CN113298732A - Image defogging method and system based on regional similarity - Google Patents
Image defogging method and system based on regional similarity Download PDFInfo
- Publication number
- CN113298732A CN113298732A CN202110635455.0A CN202110635455A CN113298732A CN 113298732 A CN113298732 A CN 113298732A CN 202110635455 A CN202110635455 A CN 202110635455A CN 113298732 A CN113298732 A CN 113298732A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- pixel point
- dark
- region
- 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 40
- 238000002834 transmittance Methods 0.000 claims abstract description 29
- 239000011159 matrix material Substances 0.000 claims abstract description 15
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 238000005457 optimization Methods 0.000 claims description 16
- 238000003860 storage Methods 0.000 claims description 6
- 239000000126 substance Substances 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 238000003384 imaging method Methods 0.000 abstract description 8
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G06T5/73—
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Abstract
The invention provides an image defogging method and system based on regional similarity, wherein the method comprises the following steps: s1: dark channel value estimation of the image layer of the image R, G, B is carried out, and a dark channel matrix is obtained; s2: estimating an atmospheric environment light value based on the region similarity to obtain an atmospheric environment light optimized value; s3: estimating the transmittance value of the R, G, B layers based on the guide filtering to obtain a transmittance optimized value of the R, G, B layers; s4: and reducing the clear image by using an atmospheric scattering model to obtain the defogged image. The system is used for realizing the method. The method can better restore the image under the heterogeneous haze condition to obtain a clearer image, solves the problems that the imaging quality of imaging equipment is difficult to guarantee under severe weather, the image color is distorted after the traditional method is used for processing the situations of bluish and darker overall color, and the like, and provides technical support for an automatic driving vision system, a road condition monitoring system, other image acquisition systems and the like under severe weather conditions.
Description
Technical Field
The invention relates to the technical field of digital image processing, in particular to an image defogging method and system based on region similarity.
Background
Fog is a weather phenomenon formed by the desublimation of suspended water droplets and the like in the near-ground atmosphere. The foggy weather condition brings inconvenience to production and life of people, particularly in the aspect of imaging, due to the scattering influence of a plurality of small particles such as PM2.5 and the like in foggy weather air on light, the problems of detail loss, reduced contrast, reduced brightness, gray image color and the like of an image shot by imaging equipment are caused, the visual experience of a user is reduced, and certain influence is caused on the normal operation of a working system in the related field such as image identification. Therefore, the method has extremely important value and significance for the research of image defogging.
Under severe weather conditions such as fog, light is scattered when encountering tiny particles suspended in the air during propagation, so that an image acquired by the imaging device generates a degradation effect. Nayer and narasiman improved the atmospheric scattering model in 1999, which has been widely used in computer vision and computer graphics. The model can be described as formula (1):
I(X)＝J(X)t(X)+A(1-t(X)) (1)
wherein, i (x) represents the foggy day image captured by the imaging device, j (x) represents the fogless image corresponding to i (x), a is the atmospheric ambient light value, t (x) is the transmittance, t (x) can be represented by formula (2):
t(X)＝e-βd(X),0<t(X)≤1 (2)
where β is the atmospheric scattering coefficient and d (x) is the scene depth, i.e. the distance between the image scene point and the point being photographed. According to the formula (1), after the fog-free image j (x) is obtained by the defogging algorithm after the atmospheric environment light value a and the transmittance t (x) are estimated for the photographed fog day image i (x).
Chinese patent application No. CN107481199B discloses an image defogging method, an image defogging device, a storage medium and a mobile terminal, wherein the method comprises: acquiring an image to be processed; acquiring a dark channel value corresponding to each pixel in the image to be processed, and counting the number of the dark channel values in a preset range; and if the number exceeds a threshold value, carrying out defogging treatment on the image to be treated according to a preset defogging mode. According to the image defogging method and device, the storage medium and the mobile terminal, before the image to be processed is defogged, whether the preset condition is met or not is judged according to the dark channel value, and the image to be processed meeting the preset condition is defogged, so that the defogging process is avoided for all the images. The atmosphere scattering model is used in the defogging process, so that the image processing efficiency is improved, and the power consumption of the image processing device is reduced. However, the estimation of the light value and the transmittance of the atmospheric environment is too simple, so that the defogging effect is not ideal, and the image can not be defogged under the high requirement condition, so that a clearer image can be obtained.
Disclosure of Invention
In order to solve the technical problems, the invention provides an image defogging method and system based on region similarity.
A first aspect of the present invention provides an image defogging method based on region similarity, including the steps of:
s1: dark channel value estimation of the image layer of the image R, G, B is carried out, and a dark channel matrix is obtained;
s2: estimating an atmospheric environment light value based on the region similarity to obtain an atmospheric environment light optimized value;
s3: estimating the transmittance value of the R, G, B layers based on the guide filtering to obtain a transmittance optimized value of the R, G, B layers;
s4: and reducing the clear image by using an atmospheric scattering model to obtain the defogged image.
Preferably, in step S1, for a hazy image with a size of m × n, regarding the R, G, B image layer, the lowest gray value of each pixel point X in the neighborhood of the square window within the size range of Φ (X) is taken as the dark channel value of the pixel point X, so as to obtain the dark channel matrix J of the R, G, B image layerc,dark(X), and obtaining a dark channel matrix J of the whole imagedark(X)：
Jc,dark(X)＝minY∈Φ(X)(Jc(Y)),c＝R,G,B，
Jdark(X)＝{Jc,dark(X)}，
Wherein Y represents a pixel point in a square window within the phi (X) size range of pixel point X, JcAnd (Y) represents the gray value of the pixel point Y relative to the layer c, wherein c is R, G and B.
In any of the above embodiments, step S2 preferably includes:
s21: for a pixel point X, selecting the mean value of the dark channel values of all pixel points in the neighborhood of a square window of the pixel point X as the atmospheric environment light value A of the pixel point Xc(X)，c＝R,G,B；
S22: selecting A of all pixel pointscMaximum value maxA of (X)cMaximum value maxA 'of atmospheric ambient light optimization values for all pixel points'cA of all the pixels arranged from large to smallcThe Nth bit of the (X) value is taken as the minimum value minA 'of the atmospheric ambient light optimization values of all pixel points'cWherein N is a constant determined according to the requirement;
s23: using the region similarity method, maxA 'obtained in step S22'cAnd min A'cFor A of all pixel pointsc(X) carrying out linear quantization to obtain an atmospheric environment light optimization value A′c(X)。
Preferably, in any of the above schemes, in step S21, the square window neighborhood region is a square window neighborhood region with a size range Ω (X) selected by taking the pixel point X as an upper left corner or an upper right corner or a lower left corner or a lower right corner.
In any of the above schemes, preferably, in step S21, if the size of the selected square window is less than Ω (X), then the square window is selected according to the side length min { X, y, m-X +1, n-y +1}, where X and y are the horizontal and vertical coordinates of the pixel point X,
preferably, in any of the above schemes, in step S23, a of all the pixel points is recordedc(X) minimum value of minAcThe method comprises the following steps:
in any of the above schemes, preferably, in step S3, based on the principle that visible light with different wavelengths has different transmittances, transmittance matrices before optimization are respectively obtained for different color layers
Where ω is a constant, IcAnd (X) is the gray value of the pixel point X in the foggy image relative to the layer c.
In any of the above schemes, preferably, in step S3, the optimized transmittance value of the layer R, G, B
Comprises the following steps:
wherein the content of the first and second substances,
is I (X) the variance within window Ω (X), e is the regularization parameter that defines the smoothing region and edge region thresholds,
is the transmittance matrix of the R, G, B image layer before optimization.
In any of the above embodiments, in step S4, the optimal transmittance value according to the atmospheric environmental light optimized value a' c (x) obtained in step S2 and the optimized transmittance value of the R, G, B image layer obtained in step S3 is preferably selected
And an atmospheric scattering model, obtaining an image J (X) after defogging:
J(X)＝{Jc(X)}，
wherein the content of the first and second substances,
a second aspect of the present invention provides a regional similarity-based image defogging system including a storage medium having a computer program stored therein for execution by a processor to implement the regional similarity-based image defogging method.
According to the image defogging method and system based on the regional similarity, the atmospheric environment light value in the atmospheric scattering model is optimized and estimated by using a regional similarity algorithm by utilizing the atmospheric scattering model and the dark channel priori knowledge, and the transmittance of the R, G, B image layer is optimized and estimated by combining the characteristics that the light with different wavelengths has different loss degrees in the transmission process, so that the optimization of key input parameters in the atmospheric scattering model is completed, and the defogged image is obtained. The image defogging method and the image defogging system based on the regional similarity can better restore the image under the heterogeneous haze condition, obtain a clearer image after defogging treatment, solve the problems that the imaging quality of imaging equipment is difficult to guarantee under severe weather, the image color is distorted after the traditional method is used for treating, the whole color is bluish and darker, and the like, and can provide technical support for an automatic driving vision system, a road condition monitoring system and other image acquisition systems under severe weather conditions.
Drawings
Fig. 1 is a flowchart illustrating an image defogging method based on region similarity according to a preferred embodiment of the present invention.
Detailed Description
For a better understanding of the present invention, reference will now be made in detail to the following examples.
Example 1
As shown in fig. 1, an image defogging method based on region similarity includes the steps of:
s1: dark channel value estimation of the image layer of the image R, G, B is carried out, and a dark channel matrix is obtained;
s2: estimating an atmospheric environment light value based on the region similarity to obtain an atmospheric environment light optimized value;
s3: estimating the transmittance value of the R, G, B layers based on the guide filtering to obtain a transmittance optimized value of the R, G, B layers;
s4: and reducing the clear image by using an atmospheric scattering model to obtain the defogged image.
In step S1, for a hazy image with a size of m × n, respectively regarding the R, G, B image layers thereof, taking the lowest gray value of each pixel point X in the neighborhood of the square window within the size range of Φ (X) as the dark channel value of the pixel point X, and obtaining the dark channel matrix J of the R, G, B image layerc,dark(X), and obtaining a dark channel matrix J of the whole imagedark(X)：
Jc,dark(X)＝minY∈Φ(X)(Jc(Y)),c＝R,G,B，
Jdark(X)＝{Jc,dark(X)}，
Wherein Y represents a pixel in the neighborhood of the square window within the phi (X) size range of pixel X, JcAnd (Y) represents the gray value of the pixel point Y relative to the layer c, wherein c is R, G and B.
The square window neighborhood region is a square window in a phi (X) size range with a pixel point X as a neighborhood center, and the side length dereferencing range of the square window phi (X) is 11-51 pixel points. Determining a dark channel matrix JdarkIn the case of (X), when the edge is insufficient (that is, when the square window is over the image), the part over the image is not considered, and only the part where the square window overlaps the image is considered. For example, when the side length of the square window phi (X) is 50 pixel points, the sitting position is determinedAnd (3) marking the pixel point as (1,1), wherein the finally selected area is a square window with the horizontal and vertical coordinates of 1-25 and the vertical coordinate of 1-25, and the lowest gray value of the 625 pixels is taken as the dark channel value of the pixel point.
Step S2 includes:
s21: for a pixel point X, selecting the mean value of the dark channel values of all pixel points in the neighborhood of a square window of the pixel point X as the atmospheric environment light value A of the pixel point Xc(X)，c＝R,G,B；
S22: selecting A of all pixel pointscMaximum value maxA of (X)cMaximum value maxA 'of atmospheric ambient light optimization values for all pixel points'cA of all the pixels arranged from large to smallcThe Nth bit of the (X) value is taken as the minimum value minA 'of the atmospheric ambient light optimization values of all pixel points'cWherein N is a constant determined according to the requirement;
s23: using the region similarity method, maxA 'obtained in step S22'cAnd minA′cFor A of all pixel pointsc(X) carrying out linear quantization to obtain an atmospheric environment light optimization value A′c(X)。
In step S21, the square window neighborhood region is a square window neighborhood region with a size range Ω (X) selected by taking a pixel point X as an upper left corner or an upper right corner or a lower left corner or a lower right corner, and a side length range of the square window Ω (X) is 11 to 51 pixel points. In this embodiment, a square window neighborhood is selected with a pixel point X as the upper left corner to determine the atmospheric ambient light value a of the pixel point Xc(X), then:
wherein, Jc,dark(i, j) represents the dark channel value of the c-th layer of the pixel point with the coordinate of (i, j), c is R, G, B, s' is the side length of the neighborhood region of the square window, X and y are the horizontal and vertical coordinates of the pixel point X respectively,
for theAnd (3) if the size of the selected square window is less than omega (X), selecting the square window according to the side length min { X, y, m-X +1, n-y +1}, wherein the pixel points at the image boundary are located at the position of the image boundary.
In this embodiment, in step S22, N is a positive integer rounded to 1% of the total number of image pixels, and the rounding mode is rounding-down, that is, N is a positive integer rounded to 1% of the total number of image pixels
Rounding or other rounding may also be used to determine the value of N. Determining the maxA 'for greater convenience'cAnd min A'cA two-dimensional matrix A of size mxnc(X) rearranging and placing the column vector Rec(h0) In (2), the column vector Rec(h0) The number of rows of (a) is m × n, that is, for the pixel point X with coordinates (X, y), there are:
wherein h is0The coordinate position of the original coordinate (x, y) after being rearranged corresponding to the atmospheric environment light value. Alignment vector Rec(h0) Forming a new column vector De after descending order arrangementc(h) Further, the maxA 'can be conveniently determined'cAnd min A'cI.e. maxA'c＝maxAc，minA′c＝Dec(N)。
In step S23, the A of all the pixel points are recordedc(X) minimum value of minAcThe method comprises the following steps:
in step S3, based on the principle that visible light with different wavelengths has different transmittances, transmittance matrices before optimization are respectively obtained for different color layers
Where ω is a constant, IcAnd (X) is the gray value of the pixel point X in the foggy image relative to the layer c. In this embodiment, the value of ω is 0.85, and may be selected as other values as needed. When a certain pixel point X is obtained by calculation
Setting the pixel point X when the value is less than 0.1
Will transmittance
And respectively carrying out guiding filtering operation on the color channels corresponding to the foggy images according to different color channels to obtain a transmittance optimized value closer to a real scene
Comprises the following steps:
wherein the content of the first and second substances,
is I (X) the variance within window Ω (X), e is the regularization parameter that defines the smoothing region and edge region thresholds,
is the transmittance matrix of the R, G, B image layer before optimization.
In step S4, the optimized value A of the atmospheric environment light obtained in step S2′c(X) and step S3Resulting optimized values of transmittance of R, G, B layers
And an atmospheric scattering model, obtaining an image J (X) after defogging:
J(X)＝{Jc(X)}，
wherein the content of the first and second substances,
an image defogging system based on regional similarity comprises a storage medium, wherein a computer program is stored in the storage medium and is used for being executed by a processor to realize the image defogging method based on regional similarity.
It should be noted that the above embodiments are only used for illustrating the technical solution of the present invention, and not for limiting the same; although the foregoing embodiments illustrate the invention in detail, those skilled in the art will appreciate that: it is possible to modify the technical solutions described in the foregoing embodiments or to substitute some or all of the technical features thereof, without departing from the scope of the technical solutions of the present invention.
Claims (10)
1. An image defogging method based on region similarity comprises the following steps: s1: dark channel value estimation of the image layer of the image R, G, B is carried out, and a dark channel matrix is obtained; the method is characterized in that: further comprising the steps of:
s2: estimating an atmospheric environment light value based on the region similarity to obtain an atmospheric environment light optimized value;
s3: estimating the transmittance value of the R, G, B layers based on the guide filtering to obtain a transmittance optimized value of the R, G, B layers;
s4: and reducing the clear image by using an atmospheric scattering model to obtain the defogged image.
2. The image defogging method based on the region similarity as recited in claim 1, wherein: step by stepIn step S1, for a hazy image with a size of m × n, respectively regarding the R, G, B image layers thereof, taking the lowest gray value of each pixel point X in the neighborhood of the square window within the size range of Φ (X) as the dark channel value of the pixel point X, and obtaining the dark channel matrix J of the R, G, B image layerc，dark(X), and obtaining a dark channel matrix J of the whole imagedark(X)：
Jc,dark(X)＝minY∈Φ(X)(Jc(Y))，c＝R,G,B，
Jdark(X)＝{Jc,dark(X)}，
Wherein Y represents a pixel point in a square window within the phi (X) size range of pixel point X, JcAnd (Y) represents the gray value of the pixel point Y relative to the layer c, wherein c is R, G and B.
3. The image defogging method based on the region similarity as recited in claim 2, wherein: step S2 includes:
s21: for a pixel point X, selecting the mean value of the dark channel values of all pixel points in the neighborhood of a square window of the pixel point X as the atmospheric environment light value A of the pixel point Xc(X)，c＝R，G,B；
S22: selecting A of all pixel pointscMaximum value maxA of (X)cMaximum value maxA 'of atmospheric ambient light optimization values for all pixel points'cA of all the pixels arranged from large to smallcThe Nth bit of the (X) value is taken as the minimum value minA 'of the atmospheric ambient light optimization values of all pixel points'cWherein N is a constant determined according to the requirement;
s23: using the region similarity method, maxA 'obtained in step S22'cAnd min A'cFor A of all pixel pointsc(X) carrying out linear quantization to obtain an atmospheric ambient light optimized value A'c(X)。
4. The image defogging method based on the region similarity as recited in claim 3, wherein: in step S21, the square window neighborhood region is a square window neighborhood region with a size range Ω (X) selected by taking the pixel point X as the upper left corner or the upper right corner or the lower left corner or the lower right corner.
5. The image defogging method based on the region similarity as recited in claim 3, wherein: in step S21, for the pixel points at the image boundary, if the size of the selected square window is less than Ω (X), then the square window is selected according to the side length min { X, y, m-X +1, n-y +1}, where X and y are the horizontal and vertical coordinates of the pixel point X,
6. the image defogging method based on the region similarity as recited in claim 3, wherein: in step S23, the A of all the pixel points are recordedc(X) minimum value of minAcThe method comprises the following steps:
7. the image defogging method based on the region similarity as recited in claim 6, wherein: in step S3, based on the principle that visible light with different wavelengths has different transmittances, transmittance matrices before optimization are respectively obtained for different color layers
Where ω is a constant, IcAnd (X) is the gray value of the pixel point X in the foggy image relative to the layer c.
8. The image defogging method based on the region similarity as recited in claim 7, wherein: in step S3, transmittance optimization of R, G, B layerValue of
Comprises the following steps:
wherein
Is I (X) the variance within window Ω (X), e is the regularization parameter that defines the smoothing region and edge region thresholds,
is the transmittance matrix of the R, G, B image layer before optimization.
9. The image defogging method based on the region similarity as recited in claim 8, wherein: in step S4, the atmospheric ambient light optimized value A 'obtained in step S2'c(X) and the optimized value of transmittance of layer R, G, B obtained in step S3
And an atmospheric scattering model, obtaining an image J (X) after defogging:
J(X)＝{Jc(X)}，
wherein the content of the first and second substances,
10. an image defogging system based on region similarity, said system comprising a storage medium having a computer program stored therein, wherein: the computer program for execution by a processor to implement the regional similarity based image defogging method according to any one of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635455.0A CN113298732A (en) | 2021-06-08 | 2021-06-08 | Image defogging method and system based on regional similarity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110635455.0A CN113298732A (en) | 2021-06-08 | 2021-06-08 | Image defogging method and system based on regional similarity |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113298732A true CN113298732A (en) | 2021-08-24 |
Family
ID=77327451
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110635455.0A Pending CN113298732A (en) | 2021-06-08 | 2021-06-08 | Image defogging method and system based on regional similarity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113298732A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116823674A (en) * | 2023-08-24 | 2023-09-29 | 湖南省水务规划设计院有限公司 | Cross-modal fusion underwater image enhancement method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2568438A2 (en) * | 2011-09-08 | 2013-03-13 | Fujitsu Limited | Image defogging method and system |
| CN104299192A (en) * | 2014-09-28 | 2015-01-21 | 北京联合大学 | Single image defogging method based on atmosphere light scattering physical model |
| CN104809709A (en) * | 2015-05-13 | 2015-07-29 | 北京邮电大学 | Single-image self-adaptation defogging method based on domain transformation and weighted quadtree decomposition |
| CN107644404A (en) * | 2017-08-28 | 2018-01-30 | 浙江工业大学 | A kind of image defogging method of sky areas vision optimization |
| CN108389175A (en) * | 2018-04-26 | 2018-08-10 | 长安大学 | Merge the image defogging method of variogram and color decaying priori |
| CN109785262A (en) * | 2019-01-11 | 2019-05-21 | 闽江学院 | Image defogging method based on dark channel prior and adaptive histogram equalization |
| CN110852971A (en) * | 2019-11-11 | 2020-02-28 | 昆明理工大学 | Video defogging method based on dark channel prior and Retinex and computer program product |
| US20200322580A1 (en) * | 2016-05-25 | 2020-10-08 | Hangzhou Hikvision Digital Technology Co., Ltd. | Image defogging method and image capture apparatus implementing image defogging |
-
2021
- 2021-06-08 CN CN202110635455.0A patent/CN113298732A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2568438A2 (en) * | 2011-09-08 | 2013-03-13 | Fujitsu Limited | Image defogging method and system |
| CN104299192A (en) * | 2014-09-28 | 2015-01-21 | 北京联合大学 | Single image defogging method based on atmosphere light scattering physical model |
| CN104809709A (en) * | 2015-05-13 | 2015-07-29 | 北京邮电大学 | Single-image self-adaptation defogging method based on domain transformation and weighted quadtree decomposition |
| US20200322580A1 (en) * | 2016-05-25 | 2020-10-08 | Hangzhou Hikvision Digital Technology Co., Ltd. | Image defogging method and image capture apparatus implementing image defogging |
| CN107644404A (en) * | 2017-08-28 | 2018-01-30 | 浙江工业大学 | A kind of image defogging method of sky areas vision optimization |
| CN108389175A (en) * | 2018-04-26 | 2018-08-10 | 长安大学 | Merge the image defogging method of variogram and color decaying priori |
| CN109785262A (en) * | 2019-01-11 | 2019-05-21 | 闽江学院 | Image defogging method based on dark channel prior and adaptive histogram equalization |
| CN110852971A (en) * | 2019-11-11 | 2020-02-28 | 昆明理工大学 | Video defogging method based on dark channel prior and Retinex and computer program product |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116823674A (en) * | 2023-08-24 | 2023-09-29 | 湖南省水务规划设计院有限公司 | Cross-modal fusion underwater image enhancement method |
| CN116823674B (en) * | 2023-08-24 | 2024-03-12 | 湖南省水务规划设计院有限公司 | Cross-modal fusion underwater image enhancement method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109523480B (en) | Defogging method and device for sea fog image, computer storage medium and terminal | |
| CN107767354B (en) | Image defogging algorithm based on dark channel prior | |
| CN111292258B (en) | Image defogging method based on dark channel prior and bright channel prior | |
| US9183617B2 (en) | Methods, devices, and computer readable mediums for processing a digital picture | |
| WO2016206087A1 (en) | Low-illumination image processing method and device | |
| CN105913390B (en) | A kind of image defogging method and system | |
| CN110782407B (en) | Single image defogging method based on sky region probability segmentation | |
| CN112419162A (en) | Image defogging method and device, electronic equipment and readable storage medium | |
| CN111145105B (en) | Image rapid defogging method and device, terminal and storage medium | |
| CN110097522B (en) | Single outdoor image defogging method based on multi-scale convolution neural network | |
| CN105023246B (en) | A kind of image enchancing method based on contrast and structural similarity | |
| CN115187472A (en) | Dark channel prior defogging method based on tolerance | |
| CN113298732A (en) | Image defogging method and system based on regional similarity | |
| CN109345479B (en) | Real-time preprocessing method and storage medium for video monitoring data | |
| CN111161167A (en) | Single image defogging method based on middle channel compensation and self-adaptive atmospheric light estimation | |
| CN114693548A (en) | Dark channel defogging method based on bright area detection | |
| CN107451962B (en) | Image defogging method and device | |
| CN112465720B (en) | Image defogging method and device based on image sky segmentation and storage medium | |
| CN107977941B (en) | Image defogging method for color fidelity and contrast enhancement of bright area | |
| CN110349113B (en) | Adaptive image defogging method based on dark primary color priori improvement | |
| CN109949239B (en) | Self-adaptive sharpening method suitable for multi-concentration multi-scene haze image | |
| CN116823686B (en) | Night infrared and visible light image fusion method based on image enhancement | |
| CN115797234B (en) | Method for enhancing low-contrast two-dimensional code image recognition effect | |
| CN112907461A (en) | Defogging and enhancing method for infrared degraded image in foggy day | |
| CN111598800A (en) | Single image defogging method based on space domain homomorphic filtering and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |