CN104299192A - Single image defogging method based on atmosphere light scattering physical model - Google Patents
Single image defogging method based on atmosphere light scattering physical model Download PDFInfo
- Publication number
- CN104299192A CN104299192A CN201410508456.9A CN201410508456A CN104299192A CN 104299192 A CN104299192 A CN 104299192A CN 201410508456 A CN201410508456 A CN 201410508456A CN 104299192 A CN104299192 A CN 104299192A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- dark
- pixel
- mist
- 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
Landscapes
- Image Processing (AREA)
- Color Image Communication Systems (AREA)
Abstract
The invention discloses a single image defogging method based on an atmosphere light scattering physical model and relates to the field of image processing. The method mainly comprises the steps that (1) visible light images under a foggy scene are input, and a variance graph of an original foggy image is obtained; (2) the foggy image is subjected to two-time minimum value filtering, and a dark channel graph is obtained; (3) according to dark channel priori knowledge, the original foggy image and the dark channel graph are used, the variance graph is used as a criterion, and an atmosphere illumination value is obtained by solving; (4) the dark channel graph is used for solving a transmittivity graph; (5) mean filtering is carried out on the basis of the transmittivity graph, and an optimized transmittivity graph is obtained; and (6) according to the atmosphere light scattering physical model formed through the foggy image, the solved atmosphere illumination value and the optimized transmittivity graph are used, and the final non-fog image can be obtained. The effectiveness of atmosphere illumination value selecting is guaranteed, and defogging effect is improved.
Description
Technical field
The present invention relates to image procossing, particularly relate to the single image defogging method capable utilizing atmosphere light scattering physical model.
Background technology
In recent years along with the aggravation of environmental pollution makes the SO2 in air, oxides of nitrogen and pellet constantly increase, the above two are gaseous contaminant, wherein pellet is the key factor causing haze sky, and when they run into the greasy weather, sky can become dusky.When we take pictures under haze weather condition, the photo taken degrades seriously, its main cause is that light that reflections off objects comes into view was subject to the scattering of a large amount of fine particle thing in air, refraction and reflection before entering camera lens, becomes disorderly and unsystematic.Therefore, photo comparison's degree of acquisition reduces, and color definition is low, and picture lost a large amount of details, is especially in the object in Vistavision, and the information that obtains from photo greatly reduces.
In actual applications as military technology, traffic, criminal investigation, meteorology and uranology field often need to extract from the video sequence of open air collection clearly characteristics of image for identify and coupling.Image mist elimination becomes a kind of very urgent and practical research topic.Image after mist elimination visually has more pleasing effect, obtains more information, and can be widely used in other field, if image after mist elimination is as the effective data input of computer vision field.How from the image of band mist, the color of Recovery image, contrast obtain image clearly and have important Research Significance and realistic meaning.
In recent years, the method for image mist elimination achieves certain effect, and wherein the image mist elimination research of physically based deformation model, is based on information such as scene depths mostly or utilizes the method for multiple image to realize mist elimination.Recently, marked improvement is achieved for single image mist elimination.But because single width has mist image to degrade by mist affects, it is less that the information that can be utilized in scene structure becomes, therefore single image mist elimination has more challenge.At the classical mist elimination algorithm of He Kaiming, use the method for soft stingy figure to cause the processing time greatly to increase, and dark channel prior knowledge has limitation, mist elimination effect can be caused undesirable.
Summary of the invention
The object of this invention is to provide a kind of fast, high, the details of clear picture, contrast and sharpness is enriched after mist elimination the single image defogging method capable based on atmosphere light scattering physical model.
For solving the problems of the technologies described above, the technical solution used in the present invention is: a kind of single image defogging method capable based on atmosphere light scattering physical model, is characterized in that, comprise the steps:
Step 1: input has the otherwise visible light color RGB image under mist scene, and calculate the gray variance figure of original mist image, method is as follows:
The mist image that has of definition input is three-channel rgb format image I (x), and in RGB cubic space, variance S is defined as
Wherein m be single pixel triple channel the average gray value of r, g, b}, its scope is (0,255), and S is the variance of single pixel, and k is scale-up factor; By asking S to pixel each in I (x), variogram S (x) of width original image I (x) can be obtained; Introduce scale-up factor λ, redefine
wherein
Step 2: to there being mist image to carry out twice mini-value filtering, obtain dark figure, method is as follows:
For any one input picture I (x), its dark figure I
darkx () is defined by formula as
wherein, the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel; Dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
it is a mini-value filtering device;
Step 3: according to dark channel prior knowledge, utilizes original mist image and dark figure, and using variogram as criterion, solve air illumination value, method is as follows:
Utilize variogram S proposed by the invention to carry out Threshold selection, introduce Δ as the threshold value chosen, threshold value Δ=36 in the present invention, if S≤Δ, then abandon these data; If S >=Δ, then this numerical value is effective, as the foundation weighing air illumination value;
Solving air illumination value is sorted by the order of successively decreasing by the brightness value of pixel in dark figure, determine that intensity level size is the position of pixel in dark channel image of front 0.1%, judge whether effectively, using the average intensity value of the pixel in the original mist image-region corresponding to effective data as air illumination value;
Step 4: utilize dark figure to solve transmissivity figure, method is as follows:
According to
w (0 < w≤1), obtains the transmissivity figure of input picture, wherein, and the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel, dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
a mini-value filtering device, A
cfor the component of c (c ∈ { r, g, the b}) passage of air illumination value, w is constant coefficient, and intermediate value of the present invention is 0.98;
Step 5: carry out mean filter on the basis of transmissivity figure, obtain and optimize transmissivity figure, method is as follows:
The transmissivity figure obtained in step 4 is carried out mean filter operation, and filtering size P (x) is 60 × 60;
Step 6: the atmosphere light scattering physical model formed according to mist image, utilizes and has solved the air illumination value that obtains and the transmissivity figure after optimizing, and can obtain final without mist image, method is as follows:
According to formula atmosphere light scattering physics model formation
for transmissivity figure t (x) after optimizing sets a lower limit t
0, intermediate value of the present invention is 0.1;
Described according to dark channel prior knowledge, utilize original mist image and dark figure, using variogram as criterion, solve air illumination value, it is characterized in that comprising dark channel prior knowledge, variogram as criterion, solve air illumination value;
Described dark channel prior knowledge, by analyzing a large amount of outdoor image without mist and summing up the rule that its statistical property draws: in the regional area of the non-sky of the overwhelming majority, the pixel that total existence is such, they have at least one Color Channel have intensity very low and close to 0 value, the minimum value of the light intensity in this region is a very little number, for any one input picture I (x), its dark figure I
darkx () is defined by formula as
wherein, the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel, if the I outdoor image without mist that is a width, except sky areas, the dark value of input picture is very little, substantially close to 0, that is: I
dark→ 0, be dark channel prior knowledge; If there is the pixel that a large amount of brightness is higher in dark figure, then these brightness should be from sky or fog, and the brightness of the denseer dark channel image of fog will be higher, can estimate transmissivity figure by dark figure, estimate the dense thin of mist with this;
Described variogram, as criterion, is characterized in that, the present invention utilizes the variogram proposed to carry out Threshold selection, introduce Δ as the threshold value chosen, threshold value Δ=36 in the present invention, if S≤Δ, then think that the brightest point comes from sky areas or white object, abandon this data; If S >=Δ, then this numerical value is effective, as the foundation weighing air illumination value;
Described solves air illumination value, it is characterized in that, definition air illumination value is A, in dark figure, the brightness value of each pixel is sorted by the order of successively decreasing, determine that intensity level size is the position of pixel in dark channel image of front 0.1%, the average intensity value of the pixel of front 0.1% maximal value in the original mist image-region then corresponding to these positions is as air illumination value, utilize variogram as criterion, if the position of selected point comes from sky areas or other white objects, i.e. S≤Δ, then abandon these data, if S>=Δ, then this numerical value is effective, can as the foundation weighing air illumination value, this operation is to triple channel { r, g, b} independently carries out, obtain A respectively
r, A
g, A
b,
The described dark figure that utilizes solves transmissivity figure, it is characterized in that, utilizes atmospheric scattering physical model, according to
w (0 < w≤1), obtains the transmissivity figure of input picture, wherein, and the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel, dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
a mini-value filtering device, A
cfor the component of c (c ∈ { r, g, the b}) passage of air illumination value, w is constant coefficient;
Mean filter is carried out on the basis of described transmissivity figure, obtain and optimize transmissivity figure, it is characterized in that, due to t (x) at an image block center not always constant, therefore estimate that a lot of blocking effects has appearred in the transmissivity figure obtained, cause mist elimination effect not ideal, mean filter operation has been carried out on the basis of guestimate transmissivity figure, and filtering size P (x) is determined by image size;
Described atmosphere light scattering physical model, it is characterized in that, be described at the optical model of the degraded image of greasy weather acquisition: I (x)=t (x) J (x)+(1-t (x)) A, wherein, I (x) represents the image collected, A is air illumination value, J (x) is the radiant illumination of scene, namely to obtain clearly without mist image, t (x) is transmissivity figure, be used for describing light and be transmitted to the part be not scattered in imaging device process by medium, the target of mist elimination be exactly from known observable have mist image I (x) obtain mist elimination image J (x) clearly.
The present invention compared with prior art, has following obvious advantage and beneficial effect:
Physically based deformation model realization mist elimination in the prior art mostly, instant invention overcomes dark channel prior knowledge inapplicable defect on white object in this process, ensure that and the validity that air illumination value is chosen improve mist elimination effect, is the useful supplement of prior art.
Accompanying drawing explanation
The implementing procedure schematic diagram of Fig. 1 embodiments of the invention;
The visible images having mist scene of Fig. 2 input;
Fig. 3 RGB color space figure;
The variogram of Fig. 4 input picture;
Fig. 5 input picture first time gets the dark figure that minimum value operates;
Fig. 6 input picture second time gets the dark figure of mini-value filtering operation;
The rough transmissivity figure that Fig. 7 obtains according to dark channel prior;
The optimization transmissivity figure that Fig. 8 obtains according to level and smooth mean filter;
The final mist elimination image that Fig. 9 obtains according to atmosphere light scattering physical model.
Embodiment
Below in conjunction with the drawings and specific embodiments, the present invention will be further described.
The implementation step of the single image defogging method capable of embodiment of the present invention physically based deformation model is as follows:
Step 1: input has the visible images under mist scene, obtains the variogram of original mist image;
The mist image that has of definition input is three-channel rgb format image I (x) (as shown in Figure 3), according to
R, g, b are image three channel intensity level, and wherein λ is constant coefficient, λ=17 in the present embodiment, and the variogram obtained as shown in Figure 4.
Step 2: to there being mist image to carry out twice mini-value filtering, obtains dark figure;
With certificate
wherein, I (x) is that a width has mist input picture, I
darkx () is the one piece square region of its dark figure, Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel.Dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
be a mini-value filtering device, the filtering taked is of a size of Ω (x)=15 × 15.First time gets the image after minimum value operation as shown in Figure 5, and second time gets the image after minimum value operation as shown in Figure 6.
Step 3: according to dark channel prior knowledge, utilizes original mist image and dark figure, using variogram as criterion, solves air illumination value;
In dark figure, the brightness value of each pixel is sorted by the order of successively decreasing, determine that intensity level size is the position of pixel in dark channel image of front 0.1%, then the average intensity value of the pixel of front 0.1% maximal value in the original mist image-region corresponding to these positions is as air illumination value.Utilize variogram as criterion, if the position of selected point comes from sky areas or other white objects, i.e. S≤Δ, then abandon these data, if S>=Δ, then we think that this numerical value is effective, can as the foundation weighing air illumination value, this operation is to triple channel { r, g, b} independently carries out, and obtains A respectively
r, A
g, A
b.
Step 4: utilize dark figure to solve transmissivity figure;
Utilize atmospherical scattering model, according to
w (0 < w≤1), obtains the transmissivity figure of input picture.Wherein,
for dark figure I
dark, the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel.Dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
be a mini-value filtering device, the filtering taked is of a size of Ω (x)=15 × 15.A
cfor the component of c (c ∈ { r, g, the b}) passage of air illumination value, w is constant coefficient, gets 0.95, and the rough transmissivity figure obtained as shown in Figure 7.
Step 5: carry out mean filter on the basis of transmissivity figure, obtains and optimizes transmissivity figure;
Mean filter operation has been carried out on the basis of guestimate transmissivity figure, and filtering size P (x) is determined by image size, usual filtering size P (x)=30 × 30, and the transmissivity figure after optimization as shown in Figure 8.
Step 6: the atmosphere light scattering physical model formed according to mist image, utilizes and has solved the air illumination value that obtains and the transmissivity figure after optimizing, and can obtain final without mist image.
According to
transmissivity when sky areas levels off to 0, and t (x) close to 0 time, directly restore the original image obtained and tend to comprise noise.Therefore, a lower limit t to be set for transmissivity figure t (x) after optimization
0, t in the implementation case
0get 0.1.Wherein, I (x) represents that the image that acquisition system collects, A are air illumination value, J (x) be obtain clearly without mist image, t (x) is transmissivity figure.Final mist elimination figure as shown in Figure 9.
Last it is noted that above example only in order to illustrate the present invention and and unrestricted technical scheme described in the invention; Therefore, although this instructions with reference to above-mentioned example to present invention has been detailed description, those of ordinary skill in the art should be appreciated that and still can modify to the present invention or equivalent to replace; And all do not depart from technical scheme and the improvement thereof of the spirit and scope of invention, it all should be encompassed in the middle of right of the present invention.
Claims (1)
1., based on a single image defogging method capable for atmosphere light scattering physical model, it is characterized in that, comprise the steps:
Step 1: input has the otherwise visible light color RGB image under mist scene, and calculate the gray variance figure of original mist image, method is as follows:
The mist image that has of definition input is three-channel rgb format image I (x), and in RGB cubic space, variance S is defined as
Wherein m be single pixel triple channel the average gray value of r, g, b}, its scope is (0,255), and S is the variance of single pixel, and k is scale-up factor; By asking S to pixel each in I (x), variogram S (x) of width original image I (x) can be obtained; Introduce scale-up factor λ, redefine
Wherein
Step 2: to there being mist image to carry out twice mini-value filtering, obtain dark figure, method is as follows:
For any one input picture I (x), its dark figure I
darkx () is defined by formula as
wherein, the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel; Dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
it is a mini-value filtering device;
Step 3: according to dark channel prior knowledge, utilizes original mist image and dark figure, and using variogram as criterion, solve air illumination value, method is as follows:
Utilize variogram S proposed by the invention to carry out Threshold selection, introduce Δ as the threshold value chosen, threshold value Δ=36 in the present invention, if S≤Δ, then abandon these data; If S >=Δ, then this numerical value is effective, as the foundation weighing air illumination value;
Solving air illumination value is sorted by the order of successively decreasing by the brightness value of pixel in dark figure, determine that intensity level size is the position of pixel in dark channel image of front 0.1%, judge whether effectively, using the average intensity value of the pixel in the original mist image-region corresponding to effective data as air illumination value;
Step 4: utilize dark figure to solve transmissivity figure, method is as follows:
According to
w (0 < w≤1), obtains the transmissivity figure of input picture, wherein, and the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel, dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
a mini-value filtering device, A
cfor the component of c (c ∈ { r, g, the b}) passage of air illumination value, w is constant coefficient, and intermediate value of the present invention is 0.98;
Step 5: carry out mean filter on the basis of transmissivity figure, obtain and optimize transmissivity figure, method is as follows:
The transmissivity figure obtained in step 4 is carried out mean filter operation, and filtering size P (x) is 60 × 60;
Step 6: the atmosphere light scattering physical model formed according to mist image, utilizes and has solved the air illumination value that obtains and the transmissivity figure after optimizing, and can obtain final without mist image, method is as follows:
According to formula atmosphere light scattering physics model formation
for transmissivity figure t (x) after optimizing sets a lower limit t
0, intermediate value of the present invention is 0.1;
Described according to dark channel prior knowledge, utilize original mist image and dark figure, using variogram as criterion, solve air illumination value, it is characterized in that comprising dark channel prior knowledge, variogram as criterion, solve air illumination value;
Described dark channel prior knowledge, by analyzing a large amount of outdoor image without mist and summing up the rule that its statistical property draws: in the regional area of the non-sky of the overwhelming majority, the pixel that total existence is such, they have at least one Color Channel have intensity very low and close to 0 value, the minimum value of the light intensity in this region is a very little number, for any one input picture I (x), its dark figure I
darkx () is defined by formula as
wherein, the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel, if the I outdoor image without mist that is a width, except sky areas, the dark value of input picture is very little, substantially close to 0, that is: I
dark→ 0, be dark channel prior knowledge; If there is the pixel that a large amount of brightness is higher in dark figure, then these brightness should be from sky or fog, and the brightness of the denseer dark channel image of fog will be higher, can estimate transmissivity figure by dark figure, estimate the dense thin of mist with this;
Described variogram, as criterion, is characterized in that, the present invention utilizes the variogram proposed to carry out Threshold selection, introduce Δ as the threshold value chosen, threshold value Δ=36 in the present invention, if S≤Δ, then think that the brightest point comes from sky areas or white object, abandon this data; If S >=Δ, then this numerical value is effective, as the foundation weighing air illumination value;
Described solves air illumination value, it is characterized in that, definition air illumination value is A, in dark figure, the brightness value of each pixel is sorted by the order of successively decreasing, determine that intensity level size is the position of pixel in dark channel image of front 0.1%, the average intensity value of the pixel of front 0.1% maximal value in the original mist image-region then corresponding to these positions is as air illumination value, utilize variogram as criterion, if the position of selected point comes from sky areas or other white objects, i.e. S≤Δ, then abandon these data, if S>=Δ, then this numerical value is effective, can as the foundation weighing air illumination value, this operation is to triple channel { r, g, b} independently carries out, obtain A respectively
r, A
g, A
b,
The described dark figure that utilizes solves transmissivity figure, it is characterized in that, utilizes atmospheric scattering physical model, according to
w (0 < w≤1), obtains the transmissivity figure of input picture, wherein, and the one piece square region of Ω (x) representative centered by pixel x; I
cthe numerical value of representing input images I (x) in c (c ∈ { r, g, b}) Color Channel, dark channel image is that input picture is got minimum operation through twice and obtained,
be for each pixel three passages get minimum value wherein in r, g, b},
a mini-value filtering device, A
cfor the component of c (c ∈ { r, g, the b}) passage of air illumination value, w is constant coefficient;
Mean filter is carried out on the basis of described transmissivity figure, obtain and optimize transmissivity figure, it is characterized in that, due to t (x) at an image block center not always constant, therefore estimate that a lot of blocking effects has appearred in the transmissivity figure obtained, cause mist elimination effect not ideal, mean filter operation has been carried out on the basis of guestimate transmissivity figure, and filtering size P (x) is determined by image size;
Described atmosphere light scattering physical model, it is characterized in that, be described at the optical model of the degraded image of greasy weather acquisition: I (x)=t (x) J (x)+(1-t (x)) A, wherein, I (x) represents the image collected, A is air illumination value, J (x) is the radiant illumination of scene, namely to obtain clearly without mist image, t (x) is transmissivity figure, be used for describing light and be transmitted to the part be not scattered in imaging device process by medium, the target of mist elimination be exactly from known observable have mist image I (x) obtain mist elimination image J (x) clearly.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410508456.9A CN104299192B (en) | 2014-09-28 | 2014-09-28 | A kind of single image to the fog method based on atmospheric light scattering physical model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410508456.9A CN104299192B (en) | 2014-09-28 | 2014-09-28 | A kind of single image to the fog method based on atmospheric light scattering physical model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN104299192A true CN104299192A (en) | 2015-01-21 |
CN104299192B CN104299192B (en) | 2017-03-29 |
Family
ID=52318913
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410508456.9A Active CN104299192B (en) | 2014-09-28 | 2014-09-28 | A kind of single image to the fog method based on atmospheric light scattering physical model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104299192B (en) |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105488769A (en) * | 2015-12-08 | 2016-04-13 | 中国航空工业集团公司西安航空计算技术研究所 | Real time video defogging method |
CN105512623A (en) * | 2015-12-02 | 2016-04-20 | 吉林大学 | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors |
CN105608683A (en) * | 2016-03-11 | 2016-05-25 | 北京理工大学 | Defogging method of single image |
CN105741246A (en) * | 2016-01-29 | 2016-07-06 | 南京航空航天大学 | Method for eliminating influence on optical picture by dust and mist |
CN106846259A (en) * | 2016-12-15 | 2017-06-13 | 上海交通大学 | A kind of the real-time of laparoscopic surgery video frame rate self adaptation goes smog method |
CN108765302A (en) * | 2018-03-29 | 2018-11-06 | 西安电子科技大学 | The real-time defogging method of image based on GPU |
CN109919859A (en) * | 2019-01-25 | 2019-06-21 | 暨南大学 | A kind of Outdoor Scene image defogging Enhancement Method calculates equipment and its storage medium |
CN110910319A (en) * | 2019-10-30 | 2020-03-24 | 中国医学科学院北京协和医院 | Operation video real-time defogging enhancement method based on atmospheric scattering model |
CN111192210A (en) * | 2019-12-23 | 2020-05-22 | 杭州当虹科技股份有限公司 | Self-adaptive enhanced video defogging method |
CN111489302A (en) * | 2020-03-27 | 2020-08-04 | 武汉理工大学 | Maritime image enhancement method in fog environment |
CN111738938A (en) * | 2020-06-01 | 2020-10-02 | 余姚市浙江大学机器人研究中心 | Nonuniform atomization video optimization method based on prior target identification |
CN111754433A (en) * | 2020-06-22 | 2020-10-09 | 哈尔滨理工大学 | Aerial image defogging method |
CN112529802A (en) * | 2020-12-09 | 2021-03-19 | 电子科技大学 | Atmospheric scattering degraded image recovery method based on scattering coefficient ratio estimation |
CN113298732A (en) * | 2021-06-08 | 2021-08-24 | 北京联合大学 | Image defogging method and system based on regional similarity |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110211758A1 (en) * | 2010-03-01 | 2011-09-01 | Microsoft Corporation | Multi-image sharpening and denoising using lucky imaging |
CN102289791A (en) * | 2011-06-29 | 2011-12-21 | 清华大学 | Method for quickly demisting single image |
CN102411774A (en) * | 2011-08-08 | 2012-04-11 | 安防科技(中国)有限公司 | Processing method, device and system based on single-image defogging |
CN102930514A (en) * | 2012-09-27 | 2013-02-13 | 西安电子科技大学 | Rapid image defogging method based on atmospheric physical scattering model |
-
2014
- 2014-09-28 CN CN201410508456.9A patent/CN104299192B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110211758A1 (en) * | 2010-03-01 | 2011-09-01 | Microsoft Corporation | Multi-image sharpening and denoising using lucky imaging |
CN102289791A (en) * | 2011-06-29 | 2011-12-21 | 清华大学 | Method for quickly demisting single image |
CN102411774A (en) * | 2011-08-08 | 2012-04-11 | 安防科技(中国)有限公司 | Processing method, device and system based on single-image defogging |
CN102930514A (en) * | 2012-09-27 | 2013-02-13 | 西安电子科技大学 | Rapid image defogging method based on atmospheric physical scattering model |
Non-Patent Citations (2)
Title |
---|
KAIMING HE ET AL.: "single image haze removal using dark channel prior", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
崔冰琪 等: "基于暗通道先验图像去雾的方法改进", 《信息通信》 * |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105512623A (en) * | 2015-12-02 | 2016-04-20 | 吉林大学 | Foggy-day driving visual enhancement and visibility early warning system and method based on multiple sensors |
CN105512623B (en) * | 2015-12-02 | 2018-09-14 | 吉林大学 | Based on multisensor travelling in fog day vision enhancement and visibility early warning system and method |
CN105488769B (en) * | 2015-12-08 | 2019-02-19 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of real-time video defogging method |
CN105488769A (en) * | 2015-12-08 | 2016-04-13 | 中国航空工业集团公司西安航空计算技术研究所 | Real time video defogging method |
CN105741246A (en) * | 2016-01-29 | 2016-07-06 | 南京航空航天大学 | Method for eliminating influence on optical picture by dust and mist |
CN105608683A (en) * | 2016-03-11 | 2016-05-25 | 北京理工大学 | Defogging method of single image |
CN106846259A (en) * | 2016-12-15 | 2017-06-13 | 上海交通大学 | A kind of the real-time of laparoscopic surgery video frame rate self adaptation goes smog method |
CN108765302B (en) * | 2018-03-29 | 2022-07-22 | 西安电子科技大学 | Image real-time defogging method based on GPU |
CN108765302A (en) * | 2018-03-29 | 2018-11-06 | 西安电子科技大学 | The real-time defogging method of image based on GPU |
CN109919859A (en) * | 2019-01-25 | 2019-06-21 | 暨南大学 | A kind of Outdoor Scene image defogging Enhancement Method calculates equipment and its storage medium |
CN110910319A (en) * | 2019-10-30 | 2020-03-24 | 中国医学科学院北京协和医院 | Operation video real-time defogging enhancement method based on atmospheric scattering model |
CN110910319B (en) * | 2019-10-30 | 2022-10-21 | 中国医学科学院北京协和医院 | Operation video real-time defogging enhancement method based on atmospheric scattering model |
CN111192210A (en) * | 2019-12-23 | 2020-05-22 | 杭州当虹科技股份有限公司 | Self-adaptive enhanced video defogging method |
CN111489302A (en) * | 2020-03-27 | 2020-08-04 | 武汉理工大学 | Maritime image enhancement method in fog environment |
CN111489302B (en) * | 2020-03-27 | 2023-12-05 | 武汉理工大学 | Maritime image enhancement method in fog environment |
CN111738938A (en) * | 2020-06-01 | 2020-10-02 | 余姚市浙江大学机器人研究中心 | Nonuniform atomization video optimization method based on prior target identification |
CN111738938B (en) * | 2020-06-01 | 2022-09-09 | 余姚市浙江大学机器人研究中心 | Nonuniform atomization video optimization method based on prior target identification |
CN111754433A (en) * | 2020-06-22 | 2020-10-09 | 哈尔滨理工大学 | Aerial image defogging method |
CN111754433B (en) * | 2020-06-22 | 2024-03-05 | 哈尔滨理工大学 | Defogging method for aerial image |
CN112529802A (en) * | 2020-12-09 | 2021-03-19 | 电子科技大学 | Atmospheric scattering degraded image recovery method based on scattering coefficient ratio estimation |
CN112529802B (en) * | 2020-12-09 | 2021-07-20 | 电子科技大学 | Atmospheric scattering degraded image recovery method based on scattering coefficient ratio estimation |
CN113298732A (en) * | 2021-06-08 | 2021-08-24 | 北京联合大学 | Image defogging method and system based on regional similarity |
Also Published As
Publication number | Publication date |
---|---|
CN104299192B (en) | 2017-03-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104299192A (en) | Single image defogging method based on atmosphere light scattering physical model | |
CN102567727B (en) | Method and device for replacing background target | |
Tripathi et al. | Single image fog removal using bilateral filter | |
Huang et al. | An efficient visibility enhancement algorithm for road scenes captured by intelligent transportation systems | |
CN103020920B (en) | Method for enhancing low-illumination images | |
Huang et al. | An advanced single-image visibility restoration algorithm for real-world hazy scenes | |
Shi et al. | Single image dehazing in inhomogeneous atmosphere | |
CN102170574A (en) | Real-time video defogging system | |
CN103985091A (en) | Single image defogging method based on luminance dark priori method and bilateral filtering | |
CN102930514A (en) | Rapid image defogging method based on atmospheric physical scattering model | |
CN112837233B (en) | Polarization image defogging method for acquiring transmissivity based on differential polarization | |
CN110544213A (en) | Image defogging method based on global and local feature fusion | |
CN111062293B (en) | Unmanned aerial vehicle forest flame identification method based on deep learning | |
CN109389569B (en) | Monitoring video real-time defogging method based on improved DehazeNet | |
CN102665034A (en) | Night effect removal method for camera-collected video | |
CN107424133A (en) | Image defogging method, device, computer can storage medium and mobile terminals | |
CN103198459A (en) | Haze image rapid haze removal method | |
CN108022225A (en) | Based on the improved dark channel prior image defogging algorithm of quick Steerable filter | |
CN103578083A (en) | Single image defogging method based on joint mean shift | |
CN104166968A (en) | Image dehazing method and device and mobile terminal | |
CN105931208A (en) | Physical model-based low-illuminance image enhancement algorithm | |
CN105701783A (en) | Single image defogging method based on ambient light model and apparatus thereof | |
CN106657948A (en) | low illumination level Bayer image enhancing method and enhancing device | |
CN105447825A (en) | Image defogging method and system | |
CN107730472A (en) | A kind of image defogging optimized algorithm based on dark primary priori |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |