CN111986119B - Interference filtering method for brightness value of dark channel image and sea fog removing method for sea fog image - Google Patents
Interference filtering method for brightness value of dark channel image and sea fog removing method for sea fog image Download PDFInfo
- Publication number
- CN111986119B CN111986119B CN202010906506.4A CN202010906506A CN111986119B CN 111986119 B CN111986119 B CN 111986119B CN 202010906506 A CN202010906506 A CN 202010906506A CN 111986119 B CN111986119 B CN 111986119B
- Authority
- CN
- China
- Prior art keywords
- data points
- straight line
- consistent set
- final
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000001914 filtration Methods 0.000 title claims abstract description 9
- 239000002245 particle Substances 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000002834 transmittance Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 4
- 238000012545 processing Methods 0.000 abstract description 4
- 238000005070 sampling Methods 0.000 abstract description 2
- 239000013535 sea water Substances 0.000 description 5
- 230000002238 attenuated effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012239 gene modification Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000005017 genetic modification Effects 0.000 description 1
- 235000013617 genetically modified food Nutrition 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention provides a dark channel image brightness value interference filtering method and a sea fog removing method of sea fog images, and relates to the technical field of image processing, wherein the dark channel image brightness value interference filtering method adopts a random sampling consistency algorithm and a least square fitting algorithm to fit a brightness curve of a row dark channel image so as to obtain dark pixel brightness values after interference is removed; and the sea fog removal of the sea fog image is carried out based on the dark pixel brightness value after the interference is removed, so that the defogging effect is improved.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a dark channel image brightness value interference filtering method and a sea fog removal method for sea fog images.
Background
With the continuous development of unmanned aerial vehicle technology, the unmanned aerial vehicle has been applied more and more widely, and various patrol tasks are started to be performed, including maritime patrol. When the unmanned aerial vehicle flies on the sea to execute patrol tasks, the unmanned aerial vehicle is easy to be interfered by sea fog, so that the influence of the sea fog on images shot by the unmanned aerial vehicle is required to be reduced through an image processing means.
The patent CN104933680B issued by the national intellectual property agency 2017, 10 and 31, discloses a method for removing image sea fog. In this scheme, the atmospheric brightness value is estimated according to the highest 0.01% of the brightness value in the image, and when the sky area (for example, fig. 1) does not exist in the image, the estimated value is likely to be from the spray or warship area in fig. 1, so that the deviation between the processing result and the actual situation is caused. In addition, seawater is not a pure dark pixel, usually biased to blue, and the R-channel value is lowest, but not near 0, and varies between 50-150 over a large number of real seawater image statistics. If the default sea water is a dark pixel, the sea water in the sea surface scene graph after defogging is obviously bluish, and an unrealistic feel is given to people, as shown in fig. 2.
Disclosure of Invention
Aiming at the technical problems, the invention provides a dark channel image brightness value interference filtering method and a sea fog image sea fog removing method.
The invention discloses a dark channel image brightness value interference filtering method, which comprises the following steps:
1. for each line of luminance data in the dark channel image, recording according to the point set, each data point P in each line of the image i Comprising x i 、d i Two dimensions, where x i Representing the horizontal coordinates of the data point in the line image, d i A luminance value representing the data point;
2. for a specific row, randomly selecting the internal fraction data points of the row to obtain an initial consistent set S0;
3. performing straight line fitting on the brightness values of the initial consistent set S0 to obtain a straight line L0;
4. setting a distance threshold d_th, screening data points in the initial consistent set S0, discarding the data points if the distance from the data points to a straight line L0 is greater than d_th, removing all the data points with the distance from the data points to the straight line L0 being greater than d_th to obtain a consistent set S1, and performing straight line fitting on the S1 to obtain L1;
5. reducing the distance threshold d_th, repeating the step 4, continuously optimizing the consistent set until the consistent set is not changed any more, recording the optimal consistent set at the moment as S_best, and recording a fitting straight line corresponding to the optimal consistent set as L_best;
6. calculating the distance from all data points in the row to the straight line L_best, judging whether the data points belong to the optimal consistent set or not, discarding the data points not belonging to the optimal consistent set to obtain a final consistent set S_final and a fitting straight line L_final thereof, and calculating the Ratio of the number of the data points in the final consistent set S_final to the total number of the data points in the row to be ratio_final;
7. repeating the step (II) for 1000 times, and selecting a fitting straight line L_final corresponding to a final consistent set S_final with the highest ratio_final value as a brightness curve L after the line fitting. Here the N rows of dark channel images correspond to N luminance curves L.
The invention also provides a sea fog removal method for the sea fog image, which comprises the following steps:
1. extracting a single-pixel dark channel of the sea surface image, and taking the minimum value in each pixel RGB value as the dark channel value of the dark channel image;
2. by the interference filtering method for the brightness values of the dark channel images, a brightness curve of each row of dark channel images is fitted by using a straight line, and the brightness value corresponding to the midpoint of the straight line obtained by fitting is taken as the brightness value of the row;
3. linear modeling of transmittance t i ＝ay i +b, where t i Representing the transmission coefficient of row i, y i Representing the y coordinate of the ith row in the dark channel image, a and b being two linear parameters;
4. optical model I (x, y) =j (x, y) ·t (x, y) + [1-t (x, y) according to haze]A (x, y) to obtain the ith channel brightness value I i ＝J·t i +A(1-t i ) Wherein J is the sea surface real brightness value in the dark channel image, and A is the atmosphere brightness value;
5. construction of energy valuesWherein N is the total number of rows of the dark channel image;
6. calculating the value of the corresponding J, A, a, b four parameters as the optimal parameter value when the energy value E is minimum by adopting a particle swarm evolution algorithm;
7. and calculating the real RGB value of each pixel according to the optimal parameter value.
According to the invention, a random sampling consistency algorithm and a least square fitting algorithm are adopted to fit the brightness curve of the row dark channel image, so as to obtain the brightness value of the dark pixel after interference is removed; and the sea fog removal of the sea fog image is carried out based on the dark pixel brightness value after the interference is removed, so that the defogging effect is improved.
Drawings
Fig. 1 is an original unmanned aerial vehicle captured image;
FIG. 2 is a graph of the default seawater of FIG. 1 as a dark pixel post-treatment effect;
FIG. 3 is the image of FIG. 1 after single pixel dark channel extraction;
FIG. 4 (a) is a graph showing luminance values of a dark channel image on a row with an ordinate 460;
FIG. 4 (b) is a graph showing luminance values of a dark channel image on a line with an ordinate 503;
FIG. 4 (c) is a graph showing luminance values of a dark channel image on a row with an ordinate 611;
FIG. 4 (d) is a graph showing luminance values of a dark channel image on a line with an ordinate 848;
FIG. 5 is a graph showing the brightness curve L after fitting in FIG. 4 (a);
FIG. 6 is a graph showing the arrangement of the brightness values of each row of the dark channel image in order from the top to the bottom;
FIG. 7 is a flow chart of a particle swarm evolution algorithm.
Detailed Description
The invention will be described in further detail with reference to the drawings and the detailed description. The embodiments of the invention have been presented for purposes of illustration and description, and are not intended to be exhaustive or limited to the invention in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, and to enable others of ordinary skill in the art to understand the invention for various embodiments with various modifications as are suited to the particular use contemplated.
For convenience of description, the basic concepts will be described in advance as follows:
1. optical model of fog
There is a two-part decay in the brightness value of the camera captured image: 1. atmospheric brightness is attenuated by foggy air; 2. the reflected light of the scene object is attenuated by the fog so that there is I (x, y) =j (x, y) ·t (x, y) + [1-t (x, y) ]·a (x, y), where J (x, y) is the image true luminance value, t (x, y) is the transmission coefficient, and a (x, y) is the atmospheric luminance value.
2. Particle swarm evolution algorithm
1. Individual/particle: each individual corresponds to a set of solutions, and in the problem to be solved by the invention, each individual contains J, A, a, b four parameters, and each individual corresponds to a fitness degree.
2. Population: a population comprises a plurality of individuals, e.g., 50, 100, etc., depending on how many computing resources are present.
3. Fitness degree: after defining an optimization problem, the fitness is related to the target value of the problem, and the closer to the target value, the higher the fitness.
4. And (3) substitution: the evolution calculation method is used for searching the optimal solution of the optimization problem, and a plurality of iterations are needed, and each iteration corresponds to one generation. The same individual at different generations has different parameter values.
5. Genetic modification: when the individual parameters iterate, the parameter values of the next generation are greatly referenced to the parameter values of the current generation, and the parameter values are similar to the genetic rule of organisms.
6. Variation: when the individual parameters iterate, the parameter values of the next generation can introduce new variation, and the parameter values of the next generation have certain difference with the parameter values of the current generation, which is similar to the variation rule of organisms.
7. Individual history optimal record: in the course of multiple iterations, the current individual historically exhibits the highest fitness corresponding parameter value.
8. Group history optimal record: over the course of multiple iterations, all individuals in the population historically exhibit parameter values corresponding to the highest fitness.
9. Speed of: the difference of each parameter of the current individual relative to the previous generation is calculated by the calculation formula v of the current particle speed during iteration i+1 ＝w×v i +c 1 r 1 ×(pbest i -x i )+c 2 r 2 (gbest i -x i ) The method is obtained by adding the following three parts:
speed w x v of the last generation i : velocity v of the current generation i+1 Reference is made to the speed v of the previous generation i W is a weight value, and according to an empirical setting, for example w=0.8, different weight values determine how much the particle changes during the iteration follow the historical change law.
Optimal record c of individual histories 1 r 1 ×(pbest i -x i ): the particles, when varied, refer to their own historically optimal position. pbest (p best) i Refers to the optimal position of the individual, i is the serial number of the particle, x i Is the position of the current particle in the feature space, i.e. the parameter value, c 1 Is a constant, r 1 Is a random number between 0 and 1, randomly generated at each iteration.
This means that the individual, when changing, is as close to his own historic optimal position as possible, since the periphery of the historic optimal position means that a better fitness is possible.
Third-party group history optimal record c 2 r 2 (gbest i -x i ): the particles, as they change, refer to the historically optimal location of all individuals of the entire population. gbest (g best) i Refers to the optimal position of the population, c 2 Is a constant, r 2 Is a random number between 0 and 1, randomly generated at each iteration.
This means that the individuals, when changing, try to get closer to the group history optimum position, since the perimeter of the group history optimum position means that a better fitness is possible.
10. Position: the parameter value of the current individual. After the individual velocity is obtained, the velocity is added with the current position to obtain the next generation position x i+1 ＝x i +v i+1 。
The sea fog removal method for the sea fog image disclosed by the invention comprises the following steps:
1. and carrying out single-pixel dark channel extraction on the sea surface image, and taking the minimum value in each pixel RGB value as the dark channel value of the dark channel image to obtain the image 3.
The dark channel values in each row of dark channel images of fig. 3 are also not completely uniform, but are disturbed by a variety of factors, such as brightness variations caused by wave fluctuations, white spray, pixels of different brightness on the ship, etc.
Fig. 4 (a) -4 (d) are four-row dark channel image luminance value curves with vertical coordinates (the uppermost vertical coordinate is 1, and the vertical coordinates become larger from top to bottom) 460, 503, 611, 848 in fig. 3, respectively. The first three rows of dark channel images are easily seen, the curves are greatly changed due to the interference of ships or spoons, and the larger interference exists when the brightness value of the true dark pixels of the row is calculated; the fourth row is almost sea surface, the impurity interference is less, and the brightness curve is more gentle.
Therefore, the interference factors must be filtered to obtain the real dark channel brightness value of each row of dark channel image, so as to improve the overall defogging effect.
2. Fitting a brightness curve of each row of dark channel images by using a straight line, and taking a brightness value corresponding to the midpoint of the straight line obtained by fitting as the brightness value of the row, wherein the method specifically comprises the following steps:
for each row of brightness data in a dark channel image, recording according to a point set, each data point P in each row of image i Comprising x i 、d i Two dimensions, where x i Representing the horizontal coordinates of the data point in the line image, d i Representing the luminance value of the data point.
The internal fractional data points (for example, half) of the row are randomly selected for a specific row to obtain an initial consistent set S0.
And thirdly, performing straight line fitting on the brightness values of the initial consistent set S0 to obtain a straight line L0.
And fourthly, setting a distance threshold d_th, screening data points in the initial consistent set S0, discarding the data points if the distance from the data points to the straight line L0 is greater than d_th, removing all the data points with the distance from the data points to the straight line L0 being greater than d_th, obtaining a consistent set S1, and performing straight line fitting on the S1 to obtain L1.
And (5) reducing the distance threshold d_th, repeating the step (4), continuously optimizing the consistent set until the consistent set is not changed, recording the optimal consistent set at the moment as S_best, and recording a fitting straight line corresponding to the optimal consistent set as L_best.
The method comprises the steps of (1) calculating the distance from all data points in a row to a straight line L_best, judging whether the data points belong to an optimal consistent set or not, discarding the data points not belonging to the optimal consistent set, obtaining a final consistent set S_final and a fitting straight line L_final thereof, and calculating the Ratio of the number of the data points in the final consistent set S_final to the total number of the data points in the row to be ratio_final.
And repeating the steps for 1000 times, and selecting a fitting straight line L_final corresponding to a final consistent set S_final with the highest ratio_final value as a brightness curve L after the line fitting. The bottom straight line in fig. 5 is the luminance curve L after the fitting of fig. 4 (a). Here the N rows of dark channel images correspond to N luminance curves L.
4. The luminance values of the respective rows of the dark channel image are arranged in order from top to bottom on the ordinate, and a curve is drawn as shown in fig. 6. Since the sea surface color is not perfectly uniform, the curve in fig. 6 is only approximately straight, approximately linearly graded, but it is sufficient to use a linear model to simulate the transmission law of fog on the sea surface.
Thus, the transmittance is linearly modeled t i ＝ay i +b, where t i Representing the transmission coefficient of row i, y i Representing the y-coordinate of row i in the dark channel image, a, b are two linear parameters.
5. Optical model I (x, y) =j (x, y) ·t (x, y) + [1-t (x, y) according to haze]A (x, y) to obtain the ith channel brightness value I i ＝J·t i +A(1-t i ) Which is provided withAnd J is the real brightness value of the sea surface in the dark channel image, and A is the atmospheric brightness value.
6. Construction of energy valuesWhere N is the total number of rows of dark channel images.
7. When the energy value E is calculated to be minimum by adopting the particle swarm evolution algorithm, the optimal parameter values of the corresponding J, A, a, b four parameters are calculated, fig. 7 is a working flow chart of the particle swarm algorithm, and the iterative process is continued for a plurality of generations until the energy value E reaches a satisfaction degree.
8. And calculating the real RGB value of each pixel according to the optimal parameter value.
Obtaining transmission coefficients t of each row by using parameters a and b i ＝ay i +b, y according to the line for a particular one i Is a known number;
obtaining real RGB values of each pixel position in the defogged clear imageWherein O is iR 、O iG 、O iB Is the RGB value of the original sea fog image.
It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art and which are included in the embodiments of the present invention without the inventive step, are intended to be within the scope of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art and which are included in the embodiments of the present invention without the inventive step, are intended to be within the scope of the present invention.
Claims (2)
1. The interference filtering method for the brightness value of the dark channel image is characterized by comprising the following steps of:
step A1, for dark channel mapEach line of brightness data in the image is recorded according to the point set, and each data point P in the line image j Comprising x j 、d j Two dimensions, where x j Representing the horizontal coordinates of the data point in the line image, d j A luminance value representing the data point;
step A2, aiming at a specific certain row, randomly selecting the internal fraction data points of the row to obtain an initial consistent set S0;
step A3, performing straight line fitting on the brightness values of the initial consistent set S0 to obtain a straight line L0;
step A4, setting a distance threshold d_th, screening data points in an initial consistent set S0, discarding the data points if the distance from the data points to a straight line L0 is greater than d_th, removing all the data points with the distance from the data points to the straight line L0 being greater than d_th to obtain a consistent set S1, and performing straight line fitting on the S1 to obtain L1;
step A5, the distance threshold d_th is reduced, the step A4 is repeated until the consistent set is not changed, the optimal consistent set at the moment is marked as S_best, and the corresponding fitting straight line is marked as L_best;
step A6, calculating the distance between all data points in the row and the straight line L_best, judging whether the data points belong to the optimal consistent set, if the distance between the data points and the straight line L_best is larger than a threshold d_th, the data points do not belong to the optimal consistent set, discarding the data points not belonging to the optimal consistent set, obtaining a final consistent set S_final and a fitting straight line L_final thereof, and calculating that the Ratio of the number of the data points in the final consistent set S_final to the total number of the data points in the row is Ratio_final;
and A7, repeating the steps A2 to A6 for a plurality of times, and selecting a fitting straight line L_final corresponding to a final consistent set S_final with the highest ratio_final value as a brightness curve L after the line fitting.
2. The sea fog removing method for the sea fog image is characterized by comprising the following steps of:
step 1, extracting a single-pixel dark channel from a sea surface image, wherein the minimum value in each pixel RGB value is used as the dark channel value of the dark channel image;
and 2, fitting a brightness curve of each row of dark channel images by using a straight line, and taking a brightness value corresponding to the midpoint of the straight line obtained by fitting as a channel brightness value of the row, wherein the method specifically comprises the following steps of:
1. recording according to the point set for the ith row of brightness data in the dark channel image, wherein each data point P in the ith row of image j Comprising x j 、d j Two dimensions, where x j Representing the horizontal coordinates of the data point in the line image, d j A luminance value representing the data point;
2. for the ith row, randomly selecting the internal fraction data points of the row to obtain an initial consistent set S0;
3. performing straight line fitting on the brightness values of the initial consistent set S0 to obtain a straight line L0;
4. setting a distance threshold d_th, screening data points in the initial consistent set S0, discarding the data points if the distance from the data points to a straight line L0 is greater than d_th, removing all the data points with the distance from the data points to the straight line L0 being greater than d_th to obtain a consistent set S1, and performing straight line fitting on the S1 to obtain L1;
5. reducing the distance threshold d_th, repeating the step A4, continuously optimizing the consistent set until the consistent set is not changed any more, and marking the optimal consistent set at the moment as S_best and the corresponding fitting straight line as L_best;
6. calculating the distance from all data points in the row to the straight line L_best, judging whether the data points belong to the optimal consistent set, if the distance from the data points to the straight line L_best is larger than a threshold d_th, the data points do not belong to the optimal consistent set, discarding the data points not belonging to the optimal consistent set to obtain a final consistent set S_final and a fitting straight line L_final thereof, and calculating the Ratio of the number of the data points in the final consistent set S_final to the total number of the data points in the row as ratio_final;
7. repeating the steps 2 to 6 for a plurality of times, and selecting a fitting straight line L_final corresponding to a final consistent set S_final with the highest ratio_final value as a brightness curve L after the line fitting;
8. taking the brightness value corresponding to the midpoint of the fitted straight line as the channel brightness value I of the ith row i ；
Step 3, linearly modeling the transmittance t i ＝ay i +b, where t i Representing the transmission coefficient of row i, y i Representing the y coordinate of the ith row in the dark channel image, a and b being two linear parameters;
step 4, according to the optical model of fog I (x, y) =j (x, y) ·t (x, y) + [1-t (x, y)]A (x, y) to obtain the ith channel brightness value I i ＝J·t i +A(1-t i ) Wherein J is the sea surface real brightness value in the dark channel image, and A is the atmosphere brightness value;
step 5, constructing an energy valueWherein N is the total number of rows of the dark channel image;
step 6, calculating the value of the four corresponding J, A, a, b parameters as the optimal parameter value when the energy value E is minimum by adopting a particle swarm evolution algorithm;
and 7, calculating the real RGB value of each pixel according to the optimal parameter value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010906506.4A CN111986119B (en) | 2020-09-01 | 2020-09-01 | Interference filtering method for brightness value of dark channel image and sea fog removing method for sea fog image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010906506.4A CN111986119B (en) | 2020-09-01 | 2020-09-01 | Interference filtering method for brightness value of dark channel image and sea fog removing method for sea fog image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111986119A CN111986119A (en) | 2020-11-24 |
| CN111986119B true CN111986119B (en) | 2023-11-28 |
Family
ID=73447376
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010906506.4A Active CN111986119B (en) | 2020-09-01 | 2020-09-01 | Interference filtering method for brightness value of dark channel image and sea fog removing method for sea fog image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111986119B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105681774A (en) * | 2016-02-26 | 2016-06-15 | 深圳市金立通信设备有限公司 | Image processing method and terminal |
| KR101705536B1 (en) * | 2015-10-08 | 2017-02-10 | 목포해양대학교 산학협력단 | A fog removing method based on camera image |
| CN106548463A (en) * | 2016-10-28 | 2017-03-29 | 大连理工大学 | Based on dark and the sea fog image automatic defogging method and system of Retinex |
| CN108416815A (en) * | 2018-03-05 | 2018-08-17 | 国家安全生产监督管理总局通信信息中心 | Assay method, equipment and the computer readable storage medium of air light value |
| CN110135434A (en) * | 2018-11-13 | 2019-08-16 | 天津大学青岛海洋技术研究院 | Underwater picture increased quality algorithm based on color line model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IL300998A (en) * | 2016-04-07 | 2023-04-01 | Carmel Haifa Univ Economic Corporation Ltd | Image dehazing and restoration |
-
2020
- 2020-09-01 CN CN202010906506.4A patent/CN111986119B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101705536B1 (en) * | 2015-10-08 | 2017-02-10 | 목포해양대학교 산학협력단 | A fog removing method based on camera image |
| CN105681774A (en) * | 2016-02-26 | 2016-06-15 | 深圳市金立通信设备有限公司 | Image processing method and terminal |
| CN106548463A (en) * | 2016-10-28 | 2017-03-29 | 大连理工大学 | Based on dark and the sea fog image automatic defogging method and system of Retinex |
| CN108416815A (en) * | 2018-03-05 | 2018-08-17 | 国家安全生产监督管理总局通信信息中心 | Assay method, equipment and the computer readable storage medium of air light value |
| CN110135434A (en) * | 2018-11-13 | 2019-08-16 | 天津大学青岛海洋技术研究院 | Underwater picture increased quality algorithm based on color line model |
Non-Patent Citations (5)
| Title |
|---|
| 双粒度光流流形学习的刮刷总成摆杆摆幅检测;郑思凡;王卫星;何占华;梁子裕;陈平平;;华南理工大学学报(自然科学版)(第01期);全文 * |
| 基于YOLOv3深度学习的海雾气象条件下海上船只实时检测;王飞;刘梦婷;刘雪芹;秦志亮;马本俊;郑毅;;海洋科学(第08期);全文 * |
| 基于相机响应曲线拟合的道路能见度检测算法;韩静;于平平;王震洲;霍威;齐林;;燕山大学学报(第03期);全文 * |
| 基于自适应雾浓度系数的暗通道先验法能见度测量;陈钟荣;张炎;张瑶;;现代电子技术(第09期);全文 * |
| 强光源影响下的单幅图像去雾;毕雪英;过洁;潘金贵;;常州大学学报(自然科学版)(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111986119A (en) | 2020-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564549B (en) | Image defogging method based on multi-scale dense connection network | |
| CN109523480B (en) | Defogging method and device for sea fog image, computer storage medium and terminal | |
| US6621937B1 (en) | Removing chroma noise from digital images by using variable shape pixel neighborhood regions | |
| CN110288550B (en) | Single-image defogging method for generating countermeasure network based on priori knowledge guiding condition | |
| CN110097522B (en) | Single outdoor image defogging method based on multi-scale convolution neural network | |
| CN108510504A (en) | Image partition method and device | |
| CN109829868B (en) | Lightweight deep learning model image defogging method, electronic equipment and medium | |
| CN110503610A (en) | A kind of image sleet trace minimizing technology based on GAN network | |
| CN114972107A (en) | Low-illumination image enhancement method based on multi-scale stacked attention network | |
| CN112580662A (en) | Method and system for recognizing fish body direction based on image features | |
| CN111145105A (en) | Image rapid defogging method and device, terminal and storage medium | |
| CN113536978A (en) | Method for detecting disguised target based on significance | |
| Cai et al. | Underwater image processing system for image enhancement and restoration | |
| CN111986119B (en) | Interference filtering method for brightness value of dark channel image and sea fog removing method for sea fog image | |
| CN114387343A (en) | Method for detecting picking position of mushroom stem of clustered oyster mushroom | |
| CN109949239B (en) | Self-adaptive sharpening method suitable for multi-concentration multi-scene haze image | |
| CN112950484B (en) | Method for removing color pollution of photographic image | |
| CN112907503B (en) | Penaeus vannamei Boone quality detection method based on self-adaptive convolutional neural network | |
| CN114170101A (en) | Structural texture keeping low-light image enhancement method and system based on high-frequency and low-frequency information | |
| CN113920391A (en) | Target counting method based on generated scale self-adaptive true value graph | |
| CN110675333A (en) | Microscopic imaging processing method based on neural network super-resolution technology | |
| CN115205668A (en) | Method and system for detecting netting attachment based on deep learning | |
| US20240029289A1 (en) | System and method for estimating a length of underwater creatures | |
| CN115496694B (en) | Method for recovering and enhancing underwater image based on improved image forming model | |
| Coffelt et al. | Marine snow simulation and elimination in video |
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 |