CN106355560B - The extracting method and system of air light value in a kind of haze image - Google Patents
The extracting method and system of air light value in a kind of haze image Download PDFInfo
- Publication number
- CN106355560B CN106355560B CN201610761884.1A CN201610761884A CN106355560B CN 106355560 B CN106355560 B CN 106355560B CN 201610761884 A CN201610761884 A CN 201610761884A CN 106355560 B CN106355560 B CN 106355560B
- Authority
- CN
- China
- Prior art keywords
- value
- image
- maximum value
- width
- filtering
- 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 28
- 238000001914 filtration Methods 0.000 claims abstract description 59
- 230000003044 adaptive effect Effects 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 abstract description 5
- 239000000284 extract Substances 0.000 abstract description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
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 present invention relates to technical field of image processing, the extracting method and system of air light value in a kind of haze image are provided, method includes: that any pixel triple channel in the image I (x, y) to input carries out mini-value filtering, obtain mini-value filtering image M (x, y);Floor projection is carried out to the mini-value filtering image M (x, y) got, and obtains the maximum value area image K (x, y) after floor projection;Upright projection is carried out to the maximum value area image K (x, y), and obtains the maximum value area image R (x, y) after upright projection;Extract maximum value area image R (x, y) pixel value in chooses the average value of a certain number of pixel values as air light value A, realizes the quick calculating to air light value, the image of different size and sky areas is adapted to, provides condition for the processing of haze image Quick demisting.
Description
Technical field
The invention belongs to a kind of extracting method of air light value in technical field of image processing more particularly to haze image and
System.
Background technique
In haze scene, the scattering process of atmospheric particles will lead to the information that optical sensor captures and seriously degrade, figure
Different degrees of decaying can all occur in terms of contrast and color fidelity as in, directly influence impression and the machine of human vision
The normal work of device vision system, therefore study image defogging method and be of great significance.Method based on image restoration is directed to
The physical process that Misty Image degrades establishes Misty Image degradation model, compensates the letter lost in foggy image by complementary operation
Breath.This method is with strong points, and obtained defog effect is naturally, thus having obtained a large amount of concerns and having had become a hot topic of research.
According to atmospheric scattering theory, model of the scenery when being imaged in the greasy weather mainly includes two parts: object reflects in scene
The light process and sunlight that are decayed during reaching sensor by the scattering of atmospheric particles by the suspension grain in atmosphere
The process of sensor is reached after son scattering.Therefore, in computer vision and computer graphics, the scattering of foggy image is described
Model may be expressed as:
I (x)=J (x) t (x)+A (1-t (x));
X is space coordinate, and I (x) is foggy image, and J (x) is scene radiant illumination or clear fogless image, and A is whole
Air light value, t (x) are atmospheric transmissivity function (parameter).Once find out transmissivity and air light value, then it can be with restoration scenario depth
Degree.
But at present in the treatment process of haze image, the estimation procedure of air light value is complex, to influence
The efficiency of whole image defogging.
Summary of the invention
The purpose of the present invention is to provide a kind of extracting methods of air light value in haze image, it is intended to solve the prior art
The estimation procedure of middle air light value is complex, thus the problem of affecting the efficiency of whole image defogging.
The invention is realized in this way in a kind of haze image air light value extracting method, the method includes following
Step:
Mini-value filtering is carried out to any pixel triple channel in the image I (x, y) of input, obtains mini-value filtering image
M(x,y);
Floor projection is carried out to the mini-value filtering image M (x, y) got, and obtains the maximum value area after floor projection
Area image K (x, y);
Upright projection is carried out to the maximum value area image K (x, y), and obtains the maximum value administrative division map after upright projection
As R (x, y);
The pixel value in maximum value area image R (x, y) is extracted, chooses the average value of the pixel value of fixed quantity as big
Gas light value A.
As an improvement scheme, the described couple of mini-value filtering image M (x, y) that gets carries out floor projection, and
Obtain floor projection after maximum value area image K (x, y) the step of specifically include the following steps:
Floor projection is carried out to the mini-value filtering image M (x, y) got, obtains the gray value of a column all pixels point
Accumu-late parameter H (y);
Calculate the width b of floor projectionH, and determine the adaptive width value of sky areas for 2b with thisH+1;
To being projected in 2bHPixel value carries out summation operation in+1 width regions, and filters out maximum value region, determines screening
Image K (x, y) corresponding to maximum value region out.
As an improvement scheme, the described couple of mini-value filtering image M (x, y) that gets carries out floor projection, obtains
After the step of taking the accumu-late parameter H (y) of the gray value of a column all pixels point, the width b for calculating floor projectionHStep
Further include following step before rapid:
Smothing filtering is carried out to accumu-late parameter H (y), eliminates kurtosis and singular value present in image.
As an improvement scheme, it is described that upright projection is carried out to the maximum value area image K (x, y), and obtain
The step of maximum value area image R (x, y) after upright projection specifically include the following steps:
Upright projection is carried out to maximum value area image K (x, y), obtains the cumulative ginseng of the gray value of a line all pixels point
Number V (x);
Calculate the width b of upright projectionV, and determine the adaptive width value of sky areas for 2b with thisV+1;
To being projected in 2bVPixel value carries out summation operation in+1 width regions, and filters out maximum value region, determines screening
Image R (x, y) corresponding to maximum value region out.
As an improvement scheme, it is described to maximum value area image K (x, y) carry out upright projection, obtain a line institute
After having the step of accumu-late parameter V (x) of the gray value of pixel, the width b for calculating upright projectionVThe step of before also
Include the following steps:
Smothing filtering is carried out to accumu-late parameter V (x), eliminates kurtosis and singular value present in image.
Another object of the present invention is to provide a kind of extraction system of air light value in haze image, the system packet
It includes:
Mini-value filtering module carries out minimum value filter for any pixel triple channel in the image I (x, y) to input
Wave obtains mini-value filtering image M (x, y);
First maximum value area image obtains module, horizontal for carrying out to the mini-value filtering image M (x, y) got
Projection, and obtain the maximum value area image K (x, y) after floor projection;
Second maximum value area image obtains module, for vertically being thrown the maximum value area image K (x, y)
Shadow, and obtain the maximum value area image R (x, y) after upright projection;
Air light value determining module chooses fixed quantity for extracting the pixel value in maximum value area image R (x, y)
Pixel value average value as air light value A.
As an improvement scheme, the first maximum value area image obtains module and specifically includes:
Floor projection module obtains a column for carrying out floor projection to the mini-value filtering image M (x, y) got
The accumu-late parameter H (y) of the gray value of all pixels point;
Floor projection width computing module, for calculating the width b of floor projectionH, and with this determine sky areas from
Adaptation width value is 2bH+1;
First image determining module, for being projected in 2bHPixel value carries out summation operation in+1 width regions, and screens
Maximum value region out determines image K (x, y) corresponding to the maximum value region filtered out.
As an improvement scheme, the system also includes:
First smothing filtering module eliminates spike present in image for carrying out smothing filtering to accumu-late parameter H (y)
Value and singular value.
As an improvement scheme, the second maximum value area image obtains module and specifically includes:
Upright projection module obtains a line all pixels for carrying out upright projection to maximum value area image K (x, y)
The accumu-late parameter V (x) of the gray value of point;
Upright projection width computing module, for calculating the width b of upright projectionV, and with this determine sky areas from
Adaptation width value is 2bV+1;
Second image determining module, for being projected in 2bVPixel value carries out summation operation in+1 width regions, and screens
Maximum value region out determines image R (x, y) corresponding to the maximum value region filtered out.
As an improvement scheme, the system also includes:
Second smothing filtering module eliminates spike present in image for carrying out smothing filtering to accumu-late parameter V (x)
Value and singular value.
In embodiments of the present invention, mini-value filtering is carried out to any pixel triple channel in the image I (x, y) of input,
Obtain mini-value filtering image M (x, y);Floor projection is carried out to the mini-value filtering image M (x, y) got, and obtains water
Maximum value area image K (x, y) after flat projection;Upright projection is carried out to the maximum value area image K (x, y), and is obtained
Maximum value area image R (x, y) after upright projection;The pixel value in maximum value area image R (x, y) is extracted, chooses and fixes
The average value of the pixel value of quantity realizes the quick calculating to air light value as air light value A, adapts to different size and sky
The image in region provides condition for the processing of haze image Quick demisting.
Detailed description of the invention
Fig. 1 is the implementation flow chart of the extracting method of air light value in haze image provided by the invention;
Fig. 2 is provided by the invention to the mini-value filtering image M (x, y) got progress floor projection, and obtains water
The implementation flow chart of maximum value area image K (x, y) after flat projection;
Fig. 3 is provided by the invention to the maximum value area image K (x, y) progress upright projection, and obtains vertical throw
The implementation flow chart of the maximum value area image R (x, y) of movie queen;
Fig. 4 is the structural block diagram of the extraction system of air light value in haze image provided by the invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 shows the implementation flow chart of the extracting method of air light value in haze image provided by the invention, specific
Include the following steps:
In step s101, mini-value filtering is carried out to any pixel triple channel in the image I (x, y) of input, obtained
Mini-value filtering image M (x, y).
Wherein,Wherein, (x, y) is the pixel in image, and c is the three of color image
Chrominance channel.
In step s 102, floor projection is carried out to the mini-value filtering image M (x, y) got, and obtains horizontal throwing
The maximum value area image K (x, y) of movie queen.
In step s 103, upright projection is carried out to the maximum value area image K (x, y), and after obtaining upright projection
Maximum value area image R (x, y).
In step S104, the pixel value in maximum value area image R (x, y) is extracted, the pixel value of fixed quantity is chosen
Average value as air light value A.
In this step, the pixel value for belonging to region of filling a vacancy is extracted, then to the pixel value in the region of filling a vacancy into
The arrangement of row descending, choose brightness be greater than certain numerical value pixel average gray value as air light value, which can be with
It is 10%, i.e. A=mean (max0.1R(x,y))
Floor projection is carried out to the mini-value filtering image M (x, y) got Fig. 2 shows provided by the invention, and is obtained
The implementation flow chart of maximum value area image K (x, y) after taking floor projection, specifically include the following steps:
In step s 201, floor projection is carried out to the mini-value filtering image M (x, y) got, it is all obtains a column
The accumu-late parameter H (y) of the gray value of pixel.
Wherein, the formula expression of floor projection are as follows:
Wherein, 1≤x≤n.
In step S202, the width b of floor projection is calculatedH, and determine that the adaptive width value of sky areas is with this
2bH+1。
Wherein, the width b of the floor projectionHCalculation there are many, it is following to provide one of which, it is no longer superfluous herein
It states.
In step S203, to being projected in 2bHPixel value carries out summation operation in+1 width regions, and filters out maximum value
Region determines image K (x, y) corresponding to the maximum value region filtered out.
In this step, maximum value region:Wherein, bH+1≤t≤n-bH;It cuts
To maximum value area image save as K (x, y), size be m × (2bH+ 1) pixel.
Wherein, window width 2bH+ 1 and be odd number, t 2bHIt is any in+1 width.
Wherein, H (y ') is the accumu-late parameter after smothing filtering, it may be assumed that
The accumu-late parameter H (y) obtained to step S201 carries out smothing filtering, eliminates kurtosis present in image and unusual
Value, in which:
Wherein, y=σ+1, σ+2 ..., m- σ;
Its smooth effect becomes more smooth with the increase of filter width, generally setting σ=2, i.e. filter
Width is 2 σ+1, totally 5 pixels.
Further, since the size of input picture is different, and sky areas is shared in entire image in image
Ratio is also different, if large percentage shared by sky areas, HmaxHmShared ratio is smaller, can choose wider water
Flat projection width, it is on the contrary then smaller fixed value is selected to determine floor projection to adapt to the image of different sizes and sky areas
Adaptive width value be 2bH+ 1, calculation are as follows:
Hm=mean (H ' (y)), Hmax=max (H ' (y)), wherein HmFor the average value of H ' (y) sequence, mean is to ask flat
Equal operation, HmaxIt is the maximum value of H ' (y) sequence, max is maximizing operation.
The image of different size and different sky areas can be preferably handled by this method.
Fig. 3 show it is provided by the invention to the maximum value area image K (x, y) carry out upright projection, and obtain hang down
The implementation flow chart of the maximum value area image R (x, y) of movie queen is delivered directly, specifically include the following steps:
In step S301, upright projection is carried out to maximum value area image K (x, y), obtains a line all pixels point
The accumu-late parameter V (x) of gray value.
Wherein, 1≤y≤m.
In step s 302, the width b of upright projection is calculatedV, and determine that the adaptive width value of sky areas is with this
2bV+1。
The calculation is identical in the manner described above, and details are not described herein.
In step S303, to being projected in 2bVPixel value carries out summation operation in+1 width regions, and filters out maximum value
Region determines image R (x, y) corresponding to the maximum value region filtered out.
The maximum value region:Wherein, bV+1≤t≤n-bV;
Wherein, the size of image R (x, y) is (2bV+1)×(2bH+1)。
In embodiments of the present invention, after being projected to image, need to calculate data in certain area and, it is adjacent
There are polyisomenisms in region, in order to improve computational accuracy, the accelerating algorithm that can be summed using displacement, specifically:
Assuming that ordered series of numbers i (x), 1≤x≤n, peak width is (2b+1), the then summation in region are as follows:
B+1≤t≤n-b, t are transmissivity;
Due to adjacent area Sum (t) and Sum (t-1) exist { i (t-b+1), i (t-b+2) ..., i (t+b-1) } total 2b-
Therefore 1 repetition point can be calculated directly using front region, it may be assumed that
Sum (t)=Sum (t-1)-i (t-b)+i (t+b);
By the acceleration, 2b+1 summation operation can be reduced to 3 operations, substantially increase arithmetic speed.
Fig. 4 is the structural block diagram of the extraction system of air light value in haze image provided by the invention, for ease of description,
Part related to the embodiment of the present invention is only gived in figure.
Any pixel triple channel in the image I (x, y) of 11 pairs of mini-value filtering module inputs carries out mini-value filtering, obtains
To mini-value filtering image M (x, y);First maximum value area image obtains module 12 to the mini-value filtering image M got
(x, y) carries out floor projection, and obtains the maximum value area image K (x, y) after floor projection;Second maximum value area image obtains
Modulus block 13 carries out upright projection to the maximum value area image K (x, y), and obtains the maximum value administrative division map after upright projection
As R (x, y);Air light value determining module 14 extracts the pixel value in maximum value area image R (x, y), chooses fixed quantity
The average value of pixel value is as air light value A.
Wherein, the first maximum value area image obtains module 12 and specifically includes:
Floor projection module 15 carries out floor projection to the mini-value filtering image M (x, y) got, and it is all to obtain a column
The accumu-late parameter H (y) of the gray value of pixel;
The width b of the calculating floor projection of floor projection width computing module 16H, and the adaptive of sky areas is determined with this
Width value is 2bH+1;
First image determining module 17 is to being projected in 2bHPixel value carries out summation operation in+1 width regions, and filters out
Maximum value region determines image K (x, y) corresponding to the maximum value region filtered out.
In this embodiment, the first smothing filtering module 18 carries out smothing filtering to accumu-late parameter H (y), eliminates in image
Existing kurtosis and singular value.
In embodiments of the present invention, the second maximum value area image obtains module 13 and specifically includes:
Upright projection module 19 carries out upright projection to maximum value area image K (x, y), obtains a line all pixels point
The accumu-late parameter V (x) of gray value;
The width b of the calculating upright projection of upright projection width computing module 20V, and the adaptive of sky areas is determined with this
Width value is 2bV+1;
Second image determining module 21 is to being projected in 2bVPixel value carries out summation operation in+1 width regions, and filters out
Maximum value region determines image R (x, y) corresponding to the maximum value region filtered out.
Wherein, the second smothing filtering module 22 carries out smothing filtering to accumu-late parameter V (x), eliminates point present in image
Peak value and singular value
Wherein, the specific implementation of above-mentioned modules is as recorded in above method embodiment, and details are not described herein.
In embodiments of the present invention, mini-value filtering is carried out to any pixel triple channel in the image I (x, y) of input,
Obtain mini-value filtering image M (x, y);Floor projection is carried out to the mini-value filtering image M (x, y) got, and obtains water
Maximum value area image K (x, y) after flat projection;Upright projection is carried out to the maximum value area image K (x, y), and is obtained
Maximum value area image R (x, y) after upright projection;The pixel value in maximum value area image R (x, y) is extracted, chooses and fixes
The average value of the pixel value of quantity realizes the quick calculating to air light value as air light value A, adapts to different size and sky
The image in region provides condition for the processing of haze image Quick demisting.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (8)
1. the extracting method of air light value in a kind of haze image, which is characterized in that the method includes the following steps:
To in the image I (x, y) of input any pixel triple channel carry out mini-value filtering, obtain mini-value filtering image M (x,
y);
Floor projection is carried out to the mini-value filtering image M (x, y) got, and obtains the maximum value administrative division map after floor projection
As K (x, y);
Upright projection is carried out to the maximum value area image K (x, y), and obtains the maximum value area image R after upright projection
(x,y);
The pixel value in maximum value area image R (x, y) is extracted, chooses the average value of the pixel value of fixed quantity as atmosphere light
Value A;
The described couple of mini-value filtering image M (x, y) got carries out floor projection, and obtains the maximum value area after floor projection
The step of area image K (x, y) specifically include the following steps:
Floor projection is carried out to the mini-value filtering image M (x, y) got, obtains the tired of the gray value of a column all pixels point
Add parameter H (y);
Calculate the width b of floor projectionH, and determine the adaptive width value of sky areas for 2b with thisH+1;
To being projected in 2bHPixel value carries out summation operation in+1 width regions, and filters out maximum value region, what determination filtered out
Image K (x, y) corresponding to maximum value region.
2. the extracting method of air light value in haze image according to claim 1, which is characterized in that described pair gets
Mini-value filtering image M (x, y) carry out floor projection, obtain the accumu-late parameter H (y) of the gray value of a column all pixels point
After step, the width b for calculating floor projectionHThe step of before further include following step:
Smothing filtering is carried out to accumu-late parameter H (y), eliminates kurtosis and singular value present in image.
3. the extracting method of air light value in haze image according to claim 1, which is characterized in that it is described to it is described most
Big value area image K (x, y) carries out upright projection, and the step of obtaining maximum value area image R (x, y) after upright projection has
Body includes the following steps:
Upright projection is carried out to maximum value area image K (x, y), obtains the accumu-late parameter V of the gray value of a line all pixels point
(x);
Calculate the width b of upright projectionV, and determine the adaptive width value of sky areas for 2b with thisV+1;
To being projected in 2bVPixel value carries out summation operation in+1 width regions, and filters out maximum value region, what determination filtered out
Image R (x, y) corresponding to maximum value region.
4. the extracting method of air light value in haze image according to claim 3, which is characterized in that described to maximum value
Area image K (x, y) carry out upright projection, obtain a line all pixels point gray value accumu-late parameter V (x) the step of it
Afterwards, the width b for calculating upright projectionVThe step of before further include following step:
Smothing filtering is carried out to accumu-late parameter V (x), eliminates kurtosis and singular value present in image.
5. the extraction system of air light value in a kind of haze image, which is characterized in that the system comprises:
Mini-value filtering module carries out mini-value filtering for any pixel triple channel in the image I (x, y) to input, obtains
To mini-value filtering image M (x, y);
First maximum value area image obtains module, for carrying out horizontal throwing to the mini-value filtering image M (x, y) got
Shadow, and obtain the maximum value area image K (x, y) after floor projection;
Second maximum value area image obtains module, for carrying out upright projection to the maximum value area image K (x, y), and
Maximum value area image R (x, y) after obtaining upright projection;
Air light value determining module chooses the picture of fixed quantity for extracting the pixel value in maximum value area image R (x, y)
The average value of element value is as air light value A;
The first maximum value area image obtains module and specifically includes:
It is all to obtain a column for carrying out floor projection to the mini-value filtering image M (x, y) got for floor projection module
The accumu-late parameter H (y) of the gray value of pixel;
Floor projection width computing module, for calculating the width b of floor projectionH, and determine with this adaptive width of sky areas
Angle value is 2bH+1;
First image determining module, for being projected in 2bHPixel value carries out summation operation in+1 width regions, and filters out most
Big value region, determines image K (x, y) corresponding to the maximum value region filtered out.
6. the extraction system of air light value in haze image according to claim 5, which is characterized in that the system is also wrapped
It includes:
First smothing filtering module, for accumu-late parameter H (y) carry out smothing filtering, eliminate image present in kurtosis and
Singular value.
7. the extraction system of air light value in haze image according to claim 5, which is characterized in that described second is maximum
Value area image obtains module and specifically includes:
Upright projection module obtains a line all pixels point for carrying out upright projection to maximum value area image K (x, y)
The accumu-late parameter V (x) of gray value;
Upright projection width computing module, for calculating the width b of upright projectionV, and determine with this adaptive width of sky areas
Angle value is 2bV+1;
Second image determining module, for being projected in 2bVPixel value carries out summation operation in+1 width regions, and filters out most
Big value region, determines image R (x, y) corresponding to the maximum value region filtered out.
8. the extraction system of air light value in haze image according to claim 7, which is characterized in that the system is also wrapped
It includes:
Second smothing filtering module, for accumu-late parameter V (x) carry out smothing filtering, eliminate image present in kurtosis and
Singular value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610761884.1A CN106355560B (en) | 2016-08-30 | 2016-08-30 | The extracting method and system of air light value in a kind of haze image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610761884.1A CN106355560B (en) | 2016-08-30 | 2016-08-30 | The extracting method and system of air light value in a kind of haze image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106355560A CN106355560A (en) | 2017-01-25 |
CN106355560B true CN106355560B (en) | 2019-03-01 |
Family
ID=57856043
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610761884.1A Active CN106355560B (en) | 2016-08-30 | 2016-08-30 | The extracting method and system of air light value in a kind of haze image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106355560B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106934779B (en) * | 2017-03-14 | 2020-12-01 | 潍坊学院 | Atmospheric light value calculation method and system in image defogging process |
CN106934836B (en) * | 2017-03-14 | 2020-12-01 | 潍坊学院 | Atmospheric light value calculation method and system based on automatic clustering of haze images |
CN108681990B (en) * | 2018-04-04 | 2022-05-24 | 高明合 | Real-time haze early warning method and system |
CN108877231A (en) * | 2018-07-07 | 2018-11-23 | 程子涵 | A kind of vehicle vehicle interconnected method and system based on vehicle start-stop prompting |
CN111696031A (en) * | 2020-06-15 | 2020-09-22 | 北京浦泰锐迅技术有限公司 | Image processing method and system suitable for landscape electronic telescope |
CN117078562B (en) * | 2023-10-16 | 2023-12-26 | 四川中科友成科技有限公司 | Video image defogging method, device, computer equipment and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101527046A (en) * | 2009-04-28 | 2009-09-09 | 青岛海信数字多媒体技术国家重点实验室有限公司 | Motion detection method, device and system |
CN102289791A (en) * | 2011-06-29 | 2011-12-21 | 清华大学 | Method for quickly demisting single image |
CN103198459A (en) * | 2013-04-10 | 2013-07-10 | 成都国腾电子技术股份有限公司 | Haze image rapid haze removal method |
JP2013141209A (en) * | 2011-12-30 | 2013-07-18 | Hitachi Ltd | Image fog removal device and image fog removal method |
CN103903234A (en) * | 2014-03-12 | 2014-07-02 | 南京第五十五所技术开发有限公司 | Real-time image defogging method based on image field depth |
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 |
-
2016
- 2016-08-30 CN CN201610761884.1A patent/CN106355560B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101527046A (en) * | 2009-04-28 | 2009-09-09 | 青岛海信数字多媒体技术国家重点实验室有限公司 | Motion detection method, device and system |
CN102289791A (en) * | 2011-06-29 | 2011-12-21 | 清华大学 | Method for quickly demisting single image |
JP2013141209A (en) * | 2011-12-30 | 2013-07-18 | Hitachi Ltd | Image fog removal device and image fog removal method |
CN103198459A (en) * | 2013-04-10 | 2013-07-10 | 成都国腾电子技术股份有限公司 | Haze image rapid haze removal method |
CN103903234A (en) * | 2014-03-12 | 2014-07-02 | 南京第五十五所技术开发有限公司 | Real-time image defogging method based on image field depth |
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 |
Non-Patent Citations (2)
Title |
---|
Image Dehazing Algorithm Based on Atmosphere Scatters Approximation Model;Zhongyi Hu等;《ICONIP 2012》;20121231;全文 |
无人机侦察图像快速去雾算法;陆士猛等;《红外技术》;20151031;第37卷(第10期);全文 |
Also Published As
Publication number | Publication date |
---|---|
CN106355560A (en) | 2017-01-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106355560B (en) | The extracting method and system of air light value in a kind of haze image | |
CN102411774B (en) | Processing method, device and system based on single-image defogging | |
CN103955905B (en) | Based on the single image to the fog method that fast wavelet transform and weighted image merge | |
CN102831591B (en) | Gaussian filter-based real-time defogging method for single image | |
CN110148095A (en) | A kind of underwater picture Enhancement Method and enhancement device | |
CN102750674B (en) | Video image defogging method based on self-adapting allowance | |
CN103218778B (en) | The disposal route of a kind of image and video and device | |
CN105913390B (en) | A kind of image defogging method and system | |
CN105023256B (en) | A kind of image defogging method and system | |
CN107767354A (en) | A kind of image defogging algorithm based on dark primary priori | |
CN110544213B (en) | Image defogging method based on global and local feature fusion | |
CN103426151B (en) | A kind of image defogging method and device | |
CN105046658B (en) | A kind of low-light (level) image processing method and device | |
CN103049888A (en) | Image/video demisting method based on combination of dark primary color of atmospheric scattered light | |
CN106462947A (en) | Haze removal device and image generation method | |
CN104574419B (en) | Lens distortion parameter calibration method and system | |
CN106157270A (en) | A kind of single image rapid defogging method and system | |
CN106780380A (en) | A kind of image defogging method and system | |
CN105976337A (en) | Image defogging method based on filtering guiding via medians | |
CN110689490A (en) | Underwater image restoration method based on texture color features and optimized transmittance | |
CN111462022B (en) | Underwater image sharpness enhancement method | |
CN107194877A (en) | A kind of guarantor side interpolation super-resolution computational methods based on single image | |
CN103778605A (en) | Greasy weather image enhancement method | |
CN111192213B (en) | Image defogging self-adaptive parameter calculation method, image defogging method and system | |
CN103226816A (en) | Haze image medium transmission rate estimation and optimization method based on quick gaussian filtering |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |