CN106530257A - Remote sensing image de-fogging method based on dark channel prior model - Google Patents
Remote sensing image de-fogging method based on dark channel prior model Download PDFInfo
- Publication number
- CN106530257A CN106530257A CN201611034397.1A CN201611034397A CN106530257A CN 106530257 A CN106530257 A CN 106530257A CN 201611034397 A CN201611034397 A CN 201611034397A CN 106530257 A CN106530257 A CN 106530257A
- Authority
- CN
- China
- Prior art keywords
- image
- value
- dark channel
- absorbance
- pixel
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 claims abstract description 13
- 230000007246 mechanism Effects 0.000 claims abstract description 8
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 239000003595 mist Substances 0.000 claims description 49
- 238000002835 absorbance Methods 0.000 claims description 35
- 230000008030 elimination Effects 0.000 claims description 27
- 238000003379 elimination reaction Methods 0.000 claims description 27
- 238000005070 sampling Methods 0.000 claims description 11
- 238000011084 recovery Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 5
- 238000002834 transmittance Methods 0.000 claims description 5
- 230000035699 permeability Effects 0.000 claims description 4
- 238000005549 size reduction Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000003412 degenerative effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000009738 saturating Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a remote sensing image de-fogging method based on a dark channel prior model and belongs to the technical field of image processing. Based on the idea of the traditional dark channel prior model de-fogging method, the invention provides the unmanned aerial vehicle image de-fogging method based on the dark channel prior model. By use of a downsampling method and an interpolation algorithm, calculation of transmissivity of the dark channel prior model is improved, and calculation complexity is greatly reduced. De-fogging processing is performed on quite white regions in the image, and a fog-free image recovering method combining the allowance mechanism based on an atmospheric scattering model is adopted, so the color rendition phenomenon is reduced. Finally, image enhancement processing is performed on a de-fogged image by use of the automatic color gradation algorithm, so brightness of the de-fogged image is increased, and high-quality de-fogging effects of the image are achieved. The unmanned aerial vehicle image de-fogging method is compatible with image de-fogging precision and efficiency, and is highly practical in unmanned aerial vehicle image de-fogging processing.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of remote sensing images based on dark channel prior model go
Mist method.
Background technology
For now, image mist elimination is processed by the image to the shooting under the weather conditions such as mist, haze, so as to
Raising has contrast, the saturation for changing image and the brightness of mist image, increases the information included by image, obtains the nothing restored
Mist image.Image mist elimination technology is increasingly becoming the focus of research at present, and it is widely used in Computer Image Processing, claps under water
Take the photograph, outdoor video monitoring etc., remote sensing image process etc. field.
Image defogging method is broadly divided into two kinds:The method of mist elimination is realized and based on atmospherical scattering model based on image enhaucament
The method for realizing mist elimination.Realize the method for mist elimination mainly by improving the contrast and prominent figure that have mist image based on image enhaucament
The details of picture to improve the visual effect of image, so as to reach the purpose of image mist elimination.This method does not account for image deterioration
The reason for, and image mist elimination is carried out in this way for the information of image ledge is likely to result in certain damage
Lose, but at the same time the scope of application of this method than wide.Realize that based on atmospherical scattering model the method for mist elimination first has to
Physical process to there is mist image quality decrease is studied, and further sets up physical degradation model by research, then by dividing
Analysis is estimated to obtain the parameter in model, and the distortion caused in decreasing or even eliminating degenerative process finally gives high-quality after restoring
The mist elimination image of amount.There is mist image recovery method to be primarily directed to single width to have mist image based on prior information, according to its mist
The change of concentration, reaches the purpose of thorough mist elimination, and current most of mist elimination technologies are all in this way.It is traditional based on helping secretly
Other algorithms of the mist elimination algorithm of road priori is asked for transmittance figure ratio of precision are higher, but absorbance to ask for process time oversize,
Cause algorithm realize real-time mist elimination.
The content of the invention
Present invention seek to address that above problem of the prior art.Propose one kind to reduce computation complexity and reduce
Colour cast phenomenon, the remote sensing images defogging method based on dark channel prior model for improving the brightness of image after mist elimination.
Technical scheme is as follows:
A kind of remote sensing images defogging method based on dark channel prior model, which comprises the following steps:
1), obtaining has mist coloured image I (x, y);
2) meansigma methodss of the top n pixel color value for having mist image dark channel value larger, are obtained as the first of ambient light
Beginning estimated value, then adjusts the pixel number of selection, corrects atmosphere light, asks for air light value A;
3), according to the air light value for obtaining, the estimated value of absorbance is asked for according to dark primary priori theoretical;
4), by the estimated value of the method optimizing absorbance based on down-sampling and interpolation algorithm, obtain the absorbance for optimizing
Value;
5), using the method restored image for recovering fog free images with reference to tolerance mechanism based on atmospherical scattering model;
6) image enhancement processing is carried out using Auto Laves algorithm to image after mist elimination, the image after being processed.
Further, step 2) air light value A ask for include step:
When N values are 30, the meansigma methodss for choosing the front 30 pixel color value for having mist image dark channel value larger are made
For the initial estimate of ambient light, i.e.,Wherein, Ar,Ag,AbRespectively three colors of atmosphere light are divided
Amount.The pixel number that adjustment is chosen, corrects atmosphere light so as to meet following condition:
Here BmaxTake 0.01.
Further, step 3) according to the air light value for obtaining, the estimation of absorbance is asked for according to dark primary priori theoretical
Value formula is:
The estimated value of absorbance
Wherein, (x ', y ') represents a window centered on pixel (x, y),Represent any one in the window
Individual pixel, Ic(x ', y ') is expressed as the intensity level of some passage of this pixel.
Further, step 4) by the estimated value of the method optimizing absorbance based on down-sampling and interpolation algorithm, obtain
The transmittance values of optimization include step:
(1) the mist image that has to being input into carries out down-sampling operation using bilinear interpolation algorithm, is defeated by its size reduction
Enter the 1/8 of image;
(2) mode asked for using step 3 absorbance, is calculated the absorbance of image after reducing;
(3) absorbance of input picture is obtained using interpolation algorithm.
Further, step 5) recover image using the method for tolerance mechanism algorithm optimization absorbance, it is new so as to obtain
Recover image formula:
In formula, A is global atmosphere light intensity, and J (x, y) is the fog free images recovered, and I (x, y) is the image for treating mist elimination, t
(x, y) is medium permeability, t0For the minimum threshold of absorbance, K is tolerance, if the difference of each passage of pixel is less than K, then it is assumed that no
Meet dark channel prior.
Further, the step 6) Auto Laves algorithm algorithm flow it is as follows:
(1) count the rectangular histogram of original image;
(2) upper lower threshold value is gone out according to histogram calculation, and draws threshold difference d=upper threshold value-lower threshold value;
(3) if artwork image pixel value<=lower threshold value, then be entered as 0 by the pixel value;
(4) if the pixel value is assigned to 255 by artwork image pixel value >=upper threshold value;
(5) if between upper lower threshold value, the pixel value=original pixel value * 255/d;
(6) image after being processed.
Advantages of the present invention and have the beneficial effect that:
The present invention adopts down-sampling method and interpolation algorithm to improve the transmittance calculation of dark primary prior model, significantly reduces
Computation complexity;And the mist elimination for the inclined white portion of image is processed, the method using fog free images are recovered with reference to tolerance mechanism,
Reduce colour cast phenomenon;Image enhancement processing is carried out using Auto Laves algorithm to image after mist elimination finally, after improving mist elimination
Fog effect is removed in the brightness of image, reached image superior quality.
Description of the drawings
Fig. 1 is that the present invention provides preferred embodiment flow chart;
Fig. 2 is that original have mist image;
Fig. 3 is the image after He Kaiming methods are processed;
Fig. 4 is the image after the present invention is processed.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, detailed
Carefully describe.Described embodiment is only a part of embodiment of the present invention.
Technical scheme is as follows:
As shown in Figures 1 to 4:
Step one:Acquisition has mist coloured image I (x, y);
Mist to the degenerative process of image is:
I (x, y)=J (x, y) t (x, y)+A (1-t (x, y)) (5)
In formula, A is global atmosphere light intensity, and J (x, y) is the fog free images recovered, and I (x, y) is the image for treating mist elimination, t
(x, y) is referred to as absorbance or transmission figure for medium permeability, and which is defined as:
T (x, y)=e-βd(i,j) (6)
In formula, distances of the d (i, j) for scene point to observation station, scattering coefficients of the β for air.Can by formula (5) conversion
:
From (7) formula, if known global atmosphere light intensity A and absorbance t (x, y), just can try to achieve the fogless figure of recovery
As J (x, y), if but t (x, y) for 0 when, will appear from mistake in computation, therefore (7) formula be rewritten as:
In formula, t0For the minimum threshold of absorbance, 0.1 is taken as herein.
Step 2:Ask for air light value A;
The meansigma methodss of front 30 pixel color value that selection has mist image dark channel value larger are used as the initial of ambient light
Estimated value, i.e.,Then the characteristics of being typically always partial to white according to atmosphere light, adjusts the pixel chosen
Point number, further corrects atmosphere light so as to meet following condition:
Here Bmax0.01 is taken, to reduce the impact that noise is estimated to atmosphere light as far as possible, the image for causing recovery is not in
Cross-color, causes the final image for recovering partially dark while ambient light is unlikely to excessive again.
Step 3:According to the air light value for obtaining, the estimated value of absorbance is asked for;
The principle of dark channel prior is pointed out, except sky areas, JdarkThe intensity level of (x, y) always levels off to 0:
Jdark(x,y)→0 (10)
Then, formula (1) is entered into line translation, obtains following formula:
Assume that t (x, y) is given in each region, is designated asGiven air light value A, enters to (11) formula simultaneously
Row the right and left takes minimum of computation twice, can obtain:
Had according to dark primary priori theoretical:
Then, formula (12) is taken in formula (13), the estimated value of absorbance can be tried to achieve
Step 4:By the estimated value of the method optimizing absorbance based on down-sampling and interpolation algorithm, the saturating of optimization is obtained
Radiance rate value;
A kind of absorbance acquiring method based on down-sampling and interpolation algorithm is proposed, specific implementation is as follows:
(1) the mist image that has to being input into carries out down-sampling operation using bilinear interpolation algorithm, is defeated by its size reduction
Enter the 1/8 of image;
(2) mode asked for using step 3 absorbance, is calculated the absorbance of image after reducing;
(3) absorbance of input picture is obtained using interpolation algorithm.
By experimental verification, absorbance is asked for by the way of based on down-sampling and interpolation algorithm and compared in processing speed
The former algorithm of He is obviously improved, and the visual effect after image mist elimination and former algorithm difference very little.But in the practice of this algorithm
During find, if sample rate arranges unreasonable, be only such as original half by size reduction, in processing speed
Lift very little.Therefore, during the selection of sample rate, larger diminution ratio to be chosen processing speed is just had and substantially carry
Rise.
Step 5:Using the method restored image for recovering fog free images with reference to tolerance mechanism based on atmospherical scattering model;
Recover image using the method for tolerance mechanism algorithm optimization absorbance, so as to obtain new recovery image formula:
In formula, A is global atmosphere light intensity, and J (x, y) is the fog free images recovered, and I (x, y) is the image for treating mist elimination, t
(x, y) is medium permeability, t0For the minimum threshold of absorbance, K is tolerance, if the difference of each passage of pixel is less than K, then it is assumed that no
Meet dark channel prior.
Step 6:Image enhancement processing is carried out using Auto Laves algorithm to image after mist elimination, image after mist elimination is improved
Brightness, reached image superior quality removes fog effect.
Its algorithm flow is as follows:
(1) count the rectangular histogram of original image;
(2) upper lower threshold value is gone out according to histogram calculation, and draws threshold difference d=upper threshold value-lower threshold value;
(3) if artwork image pixel value<=lower threshold value, then be entered as 0 by the pixel value;
(4) if the pixel value is assigned to 255 by artwork image pixel value >=upper threshold value;
(5) if between upper lower threshold value, the pixel value=original pixel value * 255/d;
(6) image after being processed.
The recovery image after mist elimination is processed using Auto Laves algorithm, the algorithm not only has substantially to image enhaucament
Effect, and complexity is low, it is possible to achieve and the real time implementation of image is processed.The above embodiment is interpreted as being merely to illustrate this
Invent rather than limit the scope of the invention.After the content of record of the present invention has been read, technical staff can be with
The present invention is made various changes or modifications, these equivalence changes and modification equally fall into the model limited by the claims in the present invention
Enclose.
Claims (7)
1. a kind of remote sensing images defogging method based on dark channel prior model, it is characterised in that comprise the following steps:
1), obtaining has mist coloured image I (x, y);
2), obtain meansigma methodss initially the estimating as ambient light of the top n pixel color value for having mist image dark channel value larger
Evaluation, then adjusts the pixel number of selection, corrects atmosphere light, asks for air light value A;
3), according to the air light value for obtaining, the estimated value of absorbance is asked for according to dark primary priori theoretical;
4), by the estimated value of the method optimizing absorbance based on down-sampling and interpolation algorithm, the transmittance values for optimizing are obtained;
5), using the method restored image for recovering fog free images with reference to tolerance mechanism based on atmospherical scattering model;
6) image enhancement processing is carried out using Auto Laves algorithm to image after mist elimination, the image after being processed.
2. the remote sensing images defogging method based on dark channel prior model according to claim 1, it is characterised in that step
2) air light value A ask for include step:
When N values are 30, the meansigma methodss of the front 30 pixel color value for having mist image dark channel value larger are chosen as ring
The initial estimate of border light, i.e.,Wherein, Ar,Ag,AbRespectively three color components of atmosphere light,
The pixel number that adjustment is chosen, corrects atmosphere light so as to meet following condition:
Here BmaxTake 0.01.
3. the remote sensing images defogging method based on dark channel prior model according to claim 2, it is characterised in that step
3) according to the air light value for obtaining, according to the estimated value formula that dark primary priori theoretical asks for absorbance it is:
The estimated value of absorbance
Wherein, (x ', y ') represents a window centered on pixel (x, y),Represent any one picture in the window
Vegetarian refreshments, Ic(x ', y ') is expressed as the intensity level of some passage of this pixel.
4. the remote sensing images defogging method based on dark channel prior model according to claim 3, it is characterised in that step
4) by the estimated value of the method optimizing absorbance based on down-sampling and interpolation algorithm, the transmittance values for obtaining optimizing include step
Suddenly:
(1) the mist image that has to being input into carries out down-sampling operation using bilinear interpolation algorithm, is input figure by its size reduction
The 1/8 of picture;
(2) mode asked for using step 3 absorbance, is calculated the absorbance of image after reducing;
(3) absorbance of input picture is obtained using interpolation algorithm.
5. the remote sensing images defogging method based on dark channel prior model according to claim 4, it is characterised in that step
5) recover image using the method for tolerance mechanism algorithm optimization absorbance, so as to obtain new recovery image formula:
In formula, A is global atmosphere light intensity, and J (x, y) is the fog free images recovered, and I (x, y) is the image for treating mist elimination, t (x, y)
For medium permeability, t0For the minimum threshold of absorbance, K is tolerance, if the difference of each passage of pixel is less than K, then it is assumed that be unsatisfactory for
Dark channel prior.
6. the remote sensing images defogging method based on dark channel prior model according to claim 5, it is characterised in that described
Step 6) Auto Laves algorithm algorithm flow it is as follows:
(1) count the rectangular histogram of original image;
(2) upper lower threshold value is gone out according to histogram calculation, and draws threshold difference d=upper threshold value-lower threshold value;
(3) if artwork image pixel value<=lower threshold value, then be entered as 0 by the pixel value;
(4) if the pixel value is assigned to 255 by artwork image pixel value >=upper threshold value;
(5) if between upper lower threshold value, the pixel value=original pixel value * 255/d;
(6) image after being processed.
7. the remote sensing images defogging method based on dark channel prior model according to one of claim 1-6, its feature exist
In the remote sensing images are unmanned aerial vehicle remote sensing image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611034397.1A CN106530257A (en) | 2016-11-22 | 2016-11-22 | Remote sensing image de-fogging method based on dark channel prior model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611034397.1A CN106530257A (en) | 2016-11-22 | 2016-11-22 | Remote sensing image de-fogging method based on dark channel prior model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106530257A true CN106530257A (en) | 2017-03-22 |
Family
ID=58356631
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611034397.1A Pending CN106530257A (en) | 2016-11-22 | 2016-11-22 | Remote sensing image de-fogging method based on dark channel prior model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106530257A (en) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194894A (en) * | 2017-05-25 | 2017-09-22 | 河南师范大学 | A kind of video defogging method and its system |
CN107274366A (en) * | 2017-06-15 | 2017-10-20 | 武汉理工大学 | Improvement dark channel prior single width atomization image recovery method based on physical model |
CN107316284A (en) * | 2017-07-19 | 2017-11-03 | 山东财经大学 | Intense light source hypograph defogging method and device |
CN107730472A (en) * | 2017-11-03 | 2018-02-23 | 昆明理工大学 | A kind of image defogging optimized algorithm based on dark primary priori |
CN107767348A (en) * | 2017-09-27 | 2018-03-06 | 重庆大学 | Single width tunnel image quick enhancement method based on imaging model constraint |
CN108269242A (en) * | 2018-01-17 | 2018-07-10 | 深圳市华星光电半导体显示技术有限公司 | Image enchancing method |
CN108460743A (en) * | 2018-03-19 | 2018-08-28 | 西安因诺航空科技有限公司 | A kind of unmanned plane image defogging algorithm based on dark |
CN108711139A (en) * | 2018-04-24 | 2018-10-26 | 特斯联(北京)科技有限公司 | One kind being based on defogging AI image analysis systems and quick response access control method |
CN109003238A (en) * | 2018-06-26 | 2018-12-14 | 西京学院 | A kind of image haze minimizing technology based on model and histogram and grey level enhancement |
CN109754372A (en) * | 2018-12-03 | 2019-05-14 | 浙江大华技术股份有限公司 | A kind of image defogging processing method and processing 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 |
CN110197469A (en) * | 2019-06-11 | 2019-09-03 | 青岛大学 | A kind of image defogging method, system and electronic equipment and storage medium |
CN110473155A (en) * | 2019-08-02 | 2019-11-19 | 西安工程大学 | A kind of image defogging method based on retina color-aware dark principle |
CN110544220A (en) * | 2019-09-05 | 2019-12-06 | 北京天地玛珂电液控制***有限公司 | intelligent defogging method, storage medium and system for underground video image of coal mine |
CN111223052A (en) * | 2019-10-24 | 2020-06-02 | 江苏大学 | Image defogging method based on improved tolerance mechanism |
CN111563852A (en) * | 2020-04-24 | 2020-08-21 | 桂林电子科技大学 | Dark channel prior defogging method based on low-complexity MF |
CN111738959A (en) * | 2020-06-30 | 2020-10-02 | 福州大学 | FPGA-based real-time demisting method for video image |
CN112419193A (en) * | 2020-11-24 | 2021-02-26 | 杭州电子科技大学 | Method and system for removing uneven fog of remote sensing image |
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 |
CN113538267A (en) * | 2021-07-09 | 2021-10-22 | 广东职业技术学院 | Unmanned aerial vehicle foggy image sharpening method, system, computer and storage medium |
CN116523801A (en) * | 2023-07-03 | 2023-08-01 | 贵州医科大学附属医院 | Intelligent monitoring method for nursing premature infants |
CN116630349A (en) * | 2023-07-25 | 2023-08-22 | 山东爱福地生物股份有限公司 | Straw returning area rapid segmentation method based on high-resolution remote sensing image |
CN117196971A (en) * | 2023-08-14 | 2023-12-08 | 上海为旌科技有限公司 | Image defogging method and device based on atmospheric scattering model and readable storage medium |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761720A (en) * | 2013-12-13 | 2014-04-30 | 中国科学院深圳先进技术研究院 | Image dehazing method and image dehazing device |
-
2016
- 2016-11-22 CN CN201611034397.1A patent/CN106530257A/en active Pending
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103761720A (en) * | 2013-12-13 | 2014-04-30 | 中国科学院深圳先进技术研究院 | Image dehazing method and image dehazing device |
Non-Patent Citations (6)
Title |
---|
KAIMING HE 等: "Single Image Haze Removal Using Dark Channel Prior", 《IEEE TRANS PATTERN ANAL MACH INTELL》 * |
YU, LINAN 等: "Video Defogging Based on Adaptive Tolerance", 《TELKOMNIKA INDONESIAN JOURNAL OF ELECTRICAL ENGINEERING》 * |
刘信: "基于FPGA水下图像像质增强实时化研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
张万绪 等: "基于暗原色先验的快速视频去雾优化算法", 《西北大学学报》 * |
杜宏博 等: "基于改进暗原色先验模型的快速图像去雾方法", 《计算机工程与应用》 * |
陈新富: "基于暗通道先验原理的图像去雾研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (38)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107194894A (en) * | 2017-05-25 | 2017-09-22 | 河南师范大学 | A kind of video defogging method and its system |
CN107274366B (en) * | 2017-06-15 | 2019-10-25 | 武汉理工大学 | Improvement dark channel prior single width based on physical model is atomized image recovery method |
CN107274366A (en) * | 2017-06-15 | 2017-10-20 | 武汉理工大学 | Improvement dark channel prior single width atomization image recovery method based on physical model |
CN107316284A (en) * | 2017-07-19 | 2017-11-03 | 山东财经大学 | Intense light source hypograph defogging method and device |
CN107767348A (en) * | 2017-09-27 | 2018-03-06 | 重庆大学 | Single width tunnel image quick enhancement method based on imaging model constraint |
CN107767348B (en) * | 2017-09-27 | 2021-06-08 | 重庆大学 | Single tunnel image rapid enhancement method based on imaging model constraint |
CN107730472A (en) * | 2017-11-03 | 2018-02-23 | 昆明理工大学 | A kind of image defogging optimized algorithm based on dark primary priori |
CN108269242A (en) * | 2018-01-17 | 2018-07-10 | 深圳市华星光电半导体显示技术有限公司 | Image enchancing method |
CN108269242B (en) * | 2018-01-17 | 2020-08-28 | 深圳市华星光电半导体显示技术有限公司 | Image enhancement method |
CN108460743A (en) * | 2018-03-19 | 2018-08-28 | 西安因诺航空科技有限公司 | A kind of unmanned plane image defogging algorithm based on dark |
CN108711139B (en) * | 2018-04-24 | 2019-04-23 | 特斯联(北京)科技有限公司 | One kind being based on defogging AI image analysis system and quick response access control method |
CN108711139A (en) * | 2018-04-24 | 2018-10-26 | 特斯联(北京)科技有限公司 | One kind being based on defogging AI image analysis systems and quick response access control method |
CN109003238A (en) * | 2018-06-26 | 2018-12-14 | 西京学院 | A kind of image haze minimizing technology based on model and histogram and grey level enhancement |
CN109003238B (en) * | 2018-06-26 | 2021-06-25 | 西京学院 | Image haze removal method based on model, histogram and gray level enhancement |
CN109754372A (en) * | 2018-12-03 | 2019-05-14 | 浙江大华技术股份有限公司 | A kind of image defogging processing method and processing device |
CN109754372B (en) * | 2018-12-03 | 2020-12-08 | 浙江大华技术股份有限公司 | 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 |
CN110197469B (en) * | 2019-06-11 | 2023-04-28 | 青岛大学 | Image defogging method and system, electronic equipment and storage medium |
CN110197469A (en) * | 2019-06-11 | 2019-09-03 | 青岛大学 | A kind of image defogging method, system and electronic equipment and storage medium |
CN110473155A (en) * | 2019-08-02 | 2019-11-19 | 西安工程大学 | A kind of image defogging method based on retina color-aware dark principle |
CN110544220A (en) * | 2019-09-05 | 2019-12-06 | 北京天地玛珂电液控制***有限公司 | intelligent defogging method, storage medium and system for underground video image of coal mine |
CN110544220B (en) * | 2019-09-05 | 2022-02-22 | 北京天玛智控科技股份有限公司 | Intelligent defogging method, storage medium and system for underground video image of coal mine |
CN111223052A (en) * | 2019-10-24 | 2020-06-02 | 江苏大学 | Image defogging method based on improved tolerance mechanism |
CN111563852A (en) * | 2020-04-24 | 2020-08-21 | 桂林电子科技大学 | Dark channel prior defogging method based on low-complexity MF |
CN111738959A (en) * | 2020-06-30 | 2020-10-02 | 福州大学 | FPGA-based real-time demisting method for video image |
CN111738959B (en) * | 2020-06-30 | 2022-08-19 | 福州大学 | Real-time defogging method for video image based on FPGA |
CN112419193A (en) * | 2020-11-24 | 2021-02-26 | 杭州电子科技大学 | Method and system for removing uneven fog of remote sensing image |
CN112419193B (en) * | 2020-11-24 | 2024-02-02 | 杭州电子科技大学 | Method and system for removing nonuniform fog of remote sensing image |
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 |
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 |
CN113538267A (en) * | 2021-07-09 | 2021-10-22 | 广东职业技术学院 | Unmanned aerial vehicle foggy image sharpening method, system, computer and storage medium |
CN113538267B (en) * | 2021-07-09 | 2023-10-20 | 广东职业技术学院 | Unmanned aerial vehicle foggy image definition method, system, computer and storage medium |
CN116523801A (en) * | 2023-07-03 | 2023-08-01 | 贵州医科大学附属医院 | Intelligent monitoring method for nursing premature infants |
CN116523801B (en) * | 2023-07-03 | 2023-08-25 | 贵州医科大学附属医院 | Intelligent monitoring method for nursing premature infants |
CN116630349A (en) * | 2023-07-25 | 2023-08-22 | 山东爱福地生物股份有限公司 | Straw returning area rapid segmentation method based on high-resolution remote sensing image |
CN116630349B (en) * | 2023-07-25 | 2023-10-20 | 山东爱福地生物股份有限公司 | Straw returning area rapid segmentation method based on high-resolution remote sensing image |
CN117196971A (en) * | 2023-08-14 | 2023-12-08 | 上海为旌科技有限公司 | Image defogging method and device based on atmospheric scattering model and readable storage medium |
CN117196971B (en) * | 2023-08-14 | 2024-05-31 | 上海为旌科技有限公司 | Image defogging method and device based on atmospheric scattering model and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106530257A (en) | Remote sensing image de-fogging method based on dark channel prior model | |
CN110148095B (en) | Underwater image enhancement method and enhancement device | |
CN106251301B (en) | A kind of single image to the fog method based on dark primary priori | |
CN106251300B (en) | A kind of quick night Misty Image restored method based on Retinex | |
CN106157267B (en) | Image defogging transmissivity optimization method based on dark channel prior | |
CN106846263B (en) | Based on the image defogging method for merging channel and sky being immunized | |
CN108734670B (en) | Method for restoring single night weak-illumination haze image | |
CN105225210B (en) | A kind of self-adapting histogram enhancing defogging method based on dark | |
CN105574830A (en) | Low-quality image enhancement method under extreme weather conditions | |
CN102831591B (en) | Gaussian filter-based real-time defogging method for single image | |
CN103077504B (en) | A kind of image defogging method capable based on self-adaptation illumination calculation | |
CN107451966B (en) | Real-time video defogging method implemented by guiding filtering through gray level image | |
CN109087254B (en) | Unmanned aerial vehicle aerial image haze sky and white area self-adaptive processing method | |
CN105976337B (en) | A kind of image defogging method based on intermediate value guiding filtering | |
CN111292258A (en) | Image defogging method based on dark channel prior and bright channel prior | |
CN107103591A (en) | A kind of single image to the fog method based on image haze concentration sealing | |
CN102750674A (en) | Video image defogging method based on self-adapting allowance | |
CN109255759A (en) | Image defogging method based on sky segmentation and transmissivity adaptive correction | |
CN107360344B (en) | Rapid defogging method for monitoring video | |
CN104253930A (en) | Real-time video defogging method | |
CN109816608B (en) | Low-illumination image self-adaptive brightness enhancement method based on noise suppression | |
CN110689490A (en) | Underwater image restoration method based on texture color features and optimized transmittance | |
CN104867121A (en) | Fast image defogging method based on dark channel prior and Retinex theory | |
CN106846258A (en) | A kind of single image to the fog method based on weighted least squares filtering | |
CN111476744B (en) | Underwater image enhancement method based on classification and atmospheric imaging model |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170322 |
|
RJ01 | Rejection of invention patent application after publication |