CN103426151A - Method and device for defogging image - Google Patents
Method and device for defogging image Download PDFInfo
- Publication number
- CN103426151A CN103426151A CN2013103495641A CN201310349564A CN103426151A CN 103426151 A CN103426151 A CN 103426151A CN 2013103495641 A CN2013103495641 A CN 2013103495641A CN 201310349564 A CN201310349564 A CN 201310349564A CN 103426151 A CN103426151 A CN 103426151A
- Authority
- CN
- China
- Prior art keywords
- pixel
- channel value
- image
- value
- dark channel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The invention discloses a method and a device for defogging an image. The method comprises the steps of: calculating a dark channel value of each pixel of a current image, wherein the minimum value of the dark channel value serves as a global environment light value; regarding a straight line where two pixels with the maximum and the minimum dark channel values in the current image as a reference line of the depth of field, and regarding a mean value of dark channel values of all the pixels on a crossed line which forms a preset angle with the reference line of the depth of field as an environment channel value of each pixel on the crossed line; calculating a transmission rate based on the environment channel value of each pixel of the current image and the global environment light value, and performing defogging treatment on the current image according to the obtained transmission rate. By the adoption of the invention, the gradual change law of the density of the fog can be reflected, invalidation of dark primary color prior information can be avoided in reference to the density condition of the pixels surrounding each pixel, better image processing effects can be obtained, and low calculation amount and high processing efficiency are achieved.
Description
Technical field
The present invention relates to image processing techniques, particularly relate to a kind of image defogging method capable and device.
Background technology
The method of at present, mist figure being carried out to the sharpening processing has two classes substantially: based on model and algorithm non-model.Wherein, the algorithm based on model carries out by the immanent cause of understanding image degradation the contrast that inverse operation improves image; The algorithm of non-model does not also require the information of knowing the image degradation reason.We are referred to as the figure image intensifying to process image by the method for non-model; We are referred to as image and recover to use method based on model to process image, and this class algorithm is more reliable, because they have utilized the Physical Mechanism of image degradation, its purpose is to improve the fidelity of degraded image.
In recent years, the research of above-mentioned two aspects has all obtained the recovery problem of larger progress, particularly Physical modeling based, has attracted more and more researchers' attention, below does concise and to the point introduction with regard to its present Research respectively.
The figure image intensifying is the basic means that image is processed, and refers to by some information in the outstanding piece image of specific needs, simultaneously, weakens or remove the disposal route of some unwanted information.It is a traditional topic in image processing field that picture contrast strengthens, and simultaneously another is directly the research field of comparatively enlivening, and still, existing technique computes amount is huge, the computing complexity, and the image processing effect of acquisition is not good yet.
Summary of the invention
Based on this, be necessary for the problems referred to above, a kind of image defogging method capable and device are provided, can obtain rapidly image comparatively clearly by a small amount of computing.
A kind of image defogging method capable comprises:
Calculate the dark channel value of each pixel of present image; Wherein, get the minimum value of described dark channel value as the global context light value;
The straight line at two pixel places that the described dark channel value in present image of take is minimum and maximum is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
Calculate transmissivity according to the environment channel value of each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
Correspondingly, a kind of image demister comprises:
Help computing unit secretly, for the dark channel value of each pixel of calculating present image;
The surround lighting acquiring unit, for the minimum value of getting described dark channel value as the global context light value;
Environment passage acquiring unit, for take the straight line at two minimum and maximum pixel places of described dark channel value in present image, it is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
The mist elimination processing unit be connected respectively with described surround lighting acquiring unit, described environment passage acquiring unit, calculate transmissivity for the environment channel value according to each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
The present invention has following beneficial effect:
The present invention is the dark channel value of each pixel on computed image at first, then demarcate depth of field datum line, described depth of field datum line has reacted " haze " deep or light gradual change rule, with reference to the deep or light situation of each pixel surrounding pixel, avoid the dark primary prior imformation to lose efficacy, thereby obtain better image processing effect.Operand of the present invention is few, and treatment effeciency is high, can be widely used in picture, rainy day picture under haze weather, or even the underwater photography picture, and the processing of the video image under above-mentioned arbitrary environment, in order to improve the sharpness of image.
The accompanying drawing explanation
The process flow diagram that Fig. 1 is image defogging method capable of the present invention;
The embodiment process flow diagram that Fig. 2 is image defogging method capable of the present invention;
The schematic diagram that Fig. 3 is image demister of the present invention;
The embodiment schematic diagram that Fig. 4 is image defogging method capable of the present invention.
Embodiment
For making the purpose, technical solutions and advantages of the present invention clearer, below in conjunction with accompanying drawing, the present invention is described in further detail.
The process flow diagram that Fig. 1 is image defogging method capable of the present invention comprises:
S101: the dark channel value of calculating each pixel of present image; Wherein, get the minimum value of described dark channel value as the global context light value;
S102: the straight line at two pixel places that the described dark channel value in present image of take is minimum and maximum is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
S103: calculate transmissivity according to the environment channel value of each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
The present invention is on the theoretical foundation of physical model, and the imaging mechanism under severe atmospheric conditions has been carried out to deep analysis, and the Enhancement Method of a kind of Misty Image processing proposed.With traditional images wild phase ratio, this method is to be based upon on the physical process of greasy weather imaging, therefore has more specific aim, and treatment effect is also comparatively desirable.
Single image mist elimination technology based on prior imformation, by collecting the image that not affected by fog in a large number, has been found a set of dark primary statistical law that can identify fog concentration.Image is divided into to a plurality of sub-blocks, the very low pixel of some brightness is arranged in each sub-block.These " stains " usually are stored in shadow of object, black object and have in the object of bright-colored.According to this rule, only need to press the local color of repairing the image each several part of fog concentration, just can effectively reach good mist elimination effect, but, when the brightness of scene target is similar to atmosphere light, the dark primary prior imformation will lose efficacy.This is also the difficult problem of prior art, and its adverse consequences is to cause the image local overexposure, or the image generation variable color after mist elimination.The present invention, by the depth of field datum line mist elimination of demarcating, has avoided the generation of dark primary prior imformation failure conditions to a certain extent.Its principle is that the distance of the depth of field in the photograph under haze weather just becomes positive correlation with the concentration of mist, select 2 points that haze is dense and the lightest in photograph, with depth of field datum line of this two-point drawing, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, carry out the mist elimination processing according to default physical model afterwards.
Than, the disposal route of the complexity that some sketch the contours along target edges in figure, the present invention just can obtain mist elimination effect preferably by calculated amount seldom, and treatment effeciency is high, and speed is fast.Can be widely used in picture, rainy day picture under haze weather, or even the underwater photography picture, and the processing of the video image under above-mentioned arbitrary environment, in order to improve the sharpness of image.
The embodiment process flow diagram that Fig. 2 is image defogging method capable of the present invention, compared to Figure 1, the schematic diagram that Fig. 2 is the preferred embodiment of the present invention.
S201: the dark channel value of calculating each pixel of present image;
S202: travel through each pixel according to preset order, according to the described dark channel value of each pixel in the default localized mass of the pixel that comprises current detection, choose the dark channel value of minimum dark channel value as the pixel correction of described current detection;
S203: get the minimum value of described dark channel value as the global context light value;
S204: the straight line at two pixel places that the described dark channel value in present image of take is minimum and maximum is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
S205: calculate transmissivity according to the environment channel value of each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
Calculate the dark channel value of each pixel, according to default from top to down or order from left to right traveled through, according to the described dark channel value of each pixel in the default localized mass of the pixel that comprises current detection, choose the dark channel value I of minimum dark channel value as the pixel correction of described current detection
Dark(x).Described localized mass can be to using the pixel of current detection as the border circular areas at center, and rectangular area, be square area especially; Can be also with (be positioned at the first row first row, coordinate is [1,1]) headed by the pixel of current detection, the matrix dot of composition or nine grids.
In the middle of embodiment, choose centered by the pixel of described current detection therein, default long, default wide rectangular area, as described localized mass.The present embodiment, centered by the pixel of current detection, fully takes into account this pixel " haze " concentration on every side.
Particularly, with the dark channel value I of current pixel
Dark(x) get centered by current pixel, radius is that R(R is defaulted as 6) window in minimum dark channel value in all pixels, that is:
Wherein, I
C(y) be the mainly observation of the outdoor images based on to fine day (haze-free) of shadow passage (Dark Channel) of pixel: the most of pixel for non-day dummy section has at least a Color Channel that low-down brightness value is arranged.Change a kind of saying, the minimum luminance value that is exactly these pixels is very low, can be according to value minimum in a Color Channel RGB and definite, be positioned at the localized mass of x centered by Ω (x).
Find 2 points that haze is dense and the lightest in image, wherein, described dark channel value is less, represents that concentration is larger.Using this two-point drawing straight line as depth of field datum line, on this straight line on the intersecting lens of preset angles the dark channel value of pixel get the average of helping secretly of all pixels on this intersecting lens, as the environment channel value.In addition, get that pixel value that haze is the denseest and be made as global context light A
C, it refers to the surround lighting in atmosphere.Described preset angles, comprise 30 °, 60 °, 90 ° etc., do not do restriction.
Therein in embodiment, choose the average of the dark channel value of each pixel on the vertical line of described depth of field datum line, as the environment channel value of each pixel on described vertical line.Implement the present embodiment, can react better the gradual change rule of " haze " concentration.Be conducive to obtain image more clearly.
So far, on present image, each pixel all has been endowed the environment channel value, according to formula (2), calculates and obtains transmissivity t (x);
Wherein, 0<ω≤1, default value is 0.95; The localized mass that Ω (x) is image block x.
According to described global context light value A
CCalculate transmissivity with the environment channel value of each pixel on present image, according to the described transmissivity obtained, in conjunction with (3) formula, present image is carried out to the mist elimination processing.
Wherein, I (x) is a default physical model.
In the middle of embodiment, utilize described transmissivity therein, choose default atmospheric scattering physical model present image is carried out to the mist elimination processing.Be I (x)=J (x) t (x)+A (1-t (x)), I (x) is the actual image received of greasy weather situation lower sensor, and A (1-t (x)) is surround lighting, and A is global context light, t0=0.1.
In computer vision and computer graphics field, the atmospheric scattering model in greasy weather is following the expression usually:
I(x)＝J(x)t(x)+A(1-t(x)) (1-1)
First is direct attenuation components, and second A (1-t (x)) is surround lighting.I (x) is the actual image received of greasy weather situation lower sensor, and J (x) is the scene radiancy, and A is global context light, and t (x) is transmissivity, means by particle scattering, finally not arrived radiometric ratio of sensor in scene.
Under atmosphere is supposed uniformly, transmissivity t (x) can be expressed as:
t(x)＝e
-βd(x) (1-2)
Wherein, β means the scattering coefficient of atmosphere, and d means the depth of field, and t (x) expression scene radiancy is exponential damping along with the increase of the depth of field.
The mist elimination of Misty Image is exactly mainly from degraded image I (x) restoration scenario radiancy J (x).
To sum up, the present invention does not limit a certain physical model or a certain transmissivity account form.
The schematic diagram that Fig. 3 is image demister of the present invention comprises:
Help computing unit secretly, for the dark channel value of each pixel of calculating present image;
The surround lighting acquiring unit, for the minimum value of getting described dark channel value as the global context light value;
Environment passage acquiring unit, for take the straight line at two minimum and maximum pixel places of described dark channel value in present image, it is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
The mist elimination processing unit be connected respectively with described surround lighting acquiring unit, described environment passage acquiring unit, calculate transmissivity for the environment channel value according to each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
Fig. 3 is corresponding with Fig. 1, identical with in method of the method for operation of unit in figure.
The embodiment schematic diagram that Fig. 4 is image defogging method capable of the present invention.
As described in Figure 4, the present invention comprises:
Help with described the amending unit of helping secretly that computing unit is connected secretly, for according to preset order, traveling through each pixel, according to the described dark channel value of each pixel in the default localized mass of the pixel that comprises current detection, choose the dark channel value of minimum dark channel value as the pixel correction of described current detection.
In the middle of embodiment, described passage amending unit comprises therein:
Unit is chosen in zone, and for choosing centered by the pixel of described current detection, default long, default wide rectangular area, as described localized mass.
In the middle of embodiment, described environment passage acquiring unit comprises therein:
Intersecting lens is chosen unit, for the average of the dark channel value of each pixel on the vertical line of choosing described depth of field datum line, as the environment channel value of each pixel on described vertical line.
In the middle of embodiment, described mist elimination processing unit comprises therein:
Model is chosen unit, for utilizing described transmissivity, chooses default atmospheric scattering physical model present image is carried out to the mist elimination processing.
Fig. 4 is corresponding with Fig. 2, identical with in method of the method for operation of unit in figure.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. an image defogging method capable, is characterized in that, comprising:
Calculate the dark channel value of each pixel of present image; Wherein, get the minimum value of described dark channel value as the global context light value;
The straight line at two pixel places that the described dark channel value in present image of take is minimum and maximum is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
Calculate transmissivity according to the environment channel value of each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
2. image defogging method capable according to claim 1, is characterized in that, after the step of the dark channel value of each pixel of calculating present image, before getting the step of minimum value as the global context light value of described dark channel value, comprising:
Travel through each pixel according to preset order, according to the described dark channel value of each pixel in the default localized mass of the pixel that comprises current detection, choose the dark channel value of minimum dark channel value as the pixel correction of described current detection.
3. image defogging method capable according to claim 2 is characterized in that:
Choose centered by the pixel of described current detection, default long, default wide rectangular area, as described localized mass.
4. according to the described image defogging method capable of claims 1 to 3 any one, it is characterized in that, described basis and described depth of field datum line form the average of the dark channel value of each pixel on the intersecting lens of preset angles, and the step as the environment channel value of each pixel on described intersecting lens comprises:
Choose the average of the dark channel value of each pixel on the vertical line of described depth of field datum line, as the environment channel value of each pixel on described vertical line.
5. according to the described image defogging method capable of claim 1 to 4 any one, it is characterized in that, according to the described transmissivity obtained, present image carried out to the step of mist elimination processing, comprising:
Utilize described transmissivity, choose default atmospheric scattering physical model present image is carried out to the mist elimination processing.
6. an image demister, is characterized in that, comprising:
Help computing unit secretly, for the dark channel value of each pixel of calculating present image;
The surround lighting acquiring unit, for the minimum value of getting described dark channel value as the global context light value;
Environment passage acquiring unit, for take the straight line at two minimum and maximum pixel places of described dark channel value in present image, it is depth of field datum line, according to the average of the dark channel value of each pixel on the intersecting lens with described depth of field datum line formation preset angles, as the environment channel value of each pixel on described intersecting lens;
The mist elimination processing unit be connected respectively with described surround lighting acquiring unit, described environment passage acquiring unit, calculate transmissivity for the environment channel value according to each pixel on described global context light value and present image, according to the described transmissivity obtained, present image is carried out to the mist elimination processing.
7. image demister according to claim 6, is characterized in that, comprising:
Help with described the amending unit of helping secretly that computing unit is connected secretly, for according to preset order, traveling through each pixel, according to the described dark channel value of each pixel in the default localized mass of the pixel that comprises current detection, choose the dark channel value of minimum dark channel value as the pixel correction of described current detection.
8. image demister according to claim 7, is characterized in that, described passage amending unit comprises:
Unit is chosen in zone, and for choosing centered by the pixel of described current detection, default long, default wide rectangular area, as described localized mass.
9. according to the described image demister of claim 6 to 8 any one, it is characterized in that, described environment passage acquiring unit comprises:
Intersecting lens is chosen unit, for the average of the dark channel value of each pixel on the vertical line of choosing described depth of field datum line, as the environment channel value of each pixel on described vertical line.
10. according to the described image demister of claim 6 to 9 any one, it is characterized in that, described mist elimination processing unit comprises:
Model is chosen unit, for utilizing described transmissivity, chooses default atmospheric scattering physical model present image is carried out to the mist elimination processing.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310349564.1A CN103426151B (en) | 2013-08-12 | 2013-08-12 | A kind of image defogging method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310349564.1A CN103426151B (en) | 2013-08-12 | 2013-08-12 | A kind of image defogging method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103426151A true CN103426151A (en) | 2013-12-04 |
| CN103426151B CN103426151B (en) | 2016-06-29 |
Family
ID=49650845
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310349564.1A Expired - Fee Related CN103426151B (en) | 2013-08-12 | 2013-08-12 | A kind of image defogging method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103426151B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103745438A (en) * | 2013-12-31 | 2014-04-23 | 中国科学院深圳先进技术研究院 | Haze removing method for large-area background light haze-containing image |
| CN103824260A (en) * | 2013-12-20 | 2014-05-28 | 中国科学院遥感与数字地球研究所 | High-resolution remote sensing image mist rapid removal technology |
| CN104182943A (en) * | 2014-08-27 | 2014-12-03 | 湖南大学 | Single image haze removal method combined with human vision characteristic |
| CN104331866A (en) * | 2014-10-29 | 2015-02-04 | 中国科学院深圳先进技术研究院 | Image haze removal processing method and device |
| CN104766284A (en) * | 2015-04-17 | 2015-07-08 | 河海大学常州校区 | Underwater color blurred image restoration method |
| CN108681990A (en) * | 2018-04-04 | 2018-10-19 | 高明合 | A kind of real-time haze method for early warning and system |
| CN110493509A (en) * | 2019-06-26 | 2019-11-22 | 盐城华昱光电技术有限公司 | A kind of pattern information processing system and processing method of mode of laser group |
| CN110544213A (en) * | 2019-08-06 | 2019-12-06 | 天津大学 | Image defogging method based on global and local feature fusion |
| CN112864947A (en) * | 2021-03-02 | 2021-05-28 | 山东鲁能软件技术有限公司智能电气分公司 | Visual monitoring system and method |
| CN113014773A (en) * | 2021-03-02 | 2021-06-22 | 山东鲁能软件技术有限公司智能电气分公司 | Overhead line video visual monitoring system and method |
| CN113030638A (en) * | 2021-03-02 | 2021-06-25 | 山东鲁能软件技术有限公司智能电气分公司 | Overhead line image visual monitoring system and method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102063706A (en) * | 2010-12-23 | 2011-05-18 | 哈尔滨工业大学（威海） | Rapid defogging method |
| US20110188775A1 (en) * | 2010-02-01 | 2011-08-04 | Microsoft Corporation | Single Image Haze Removal Using Dark Channel Priors |
-
2013
- 2013-08-12 CN CN201310349564.1A patent/CN103426151B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110188775A1 (en) * | 2010-02-01 | 2011-08-04 | Microsoft Corporation | Single Image Haze Removal Using Dark Channel Priors |
| CN102063706A (en) * | 2010-12-23 | 2011-05-18 | 哈尔滨工业大学（威海） | Rapid defogging method |
Non-Patent Citations (2)
| Title |
|---|
| ZHONGYI HU等: "Image Dehazing Algorithm Based on Atmosphere Scatters Approximation Model", 《NEURAL INFORMATION PROCESSING》, vol. 7667, 31 December 2012 (2012-12-31), pages 159 - 168 * |
| 郭珈等: "基于单幅图像景深和大气散射模型的去雾方法", 《中国图象图形学报》, vol. 17, no. 1, 31 January 2012 (2012-01-31), pages 27 - 32 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824260A (en) * | 2013-12-20 | 2014-05-28 | 中国科学院遥感与数字地球研究所 | High-resolution remote sensing image mist rapid removal technology |
| CN103745438A (en) * | 2013-12-31 | 2014-04-23 | 中国科学院深圳先进技术研究院 | Haze removing method for large-area background light haze-containing image |
| CN104182943A (en) * | 2014-08-27 | 2014-12-03 | 湖南大学 | Single image haze removal method combined with human vision characteristic |
| CN104182943B (en) * | 2014-08-27 | 2015-12-02 | 湖南大学 | A kind of single image defogging method capable merging human-eye visual characteristic |
| CN104331866A (en) * | 2014-10-29 | 2015-02-04 | 中国科学院深圳先进技术研究院 | Image haze removal processing method and device |
| CN104766284A (en) * | 2015-04-17 | 2015-07-08 | 河海大学常州校区 | Underwater color blurred image restoration method |
| CN108681990B (en) * | 2018-04-04 | 2022-05-24 | 高明合 | Real-time haze early warning method and system |
| CN108681990A (en) * | 2018-04-04 | 2018-10-19 | 高明合 | A kind of real-time haze method for early warning and system |
| CN110493509A (en) * | 2019-06-26 | 2019-11-22 | 盐城华昱光电技术有限公司 | A kind of pattern information processing system and processing method of mode of laser group |
| CN110544213A (en) * | 2019-08-06 | 2019-12-06 | 天津大学 | Image defogging method based on global and local feature fusion |
| CN110544213B (en) * | 2019-08-06 | 2023-06-13 | 天津大学 | Image defogging method based on global and local feature fusion |
| CN112864947A (en) * | 2021-03-02 | 2021-05-28 | 山东鲁能软件技术有限公司智能电气分公司 | Visual monitoring system and method |
| CN113014773A (en) * | 2021-03-02 | 2021-06-22 | 山东鲁能软件技术有限公司智能电气分公司 | Overhead line video visual monitoring system and method |
| CN113030638A (en) * | 2021-03-02 | 2021-06-25 | 山东鲁能软件技术有限公司智能电气分公司 | Overhead line image visual monitoring system and method |
| CN113030638B (en) * | 2021-03-02 | 2022-06-14 | 山东鲁软数字科技有限公司智慧能源分公司 | Overhead line image visual monitoring system and method |
| CN112864947B (en) * | 2021-03-02 | 2022-07-05 | 山东鲁软数字科技有限公司智慧能源分公司 | Visual monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103426151B (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103426151A (en) | Method and device for defogging image | |
| CN102831591B (en) | Gaussian filter-based real-time defogging method for single image | |
| CN103020920B (en) | Method for enhancing low-illumination images | |
| CN102063706B (en) | Rapid defogging method | |
| CN103218778B (en) | The disposal route of a kind of image and video and device | |
| CN102768760B (en) | Quick image dehazing method on basis of image textures | |
| CN103049888A (en) | Image/video demisting method based on combination of dark primary color of atmospheric scattered light | |
| CN103198459B (en) | Haze image rapid haze removal method | |
| CN104200445B (en) | Image defogging method with optimal contrast ratio and minimal information loss | |
| CN103778599B (en) | A kind of image processing method and system | |
| CN107301623A (en) | A kind of traffic image defogging method split based on dark and image and system | |
| CN105225210A (en) | A kind of self-adapting histogram based on dark strengthens defogging method capable | |
| CN105913390B (en) | A kind of image defogging method and system | |
| CN107578386A (en) | A kind of optimization defogging processing method of unmanned plane shooting image | |
| CN104036466A (en) | Video defogging method and system | |
| CN104809709A (en) | Single-image self-adaptation defogging method based on domain transformation and weighted quadtree decomposition | |
| CN103578083A (en) | Single image defogging method based on joint mean shift | |
| CN104050637A (en) | Quick image defogging method based on two times of guide filtration | |
| CN102436643A (en) | Image defogging method facing to atmospheric scattering proximity effect | |
| CN103700078A (en) | Defogging method for image with few backgrounds containing fog | |
| CN104616258A (en) | Rapid defogging method for road image | |
| CN103971337A (en) | Infrared image haze removal method based on atmospheric transmission characteristics | |
| CN103034983A (en) | Defogging method based on anisotropic filtering | |
| CN103903234A (en) | Real-time image defogging method based on image field depth | |
| CN106355560A (en) | Method and system for extracting atmospheric light value in haze image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 510670 Guangdong Province, Guangzhou high tech Industrial Development Zone Kezhu Road No. 233 Patentee after: VTRON GROUP Co.,Ltd. Address before: 510663 Guangzhou province high tech Industrial Development Zone, Guangdong, Cai road, No. 6, No. Patentee before: VTRON TECHNOLOGIES Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160629 Termination date: 20210812 |