CN108109129A - A kind of rapid image defogging method based on near-infrared - Google Patents
A kind of rapid image defogging method based on near-infrared Download PDFInfo
- Publication number
- CN108109129A CN108109129A CN201711345888.2A CN201711345888A CN108109129A CN 108109129 A CN108109129 A CN 108109129A CN 201711345888 A CN201711345888 A CN 201711345888A CN 108109129 A CN108109129 A CN 108109129A
- Authority
- CN
- China
- Prior art keywords
- mrow
- image
- msub
- infrared
- fusion
- 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 24
- 230000004927 fusion Effects 0.000 claims abstract description 17
- 239000003595 mist Substances 0.000 claims abstract description 13
- 238000012937 correction Methods 0.000 claims description 9
- 238000000354 decomposition reaction Methods 0.000 claims description 8
- 238000002156 mixing Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract description 4
- 238000010521 absorption reaction Methods 0.000 abstract description 2
- 238000005352 clarification Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 239000000284 extract Substances 0.000 abstract description 2
- 238000003384 imaging method Methods 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 3
- 239000003086 colorant Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011084 recovery Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 239000000443 aerosol Substances 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000003760 hair shine Effects 0.000 description 1
- 238000012880 independent component analysis Methods 0.000 description 1
- 239000011229 interlayer Substances 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 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
- G06T5/50—Image enhancement or restoration using two or more images, e.g. averaging or subtraction
-
- 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
- G06T2207/10048—Infrared 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
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20221—Image fusion; Image merging
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to digital image processing fields, and in particular to a kind of quickly and effectively defogging method based on near-infrared and visual image fusion.Due to the light that imaging sensor receives be scattering after scene light and atmosphere light mixed light, the absorption scattering process of mist, haze, smog, vapor and small water droplet to scene light in air, cause deteriroation of image quality, contrast and color fidelity are lost, this kind of image is referred to as foggy image.In the airport scene monitoring system of view-based access control model image information, foggy image, which seriously affects, extracts clarification of objective, so as to carry out the work such as target detection, target following.Therefore, it is significantly defogging processing to be carried out to foggy image.
Description
Technical field
The invention belongs to digital image processing fields, and in particular to a kind of fast based on near-infrared and visual image fusion
The effective defogging method of speed.
Background technology
Since the light that imaging sensor receives is scene light after scattering and the mixed light of atmosphere light, mist in air,
The absorption scattering process of haze, smog, vapor and small water droplet to scene light, causes deteriroation of image quality, lose contrast and
Color fidelity, this kind of image are referred to as foggy image.In the airport scene monitoring system of view-based access control model image information, there is mist
Image, which seriously affects, extracts clarification of objective, so as to carry out the work such as target detection, target following.Therefore, to having
It is significantly that mist image, which carries out defogging processing,.
Currently, the method for image defogging is broadly divided into two classes：Method based on image enhancement and based on atmospherical scattering model
Method.The method of image enhancement can effectively improve the contrast and color saturation of Misty Image, but image often occurs
Quality declines.Defogging method based on atmospherical scattering model becomes the hot spot of image defogging research in recent years.Fattal is used
Independent component analysis original fog image is incoherent by assuming transmissivity and surface projection in regional area, estimates scenery
Reflectivity, and then realize scene recovery.But this method is based on Color Statistical, can not handle gray level image, and to thick fog figure
The treatment effect of picture is bad.He [5] proposes dark channel prior estimation light transmission transmissivity, realizes that Misty Image is restored, but
It is that transmissivity makes the algorithm time very long using soft pick figure.The it is proposed of wave filter solves the problems, such as that transmissivity reparation is slow,
But it can not solve the problems, such as cross-color.Document shines into atmosphere light row white balance, estimates big gas consumption using quick bilateral filtering
Function is dissipated, simplified atmospherical scattering model is solved and realizes image defogging, however this method is inadequate to the recovery effects of white object
It is preferable.The shortcomings that defogging method based on more than atmospherical scattering model.Schaul et al. propositions are melted based on near-infrared (NIR) image
The defogging method of conjunction, this method is merged by the visible ray of Same Scene with near-infrared image carries out defogging, due to near-infrared figure
As easily obtaining, mist transmitting performance is strong, and defogging process need not be by model solution, therefore defogging algorithm is simple and effective.Tradition
Image Fusion, such as to have interlayer to have related for laplacian pyramid, grad pyramid and ratio low pass pyramid
The shortcomings that property, often there is false profile in the image after fusion.Schaul employs Weighted linear regression (WLS) to image
Decomposed, although obtained blending image without false profile, with the increase of iterations and the change of picture size
Greatly, the algorithm process time steeply rises, and the fogless region of image is susceptible to supersaturation.
The content of the invention
In consideration of it, set forth herein a kind of fast algorithm merged based on visible ray and near-infrared image, while in order to ensure
Picture quality after defogging carries out color correction, finally using navigational figure wave filter to defogging according to mistiness degree to mist elimination image
Image does edge preserving smoothing, finally obtains a distortionless fog free images.
Technical scheme is implemented as follows：
(1) near-infrared image is obtained.The intensity of scattering light is determined by two variables of incident light：The wavelength X of light and scattering grain
The size of son.When aerosol particle is less than λ/10, the Scattering Rules of fog follow the following formula：
As can be seen that the scattering strength E of lightδWith incident intensity E0It is in direct ratio with the quadruplicate ratio of optical wavelength.Namely
Say that wavelength X is longer, scattered light intensity is weaker.Wave band of the visible wavelength between 400-700nm, the wavelength band of NIR are
700-1100nm, therefore with stronger " penetration power ".Therefore, there is greasy weather gas, it is thin that NIR images can include more scenery
Save information.Using 1 spectrum from all good CCD camera of 400-1100nm wave bands frequency response curve, by the side for converting optical filter
Method can obtain near-infrared image and visible images simultaneously, and without doing registration process again.
(2) color space conversion.Image co-registration is by the image of two or two or more merge, and obtains one
The process of the more rich combination picture of information, its object is to the complementary informations of each image of synthesis, improve single-sensor not
Foot.Since NIR images only have single channel information, it is seen that light image has triple channel information, herein it will be seen that light image switchs to HSI skies
Between, and its luminous intensity I passages are merged with NIR images.
(3) near-infrared and visual image fusion.It is calculated herein using the fusion based on dual-tree complex wavelet transform (DT-CWT)
Method carries out image co-registration.Blending algorithm step is as follows：
(a) DT-CWT decomposition is carried out by the following formula respectively to visible ray and near-infrared image I first：
Obtain a series of high-frequency sub-band imagesA series of and low frequency subband image IL.Wherein l represents Decomposition order, and θ is
Decompose direction.
(b) profile information of the mainly image of the low frequency part performance of image, using Weighted Fusion：
FL=0.5 × VL+0.5×NL。
(c) detailed information of the high frequency section high-frequency sub-band reflection image of image, is merged using the spatial frequency of image
Estimate, the ability of the spatial frequency reflection image expression detailed information of image, spatial frequency is bigger, represents the detailed information included
It is more rich.It is as follows to solve image space frequency expression：
The frequency of the row and column of RF and CF difference tabular form images, local spatial frequencies of the pixel (m, n) in the range of [- d, d]
Solve such as following formula：
F (i, j) is the pixel value at (i, j).Spatial frequency is bigger, represents that the detailed information included is more rich.Therefore, high frequency division
The fusion rule of amount is as follows：
FH is fused image, and l represents Decomposition order, and θ is decomposition direction.β merges weight coefficient, and value is determined by following formula：
SFYAnd SFNIt is the local spatial frequencies of visible ray and near-infrared image respectively.It is clear that one width can be rebuild according to above-mentioned calculating
Fogless image, but due to fogless region originally, the luminance channel value of near-infrared and visible images has differences, this causes to melt
Image is closed in fogless region there are part colours distortion, therefore, it is necessary to carry out color correction.
(4) color correction.To reach preferable defog effect, and the clear part of visible images can be retained to greatest extent,
And the detailed information of near-infrared image can be made full use of in fog bank, the present invention according to the concentration of mist to blending image into
Row color correction.Image mist concentration sealing figure is acquired according to dark primary priori principle：
JdarkIt is the dark primary priori of image J, reflects the mistiness degree of image, c represents the RGB channel of image J.Ω (x) be with
Neighborhood centered on point x.
Color correction is carried out to the image of fusion according to the above-mentioned mistiness degree acquired.Updating formula is as follows：
FI=F0×W+VI×(1-W)
F0For the blending image of near-infrared and visible images based on dual-tree complex wavelet transform, W is JdarkNormalization represent, table
Show mist concentration factor, VIFor the luminance channel of visible images.FIFor the image after color calibration.
JdarkIntroducing that image will be caused to occur will be block, the present invention is using navigational figure wave filter to FIIt does edge and keeps flat
It is sliding, image bulk is eliminated, obtains an image for more meeting human-eye visual characteristic.Filtering is as follows：
F '=guidfedfilter (V, FI, r, ∈)
F ' is filtered image, and V is visible images, i.e. navigational figure, and r is section radius, and ε is adjustment parameter, two above
Parameter can be automatically adjusted according to input image size.
The present invention is based on dual-tree complex wavelet to near-infrared and visible images rapid fusion defogging, and carried out according to mistiness degree
Color correction obtains a undistorted fog free images, solves in single image defogging that there are residual mist or cross-colors
Problem.
Description of the drawings
Fig. 1 is the flow chart of image defogging in the embodiment of the present invention.
Fig. 2 is the visible images in the embodiment of the present invention.
Fig. 3 is the near-infrared image in the embodiment of the present invention.
Fig. 4 is the blending image of visible ray and near-infrared in the embodiment of the present invention.
Fig. 5 is mist concentration sealing figure in the embodiment of the present invention.
Fig. 6 is the undistorted fogless figure of correction of a final proof in the embodiment of the present invention.
Claims (6)
1. a kind of fusion defogging method based on near-infrared and visible images, which is characterized in that detailed process is：
(1) near-infrared and visible images are decomposed respectively, that is, asks the dual-tree complex wavelet transform of two images, decomposition layer
Number N=3, obtains a series of high-frequency sub-band imagesWith a series of low frequency subband image IL, wherein l expression decomposition layers
Number, θ are decomposition direction
(2) low frequency sub-band component and high-frequency sub-band component are merged respectively, the fusion rule of low frequency sub-band is：
FL=0.5 × VL+0.5×NL
FL be low-frequency subband fusion image, VLAnd NLIt is the low frequency component of visible ray and near-infrared respectively,
(3) for high-frequency sub-band fusion rule according to the spatial frequency of image, fusion rule is as follows：
<mrow>
<mi>F</mi>
<mi>H</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>)</mo>
</mrow>
<mrow>
<mo>(</mo>
<mo>:</mo>
<mo>,</mo>
<mo>:</mo>
<mo>,</mo>
<mi>&theta;</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<msubsup>
<mi>&beta;V</mi>
<mrow>
<mo>(</mo>
<msup>
<mi>L</mi>
<mo>&prime;</mo>
</msup>
<mo>,</mo>
<mi>&theta;</mi>
<mo>)</mo>
</mrow>
<mi>H</mi>
</msubsup>
<mo>+</mo>
<mrow>
<mo>(</mo>
<mn>1</mn>
<mo>-</mo>
<mi>&beta;</mi>
<mo>)</mo>
</mrow>
<msubsup>
<mi>N</mi>
<mrow>
<mo>(</mo>
<mi>l</mi>
<mo>,</mo>
<mi>&theta;</mi>
<mo>)</mo>
</mrow>
<mi>H</mi>
</msubsup>
</mrow>
Wherein FH is fused image, and l represents Decomposition order, and θ is decomposes direction, and β merges weight coefficient, and value is true by following formula
It is fixed：
<mfenced open = "{" close = "">
<mtable>
<mtr>
<mtd>
<mrow>
<mi>&beta;</mi>
<mo>=</mo>
<mn>1</mn>
<mo>,</mo>
<msub>
<mi>SF</mi>
<mi>Y</mi>
</msub>
<mo>></mo>
<msub>
<mi>SF</mi>
<mi>N</mi>
</msub>
<mo>+</mo>
<mn>1</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>&beta;</mi>
<mo>=</mo>
<mn>0</mn>
<mo>,</mo>
<msub>
<mi>SF</mi>
<mi>N</mi>
</msub>
<mo>></mo>
<msub>
<mi>SF</mi>
<mi>Y</mi>
</msub>
<mo>+</mo>
<mn>1</mn>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<mi>&beta;</mi>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>SF</mi>
<mi>Y</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>SF</mi>
<mi>Y</mi>
</msub>
<mo>+</mo>
<msub>
<mi>SF</mi>
<mi>N</mi>
</msub>
</mrow>
</mfrac>
<mo>,</mo>
<mi>o</mi>
<mi>t</mi>
<mi>h</mi>
<mi>e</mi>
<mi>r</mi>
<mi>s</mi>
</mrow>
</mtd>
</mtr>
</mtable>
</mfenced>
SFYAnd SFNIt is the local spatial frequencies of visible ray and near-infrared image respectively, it is clear to rebuild a width according to above-mentioned calculating
Fogless image.
2. estimating the mistiness degree of image, according to the mistiness of dark primary prior estimate image, following formula can acquire mistiness degree：
<mrow>
<msup>
<mi>J</mi>
<mrow>
<mi>d</mi>
<mi>a</mi>
<mi>r</mi>
<mi>k</mi>
</mrow>
</msup>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<munder>
<mi>min</mi>
<mrow>
<mi>c</mi>
<mo>&Element;</mo>
<mi>r</mi>
<mo>,</mo>
<mi>g</mi>
<mo>,</mo>
<mi>b</mi>
</mrow>
</munder>
<munder>
<mrow>
<mo>(</mo>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
<mo>(</mo>
<msup>
<mi>J</mi>
<mi>c</mi>
</msup>
<mo>(</mo>
<mi>y</mi>
<mo>)</mo>
<mo>)</mo>
<mo>)</mo>
</mrow>
<mrow>
<mi>y</mi>
<mo>&Element;</mo>
<mi>&Omega;</mi>
<mrow>
<mo>(</mo>
<mi>x</mi>
<mo>)</mo>
</mrow>
</mrow>
</munder>
</mrow>
JdarkIt is the dark primary priori of image J, reflects the mistiness degree of image, c represents the RGB channel of image J, and Ω (x) is with point
Neighborhood centered on x carries out color correction according to the above-mentioned mistiness degree acquired to the image of fusion.
3. carrying out color correction to blending image according to mistiness degree, updating formula is as follows：
FI=F0×W+VI×(1-W)
F0For the blending image of near-infrared and visible images based on dual-tree complex wavelet transform, W is JdarkNormalization represent, table
Show mist concentration factor, VIFor the luminance channel of visible images, FIFor the image after color calibration.
4. using navigational figure wave filter to FIEdge preserving smoothing is done, image bulk is eliminated, obtains one and more meet human eye vision
The image of characteristic, filtering are as follows：
F '=guidedfilter (V, FI, r, ∈)
F ' is filtered image, and V is visible images, i.e. navigational figure, and r is section radius, and ε is adjustment parameter, two above
Parameter can be automatically adjusted according to input image size.
5. r values 60 in claim 4, ε values 0.001.
6. the present invention is based on dual-tree complex wavelet to near-infrared and visible images rapid fusion defogging, and face is carried out according to mistiness degree
Color corrects, and obtains a undistorted fog free images, solves asking there are residual mist or cross-color in single image defogging
Topic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711345888.2A CN108109129A (en) | 2017-12-15 | 2017-12-15 | A kind of rapid image defogging method based on near-infrared |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711345888.2A CN108109129A (en) | 2017-12-15 | 2017-12-15 | A kind of rapid image defogging method based on near-infrared |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108109129A true CN108109129A (en) | 2018-06-01 |
Family
ID=62216094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711345888.2A Pending CN108109129A (en) | 2017-12-15 | 2017-12-15 | A kind of rapid image defogging method based on near-infrared |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108109129A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360177A (en) * | 2018-10-17 | 2019-02-19 | 成都森川科技股份有限公司 | The Fast Wavelet fusion method of rapid moving object graphic images and optical imagery |
| CN109934781A (en) * | 2019-02-27 | 2019-06-25 | 合刃科技（深圳）有限公司 | Image processing method, device, terminal device and computer readable storage medium |
| CN110717858A (en) * | 2019-10-09 | 2020-01-21 | 济源职业技术学院 | Image preprocessing method and device under low-illuminance environment |
| WO2021147418A1 (en) * | 2020-01-20 | 2021-07-29 | 腾讯科技（深圳）有限公司 | Image dehazing method and apparatus, device and computer storage medium |
| US11346938B2 (en) | 2019-03-15 | 2022-05-31 | Msa Technology, Llc | Safety device for providing output to an individual associated with a hazardous environment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102243758A (en) * | 2011-07-14 | 2011-11-16 | 浙江大学 | Fog-degraded image restoration and fusion based image defogging method |
| US8755597B1 (en) * | 2011-02-24 | 2014-06-17 | Exelis, Inc. | Smart fusion of visible and infrared image data |
| CN104809709A (en) * | 2015-05-13 | 2015-07-29 | 北京邮电大学 | Single-image self-adaptation defogging method based on domain transformation and weighted quadtree decomposition |
| CN105096272A (en) * | 2015-08-19 | 2015-11-25 | 常州工学院 | De-hazing method based on dual-tree complex wavelet |
| US20160086052A1 (en) * | 2014-09-19 | 2016-03-24 | Brain Corporation | Apparatus and methods for saliency detection based on color occurrence analysis |
| AU2020100274A4 (en) * | 2020-02-25 | 2020-03-26 | Huang, Shuying DR | A Multi-Scale Feature Fusion Network based on GANs for Haze Removal |
-
2017
- 2017-12-15 CN CN201711345888.2A patent/CN108109129A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8755597B1 (en) * | 2011-02-24 | 2014-06-17 | Exelis, Inc. | Smart fusion of visible and infrared image data |
| CN102243758A (en) * | 2011-07-14 | 2011-11-16 | 浙江大学 | Fog-degraded image restoration and fusion based image defogging method |
| US20160086052A1 (en) * | 2014-09-19 | 2016-03-24 | Brain Corporation | Apparatus and methods for saliency detection based on color occurrence analysis |
| CN104809709A (en) * | 2015-05-13 | 2015-07-29 | 北京邮电大学 | Single-image self-adaptation defogging method based on domain transformation and weighted quadtree decomposition |
| CN105096272A (en) * | 2015-08-19 | 2015-11-25 | 常州工学院 | De-hazing method based on dual-tree complex wavelet |
| AU2020100274A4 (en) * | 2020-02-25 | 2020-03-26 | Huang, Shuying DR | A Multi-Scale Feature Fusion Network based on GANs for Haze Removal |
Non-Patent Citations (9)
| Title |
|---|
| CHANGXIN HUANG等: "A Novel Image Dehazing Algorithm Based on Dual-tree Complex Wavelet Transform", 《KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS》 * |
| JIAN CHENG等: "Remote sensing image fusion via wavelet transform and sparse representation", 《ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING》 * |
| QIUYUN WANG: "Depth estimation based underwater image enhancement", 《ADVANCED MATERIALS RESEARCH》 * |
| 万伟国: "应急物流道路识别中的遥感图像融合方法研究", 《中国优秀硕士学位论文全文数据库：信息科技辑》 * |
| 杨晓慧等: "基于ＤＴ-ＣＷＴ的红外与可见光图像自适应融合", 《红外与毫米波学报》 * |
| 杨爱萍等: "基于暗原色融合和维纳滤波的单幅图像去雾", 《天津大学学报(自然科学与工程技术版)》 * |
| 王峰等: "基于MSSTO与NSCT变换的可见光与红外图像增强融合", 《控制与决策》 * |
| 程鹏等: "基于近红外的图像去雾方法", 《四川大学学报（工程科学版）》 * |
| 黄畅昕等: "一种基于近红外和可见光图像融合的去雾方法", 《第七届中国航空学会航空通信导航监视及空管学术会议暨航电与空管分会2016年学术年会 （CCATM2016）》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109360177A (en) * | 2018-10-17 | 2019-02-19 | 成都森川科技股份有限公司 | The Fast Wavelet fusion method of rapid moving object graphic images and optical imagery |
| CN109360177B (en) * | 2018-10-17 | 2021-09-28 | 成都森川科技股份有限公司 | Rapid wavelet fusion method for thermal imaging image and optical image of rapid moving object |
| CN109934781A (en) * | 2019-02-27 | 2019-06-25 | 合刃科技（深圳）有限公司 | Image processing method, device, terminal device and computer readable storage medium |
| CN109934781B (en) * | 2019-02-27 | 2020-10-23 | 合刃科技（深圳）有限公司 | Image processing method, image processing device, terminal equipment and computer readable storage medium |
| US11346938B2 (en) | 2019-03-15 | 2022-05-31 | Msa Technology, Llc | Safety device for providing output to an individual associated with a hazardous environment |
| CN110717858A (en) * | 2019-10-09 | 2020-01-21 | 济源职业技术学院 | Image preprocessing method and device under low-illuminance environment |
| WO2021147418A1 (en) * | 2020-01-20 | 2021-07-29 | 腾讯科技（深圳）有限公司 | Image dehazing method and apparatus, device and computer storage medium |
| US11861810B2 (en) | 2020-01-20 | 2024-01-02 | Tencent Technology (Shenzhen) Company Limited | Image dehazing method, apparatus, and device, and computer storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108109129A (en) | A kind of rapid image defogging method based on near-infrared | |
| CN108734670B (en) | Method for restoring single night weak-illumination haze image | |
| CN103955905B (en) | Based on the single image to the fog method that fast wavelet transform and weighted image merge | |
| CN106846263B (en) | Based on the image defogging method for merging channel and sky being immunized | |
| CN106709893B (en) | A kind of round-the-clock haze image sharpening restoration methods | |
| US9197789B2 (en) | Method and system for removal of fog, mist, or haze from images and videos | |
| CN107133927B (en) | Single image defogging method based on mean-square error dark channel under super-pixel frame | |
| Gao et al. | Sand-dust image restoration based on reversing the blue channel prior | |
| CN102289791B (en) | Method for quickly demisting single image | |
| CN107103591A (en) | A kind of single image to the fog method based on image haze concentration sealing | |
| CN106886985A (en) | A kind of self adaptation enhancement method of low-illumination image for reducing colour cast | |
| CN105701783B (en) | A kind of single image to the fog method and device based on environment light model | |
| CN111563852A (en) | Dark channel prior defogging method based on low-complexity MF | |
| CN111598814B (en) | Single image defogging method based on extreme scattering channel | |
| CN114841885B (en) | Defogging fusion processing method based on polarization image data | |
| Lu et al. | Single underwater image descattering and color correction | |
| CN111489299B (en) | Defogging method for multispectral remote sensing satellite image | |
| CN106780362B (en) | Road video defogging method based on dichromatic reflection model and bilateral filtering | |
| CN109118450A (en) | A kind of low-quality images Enhancement Method under the conditions of dust and sand weather | |
| CN111598811A (en) | Single full-color remote sensing haze image sharpening method | |
| Chen et al. | An improved dark channel prior image defogging algorithm based on wavelength compensation | |
| CN110349113A (en) | One kind being based on the improved adapting to image defogging method of dark primary priori | |
| Jingyun et al. | Real-time defog model based on visible and near-infrared information | |
| Mathur et al. | Dual domain approach for colour enhancement of underwater images | |
| CN110400270A (en) | It is a kind of using picture breakdown and it is multiple correction fusion license plate defogging method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180601 |
|
| WD01 | Invention patent application deemed withdrawn after publication |