (en) | 2017-12-29 | 2017-12-29 | A kind of defogging self-adaptation control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711497617.9A CN109993705A (en) | 2017-12-29 | 2017-12-29 | A kind of defogging self-adaptation control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109993705A true CN109993705A (en) | 2019-07-09 |
Family
ID=67111207
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711497617.9A Pending CN109993705A (en) | 2017-12-29 | 2017-12-29 | A kind of defogging self-adaptation control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109993705A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156968A (en) * | 2011-04-11 | 2011-08-17 | 合肥工业大学 | Color cubic priori based single image visibility restoration method |
| CN103164845A (en) * | 2011-12-16 | 2013-06-19 | 中国科学院沈阳自动化研究所 | Real-time image mist elimination device and method |
| CN105303525A (en) * | 2014-07-25 | 2016-02-03 | 株式会社索思未来 | Haze image discriminating apparatus and discriminating method |
| 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
- 2017-12-29 CN CN201711497617.9A patent/CN109993705A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156968A (en) * | 2011-04-11 | 2011-08-17 | 合肥工业大学 | Color cubic priori based single image visibility restoration method |
| CN103164845A (en) * | 2011-12-16 | 2013-06-19 | 中国科学院沈阳自动化研究所 | Real-time image mist elimination device and method |
| CN105303525A (en) * | 2014-07-25 | 2016-02-03 | 株式会社索思未来 | Haze image discriminating apparatus and discriminating method |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765342A (en) | A kind of underwater image restoration method based on improvement dark | |
| CN107767354B (en) | Image defogging algorithm based on dark channel prior | |
| Xu et al. | Fast image dehazing using improved dark channel prior | |
| CN106886985B (en) | A kind of adaptive enhancement method of low-illumination image reducing colour cast | |
| CN102750674B (en) | Video image defogging method based on self-adapting allowance | |
| CN101783012B (en) | Automatic image defogging method based on dark primary colour | |
| US10290081B2 (en) | System for image dehazing by modifying lower bound of transmittance and method therefor | |
| Peng et al. | Image haze removal using airlight white correction, local light filter, and aerial perspective prior | |
| CN104794697B (en) | A kind of image defogging method based on dark primary priori | |
| CN103218778B (en) | The disposal route of a kind of image and video and device | |
| WO2016206087A1 (en) | Low-illumination image processing method and device | |
| JP2006121713A (en) | Enhancing contrast | |
| CN105139347B (en) | A kind of polarization imaging defogging method of combination dark channel prior principle | |
| JP2014044302A5 (en) | ||
| KR20210006276A (en) | Image processing method for flicker mitigation | |
| CN105741245B (en) | Adaptive contrast enhancement algorithm based on greyscale transformation | |
| CN107527325B (en) | Monocular underwater vision enhancement method based on dark channel priority | |
| CN107533756A (en) | Image processing apparatus, camera device, image processing method and storage image processing unit image processing program storage medium | |
| CN109523474A (en) | A kind of enhancement method of low-illumination image based on greasy weather degradation model | |
| CN110473152A (en) | Based on the image enchancing method for improving Retinex algorithm | |
| CN110400274A (en) | A kind of vehicle mounted infrared pedestrian detection infrared image enhancing method | |
| CN107025641A (en) | Image interfusion method based on Analysis of Contrast | |
| CN104463812B (en) | The method for repairing the video image by raindrop interference when shooting | |
| CN101510306B (en) | Estimation method for video image illumination distribution | |
| CN108898561A (en) | A kind of defogging method, server and the system of the Misty Image containing sky areas |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190709 |