CN113962872B - Dual-channel joint optimization night image defogging method - Google Patents
Dual-channel joint optimization night image defogging method Download PDFInfo
- Publication number
- CN113962872B CN113962872B CN202010704829.5A CN202010704829A CN113962872B CN 113962872 B CN113962872 B CN 113962872B CN 202010704829 A CN202010704829 A CN 202010704829A CN 113962872 B CN113962872 B CN 113962872B
- Authority
- CN
- China
- Prior art keywords
- channel
- image
- function
- transmittance
- max
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000005457 optimization Methods 0.000 title claims abstract description 6
- 238000001914 filtration Methods 0.000 claims abstract description 14
- 230000004927 fusion Effects 0.000 claims abstract description 6
- 238000002834 transmittance Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 238000003384 imaging method Methods 0.000 claims description 6
- 230000001629 suppression Effects 0.000 claims description 3
- 238000007500 overflow downdraw method Methods 0.000 claims 2
- 230000002708 enhancing effect Effects 0.000 claims 1
- 238000007670 refining Methods 0.000 claims 1
- 230000009466 transformation Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 abstract description 2
- 230000015556 catabolic process Effects 0.000 abstract 1
- 238000006731 degradation reaction Methods 0.000 abstract 1
- 238000002474 experimental method Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000012733 comparative method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 125000001475 halogen functional group Chemical group 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000003313 weakening effect Effects 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
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention provides a two-channel joint optimization night image defogging algorithm, and mainly relates to image defogging. The method comprises the steps of calculating an atmospheric light function and calculating a transmissivity function, estimating an atmospheric light component containing contour information through weighted differential image guided filtering when estimating the atmospheric light, estimating an atmospheric light component of supplementary details through Laplace sharpening gray level diagram guided filtering, and fusing the two atmospheric light components to obtain final atmospheric light. When the transmissivity function is calculated, the respective advantages of the dark channel and the bright channel are combined, the transmissivity is calculated through the fusion of the self-adaptive weight map and the dark channel and the bright channel, and then the precision of the transmissivity is improved through the limitation contrast self-adaptive histogram equalization and the guided filtering treatment of the transmissivity. And finally, defogging is realized by using a haze image degradation model function. The advantage of this algorithm is that the loss of detail is small while defogging.
Description
Technical Field
The invention belongs to the technical field of computer vision, in particular to a night image defogging problem, and particularly relates to a calculation method of an atmospheric light function and a transmissivity function in a haze scene imaging model.
Background
Under the condition of night haze, light is influenced by reflection, scattering and absorption of particles in the air, and imaging blurring is easy to occur, so that the performance of computer vision systems such as image acquisition, target tracking, significance detection, auxiliary driving, monitoring systems, remote sensing systems and the like can be influenced, and in order to improve the performance of the computer vision systems, the haze elimination from a foggy image is particularly important.
Image defogging can be generally classified into an enhancement-based method and a physical model restoration-based method, and the image enhancement method can improve contrast, but may lose part of details during defogging because the imaging principle is not considered. The defogging method based on the physical model generally has three steps of estimating an atmospheric light function, estimating a transmittance function and recovering an image based on the model. Among them, calculation of atmospheric light and transmittance is a crucial step. The influence of the artificial light source is considered for defogging at night, so that a good defogging effect can be realized. He Kaiming et al propose classical dark channel prior defogging algorithm, which is poor in defogging result for night images because the influence of non-uniform illumination condition and artificial light source at night is not considered; the maximum reflectivity prior is proposed by jin Zhang et al to estimate the changing atmospheric light color map and eliminate the influence of the color map on the input image, then the transmissivity function is estimated by an improved dark channel method, and finally the defogging image with balanced colors is obtained, but color distortion can occur after defogging.
Disclosure of Invention
Aiming at the defect of estimating the night image light source area by dark channel prior, the invention provides a method for jointly optimizing the dark channel and the bright channel to estimate the transmissivity; in addition, the invention uses a guided filtering method to estimate the atmospheric light, and can keep the texture details of elements in the image while defogging. The invention mainly achieves the above purpose through the following steps:
(1) Obtaining atmospheric light component A using Laplace sharpened image as reference guide filtering laplace Obtaining an atmospheric light component A using a weighted difference image as a reference guide filter wcd The two are fused to obtain an atmospheric light function A (x);
(2) Calculating a dark channel transmittance function using the modified dark channel method, and calculating a bright channel transmittance function using the bright channel method;
(3) Calculating self-adaptive weight graphs of a dark channel and a bright channel;
(4) Dark channel transmittance and bright channel transmittance are weighted and fused, and a limiting contrast adaptive histogram equalization and guided filtering refinement transmittance function is used;
(5) And calculating a defogging image by combining the atmospheric light and transmittance functions obtained by using the improved method and a night foggy image imaging model.
Drawings
FIG. 1 is a block diagram of a dual channel joint optimization night image defogging method;
Detailed Description
(1) Acquisition of atmospheric light A (x)
The calculation formula is as follows:
I wcd (x)＝[(I max (x)-0.7I min (x))+(I median (x)-0.7I min (x))]/2 (1)
I laplace ＝I gray -Laplace(I gray )/2 (2)
A(x)＝αA wcd (x)+(1-α)A laplace (x) (3)
in which I max 、I median 、I min Respectively obtaining the maximum value, the median value and the minimum value of gray values at the pixel point x in the image; i gray A gray scale map for an input image; laplace is a Laplacian transform with a kernel size of 3×3; a is that wcd ＝GuidedFilter(I wcd ,I eq )，A wcd To be I wcd Guiding the filtered atmospheric light for the reference image; a is that laplace ＝GuidedFilter(I laplace ,I eq )，A laplace To be I laplace Guiding the filtered atmospheric light for the reference image; wherein alpha has a value of 3/4 and A (x) is an atmospheric light function.
(2) Improved acquisition of dark channel transmittance and bright channel transmittance functions
Calculation of dark channel a priori transmittance function:
the calculation of the transmittance of the dark channel refers to He Kaiming and the like in paper "Single Image Haze Removal Using Dark Channel Prior" published in 2011, and is improved by setting a threshold to determine whether the dark channel is a light source region, determining that the dark channel is greater than T is a light source position, and adding a coefficient to the light source region to prevent the dark channel transmittance in the region from having a value of 0 or minimum:
wherein Ω (x) is a window region centered on the pixel point x;T＝max(T mean ,T max ,T Gmax )；/>T Gmax ＝0.4×max(IA)。
the bright channel a priori transmittance is calculated as follows:
equation (5) references the luminance channel transmittance t in the paper "Nighttime Single Image Dehazing via Pixel-Wise Alpha Blending" published in 2019 by Yu Teng et al BCP (x) And adds the enhancement of t using equation (6) BCP (x) In (2), equation (6) refers to the content of Zohai Al-Amen in the paper "Nighttime image enhancement using a new illumination boostalgorithm" published in 2019.
(3) Acquisition of dark channel and bright channel transmittance weighting maps
The adaptive weights are calculated as follows:
equation (7) refers to Tang ChThe content of the paper "Low-light imageenhancement with strong light weakening and bright halo suppressing" published by aoying et al in 2018, wherein I c For the input image, δ is a luminance suppression coefficient, here set to 0.8; in the formula (8)T i ＝max(t mean ,t max ,t Gmax )，/> t Gmax ＝0.4×max(I max )。
(4) The method for weighted fusion of the dark channel and the bright channel is as follows:
the result is subjected to limited contrast histogram equalization and guided filtering refinement treatment, and the guided filtered reference image is I gray 。
(5) Defogging is realized by using a night foggy image imaging model, and the calculation method is as follows:
wherein I (x) is an input image, J (x) is an defogged image, and the diameter of a guide filtering convolution kernel used by A (x) is calculated to be 60; at t DCP And t BCP When the light transmittance is obtained, corresponding values are respectively obtained by using the omega sizes of 11 multiplied by 11, 15 multiplied by 15 and 29 multiplied by 29, and then the corresponding transmittance is obtained by carrying out equal proportion fusion; the size of the omega window for alpha (x) is 15×15; grid size for limiting contrast adaptive histogram equalization to 16 x 16; the guided filter convolution kernel for the refinement of the transmittance t (x) has a diameter of 30.
In order to verify the effectiveness of the dual-channel joint optimization night image defogging method provided by the invention, a comparison experiment is carried out on a classical night defogging method A, B, C, D and the method mentioned herein under the same experimental environment condition. In the experiment, a synthetic image in a paper of Nighttime Single ImageDehazing via Pixel-Wise Alpha Blending published in 2019 by Yu Teng et al is selected and used for calculating a peak signal-to-noise ratio (PSNR) and a Structural Similarity (SSIM) with reference indexes, and the two index values are larger and better, and the result is shown in a table 1; because it is difficult to obtain the foggy image and the reference image thereof under the same condition in the real environment, 10 night foggy images photographed under the real condition are selected in the experiment, the defogging results are obtained by using the methods respectively, and then, no reference index brique value is calculated for the defogging image, the brique can measure the loss degree of image details, the lower the index value is, the better the experimental results are shown in table 2:
table 1 comparison of PSNR and SSIM of defogging results on synthesized pictures by different methods
Table.1 PSNR and SSIM comparison of dehazing results of different algorithms
As can be seen from Table 1, the inventive method is superior to the comparative method in terms of PSNR and SSIM indexes.
TABLE 2 BRISQUE index comparison
Tab.2Comparison of BRISQUE indicators
It can be seen from table 2 that the method of the present invention maintains more detailed information of the original image and that the loss of detail after defogging is smaller, and the average brique index is reduced by 9.2341, 12.3649, 4.5063, 9.6094, respectively, than that of method A, B, C, D.
Claims (4)
1. A dual-channel joint optimization night image defogging method is characterized by comprising the following steps:
(1) Obtaining atmospheric light component A using Laplace sharpened image as reference guide filtering laplace Obtaining an atmospheric light component A using a weighted difference image as a reference guide filter wcd The two are weighted and fused to obtain an atmospheric light function A (x);
(2) Judging whether the light source area is the light source area or not by setting a threshold value, improving the dark channel transmittance function in a mode of increasing the coefficient to the light source area, enhancing the medium-low intensity content in the bright channel transmittance function, and respectively calculating the improved dark channel transmittance function and the bright channel transmittance function, wherein the steps are as follows:
characteristic one: acquisition of dark channel transmittance
The formula for the dark channel transmittance function is as follows:
where Ω (x) is a window region centered around pixel x,I c (y)、I c (x) For the gray value of a certain color channel of an input image, three different thresholds are obtained through different maximum values and average value calculation modes, then the maximum value is taken as T, and the calculation formula of T is as follows:
T＝max(T mean ,T max ,T Gmax ) (2)
T Gmax ＝0.4×max(IA) (5)
and the second characteristic is: acquisition of light channel transmittance
The low-luminance enhancement calculation formula in the light channel transmittance is as follows:
t in the above BCP (x) As a function of the light channel transmittance, max (t BCP ) At t BCP Maximum value of (2);
(3) According to the brightness suppression coefficient, calculating an adaptive weight coefficient, and further obtaining an adaptive weight map of a dark channel and a bright channel, wherein the method comprises the following steps:
and (3) the following characteristics: acquisition of weight map
The adaptive weight coefficient calculation formula is as follows:
the calculation formula of the weight graph is as follows:
wherein Ω (x) is a window region centered on the pixel point x, δ is a luminance suppression coefficient, I c (y)、I c (x) For inputting gray value of a certain color channel of image, I max (x) For the maximum value of gray values of three color channels at the pixel point x, three different thresholds are obtained through different maximum value and average value calculation modes, and then the maximum value is taken as T i ，T i The calculation formula of (2) is as follows:
T i ＝max(t mean ,t max ,t Gmax ) (9)
t Gmax ＝0.4×max(I max ) (12)
(4) Fusing the transmittance of the dark channel and the bright channel by using a weighted fusion method, and refining a transmittance function by using limiting contrast adaptive histogram equalization and guided filtering;
(5) And (3) using the atmospheric light and transmittance functions obtained by the improved method, and combining the night foggy image imaging model, namely the atmospheric scattering model to calculate a defogging image.
2. The method of claim 1, wherein the laplacian sharpened gray map and the weighted difference gray map are added as the guided filtering of the reference image in the step (1), and the atmospheric light function a (x) is calculated by using a weighted fusion method, and the new features are added as follows:
and four characteristics: acquisition of weighted fusion atmospheric light function
The specific process of solving the atmospheric light function is as follows:
I wcd (x)＝[(I max (x)-0.7I min (x))+(I median (x)-0.7I min (x))]/2 (13)
I laplace ＝I gray -Laplace(I gray )/2 (14)
A(x)＝αA wcd (x)+(1-α)A laplace (x) (15)
in which I max 、I median 、I min Respectively the maximum value, the median value and the minimum value of gray values at the pixel point x in the image, I gray Laplace is Laplacian transformation, A, for gray scale of input image wcd To be I wcd Guiding filtering for reference imagesAtmospheric light obtained by wave, A laplace To be I laplace The atmospheric light obtained by the filtering is guided by the reference image, wherein the value of alpha is 3/4, and A (x) is the atmospheric light function obtained.
3. The method of claim 1, wherein the dark channel and bright channel transmissivities are fused in step (4);
and fifth feature: weighted fusion of dark channel transmittance and bright channel transmittance
And (3) performing limit contrast self-adaptive histogram equalization and guided filtering refinement processing on t (x) obtained by the formula.
4. The method of claim 1, wherein the acquisition of atmospheric light, the adaptively weighted fusion of the characteristics of the dark and light channels reduces detail loss while defogging.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010704829.5A CN113962872B (en) | 2020-07-21 | 2020-07-21 | Dual-channel joint optimization night image defogging method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010704829.5A CN113962872B (en) | 2020-07-21 | 2020-07-21 | Dual-channel joint optimization night image defogging method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113962872A CN113962872A (en) | 2022-01-21 |
| CN113962872B true CN113962872B (en) | 2023-08-18 |
Family
ID=79459823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010704829.5A Active CN113962872B (en) | 2020-07-21 | 2020-07-21 | Dual-channel joint optimization night image defogging method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113962872B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631829A (en) * | 2016-01-15 | 2016-06-01 | 天津大学 | Night haze image defogging method based on dark channel prior and color correction |
| CN106157267A (en) * | 2016-07-12 | 2016-11-23 | 中国科学技术大学 | A kind of image mist elimination absorbance optimization method based on dark channel prior |
| CN106709893A (en) * | 2016-12-28 | 2017-05-24 | 西北大学 | All-time haze image sharpness recovery method |
| CN107798670A (en) * | 2017-09-20 | 2018-03-13 | 中国科学院长春光学精密机械与物理研究所 | A kind of dark primary prior image defogging method using image wave filter |
| WO2018119406A1 (en) * | 2016-12-22 | 2018-06-28 | Aestatix LLC | Image processing to determine center of balance in a digital image |
| CN108629750A (en) * | 2018-05-03 | 2018-10-09 | 明见（厦门）技术有限公司 | A kind of night defogging method, terminal device and storage medium |
| CN108734670A (en) * | 2017-04-20 | 2018-11-02 | 天津工业大学 | The restoration algorithm of single width night weak illumination haze image |
| CN108765323A (en) * | 2018-05-16 | 2018-11-06 | 南京理工大学 | A kind of flexible defogging method based on improvement dark and image co-registration |
| CN109785262A (en) * | 2019-01-11 | 2019-05-21 | 闽江学院 | Image defogging method based on dark channel prior and adaptive histogram equalization |
| CN109919879A (en) * | 2019-03-13 | 2019-06-21 | 重庆邮电大学 | A kind of image defogging method based on dark channel prior Yu bright channel prior |
| CN110148093A (en) * | 2019-04-17 | 2019-08-20 | 中山大学 | A kind of image defogging improved method based on dark channel prior |
| CN110827221A (en) * | 2019-10-31 | 2020-02-21 | 天津大学 | Single image defogging method based on double-channel prior and side window guide filtering |
| CN110889805A (en) * | 2019-10-08 | 2020-03-17 | 西安理工大学 | Image defogging method based on dark channel compensation and atmospheric light value improvement |
| CN111161167A (en) * | 2019-12-16 | 2020-05-15 | 天津大学 | Single image defogging method based on middle channel compensation and self-adaptive atmospheric light estimation |
| CN111292258A (en) * | 2020-01-15 | 2020-06-16 | 长安大学 | Image defogging method based on dark channel prior and bright channel prior |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102207939B1 (en) * | 2014-03-27 | 2021-01-26 | 한화테크윈 주식회사 | Defog system and method |
| US10477128B2 (en) * | 2017-01-06 | 2019-11-12 | Nikon Corporation | Neighborhood haze density estimation for single-image dehaze |
| TWI674804B (en) * | 2018-03-15 | 2019-10-11 | 國立交通大學 | Video dehazing device and method |
-
2020
- 2020-07-21 CN CN202010704829.5A patent/CN113962872B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105631829A (en) * | 2016-01-15 | 2016-06-01 | 天津大学 | Night haze image defogging method based on dark channel prior and color correction |
| CN106157267A (en) * | 2016-07-12 | 2016-11-23 | 中国科学技术大学 | A kind of image mist elimination absorbance optimization method based on dark channel prior |
| WO2018119406A1 (en) * | 2016-12-22 | 2018-06-28 | Aestatix LLC | Image processing to determine center of balance in a digital image |
| CN106709893A (en) * | 2016-12-28 | 2017-05-24 | 西北大学 | All-time haze image sharpness recovery method |
| CN108734670A (en) * | 2017-04-20 | 2018-11-02 | 天津工业大学 | The restoration algorithm of single width night weak illumination haze image |
| CN107798670A (en) * | 2017-09-20 | 2018-03-13 | 中国科学院长春光学精密机械与物理研究所 | A kind of dark primary prior image defogging method using image wave filter |
| CN108629750A (en) * | 2018-05-03 | 2018-10-09 | 明见（厦门）技术有限公司 | A kind of night defogging method, terminal device and storage medium |
| CN108765323A (en) * | 2018-05-16 | 2018-11-06 | 南京理工大学 | A kind of flexible defogging method based on improvement dark and image co-registration |
| CN109785262A (en) * | 2019-01-11 | 2019-05-21 | 闽江学院 | Image defogging method based on dark channel prior and adaptive histogram equalization |
| CN109919879A (en) * | 2019-03-13 | 2019-06-21 | 重庆邮电大学 | A kind of image defogging method based on dark channel prior Yu bright channel prior |
| CN110148093A (en) * | 2019-04-17 | 2019-08-20 | 中山大学 | A kind of image defogging improved method based on dark channel prior |
| CN110889805A (en) * | 2019-10-08 | 2020-03-17 | 西安理工大学 | Image defogging method based on dark channel compensation and atmospheric light value improvement |
| CN110827221A (en) * | 2019-10-31 | 2020-02-21 | 天津大学 | Single image defogging method based on double-channel prior and side window guide filtering |
| CN111161167A (en) * | 2019-12-16 | 2020-05-15 | 天津大学 | Single image defogging method based on middle channel compensation and self-adaptive atmospheric light estimation |
| CN111292258A (en) * | 2020-01-15 | 2020-06-16 | 长安大学 | Image defogging method based on dark channel prior and bright channel prior |
Non-Patent Citations (1)
| Title |
|---|
| 李鹏飞 等.暗通道融合亮通道优化的夜间图像去雾算法.《液晶与显示》.2021,第36卷(第04期),596-604. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113962872A (en) | 2022-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108053374B (en) | Underwater image enhancement method combining bilateral filtering and Retinex | |
| CN108389175B (en) | Image defogging method integrating variation function and color attenuation prior | |
| CN112419162B (en) | Image defogging method, device, electronic equipment and readable storage medium | |
| Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
| CN108765342A (en) | A kind of underwater image restoration method based on improvement dark | |
| CN107527325B (en) | Monocular underwater vision enhancement method based on dark channel priority | |
| CN107705258B (en) | Underwater image enhancement method based on three-primary-color combined pre-equalization and deblurring | |
| CN111861896A (en) | UUV-oriented underwater image color compensation and recovery method | |
| CN112967273B (en) | Image processing method, electronic device, and storage medium | |
| CN107067375A (en) | A kind of image defogging method based on dark channel prior and marginal information | |
| CN111833258A (en) | Image color correction method based on double-transmittance underwater imaging model | |
| CN111311502A (en) | Method for processing foggy day image by using bidirectional weighted fusion | |
| Kudo et al. | Image dehazing method by fusing weighted near-infrared image | |
| Zhu et al. | Adaptive underwater image enhancement based on color compensation and fusion | |
| CN113962872B (en) | Dual-channel joint optimization night image defogging method | |
| Tao et al. | Improved Retinex for low illumination image enhancement of nighttime traffic | |
| CN117152016A (en) | Image defogging method and system based on improved dark channel prior | |
| Abbaspour et al. | A new fast method for foggy image enhancement | |
| CN113298730B (en) | Defogging restoration method based on image decomposition | |
| Zheng et al. | An illumination adaptive underwater image enhancement method | |
| CN114418874A (en) | Low-illumination image enhancement method | |
| Tong et al. | Infrared and visible image fusion under different illumination conditions based on illumination effective region map | |
| Tang et al. | Single image dehazing algorithm based on sky segmentation | |
| Li et al. | Haze density estimation and dark channel prior based image defogging | |
| Chen et al. | Low-light image enhancement based on Double component processing of Retinex model |
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 |