CN106960421B - Night image defogging method based on statistical characteristics and brightness estimation - Google Patents
Night image defogging method based on statistical characteristics and brightness estimation Download PDFInfo
- Publication number
- CN106960421B CN106960421B CN201710152244.5A CN201710152244A CN106960421B CN 106960421 B CN106960421 B CN 106960421B CN 201710152244 A CN201710152244 A CN 201710152244A CN 106960421 B CN106960421 B CN 106960421B
- Authority
- CN
- China
- Prior art keywords
- image
- night
- light
- defogging
- color cast
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000012937 correction Methods 0.000 claims abstract description 9
- 238000002834 transmittance Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 23
- 238000005286 illumination Methods 0.000 description 9
- 238000000354 decomposition reaction Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 2
- 125000001475 halogen functional group Chemical group 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000004438 eyesight Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a night image defogging method based on statistical characteristics and brightness estimation, which comprises the following steps of: inverting the foggy image at night to obtain an inverted image; calculating the atmospheric light with local color cast of the reverse image, and optimizing through guiding filtering; calculating the initial transmissivity of the three channels and the roughly estimated transmissivity of the three channels, correcting the roughly estimated transmissivity of the three channels by utilizing a bright channel of a reverse image, and obtaining optimized transmissivity through guiding filtering: solving the restored image by utilizing the atmosphere light with color cast locally and the optimized transmissivity, and then reversing again to obtain a defogged image with color cast at night; and carrying out color correction by adopting a local grey word to finally obtain a defogged image at night. The defogged image of the night image obtained by the invention not only can effectively recover the brightness and the contrast of the image, but also can effectively correct the color cast of the night image, obviously improve the visual effect, simultaneously reserve more image detail information and greatly reduce the operation complexity.
Description
Technical Field
The invention relates to a computer image processing method, in particular to a method for defogging an image at night.
Background
When the image is shot in a foggy environment at night, the whole gray value and the contrast of the image are reduced, a large amount of detail information is lost, an interested area is difficult to identify, and great difficulty is brought to video monitoring, outdoor target identification and tracking, remote sensing imaging and the like. Therefore, the problem of image defogging at night needs to be solved in the fields of computer vision application and digital image processing.
The existing method for defogging images at night is few, and mainly has Pei[1]Proposed night image defogging algorithm based on dark channel prior and color conversion, Zhang[2]Proposed defogging algorithm based on new model and Li[3]A hierarchical decomposition defogging algorithm based on relatively smooth constraint, and the like. The defogging main frame of the algorithms is still based on dark channel prior, but the defogging main frame is special due to the foggy image at nightThe imaging environment of (2) is not applicable to dark channel prior in the night environment, so the images restored by the algorithms are dark as a whole, have color distortion of different degrees, have obvious halo effect at an image light source, are not completely defogged, and are complex in calculation.
[ reference documents ]
[1]Pei S C,Lee T Y.Nighttime haze removal using color transfer pre-processing and dark channel prior[A].Proceedings of the IEEE InternationalConference on Image Processing[C].Orlando:IEEE Computer Society Press,2012,957-960。
[2]Zhang J,Cao Y,Wang Z.Nighttime haze removal based on a new imagingmodel[A].Proceedings of the IEEE International Conference on Image Processing[C].Paris:IEEE Computer Society Press,2014.4557-4561。
[3]Li Y,Tan R T,Brown S Michael.Nighttime haze remov-al with glow andmultiple light colors[C].Proceedings of IEEE International Conference onComputer Vi-sion.Santiago:IEEE Computer Society Press,2015:226-234。
[4]He K,Sun J,Tang X.Single image haze removal using dark channelprior[J].Pattern Analysis and Machine Intelligence,IEEE Transactions on,2011,33(12):2341-2353。
[5]G.Buchsbaum.A spatial processor model for object colourperception.Journal of the Franklin Institute,1980,310(80):1–26。
[6]Meng Gaofeng,WANG Ying,DUAN Jiangyong,et al.Efficient imagedehazing with boundary constraint and contextual regularization[C].IEEEInternational Con-ference on Computer Vision(ICCV),Sydney,Australia,2013:617-624。
[7]X.Dong,J.T.Wen,W.X.Li,An efficient and integrated algorithm forvideo enhancement in challenging lighting conditions,in Proceedings ofInstitute of Electrical and Electronic Engineers International Conference onComputer Vision and Pattern Recognition,pp.1241-1249,2011。
Disclosure of Invention
To the aboveThe invention provides a night image defogging method based on statistical characteristics and brightness estimation. Firstly, establishing a new night foggy image model with a color cast factor according to a special imaging environment of the night foggy image; then converting the defogging problem of the image with fog at night into the enhancement problem of the image with low illumination intensity by counting the histogram distribution of the bright channels of the reversed image of the image with fog at night and the image with low illumination intensity and utilizing improved He[4]The method estimates local atmospheric light with color cast, corrects the transmissivity through a bright channel of a reverse image of a foggy image at night to reserve more edge detail information of a defogged image, and finally passes through local grey-world[5]And carrying out color correction on the defogged image. The method for defogging the image at night can effectively restore the brightness and the contrast of the image, can effectively correct the color cast of the image at night, obviously improves the visual effect, simultaneously retains more image detail information and greatly reduces the operation complexity.
In order to solve the technical problem, the invention provides a night image defogging method based on statistical characteristics and brightness estimation, which comprises the following steps:
step 1, the input night fog image is an image I (x), and the image I (x) is inverted to obtain an inverted image
In the formula (1), c belongs to { r, g, b };
step 2, calculating a reverse imageAtmosphere light r with local color castL(x)AL(x) And optimized by guiding filtering:
in the formula (2), Ω (x) is a local neighborhood of the pixel x, Ω (y) is a local neighborhood of the neighborhood y, and GF represents guiding filtering;
step 3, calculating a reverse imageInitial transmittance t of three channels ofaL(x) And roughly estimated transmittance t of three channelsbL(x):
Step 4, utilizing the reverse imageFor the bright channel versus the three channelsbL(x) Correction is performed and optimization is performed by guided filtering:
tL(x)=GF(eA_lighttbL(x)) (6)
in formulae (5) and (6): a _ light is a reverse imageBright channel of, tL(x) For rough estimation of the transmission t for three channelsbL(x) The corrected optimized transmittance;
step 5, utilizing the atmosphere light r with partial color cast obtained in the step 2L(x)AL(x) And the optimized transmittance t obtained in step 4L(x) Solving the restored image rL(x)JL(x):
In formula (7): epsilon is a fixed constant, epsilon is 0.1;
step 6, restoring the image rL(x)JL(x) Then the image is reversed again to obtain a defogged image J with color cast at nightp(x):
Jp(x)=255-r(x)J(x) (8)
Step 7, adopting local grey word to carry out defogging image J with color cast at nightp(x) Color correction is carried out to obtain a final night defogging image J (x),
in formula (9): ω represents the entire visible light range, λ is the wavelength of light, e (λ) represents the distribution of light of a certain wavelength band, s (x, λ) represents the reflectance of a certain point in space to a certain wavelength, p (λ) represents the light sensing characteristic of the camera to a certain light, and m is a constant between [0,1 ].
Compared with the prior art, the invention has the beneficial effects that:
the method comprises the steps of defogging the night image based on statistical characteristics, treating the night foggy image as a low-illumination image, solving local atmospheric light with color cast by using an improved He atmospheric light solving method, correcting the roughly estimated transmissivity by using a bright channel of a reverse image so as to further keep the detail and brightness information of the image, and finally performing color correction on the restored image through a local grey world so as to improve the robustness of the algorithm on the multi-light-source night foggy scene.
Drawings
FIG. 1(a) is a bright channel histogram of a reverse image of a foggy night image;
fig. 1(b) is a bright channel histogram of an inverted image of a low-illuminance image;
FIG. 2(a) is a night fogging image train;
FIG. 2(b) is the result of the defogging algorithm based on the new model in the document [2] after processing the images train;
FIG. 2(c) is the result of document [3] after processing the images train based on the hierarchical decomposition defogging algorithm with relatively smooth constraint;
FIG. 2(d) is the result of processing the images train by the method for defogging images at night according to the present invention;
FIG. 3(a) is a night fog image Street;
FIG. 3(b) is the result of document [2] after the image Street is processed by the defogging algorithm based on the new model;
FIG. 3(c) is the result of document [3] after processing the image Street based on the hierarchical decomposition defogging algorithm with relatively smooth constraint;
fig. 3(d) shows the result of processing the image Street by the night image defogging method according to the present invention.
Detailed Description
The technical solutions of the present invention are further described in detail with reference to the accompanying drawings and specific embodiments, which are only illustrative of the present invention and are not intended to limit the present invention.
The design idea of the night image defogging method is as follows:
1. the algorithm basic principle in the general night image defogging method is as follows: according to document [2], night fog image imaging model:
I(x)=r(x)(J(x)t(x)+(1-t(x))A(x)) ①
wherein, I (x) is a fog image at night, J (x) is a fog image at night, t (x) is a transmittance, A (x) is a background light intensity, and r (x) is a color shift factor.
According to boundary constraints[6]Initial transmittance t of the available foggy day imagea(x) And roughly estimated transmittance tb(x):
And further obtaining a clear image at night:
for low illumination image IL(x) Firstly, reversing the process:
RL(x)=255-IL(x) ⑤
then R isL(x) Substitution of formula ④ yields:
to JL(x) And performing inversion again to obtain the final enhanced image.
2. The method comprises the steps of comparing histogram distribution of bright channels of 50 randomly selected night fogging images and reverse images of 50 low-illumination images, as shown in fig. 1(a) and fig. 1(b), finding that the night fogging images and the reverse images of the low-illumination images have great similarity, so that the problem of defogging of the night fogging images can be converted into the problem of enhancement of the low-illumination images, according to the document [7], regarding the reverse images of the low-illumination images as daytime fogging images, and similarly, regarding the reverse images of the night fogging images as daytime fogging images for processing, but because of the existence of color cast of the night environment, the reverse images of the night fogging images still have the properties of uneven illumination, color cast and the like, and the existing defogging algorithm is still not applicable.
The invention provides a night image defogging method based on statistical characteristics and brightness estimation, which comprises the following specific steps:
step 1, inputting a fog image at night as an image I (x), and inverting the image I (x)Obtaining a reverse image
In the formula (1), c belongs to { r, g, b }, and x is the position of a pixel in an image I (x);
step 2, calculating a reverse imageAtmosphere light r with local color castL(x)AL(x) And optimized by guiding filtering:
in the formula (2), Ω (x) is a local neighborhood of the pixel x, Ω (y) is a local neighborhood of the field y, and GF represents guiding filtering;
step 3, to make the solution of the transmittance more accurate, the document [6 ]]The method for calculating the transmissivity is improved, and the initial transmissivity t of three channels is calculatedaL(x) And roughly estimated transmittance t of three channelsbL(x):
Step 4, using the reversed image to make the transmissivity smooth locally and keep good brightness characteristicFor the bright channel versus the three channelsbL(x) Correction is performed and optimization is performed by guided filtering:
tL(x)=GF(eA_lighttbL(x)) (6)
in formulae (5) and (6): a _ light is a reverse imageBright channel of, tL(x) For rough estimation of the transmission t for three channelsbL(x) The corrected optimized transmittance;
step 5, utilizing the atmosphere light r with partial color cast obtained in the step 2L(x)AL(x) And the optimized transmittance t obtained in step 4L(x) Solving the restored image rL(x)JL(x):
In formula (7): ε is a fixed constant, preventing the denominator to be zero, and ε is taken to be 0.1.
Step 6, restoring the image rL(x)JL(x) Then the image is reversed again to obtain a defogged image J with color cast at nightp(x):
Jp(x)=255-r(x)J(x) (8)
Step 7, in order to improve the robustness of the algorithm to a scene with multiple light sources at night, a document [5 ] is adopted]The greyword algorithm proposed in the publication and the localized improvement are carried out on the defogged image J with color cast at nightp(x) Color correction is carried out to finally obtain a defogged image J (x) at night,
in formula (9): ω represents the entire visible light range, λ is the wavelength of light, e (λ) represents the distribution of light of a certain wavelength band, s (x, λ) represents the reflectance of a certain point in space to a certain wavelength, p (λ) represents the light sensing characteristic of the camera to a certain light, and m is a constant between [0,1 ].
In order to verify the effectiveness of the defogging method for the images at night, the defogging experiment is carried out on the images with the fog at night, and the defogging experiment is compared with a related algorithm. Fig. 2(a) is an image train with fog at night, fig. 2(b) is a defogging effect of the image train after being processed by adopting a defogging algorithm based on a new model proposed by a document [2], fig. 2(c) is a defogging effect of the image train after being processed by adopting a hierarchical decomposition defogging algorithm based on a relative smooth constraint proposed by a document [3], and fig. 2(d) is a defogging effect of the image train after being processed by the defogging method for the image at night. FIG. 3(a) is a night fogging image Street, FIG. 3(b) is a defogging result of the image Street after being processed by the defogging algorithm based on the new model proposed in the document [2], and FIG. 3(c) is a defogging result of the image Street after being processed by the hierarchical decomposition defogging algorithm based on the relative smoothness constraint proposed in the document [3 ]; fig. 3(d) shows the defogging result after the image Street is processed by the night image defogging method according to the invention. Compared with the defogging algorithm based on a new model and the hierarchical decomposition defogging algorithm based on the relative smooth constraint, which are proposed by the document [2] Zhang, the defogging algorithm based on the new model and the hierarchical decomposition defogging algorithm based on the relative smooth constraint, which is proposed by the document [3] Li, the night defogging image processed by the method for defogging the night image can be balanced and improved in brightness and contrast, the halo artifact caused by the light source region can be effectively removed, more image detail information can be recovered, the color cast of the image can be corrected, and the visibility of the visual effect can be better.
In order to objectively evaluate the night image defogging method, the color cast degree and the contrast of the night image defogging are calculated. As shown in table 1.
TABLE 1 Objective index comparison results
The data of the color cast degree in the table 1 shows that the method can effectively correct the color cast of the image; as can be seen from the contrast results, the method of the invention can improve the overall contrast of the defogged image.
Experimental results show that the night image defogging method based on the statistical characteristic and the brightness estimation can effectively correct color cast of the night image, retain more image details, improve the overall brightness and contrast of the image in a balanced manner and have better visual performance aiming at the defects of the traditional night image defogging method based on the dark primary color.
While the present invention has been described with reference to the accompanying drawings, the present invention is not limited to the above-described embodiments, which are illustrative only and not restrictive, and various modifications which do not depart from the spirit of the present invention and which are intended to be covered by the claims of the present invention may be made by those skilled in the art.
Claims (1)
1. A night image defogging method based on statistical characteristics and brightness estimation is characterized by comprising the following steps:
step 1, the input night fog image is an image I (x), and the image I (x) is inverted to obtain an inverted image
In the formula (1), c belongs to { r, g, b };
step 2, calculating a reverse imageAtmosphere light r with local color castL(x)AL(x) And optimized by guiding filtering:
in the formula (2), Ω (x) is a local neighborhood of the pixel x, Ω (y) is a local neighborhood of the neighborhood y, and GF represents guiding filtering;
step 3, calculating a reverse imageInitial transmittance t of three channels ofaL(x) And roughly estimated transmittance t of three channelsbL(x):
Step 4, utilizing the reverse imageFor the bright channel versus the three channelsbL(x) Correction is performed and optimization is performed by guided filtering:
tL(x)=GF(eA_lighttbL(x)) (6)
in formulae (5) and (6): a _ light is a reverse imageBright channel of, tL(x) For rough estimation of the transmission t for three channelsbL(x) The corrected optimized transmittance;
step 5, utilizing the atmosphere light r with partial color cast obtained in the step 2L(x)AL(x) And the optimized transmittance t obtained in step 4L(x) Solving the restored image rL(x)JL(x):
In formula (7): epsilon is a fixed constant, epsilon is 0.1;
step 6, restoring the image rL(x)JL(x) Reversing again to obtain a color cast at nightDefogged image Jp(x):
Jp(x)=255-rL(x)JL(x) (8)
Step 7, adopting local grey word to carry out defogging image J with color cast at nightp(x) Color correction is carried out to obtain a final night defogging image J (x),
in formula (9): ω represents the entire visible light range, λ is the wavelength of light, e (λ) represents the distribution of light of a certain wavelength band, s (x, λ) represents the reflectance of a certain point in space to a certain wavelength, p (λ) represents the light sensing characteristic of the camera to a certain light, and m is a constant between [0,1 ].
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710152244.5A CN106960421B (en) | 2017-03-16 | 2017-03-16 | Night image defogging method based on statistical characteristics and brightness estimation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710152244.5A CN106960421B (en) | 2017-03-16 | 2017-03-16 | Night image defogging method based on statistical characteristics and brightness estimation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106960421A CN106960421A (en) | 2017-07-18 |
CN106960421B true CN106960421B (en) | 2020-04-17 |
Family
ID=59470835
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710152244.5A Expired - Fee Related CN106960421B (en) | 2017-03-16 | 2017-03-16 | Night image defogging method based on statistical characteristics and brightness estimation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106960421B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109658447B (en) * | 2018-11-06 | 2023-03-28 | 天津大学 | Night image defogging method based on edge detail preservation |
CN113112429B (en) * | 2021-04-27 | 2024-04-16 | 大连海事大学 | Universal enhancement frame for foggy images under complex illumination conditions |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105118027A (en) * | 2015-07-28 | 2015-12-02 | 北京航空航天大学 | Image defogging method |
CN105354806A (en) * | 2015-11-20 | 2016-02-24 | 上海熙菱信息技术有限公司 | Dark channel based rapid defogging method and system |
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 |
-
2017
- 2017-03-16 CN CN201710152244.5A patent/CN106960421B/en not_active Expired - Fee Related
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105118027A (en) * | 2015-07-28 | 2015-12-02 | 北京航空航天大学 | Image defogging method |
CN105354806A (en) * | 2015-11-20 | 2016-02-24 | 上海熙菱信息技术有限公司 | Dark channel based rapid defogging method and system |
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 |
Non-Patent Citations (2)
Title |
---|
Nighttime haze removal using color transfer pre-processing and dark channel prior;Pei S C et al.;《Proceedings of the IEEE International Conference on Image Processing》;20121231;第957-960页 * |
Single image haze removal using dark channel prior;He K et al.;《IEEE Transactions》;20111231;第2341-2353页 * |
Also Published As
Publication number | Publication date |
---|---|
CN106960421A (en) | 2017-07-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106157267B (en) | Image defogging transmissivity optimization method based on dark channel prior | |
CN107301623B (en) | Traffic image defogging method and system based on dark channel and image segmentation | |
CN110148095B (en) | Underwater image enhancement method and enhancement device | |
Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
CN108734670B (en) | Method for restoring single night weak-illumination haze image | |
CN109064426B (en) | Method and device for suppressing glare in low-illumination image and enhancing image | |
CN104794688B (en) | Single image to the fog method and device based on depth information separation sky areas | |
CN102170574B (en) | Real-time video defogging system | |
CN109087254B (en) | Unmanned aerial vehicle aerial image haze sky and white area self-adaptive processing method | |
CN112837233B (en) | Polarization image defogging method for acquiring transmissivity based on differential polarization | |
CN107451966B (en) | Real-time video defogging method implemented by guiding filtering through gray level image | |
CN107360344B (en) | Rapid defogging method for monitoring video | |
CN104253930A (en) | Real-time video defogging method | |
CN103258332A (en) | Moving object detection method resisting illumination variation | |
CN104966274B (en) | A kind of On Local Fuzzy restored method using image detection and extracted region | |
CN106960421B (en) | Night image defogging method based on statistical characteristics and brightness estimation | |
CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
CN106327450A (en) | Method for enhancing low-light video image based on space-time accumulation and image degradation model | |
CN110874823A (en) | Mine fog image enhancement method based on dark primary color prior and homomorphic filtering | |
Liang et al. | Learning to remove sandstorm for image enhancement | |
CN106709876B (en) | Optical remote sensing image defogging method based on dark image element principle | |
Tao et al. | Improved Retinex for low illumination image enhancement of nighttime traffic | |
CN107203979B (en) | Low-illumination image enhancement method | |
CN105225245B (en) | Natural image matting method based on the weak hypothesis of grain distribution and Regularization Strategy | |
CN106780381B (en) | Low-illumination image self-adaptive enhancement method based on dark primary color and bilateral filtering |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200417 Termination date: 20210316 |
|
CF01 | Termination of patent right due to non-payment of annual fee |