CN107123101B - Image defogging method based on average saturation prior - Google Patents
Image defogging method based on average saturation prior Download PDFInfo
- Publication number
- CN107123101B CN107123101B CN201710323554.9A CN201710323554A CN107123101B CN 107123101 B CN107123101 B CN 107123101B CN 201710323554 A CN201710323554 A CN 201710323554A CN 107123101 B CN107123101 B CN 107123101B
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- value
- intensity value
- channel
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 238000001914 filtration Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000003384 imaging method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides an image defogging method based on average saturation prior, which comprises the following steps: calculating an atmospheric light value according to the foggy image; obtaining the depth value of each pixel in the foggy image; acquiring a large number of clear-day images, and calculating the average saturation value of each clear-day image; counting the average saturation values of all images in sunny days to obtain the average saturation probability distribution of the images in sunny days, and calculating an expected value as an average saturation prior; an optimization model of the scattering coefficient is established by using average saturation prior; solving an optimization model of the scattering coefficient to obtain the scattering coefficient of each pixel in the foggy image; obtaining the scene albedo of each pixel in the foggy image; an intensity value of each pixel in the defogged image corresponding to each pixel in the fogging image is calculated, thereby composing the defogged image. The method can effectively remove fog from the atmosphere non-homogeneous fog images, and can obtain better fog removing effect when the atmosphere homogeneous fog images are processed.
Description
Technical Field
The invention particularly relates to an image defogging method based on average saturation prior, which is used for performing achromatic defogging on a color image and belongs to the technical field of digital image processing.
Background
Under the foggy environment, due to the influence of suspended particles in the atmosphere, the images acquired by the imaging equipment are poor in visibility, low in saturation and seriously insufficient in definition. Therefore, the method has important practical significance for carrying out the sharpening processing on the foggy degraded image.
In the field of computer vision, an atmospheric scattering model is commonly used to describe an imaging process under a haze weather condition, and an image defogging process is to recover an intensity value of each pixel in a defogged image from the intensity value of each pixel in the foggy image according to the atmospheric scattering model. Most of the existing image defogging methods use an atmospheric scattering model described by the following equation:
Ic(x,y)=Jc(x,y)·e-β·d(x,y)+A·(1-e-β·d(x,y))
wherein, Ic(x, y) represents the intensity value of pixel (x, y) in the hazy image, Jc(x, y) represents an intensity value of a pixel (x, y) in the defogged image, JcThe size of the foggy image is the same as the size of the defogged image, and the pixel (x, y) in the foggy image corresponds to the pixel (x, y) in the defogged image, i.e., the pixel (x, y) is at the same position in the foggy image and the defogged image.
Disclosure of Invention
The technical problem solved by the invention is as follows: the existing image defogging method can only process fogging images with homogeneous atmosphere, cannot process fogging images under the condition of non-homogeneous atmosphere, and has the defects of low accuracy due to the fact that scattering coefficients are set according to manual experience.
In order to solve the problems, the invention provides an image defogging method based on average saturation prior, which comprises the following steps:
s1, calculating an atmospheric light value according to the foggy image;
s2, obtaining the depth value of each pixel in the foggy image;
s3, obtaining a scattering coefficient of each pixel in the fog image, specifically including:
s301, acquiring a large number of images in sunny days, and calculating the average saturation value of each image in sunny days according to the following equation:
n denotes the entire area of the clear sky image, (x, y) denotes any one pixel in the clear sky image, and Jc 1(x, y) represents the intensity value of pixel (x, y), JR 1(x, y) represents the intensity value of the R channel of pixel (x, y), JG 1(x, y) represents the intensity value of the G channel of pixel (x, y), JB 1(x, y) represents the intensity value of the B channel of pixel (x, y), mean () represents the mean;
s302, counting the average saturation values of all images in sunny days, obtaining the average saturation probability distribution of the images in sunny days, and calculating an expected value as an average saturation prior
S303, constructing an optimization model of the scattering coefficient as follows:
β (x, y) denotes the scattering coefficient of a pixel (x, y) in the foggy image, ω (x, y) denotes a local block of pixels centered on the pixel (x, y) in the foggy image, Ic(x ', y') represents an intensity value of any one pixel (x ', y') in the local pixel block ω (x, y), Jc(x ', y') represents the intensity value of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, IR(x ', y') denotes a local pixelIntensity value of R channel of any one pixel (x ', y') in block ω (x, y), JR(x ', y') represents the intensity value of the R channel of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, IG(x ', y') represents an intensity value of the G channel of any one pixel (x ', y') in the local pixel block ω (x, y), JG(x ', y') represents the intensity value of the G channel of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, IB(x ', y') represents an intensity value of the B channel of any one pixel (x ', y') in the local pixel block ω (x, y), JB(x ', y') represents an intensity value of the B channel of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, d (x ', y') represents a depth value of any one pixel (x ', y') in the local pixel block ω (x, y), β (x ', y') represents a scattering coefficient of any one pixel (x ', y') in the local pixel block ω (x, y) and the scattering coefficients of all the pixels in the local pixel block ω (x, y) are equal;
s304, solving the optimization model of the scattering coefficient to obtain the scattering coefficient of each pixel in the foggy image;
s4, the scene albedo for each pixel in the hazy image is found according to the following equation:
where ρ (x, y) represents the scene albedo of pixel (x, y) in the foggy image, Ic(x, y) represents an intensity value of the pixel (x, y) in the foggy image, a represents an atmospheric light value, d (x, y) represents a depth value of the pixel (x, y) in the foggy image, and β (x, y) represents a scattering coefficient of the pixel (x, y) in the foggy image;
and S5, calculating the intensity value of each pixel in the defogged image corresponding to each pixel in the fogging image according to the atmospheric light value and the scene albedo of each pixel in the fogging image, thereby forming the defogged image.
Preferably, the step 1 specifically includes:
s101, finding out the minimum intensity value in an R channel, a G channel and a B channel of each pixel of the foggy image to obtain a minimum channel image, setting a window by taking each pixel as a center, and performing minimum filtering on each window to obtain a dark primary color image;
s102, finding out an area 0.1% before the intensity value in the dark primary color image, and selecting the maximum value of the brightness values of all pixels in the area corresponding to the coverage in the foggy image in the area as the atmospheric light value.
The invention has the beneficial effects that: the method utilizes the condition that the defogged image obtained after defogging treatment accords with the average saturation prior of the image on a sunny day, reversely deduces and constructs an optimization model of the scattering coefficient, obtains the scattering coefficient corresponding to each pixel point by solving the optimization model, can effectively reflect the spatial distribution characteristic of the fog in the atmosphere when the fogging image is formed, can effectively defogge the non-uniform fogging image in the atmosphere, simultaneously solves the problem of uncertainty generated by setting the scattering coefficient according to experience in the prior art, and can obtain better defogging effect when the uniform fogging image in the atmosphere is treated.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Fig. 2 is a diagram of the effect of the first foggy image and the processing thereof by the method of the embodiment of the present invention and the two methods in the prior art.
Fig. 3 is a diagram of the effect of the second foggy image and the processing thereof by the method of the embodiment of the present invention and the two prior art methods.
Fig. 4 is a diagram of the effect of the third hazy image and the processing thereof by the method of the embodiment of the present invention and the two methods of the related art.
Fig. 5 is a diagram of the effect of the fourth foggy image and the processing thereof by the method of the embodiment of the present invention and the two methods in the prior art.
Fig. 6 is a diagram of the effect of the fifth hazy image and the processing thereof by the method of the embodiment of the present invention and the two methods in the related art.
Detailed Description
The invention provides an image defogging method based on average saturation prior, which comprises the following steps as shown in figure 1:
s1, calculating an atmospheric light value according to the foggy image, specifically including:
s101, finding out the minimum intensity value in an R channel, a G channel and a B channel of each pixel of the foggy image to obtain a minimum channel image, setting a plurality of windows by taking each pixel as the center, and performing minimum filtering on each window to obtain a dark primary color image.
Specifically, the minimum intensity value corresponding to each pixel in the foggy image is found according to the following equation, thereby composing the dark primary color image:
where Ω (x, y) denotes a local pixel block centered on any one pixel (x, y) in the fogging image, and the size of the local pixel block is preferably 15 × 15, Ic(a, b) represents the intensity value of any one pixel (a, b) in the local pixel block Ω (x, y), Idark(x, y) represents the smallest one of the intensity values of all channels of all pixels in the local pixel block Ω (x, y).
S102, finding out an area 0.1% before the intensity value in the dark primary color image, and selecting the maximum value of the brightness values of all pixels in the area corresponding to the area covered in the foggy image as the atmospheric light value A, namely
Where U represents the area 0.1% before the intensity corresponding to the area covered in the foggy color image, I' (p)1,p2) Represents any one pixel (p) in the region U1,p2) The luminance value of (a).
S2, a depth value for each pixel in the hazy image is found according to the following equation:
d(x,y)=θ0+θ1·I'(x,y)+θ2·I°(x,y)+ε(x,y) (3)
wherein, theta0Denotes a first linear coefficient, θ1Is shown asCoefficient of linearity, θ2Representing a third linear coefficient, theta in a particular embodiment of the invention0=0.1218,θ1=0.96,θ2As-0.78, epsilon (x, y) indicates obeying a normal distribution N (0, (0.0413)2) D (x, y) represents the depth value of the pixel (x, y) in the fogging image, I' (x, y) and I°(x, y) respectively represent the luminance value and the contrast value of the pixel (x, y) in the fogging image.
S3, obtaining a scattering coefficient of each pixel in the fog image, specifically including:
s301, acquiring a large number of images in sunny days, and calculating the average saturation value of each image in sunny days according to the following equation:
n denotes the entire area of the clear sky image, (x, y) denotes any one pixel in the clear sky image, and Jc 1(x, y) represents the intensity value of pixel (x, y) in a clear sky image, JR 1(x, y) represents the intensity value of the R channel for pixel (x, y) in a clear sky image, JG 1(x, y) represents the intensity value of the G channel for pixel (x, y) in a clear sky image, JB 1(x, y) represents the intensity value of the B channel of pixel (x, y) in a sunny day image, and mean () represents the mean value.
S302, counting the average saturation values of all images in sunny days, obtaining the average saturation probability distribution of the images in sunny days, and calculating an expected value as an average saturation prior
S303, defining the scattering coefficient in the atmospheric scattering model as a variable related to a pixel, and obtaining an improved atmospheric scattering model as follows:
Ic(x,y)=A·ρ(x,y)·e-β(x,y)·d(x,y)+A·(1-e-β(x,y)·d(x,y)) (5)
wherein, Ic(x, y) represents an intensity value of a pixel (x, y) in the fogging image, and ρ (x, y) represents foggingThe scene albedo of pixel (x, y) in the image, a represents the atmospheric light value, β (x, y) represents the scattering coefficient of pixel (x, y) in the hazy image, and d (x, y) represents the depth value of pixel (x, y) in the hazy image.
According to the atmospheric scattering model described above, the scene albedo ρ (x, y) in the atmospheric scattering model is expressed as a function related to the scattering coefficient β (x, y), i.e.The value range of the scene albedo ρ (x, y) is (0,1), and in order to prevent the obtained scene albedo from overflowing the value space, the scene albedo is represented as follows:
where ρ (x, y) represents the scene albedo of pixel (x, y) in the foggy image, Ic(x, y) denotes an intensity value of the pixel (x, y) in the foggy image, a denotes an atmospheric light value, d (x, y) denotes a depth value of the pixel (x, y) in the foggy image, and β (x, y) denotes a scattering coefficient of the pixel (x, y) in the foggy image.
According to the fact that the average saturation of the defogged image obtained after the fog image is processed is in accordance with the average saturation prior, and the scattering coefficients of all pixels in the local range in the fog image are assumed to be equal, an optimization model of the scattering coefficients is constructed as follows:
β (x, y) represents the scattering coefficient of a pixel (x, y) in the fogging image, ω (x, y) represents a local pixel block centered on any pixel (x, y) in the fogging image, preferably the local pixel block has a size of 15 × 15, and Ic(x ', y') represents an intensity value of any one pixel (x ', y') in the local pixel block ω (x, y), Jc(x ', y') represents the intensity value I from the pixel (x ', y') in the hazy imagec(x ', y') pixel-restored intensity value, I, of pixel (x ', y') in the defogged imageR(x ', y') represents an intensity value of the R channel of any one pixel (x ', y') in the local pixel block ω (x, y), JR(x ', y') represents the intensity value I of the R channel from pixel (x ', y') in the hazy imageR(x ', y') the intensity value, I, of the R channel of the pixel (x ', y') in the restored defogged imageG(x ', y') represents an intensity value of the G channel of any one pixel (x ', y') in the local pixel block ω (x, y), JG(x ', y') represents the intensity value I of the G channel from pixel (x ', y') in the foggy imageG(x ', y') the intensity value of the G channel of the pixel (x ', y') in the restored defogged image, IB(x ', y') represents an intensity value of the B channel of any one pixel (x ', y') in the local pixel block ω (x, y), JB(x ', y') represents the intensity value I of the B channel from pixel (x ', y') in the foggy imageB(x ', y') the restored intensity value of the B channel for the pixel (x ', y') in the defogged image, d (x ', y') represents the depth value of any one pixel (x ', y') in the local pixel block ω (x, y), β (x ', y') represents the scattering coefficient of any one pixel (x ', y') in the local pixel block ω (x, y) and the scattering coefficients of all the pixels in the local pixel block ω (x, y) are equalThe value is 0.106.
S304, solving an optimal scattering coefficient in a local range taking each pixel in the foggy image as a center by using the optimization model of the scattering coefficient to serve as the scattering coefficient of the pixel.
S4, the scene albedo of each pixel in the fogging image is obtained from equation (7).
S5, an intensity value of each pixel in the defogged image corresponding to each pixel in the defogged image is obtained according to the following equation, thereby composing the defogged image:
Jc(x,y)=A·ρ(x,y) (9)
wherein, Jc(x, y) is the intensity value of the pixel (x, y) in the defogged image.
Figures 2-6 are graphs showing the effect of processing the same five hazy images using the method of an embodiment of the present invention and two methods known in the art, wherein FIGS. 2(a) and 3(a) are aerial homogeneous fogging images, FIGS. 4(a), 5(a) and 6(a) are aerial non-homogeneous fogging images, FIGS. 2(b), 3(b), 4(b), 5(b) and 6(b) are defogged images after the He method treatment, FIGS. 2(c), 3(c), 4(c), 5(c) and 6(c) are dehazed images after the Zhu method, FIGS. 2(d), 3(d), 4(d), 5(d) and 6(d) are scattering maps obtained by calculating the scattering coefficient of each pixel according to the method of the present invention, FIGS. 2(e), 3(e), 4(e), 5(e) and 6(e) are defogged images processed by the method of the present invention. 2-6, the obtained scattering map can accurately express the distribution of fog in the atmosphere when the method of the invention processes fog images under various atmospheric conditions (whether the atmosphere is homogeneous or heterogeneous). By comparing the defogging effect, the method can obtain better visual effect when processing the uniform and foggy image of the atmosphere; when the fog image with non-uniform atmosphere is processed, the existing algorithm generally has the problem of fog residue, and the method can effectively remove the fog of the whole image.
Claims (2)
1. An image defogging method based on average saturation prior is characterized by comprising the following steps:
s1, calculating an atmospheric light value according to the foggy image;
s2, obtaining the depth value of each pixel in the foggy image;
s3, obtaining a scattering coefficient of each pixel in the fog image, specifically including:
s301, acquiring a large number of images in sunny days, and calculating the average saturation value of each image in sunny days according to the following equation:
n denotes the entire area of the clear sky image, (x, y) denotes any one pixel in the clear sky image, and Jc 1(x, y) represents the intensity value of pixel (x, y), JR 1(x, y) represents the intensity value of the R channel of pixel (x, y), JG 1(x, y) represents the intensity value of the G channel of pixel (x, y), JB 1(x, y) represents the intensity value of the B channel of pixel (x, y), mean () represents the mean;
s302, counting the average saturation values of all images in sunny days, obtaining the average saturation probability distribution of the images in sunny days, and calculating an expected value as an average saturation prior
S303, constructing an optimization model of the scattering coefficient as follows:
β (x, y) denotes a scattering coefficient of a pixel (x, y) in the fogging image, ω (x, y) denotes a local pixel block centered on the pixel (x, y) in the fogging image, (x ', y') denotes any one of the local pixel blocks ω (x, y), and Ic(x ', y') represents the intensity value of the pixel (x ', y'), Jc(x ', y') denotes a fogging patternIntensity value of pixel (x ', y') in the defogged image corresponding to pixel (x ', y') in the image, IR(x ', y') represents the intensity value of the R channel of the pixel (x ', y'), JR(x ', y') represents the intensity value of the R channel of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, IG(x ', y') represents the intensity value of the G channel of pixel (x ', y'), JG(x ', y') represents the intensity value of the G channel of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, IB(x ', y') represents the intensity value of the B channel of the pixel (x ', y'), JB(x ', y') represents the intensity value of the B channel of the pixel (x ', y') in the defogged image corresponding to the pixel (x ', y') in the fogging image, d (x ', y') represents the depth value of the pixel (x ', y'), β (x ', y') represents the scattering coefficient of the pixel (x ', y') and the scattering coefficients of all pixels in the local pixel block ω (x, y) are equal;
s304, solving an optimization model of the scattering coefficient to obtain the scattering coefficient of each pixel in the foggy image;
s4, the scene albedo for each pixel in the hazy image is found according to the following equation:
where ρ (x, y) represents the scene albedo of pixel (x, y) in the foggy image, Ic(x, y) represents an intensity value of the pixel (x, y) in the foggy image, a represents an atmospheric light value, d (x, y) represents a depth value of the pixel (x, y) in the foggy image, and β (x, y) represents a scattering coefficient of the pixel (x, y) in the foggy image;
s5, an intensity value of each pixel in the defogged image corresponding to each pixel in the fogging image is calculated based on the atmospheric light value and the scene albedo of each pixel in the fogging image, thereby composing the defogged image.
2. The average saturation prior-based image defogging method according to claim 1, wherein the step 1 specifically comprises:
s101, finding out the minimum intensity value in an R channel, a G channel and a B channel of each pixel of the foggy image to obtain a minimum channel image, setting a window by taking each pixel as a center, and performing minimum filtering on each window to obtain a dark primary color image;
s102, finding out an area 0.1% before the intensity value in the dark primary color image, and selecting the maximum value of the brightness values of all pixels in the area corresponding to the coverage in the foggy image in the area as the atmospheric light value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710323554.9A CN107123101B (en) | 2017-05-10 | 2017-05-10 | Image defogging method based on average saturation prior |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710323554.9A CN107123101B (en) | 2017-05-10 | 2017-05-10 | Image defogging method based on average saturation prior |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107123101A CN107123101A (en) | 2017-09-01 |
CN107123101B true CN107123101B (en) | 2020-04-28 |
Family
ID=59727879
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710323554.9A Active CN107123101B (en) | 2017-05-10 | 2017-05-10 | Image defogging method based on average saturation prior |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107123101B (en) |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102968760A (en) * | 2011-08-30 | 2013-03-13 | 富士通株式会社 | Image dehazing method and image dehazing system |
CN106530246A (en) * | 2016-10-28 | 2017-03-22 | 大连理工大学 | Image dehazing method and system based on dark channel and non-local prior |
-
2017
- 2017-05-10 CN CN201710323554.9A patent/CN107123101B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102968760A (en) * | 2011-08-30 | 2013-03-13 | 富士通株式会社 | Image dehazing method and image dehazing system |
CN106530246A (en) * | 2016-10-28 | 2017-03-22 | 大连理工大学 | Image dehazing method and system based on dark channel and non-local prior |
Non-Patent Citations (2)
Title |
---|
A Single Image Dehazing Method Using Average Saturation Prior;Zhenfei Gu et al.;《Mathematical Problems in Engineering》;20170315;第1-17页 * |
基于单幅图像的去雾算法研究;肖胜笔;《中国优秀硕士论文全文数据库 信息科技辑》;20151215;第22、28页 * |
Also Published As
Publication number | Publication date |
---|---|
CN107123101A (en) | 2017-09-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107767354B (en) | Image defogging algorithm based on dark channel prior | |
US9189830B2 (en) | Image defogging method and system | |
CN107301623B (en) | Traffic image defogging method and system based on dark channel and image segmentation | |
CN111292258B (en) | Image defogging method based on dark channel prior and bright channel prior | |
CN104794688B (en) | Single image to the fog method and device based on depth information separation sky areas | |
EP2568438B1 (en) | Image defogging method and system | |
WO2016206087A1 (en) | Low-illumination image processing method and device | |
CN107358585B (en) | Foggy day image enhancement method based on fractional order differential and dark channel prior | |
CN110827218B (en) | Airborne image defogging method based on weighted correction of HSV (hue, saturation, value) transmissivity of image | |
CN103700078B (en) | The defogging method of a small amount of background image containing mist | |
CN107301624A (en) | The convolutional neural networks defogging algorithm pre-processed based on region division and thick fog | |
CN108154492B (en) | A kind of image based on non-local mean filtering goes haze method | |
CN106355560B (en) | The extracting method and system of air light value in a kind of haze image | |
CN107330870B (en) | A kind of thick fog minimizing technology accurately estimated based on scene light radiation | |
CN104331867B (en) | The method, device and mobile terminal of image defogging | |
CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
CN103226816A (en) | Haze image medium transmission rate estimation and optimization method based on quick gaussian filtering | |
CN105989583A (en) | Image defogging method | |
CN110175967B (en) | Image defogging processing method, system, computer device and storage medium | |
CN108765337B (en) | Single color image defogging processing method based on dark channel prior and non-local MTV model | |
CN108416742B (en) | Sand and dust degraded image enhancement method based on color cast correction and information loss constraint | |
CN106709876B (en) | Optical remote sensing image defogging method based on dark image element principle | |
CN107977941B (en) | Image defogging method for color fidelity and contrast enhancement of bright area | |
CN104299195B (en) | A kind of image defogging method based on auto-adaptive doublethreshold and dark channel prior | |
CN114119383A (en) | Underwater image restoration method based on multi-feature fusion |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20170901 Assignee: Wuxi Wangfeng Internet of things Technology Research Institute Co.,Ltd. Assignor: Nanjing Vocational College of Information Technology Contract record no.: X2020980008364 Denomination of invention: An image defogging method based on average saturation prior Granted publication date: 20200428 License type: Common License Record date: 20201123 |
|
EE01 | Entry into force of recordation of patent licensing contract |