CN110827218A - Airborne image defogging method based on image HSV transmissivity weighted correction - Google Patents
Airborne image defogging method based on image HSV transmissivity weighted correction Download PDFInfo
- Publication number
- CN110827218A CN110827218A CN201911051491.1A CN201911051491A CN110827218A CN 110827218 A CN110827218 A CN 110827218A CN 201911051491 A CN201911051491 A CN 201911051491A CN 110827218 A CN110827218 A CN 110827218A
- Authority
- CN
- China
- Prior art keywords
- image
- fog
- airborne
- atmospheric
- transmittance
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012937 correction Methods 0.000 title claims abstract description 11
- 238000002834 transmittance Methods 0.000 claims abstract description 39
- ZXQYGBMAQZUVMI-QQDHXZELSA-N [cyano-(3-phenoxyphenyl)methyl] (1r,3r)-3-[(z)-2-chloro-3,3,3-trifluoroprop-1-enyl]-2,2-dimethylcyclopropane-1-carboxylate Chemical compound CC1(C)[C@@H](\C=C(/Cl)C(F)(F)F)[C@H]1C(=O)OC(C#N)C1=CC=CC(OC=2C=CC=CC=2)=C1 ZXQYGBMAQZUVMI-QQDHXZELSA-N 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 239000004576 sand Substances 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 239000002245 particle Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 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
-
- 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
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an airborne image defogging method based on image HSV (hue, saturation, value) transmissivity weighting correction, which is used for solving the technical problem of poor definition of the existing airborne image defogging method. Firstly, establishing an atmospheric scattering physical model; establishing a dark channel prior model; then estimating an atmospheric light value; calculating the weighted transmittance according to the image HSV model; and finally, according to the local atmospheric light value and the rough transmissivity, carrying out defogging operation on the input image until an expected fog-free image is obtained. The method corrects the relevant parameters of the atmospheric model according to the fog-containing grade, has higher adaptability and flexibility, and ensures that the image structure restored by defogging treatment is clearer, the details are richer and the color is more real.
Description
Technical Field
The invention relates to an airborne image defogging method, in particular to an airborne image defogging method based on image HSV transmissivity weighted correction.
Background
In the unmanned aerial vehicle earth observation technology, clear image data needs to be shot on the ground interested region by utilizing an airborne image. At present, in the reconnaissance of an unmanned aerial vehicle to the ground, airborne image acquisition equipment is required to be utilized to acquire clear image data of a ground interested target. Due to the influence of aerial cloud and fog, the visibility of the atmosphere is reduced due to the cloud and fog, scene images are degraded, the content of images shot in the foggy days is fuzzy, the contrast is reduced, the quality of airborne images acquired and processed by an unmanned aerial vehicle is degraded, and an unmanned aerial vehicle airborne image defogging method with a good defogging effect needs to be researched. On the other hand, due to the development of image processing, in order to ensure that the vision system works normally all day long, the system must adapt to various weather conditions, and the image contrast and color in fog days are degraded, so that the onboard systems cannot work normally. Therefore, due to the influence of factors such as aerial haze, the quality of the image acquired by the acquisition equipment can be degraded, and the ground observation effect of the unmanned aerial vehicle is seriously influenced. In recent years, algorithms are mostly adopted for research on video defogging processing, and defogging methods can be classified into image processing and atmospheric scattering model-based methods.
Document 1 He K M, Sun J, Tang X o, single image size removal using dark channel prior ieee Transactions on Pattern Analysis and Machine Analysis, 2011,33(12): 2341-.
Document 2 liujiping, yanghuang, weigang, single image fast defogging algorithm combined with dark channel prior [ J ], university of south china academic press (nature science edition), 2018,46(3):86-91 ] adopts single image fast defogging algorithm combined with dark channel prior, and has the characteristics of good defogging flexibility and adaptability.
Document 3 "marrongye, wangsite, liuwei, et al," defogging algorithm combining fractional order differential and dark channel prior and Retinex, "proceedings of south china university of technology (nature science edition), 2016,44(9):16-23," defogging algorithm combining fractional order differential and dark channel prior and Retinex, combines Retinex algorithm with a propagation map of a haze image, and then performs gaussian filtering using a scale related to the depth of field in different regions of the image based on the difference in depth of field.
Disclosure of Invention
In order to overcome the defect of poor definition of the existing airborne image defogging method, the invention provides an airborne image defogging method based on image HSV transmissivity weighting correction. Firstly, establishing an atmospheric scattering physical model; establishing a dark channel prior model; then estimating an atmospheric light value; calculating the weighted transmittance according to the image HSV model; and finally, according to the local atmospheric light value and the rough transmissivity, carrying out defogging operation on the input image until an expected fog-free image is obtained. The method corrects the relevant parameters of the atmospheric model according to the fog-containing grade, has higher adaptability and flexibility, and ensures that the image structure restored by defogging treatment is clearer, the details are richer and the color is more real.
The technical scheme adopted by the invention for solving the technical problems is as follows: an airborne image defogging method based on image HSV transmissivity weighting correction is characterized by comprising the following steps:
step one, establishing an atmospheric scattering physical model
Obtaining an original airborne fog-containing image I (x), and establishing an atmospheric scattering physical model for the original airborne fog-containing image:
I(x)＝t(x)J(x)+A(1-t(x)) (1)
in the formula, x represents the position of a pixel point of an airborne image, i (x) represents an airborne fog-containing image, j (x) represents an image after the airborne defogging treatment, a represents an atmospheric light value, t (x) represents a transmittance, t (x) j (x) represents a direct attenuation term, and a (1-t (x)) represents an atmospheric light intensity.
And step two, establishing a dark channel prior model.
If a mathematical definition is given to the dark channel, from the knowledge of the atmospheric light intensity a and transmittance t (x), for any airborne fogging image j (x), the airborne defogging image dark channel is represented by equation (2):
the pixel points in the image and the RGB three channels thereof have very low brightness values and are close to 0, and the points are called image dark channels.
In the formula, Ω (x) represents a square region centered on x, IcRepresenting one color channel of the fog-containing image.
When the atmospheric light value a is estimated, the atmospheric light value is estimated from the dark primary color information. Firstly, searching pixel points 1% of the brightness in the dark primary color image, then corresponding the pixel points to the foggy image, and searching out the maximum brightness value as an atmospheric light value A.
And step three, estimating an atmospheric light value.
After the atmospheric light value A is estimated, the atmospheric scattering physical model formula (1) is transformed into:
assuming that the transmittance is a constant, denoted as t (x), two minimum operations are performed on the two sides to obtain:
combining an atmospheric model and a dark channel prior theory to obtain a coarse step estimation value of the transmissivity:
wherein, IcOne color channel representing the fog-containing image, AcRepresenting the entirety of one color channel of a fog-containing imageLocal atmospheric light intensity. Considering that the airborne image has some granular sense, the image is not real after defogging, and the image depth sense is lost. Thus introducing a constant ω (0 < ω < 1), the corrected transmission is as follows:
atmospheric light A in equation (7) when transmittance is estimated using a dark channel pre-test algorithmcTaking the atmospheric light mean value of RGB channel, namely A ═ mean (A)c)，c∈{r,g,b}。
And step four, calculating the weighted transmittance according to the image HSV model.
Firstly, the average values of the hue, saturation and lightness components of the computer-mounted image are respectively as follows:
wherein Sum (H), Sum (S) and Sum (V) are the sum of hue component H, saturation component S and lightness component V of all pixel points in the image, respectively, N1、N2、N3The number of pixels, Ave, whose component values are not 0H，AveSAnd AveVRespectively, the average value of each component in the image. According to experimental data analysis, the following fog-containing grade setting is adopted in combination with the defogging treatment requirement of the airborne image.
Haze-containing image level 1:
(AveH＜100)&&(AveS＜0.07)&&(AveV＜0.5) (11)
haze-containing image level 2:
(AveH＜125)&&(AveS＜0.2)&&(AveV＜0.48) (12)
secondly, the transmittance is adjusted according to the fog-containing image level obtained by the HSV component, the transmittance needs to be amplified in a region with the fog-containing image level of 1 in the specified region, the transmittance needs to be kept unchanged in a region with the fog-containing image level of 2, and the transmittance is redefined as follows:
in the formula, i (x) is a fog-containing degraded image, a is an atmospheric light value, and a threshold value M is defined as a comparison between the number p of pixel values in the fog-containing image, the contrast of which is greater than the contrast threshold value S of HSV components of the image, and the number n of total pixel points, that is: and M is p/n. And selecting a larger M value for the image with a smaller contrast area in the image, and selecting a smaller threshold M for the image with a larger contrast area in the image.
And step five, calculating the defogged image according to the atmospheric light value and the transmissivity.
After readjusting the transmittance, according to the formula
And calculating an image J (x) of the defogged fog image, wherein A is the atmospheric light value in the calculated atmospheric scattering model, t (x) is the refractive index of the defogged fog image after being corrected, and I (x) is the airborne fog image.
The invention has the beneficial effects that: firstly, establishing an atmospheric scattering physical model; establishing a dark channel prior model; then estimating an atmospheric light value; calculating the weighted transmittance according to the image HSV model; and finally, according to the local atmospheric light value and the rough transmissivity, carrying out defogging operation on the input image until an expected fog-free image is obtained. The method corrects the relevant parameters of the atmospheric model according to the fog-containing grade, has higher adaptability and flexibility, and ensures that the image structure restored by defogging treatment is clearer, the details are richer and the color is more real.
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Drawings
FIG. 1 is a flow chart of an on-board image defogging method based on image HSV transmittance weighted correction according to the invention.
FIG. 2 is a graph comparing the effect of airborne fogging images before and after defogging. Wherein, fig. 2(a) is an original image of level 1 including a fog image; FIG. 2(b) is the image of FIG. 2(a) after defogging; FIG. 2(c) is a level 2 original image containing a fog image; fig. 2(d) is the image after defogging of fig. 2 (c).
Detailed Description
Reference is made to fig. 1-2. The airborne image defogging method based on the image HSV transmissivity weighted correction specifically comprises the following steps:
step one, establishing an atmospheric scattering physical model.
Obtaining an original airborne fog-containing image I (x), and establishing an atmospheric scattering physical model for the original airborne fog-containing image:
I(x)＝t(x)J(x)+A(1-t(x)) (1)
in the formula, x represents the position of a pixel point of an airborne image, i (x) represents an airborne fog-containing image, j (x) represents an image after the airborne defogging treatment, a represents an atmospheric light value, t (x) represents a transmittance, t (x) j (x) represents a direct attenuation term, and a (1-t (x)) represents an atmospheric light intensity. As can be seen from the formula (1), if the values of the atmospheric illumination intensity a and the transmittance t (x) can be obtained from the airborne fog image i (x), the corresponding fog-free clear image j (x) can be calculated. Therefore, the purpose of the on-board image defogging process is to recover an image J (x) from I (x), A and t (x), and the atmospheric light value A and the transmittance t (x) must be solved first.
And step two, establishing a dark channel prior model.
Given a mathematical definition of the dark channel, from the knowledge of the atmospheric light intensity a and transmittance t (x), for any airborne fogging image j (x), the airborne defogging image dark channel can be represented by the following equation:
the pixel points in the image and the RGB three channels thereof have very low brightness values and are close to 0, and the points are called image dark channels.
Wherein Ω (x) represents a square area centered on x, IcRepresenting one color channel of the fog-containing image.
When the atmospheric light value a is estimated, the atmospheric light value is estimated from the dark primary color information. Firstly, searching pixel points 1% of the brightness in the dark primary color image, then corresponding the pixel points to the foggy image, and searching out the maximum brightness value as an atmospheric light value A.
And step three, estimating an atmospheric light value.
After the atmospheric light value A is estimated, the atmospheric scattering physical model formula (1) is transformed into:
assuming that the transmittance is a constant, denoted as t (x), two minimum operations are performed on the two sides to obtain:
by combining an atmospheric model and a dark channel prior theory, the rough step estimation value of the transmissivity can be obtained as follows:
wherein IcOne color channel representing the fog-containing image, AcRepresenting the global atmospheric illumination intensity of one color channel of the fog-containing image. Considering that the airborne image has some granular sense, the image is not real after defogging, and the image depth sense is lost. Thus, a constant ω (0 < ω < 1), 0.95 is introduced in this example, correctedThe transmittance of (a) is as follows:
atmospheric light A in equation (7) when transmittance is estimated using a dark channel pre-test algorithmcTaking the atmospheric light mean value of RGB channel, namely A ═ mean (A)c),c∈{r,g,b}
And step four, calculating the weighted transmittance according to the image HSV model.
Firstly, the average values of the hue, saturation and lightness components of the computer-mounted image are respectively as follows:
wherein Sum (H), Sum (S) and Sum (V) are the sum of hue component H, saturation component S and lightness component V of all pixel points in the image, respectively, N1、N2、N3The number of pixels, Ave, whose component values are not 0H，AveSAnd AveVRespectively, the average value of each component in the image. According to experimental data analysis, the following fog-containing grade setting is adopted in combination with the defogging treatment requirement of the airborne image.
Haze-containing image level 1:
(AveH＜100)&&(AveS＜0.07)&&(AveV＜0.5) (11)
haze-containing image level 2:
(AveH＜125)&&(AveS＜0.2)&&(AveV＜0.48) (12)
secondly, the transmittance is adjusted according to the fog-containing image level obtained by the HSV component, the transmittance needs to be amplified in a region with the fog-containing image level of 1 in the specified region, the transmittance needs to be kept unchanged in a region with the fog-containing image level of 2, and the transmittance is redefined as follows:
in the formula, i (x) is a fog-containing degraded image, a is an atmospheric light value, and the threshold M is defined as a comparison between the number p of pixel values in the fog-containing image, the contrast of which is greater than the contrast threshold S of HSV components of the image (in this embodiment, S is 2), and the total number n of pixel points, that is: and M is p/n. The video obtained by the unmanned aerial vehicle through earth observation shows that the fog-containing image has poor contrast, the selected threshold value M should be different, a larger M value should be selected for an image with a smaller contrast area in the image, and a smaller threshold value M should be selected for an image with a larger area and a larger contrast area.
And step five, calculating the defogged image according to the atmospheric light value and the transmissivity.
After readjusting the transmittance, according to the formula
And calculating an image J (x) of the defogged fog image, wherein A is the atmospheric light value in the calculated atmospheric scattering model, t (x) is the refractive index of the defogged fog image after being corrected, and I (x) is the airborne fog image. Therefore, through the processing, the defogging processing of the airborne image can be completed, and the acquisition requirement of the airborne earth observation image is met.
The effects of the present invention will be further described with reference to fig. 1 and 2.
1. Experimental conditions.
The experimental environment is CPU Intel Core i7-3610QM @2.30GHz, the internal memory is 8GB, and the programming is carried out by MATLABR2014 b. The invention adopts the fog-containing image to carry out experimental test and comparison. Wherein FIGS. 2(a), 2(b), 2(c) and 2(d) are experimental results comparing two haze images before and after haze removal, respectively.
2. And (4) experimental contents.
The fog-containing images are processed by utilizing a defogging processing method respectively, the processing of the fog-containing images is completed, and the effect pairs of the images before and after defogging are respectively selected as shown in FIG. 2. As can be seen from FIG. 2, before defogging, the image is blurred due to the influence of haze, the layering sense is not strong, the contrast is low, and the details are basically unclear. The method is used for weighting the perspective ratio of the area, adopts contrast calculation and sets a threshold value, and selects a smaller threshold value for the image without sky or with a smaller sky area and selects a larger threshold value for the image with a large area of sky area. As seen from the results of the haze level 1 in fig. 2, the haze content is heavy, sufficient defogging processing is required, and the defogging method has good adaptability by using a correction method for reducing the transmittance adjustment probability for the non-sky area. From the results of fig. 2, the haze level 2 shows that the haze content is general, and the haze region transmittance is maintained unchanged, so that the image after the haze treatment is transited naturally and the details of the ground features can be clearly displayed. Therefore, the defogging algorithm realized by the invention can be used for processing the foggy image area, and can be used for pertinently solving the characteristic of non-sky areas in the unmanned aerial vehicle airborne acquired image, the image processed after defogging is transparent, and the image hierarchy and the details are good, which shows that the invention can better process the foggy image and meet the requirements of an airborne video defogging system.
In order to more objectively compare the defogging effect of the airborne image, three definition evaluation functions, namely a variance function, a square gradient function and a TenenGrad function, are selected to evaluate the defogging effect, the function value obtained through calculation is normalized, and the calculation result is shown in table 1.
TABLE 1 evaluation results of haze removal clarity
The observation shows that compared with the original image, the image processed by the method has the advantages that the three definition evaluation function values are improved, namely, the definition of the image after defogging is better improved, so that the defogging effect of the method is very obvious.
In a word, by adopting the method and the device, HSV component defogging grade parameter analysis is carried out on the airborne fog-containing image of the unmanned aerial vehicle, the transmissivity and relevant correction of the defogging method are determined, and the purposes of judging and processing the airborne image according to the fog-containing grade are achieved. The method for correcting the relevant parameters of the atmospheric model according to the fog-containing grade has high adaptability and flexibility, and the defogging effect can meet the requirements of an airborne defogging processing system, so that the problems of complex relevant defogging methods and general image defogging effect in the past are solved.
Claims (1)
1. An airborne image defogging method based on image HSV transmissivity weighting correction is characterized by comprising the following steps:
step one, establishing an atmospheric scattering physical model;
obtaining an original airborne fog-containing image I (x), and establishing an atmospheric scattering physical model for the original airborne fog-containing image:
I(x)＝t(x)J(x)+A(1-t(x)) (1)
in the formula, x represents the position of a pixel point of an airborne image, I (x) represents an airborne fog-containing image, J (x) represents an image after the airborne fog removal treatment, A represents an atmospheric light value, t (x) represents a transmittance, t (x) J (x) represents a direct attenuation term, and A (1-t (x)) represents atmospheric light intensity;
step two, establishing a dark channel prior model;
if a mathematical definition is given to the dark channel, from the knowledge of the atmospheric light intensity a and transmittance t (x), for any airborne fogging image j (x), the airborne defogging image dark channel is represented by equation (2):
the pixel points in the image and the RGB three channels thereof have very low brightness values and are close to 0, and the points are called as image dark channels;
in the formula, Ω (x) represents a square region centered on x, IcOne color channel representing a fog-containing image;
when the atmospheric light value A is estimated, the atmospheric light value is estimated according to the dark primary color information; firstly, searching pixel points which are 1% of the brightness in a dark primary color image, then corresponding the pixel points to a foggy image, and searching out a brightness maximum value as an atmospheric light value A;
estimating an atmospheric light value;
after the atmospheric light value A is estimated, the atmospheric scattering physical model formula (1) is transformed into:
assuming that the transmittance is a constant, denoted as t (x), two minimum operations are performed on the two sides to obtain:
combining an atmospheric model and a dark channel prior theory to obtain a coarse step estimation value of the transmissivity:
wherein, IcOne color channel representing the fog-containing image, AcRepresenting the global atmospheric illumination intensity of one color channel of the fog-containing image; considering that airborne images have particle feelings, the images are not real after defogging, and the image depth feeling is lost; thus introducing a constant ω (0 < ω < 1), the corrected transmission is as follows:
atmospheric light A in equation (7) when transmittance is estimated using a dark channel pre-test algorithmcTaking the atmospheric light mean value of RGB channel, namely A ═ mean (A)c)，c∈{r,g,b}；
Step four, calculating the weighted transmittance according to the HSV model;
firstly, the average values of the hue, saturation and lightness components of the computer-mounted image are respectively as follows:
wherein Sum (H), Sum (S) and Sum (V) are the sum of hue component H, saturation component S and lightness component V of all pixel points in the image, respectively, N1、N2、N3The number of pixels, Ave, whose component values are not 0H，AveSAnd AveVRespectively taking the average value of each component in the image; according to experimental data analysis, combining with the defogging treatment requirement of the airborne image, the following fogging grade setting is adopted;
haze-containing image level 1:
(AveH＜100)&&(AveS＜0.07)&&(AveV＜0.5) (11)
haze-containing image level 2:
(AveH＜125)&&(AveS＜0.2)&&(AveV＜0.48) (12)
secondly, the transmittance is adjusted according to the fog-containing image level obtained by the HSV component, the transmittance needs to be amplified in a region with the fog-containing image level of 1 in the specified region, the transmittance needs to be kept unchanged in a region with the fog-containing image level of 2, and the transmittance is redefined as follows:
in the formula, i (x) is a fog-containing degraded image, a is an atmospheric light value, and a threshold value M is defined as a comparison between the number p of pixel values in the fog-containing image, the contrast of which is greater than the contrast threshold value S of HSV components of the image, and the number n of total pixel points, that is: m is p/n; selecting a larger M value for an image with a smaller contrast area in the image, and selecting a smaller threshold M for an image with a large area with a larger contrast;
calculating a defogged image according to the atmospheric light value and the transmissivity;
after readjusting the transmittance, according to the formula
And calculating an image J (x) of the defogged fog image, wherein A is the atmospheric light value in the calculated atmospheric scattering model, t (x) is the refractive index of the defogged fog image after being corrected, and I (x) is the airborne fog image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911051491.1A CN110827218B (en) | 2019-10-31 | 2019-10-31 | Airborne image defogging method based on weighted correction of HSV (hue, saturation, value) transmissivity of image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911051491.1A CN110827218B (en) | 2019-10-31 | 2019-10-31 | Airborne image defogging method based on weighted correction of HSV (hue, saturation, value) transmissivity of image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110827218A true CN110827218A (en) | 2020-02-21 |
| CN110827218B CN110827218B (en) | 2023-08-29 |
Family
ID=69551622
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911051491.1A Active CN110827218B (en) | 2019-10-31 | 2019-10-31 | Airborne image defogging method based on weighted correction of HSV (hue, saturation, value) transmissivity of image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110827218B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861939A (en) * | 2020-07-30 | 2020-10-30 | 四川大学 | Single image defogging method based on unsupervised learning |
| CN112270220A (en) * | 2020-10-14 | 2021-01-26 | 西安工程大学 | Sewing gesture recognition method based on deep learning |
| CN112651925A (en) * | 2020-12-04 | 2021-04-13 | 合肥阳光智维科技有限公司 | Diagnosis method and device of photovoltaic module |
| CN112750089A (en) * | 2020-12-27 | 2021-05-04 | 同济大学 | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior |
| CN112927157A (en) * | 2021-03-08 | 2021-06-08 | 电子科技大学 | Improved dark channel defogging method using weighted least square filtering |
| CN116612050A (en) * | 2023-07-19 | 2023-08-18 | 国药新光医疗科技有限公司 | Priori defogging method based on dark channel |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150161769A1 (en) * | 2013-03-11 | 2015-06-11 | Industry Foundation Of Chonnam National University | System for improving foggy luminance image using fog reduction estimation model |
| 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 |
| US20170132771A1 (en) * | 2014-06-13 | 2017-05-11 | Board Of Regents Of The University Of Texas System | Systems and methods for automated hierarchical image representation and haze removal |
| CN107767354A (en) * | 2017-12-08 | 2018-03-06 | 福州大学 | A kind of image defogging algorithm based on dark primary priori |
| CN108765336A (en) * | 2018-05-25 | 2018-11-06 | 长安大学 | Image defogging method based on dark bright primary colors priori with auto-adaptive parameter optimization |
| CN109584186A (en) * | 2018-12-25 | 2019-04-05 | 西北工业大学 | A kind of unmanned aerial vehicle onboard image defogging method and device |
| CN109785262A (en) * | 2019-01-11 | 2019-05-21 | 闽江学院 | Image defogging method based on dark channel prior and adaptive histogram equalization |
-
2019
- 2019-10-31 CN CN201911051491.1A patent/CN110827218B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150161769A1 (en) * | 2013-03-11 | 2015-06-11 | Industry Foundation Of Chonnam National University | System for improving foggy luminance image using fog reduction estimation model |
| US20170132771A1 (en) * | 2014-06-13 | 2017-05-11 | Board Of Regents Of The University Of Texas System | Systems and methods for automated hierarchical image representation and haze removal |
| 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 |
| CN107767354A (en) * | 2017-12-08 | 2018-03-06 | 福州大学 | A kind of image defogging algorithm based on dark primary priori |
| CN108765336A (en) * | 2018-05-25 | 2018-11-06 | 长安大学 | Image defogging method based on dark bright primary colors priori with auto-adaptive parameter optimization |
| CN109584186A (en) * | 2018-12-25 | 2019-04-05 | 西北工业大学 | A kind of unmanned aerial vehicle onboard image defogging method and device |
| CN109785262A (en) * | 2019-01-11 | 2019-05-21 | 闽江学院 | Image defogging method based on dark channel prior and adaptive histogram equalization |
Non-Patent Citations (4)
| Title |
|---|
| KAIMING HE ET AL.: "Single Image Haze Removal Using Dark Channel Prior", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| TIANYU ZHANG ET AL.: "A Naturalness Preserved Fast Dehazing Algorithm Using HSV Color Space", 《IEEE ACCESS》 * |
| 刘安娜 等: "基于颜色空间的单幅图像去雾算法", 《现代电子技术》 * |
| 耿威: "基于视频图像的雾天能见度检测方法研究与实现", 《万方数据》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111861939A (en) * | 2020-07-30 | 2020-10-30 | 四川大学 | Single image defogging method based on unsupervised learning |
| CN112270220A (en) * | 2020-10-14 | 2021-01-26 | 西安工程大学 | Sewing gesture recognition method based on deep learning |
| CN112651925A (en) * | 2020-12-04 | 2021-04-13 | 合肥阳光智维科技有限公司 | Diagnosis method and device of photovoltaic module |
| CN112750089A (en) * | 2020-12-27 | 2021-05-04 | 同济大学 | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior |
| CN112750089B (en) * | 2020-12-27 | 2023-03-28 | 同济大学 | Optical remote sensing image defogging method based on local block maximum and minimum pixel prior |
| CN112927157A (en) * | 2021-03-08 | 2021-06-08 | 电子科技大学 | Improved dark channel defogging method using weighted least square filtering |
| CN112927157B (en) * | 2021-03-08 | 2023-08-15 | 电子科技大学 | Improved dark channel defogging method adopting weighted least square filtering |
| CN116612050A (en) * | 2023-07-19 | 2023-08-18 | 国药新光医疗科技有限公司 | Priori defogging method based on dark channel |
| CN116612050B (en) * | 2023-07-19 | 2023-10-31 | 国药新光医疗科技有限公司 | Priori defogging method based on dark channel |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110827218B (en) | 2023-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110827218B (en) | Airborne image defogging method based on weighted correction of HSV (hue, saturation, value) transmissivity of image | |
| Ju et al. | IDGCP: Image dehazing based on gamma correction prior | |
| Hu et al. | Single image defogging based on illumination decomposition for visual maritime surveillance | |
| CN106910175B (en) | Single image defogging algorithm based on deep learning | |
| Negru et al. | Exponential contrast restoration in fog conditions for driving assistance | |
| Huang et al. | An efficient visibility enhancement algorithm for road scenes captured by intelligent transportation systems | |
| Galdran et al. | Enhanced variational image dehazing | |
| EP2568438B1 (en) | Image defogging method and system | |
| CN103218778B (en) | The disposal route of a kind of image and video and device | |
| CN108734670B (en) | Method for restoring single night weak-illumination haze image | |
| Shiau et al. | Weighted haze removal method with halo prevention | |
| Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
| CN107798670A (en) | A kind of dark primary prior image defogging method using image wave filter | |
| Gao et al. | A novel UAV sensing image defogging method | |
| CN105701783A (en) | Single image defogging method based on ambient light model and apparatus thereof | |
| He et al. | Single image dehazing with white balance correction and image decomposition | |
| Halmaoui et al. | Contrast restoration of road images taken in foggy weather | |
| CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
| CN106023108A (en) | Image defogging algorithm based on boundary constraint and context regularization | |
| CN112365467A (en) | Foggy image visibility estimation method based on single image depth estimation | |
| Zhang et al. | Image dehazing based on dark channel prior and brightness enhancement for agricultural remote sensing images from consumer-grade cameras | |
| CN113436124A (en) | Single-image defogging method applied to marine foggy environment | |
| CN102646267A (en) | Degraded image restoration method and system | |
| Fu et al. | An anisotropic Gaussian filtering model for image de-hazing | |
| CN112419163A (en) | Single image weak supervision defogging method based on priori knowledge and deep learning |
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 |