CN103632351B - All-weather traffic image enhancement method based on brightness datum drift - Google Patents
All-weather traffic image enhancement method based on brightness datum drift Download PDFInfo
- Publication number
- CN103632351B CN103632351B CN201310689070.8A CN201310689070A CN103632351B CN 103632351 B CN103632351 B CN 103632351B CN 201310689070 A CN201310689070 A CN 201310689070A CN 103632351 B CN103632351 B CN 103632351B
- Authority
- CN
- China
- Prior art keywords
- image
- brightness
- reference value
- luminance reference
- luminance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses an all-weather traffic image enhancement method based on brightness datum drift. The all-weather traffic image enhancement method comprises the following steps: fully considering mutual relation between a monitoring image and the illumination intensity and mutual relation between the monitoring image and the shooting time, analyzing total change and real-time change of illumination, respectively obtaining a brightness datum curve and brightness real-time feedback, and weighting to obtain the brightness datum value of the current time; before enhancing a traffic monitoring image, firstly converting the image from an RGB (Red-Green-Blue) color space to an HSV (Hue-Saturation-Value) color space; on the basis of maintaining constancy of the chrominance information of the image, and applying the brightness datum value to segment a brightness component, thereby obtaining a low-brightness area and a high-brightness area; respectively gaining a drift parameter of each brightness level, obtaining enhanced brightness levels by multiplying each brightness level by the drift parameter of the corresponding brightness level, and finally converting the image to the RGB color space so as to obtain the enhanced image. The all-weather traffic image enhancement method disclosed by the invention has the advantages that when the all-weather real-time monitoring image, especially the image under the conditions of frontlighting and backlighting, is processed, an image with clearer contrast and more obvious useful information can be provided for a user.
Description
Technical field
The invention belongs to intelligent transport system field, relate to a kind of all-weather traffic image based on luminance reference drift and increase
Strong method, is a kind of rapid and effective method realizing traffic image enhancing.
Background technology
It is the people in the useful information in order to strengthen in traffic image, such as image or car that traffic image strengthens, enhancing
Purpose is intended to improve the visual effect of image, for specific occasion, on purpose emphasizes entirety or the local characteristics of image, will
The most unsharp car plate being apparent from or emphasizing in some feature interested, such as image or the face of people in traffic image
Portion's feature, difference between different objects feature in expanded view picture, suppress uninterested feature, be allowed to improve picture quality,
Abundant information amount, strengthens image interpretation and recognition effect, meets the needs of actual traffic monitoring analysis.Along with intelligent transportation field
Develop rapidly, the problem such as image procossing based on video monitoring and computer vision also becomes the hot topic of Recent study and asks
Topic.Research for Intelligent traffic video monitoring has had the time of decades, all takes in terms of theoretical research and actual development
Obtained certain progress.Traffic image has its particularity compared with other images, and traffic image is by the change shadow of illumination and weather
Ringing relatively big, and the image of specific direction collection has along backlight situation, during frontlighting, image entirety is the brightest, and during backlight, specular is very
Bright, shadow region is the darkest.How enhancing effective to traffic image under round-the-clock various weather conditions, becomes current intelligent transportation system
System and image processing field very stubborn problem.
Brightness refers to the physical quantity that luminous body (refractive body) surface light emitting (reflective) is strong and weak.Human eye observes light from a direction
Source, the light source area ratio that light intensity in this direction and human eye institute " see ", it is defined as the brightness of this light source unit, the most singly
Luminous intensity in the projected area of position.Brightness is also a kind of character of color, or with bright related color space
One dimension.General brightness is defined to reflect the bright sensation of subjectivity of the mankind.According to human eye mechanism and the vision mode of people, people
Eye perception brightness and the objective brightness of reality between the most identical.
The brightness in different color space all characterizes the light levels of image color, is a key character of image.Brightness
Being worth the biggest, image is the brightest, and brightness value is the least, and image is the darkest.Luminance reference is then a brightness reference value of image, based on
The change of luminance reference value is then as the change of brightness reference value.
At present, general image enhaucament mode is in accordance with the brightness of image and color information strengthens, and have ignored light
According to fixing variation tendency in time and the Real-time Feedback result of illumination.
It is true that the effect of the enhancing in order to improve image, the method that traffic image strengthens needs to consider image and illumination
Connecting each other between intensity, shooting time, and optimal parameter can be selected to carry out under the conditions of different illumination, different weather
Self adaptation strengthens, and just can be greatly improved the effect of image enhaucament.
Summary of the invention
For the technical problem on solving, the present invention propose one consider image and intensity of illumination, shooting time it
Between connect each other, and optimal parameter can be selected under the conditions of different illumination, different weather to carry out the base of self adaptation enhancing
All-weather traffic image enhancement method in luminance reference drift.This method is applied to traffic image and strengthens, and contrasts common method,
Reinforced effects becomes apparent from, and useful information is more prominent.
The technical solution adopted in the present invention is: a kind of all-weather traffic image enhaucament side based on luminance reference drift
Method, it is characterised in that comprise the following steps:
Step 1: obtain original traffic image；
Step 2: original traffic image is transformed into HSV color space from rgb color space；
Step 3: extract the luminance component channel data of HSV color space traffic image；
Step 4: obtain brightness flop curve according to the entire change of illumination, obtains brightness according to the real-time change of illumination real
Time feedback, both weight after obtain monitor the moment luminance reference value；
Step 5: luminance component channel data is divided into high luminance area and low-light level district according to luminance reference value is the most right
The each intensity level in high luminance area and low-light level district calculates its corresponding drift parameter, and then, each intensity level is multiplied by the drift of correspondence
The intensity level that shifting parameter is new after being strengthened；
Step 6: by new luminance level component and original chromatic component and saturation component combination and be transformed into rgb color
Space obtains the coloured image that original traffic image finally strengthens.
As preferably, described luminance reference value, because the mean flow rate in evening is held essentially constant, therefore the brightness base in evening
Quasi-value is definite value, the luminance reference value on daytime regard crossing towards different become multi-forms Gauss distribution.
As preferably, described luminance reference value, it specifically determines that process is:
The mean flow rate in evening is held essentially constant, and the luminance reference value in evening is set to definite value, it may be assumed that L (t)=c；
The luminance reference value on daytime regard crossing towards difference, crossing, north-south, moment at noon video scene is the brightest,
Morning and at dusk scene are dark, and the change of luminance reference value is arrived low the most again, and whole process Gaussian function represents:
L(t)=l0 *Exp(-(t-μ)2/2σ2)
Wherein l0For the luminance reference value in illumination the strongest moment, μ is brightness curve average, and σ is the standard deviation of brightness curve,
The following principle of selection gist of σ: setting daytime is from moment t0To t1, then t0To t1Include process on whole daytime, and Gauss distribution
Transverse axis interval (μ-2.58 σ, μ+2.58 σ) occupy more than 99.7% ratio of whole distribution, so σ=(t1-t0)/(2.58*
2)；
East and West direction crossing exists along the situation of backlight, if camera is exposed to the west, the morning frontlighting, image entirety is the brightest, in order to make figure
As a rational brightness range, luminance reference should reduce, afternoon backlight, image is the brightest, at the moon in illumination direct projection region
Territory, shadow zone is very dark, and in monitoring, car plate and other useful information of vehicle body all concentrate on shadow region, so luminance reference should carry
High；Otherwise when camera is towards east, this impact along backlight describes with along BLC function:
COM(t)=λsin(w(t-ts))*c0
Wherein λ is penalty coefficient, when camera is exposed to the west on the occasion of, towards being negative value during east, w is the angular frequency of penalty function, ts
The initial time compensated for light, if teThe end time compensated for light, then w=2 π/(te-ts)；c0For standard of compensation value.
By above-mentioned, it is appreciated that the luminance reference curve L(t of t image) can be expressed as:
As preferably, intensity level new after being strengthened described in step 5, it implements process and is: luminance reference value
The region in left side is defined as low brightness area, and the region on the right side of luminance reference value is defined as high-brightness region, first asks for image bright
Degree averageWherein i is brightness value, s (i) be brightness value be the pixel count of i, mpFor the luminance mean value of image,
Then low-light level district offset parameter is asked forOffset parameter with high-brightness regionWherein, l0For step
The luminance reference value in rapid 4 gained image acquisition moment, mpFor the luminance mean value of image, α is the drift ginseng on the left of luminance reference value
Number, β is the drift parameter on the right side of luminance reference value, on the left of luminance reference value and the intensity level of right side area is multiplied by drift respectively
Parameter alpha and β obtain enhanced new intensity level.
Contrasting with existing image enchancing method, what the present invention proposed utilizes luminance reference drift to realize traffic image increasing
Strong method has the advantage that
Intensity of illumination process over time is the key factor affecting picture characteristics.Traditional image enhaucament side
Method relies solely on brightness and the color information enhancing of image itself, lost the time dependent multidate information of image, to along inverse
Light situation and other practical situations complicated and changeable are difficult to the preferable reinforced effects taken.Communication chart based on luminance reference drift
The method of image intensifying, considers image general morphologictrend in time and the real-time slight change of image while strengthening, logical
Cross general morphologictrend and real-time change feedback obtains strengthening moment optimal luminance reference value, then select according to it optimal
Coefficient strengthens, and substantially increases the adaptability to various complex environments, and the method plays effectively carrying out traffic image enhancing
Vital effect.
Accompanying drawing explanation
Fig. 1: for the traffic image Enhancement Method flow chart based on adaption brightness datum drift of the present invention.
Fig. 2: for the luminance reference value curve model schematic diagram of the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the drawings and specific embodiments, the present invention is described further.
Asking for an interview Fig. 1, the technical solution adopted in the present invention is: a kind of all-weather traffic image based on luminance reference drift
Enhancement Method, comprises the following steps:
Step 1: obtain original traffic image.
Step 2: original traffic image is transformed into HSV color space from rgb color space.
Step 3: extract the luminance component channel data of HSV color space traffic image.
Step 4: obtain brightness flop curve according to the entire change of illumination, obtains brightness according to the real-time change of illumination real
Time feedback, both weight after obtain monitor the moment luminance reference value；
Asking for an interview Fig. 2, for the luminance reference value curve model schematic diagram of the embodiment of the present invention, curve shown in λ=0 is camera south
The Northern Dynasties to time luminance reference value curve；Curve shown in λ > 0 is camera luminance reference value curve when being exposed to the west；λ < curve shown in 0 is phase
Machine is towards luminance reference value curve during east；Luminance reference value curve table understands intensity of illumination general morphologictrend in time, each
There is a brightness reference value substantially in the individual moment, is defined as the luminance reference value of current time；
The process that specifically determines of luminance reference value is:
The mean flow rate in evening is held essentially constant, and the luminance reference value in evening can be set to definite value, it may be assumed that L (t)=c(c is
Evening luminance reference definite value).
The luminance reference value on daytime regard crossing towards difference.Crossing, north-south, moment at noon video scene is the brightest,
Morning and at dusk scene are dark, and the change of luminance reference value is arrived low the most again, and whole process can carry out table with Gaussian function
Show:
L(t)=l0 *Exp(-(t-μ)2/2σ2)
Wherein l0For the luminance reference value in illumination the strongest moment, μ is brightness curve average, and σ is the standard deviation of brightness curve,
The following principle of selection gist of σ: setting daytime is from moment t0To t1, then t0To t1Include process on the most whole daytime, and Gauss
The transverse axis of distribution interval (μ-2.58 σ, μ+2.58 σ) occupies more than 99.7% ratio of whole distribution, so σ=(t1-t0)/
(2.58*2)。
East and West direction crossing exists along the situation of backlight, if camera is exposed to the west, the morning frontlighting, image entirety is the brightest, in order to make figure
As a rational brightness range, luminance reference should reduce, afternoon backlight, image is the brightest, at the moon in illumination direct projection region
Territory, shadow zone is very dark, and in monitoring, car plate and other useful information of vehicle body all concentrate on shadow region, so luminance reference should carry
High；Otherwise when camera is towards east.This impact along backlight describes with along BLC function:
COM(t)=λsin(w(t-ts))*c0
Wherein λ is penalty coefficient, when camera is exposed to the west on the occasion of, towards being negative value during east, w is the angular frequency of penalty function, ts
The initial time compensated for light, if teThe end time compensated for light, then w=2 π/(te-ts)；c0For standard of compensation value.
By above-mentioned, it is appreciated that the luminance reference curve L(t of t image) can be expressed as:
In luminance reference value curve, under different weather and illumination condition, in the same time period, image has bigger difference, only
Determine that luminance reference value may make image bigger with real image deviation only with luminance reference value curve.The present invention uses
Brightness Real-time Feedback carrys out auxiliary judgment luminance reference value, first obtains luminance reference value L in this moment according to luminance reference curve
T (), then calculates present image luminance mean value μ and luminance reference value L(t) between deviation E=μ-L(t), then the brightness of image
Correction is: Δ B (t)=η E, and wherein η is for revising step-length, and E is the deviation between present image luminance mean value and luminance reference value.
In practice, due to acute variation or the interference of moving object of illumination, front and back two frame luminance differences may be relatively big, in order to make brightness
Correction tends to a stable change, plus previous brightness correction amount in correction, is defined as Inertia, it may be assumed that Δ
Bk(t)=ηE+αΔBk-1(t), wherein Δ BkT () is present frame brightness correction amount, Δ Bk-1T () is previous frame brightness correction amount, α
For Inertia coefficient, its value is between 0～1.
Final adaption brightness reference value is added by brightness curve and brightness Real-time Feedback and obtains:
L(t)B(t)=L(t)+Δ Bk(t)
Step 5: luminance component channel data is divided into high luminance area and low-light level district according to luminance reference value is the most right
The each intensity level in high luminance area and low-light level district calculates its corresponding drift parameter, and then, each intensity level is multiplied by the drift of correspondence
The intensity level that shifting parameter is new after being strengthened；
Region on the left of luminance reference value is defined as low brightness area, and the region on the right side of luminance reference value is defined as high brightness
Region, first asks for brightness of image averageWherein i is brightness value, s (i) be brightness value be the pixel count of i, mp
For the luminance mean value of image, then ask for low-light level district offset parameterOffset parameter with high-brightness regionWherein, l0For the luminance reference value in step 4 gained image acquisition moment, mpFor the luminance mean value of image, α is
Drift parameter on the left of luminance reference value, β is the drift parameter on the right side of luminance reference value, on the left of luminance reference value and right side region
The intensity level in territory is multiplied by drift parameter α and β respectively and obtains enhanced new intensity level.
Step 6: by new luminance level component and original chromatic component and saturation component combination and be transformed into rgb color
Space obtains the coloured image that original traffic image finally strengthens.
These are only presently preferred embodiments of the present invention, be not intended to limit protection scope of the present invention, therefore, all
Any modification, equivalent substitution and improvement etc. made within the spirit and principles in the present invention, should be included in the protection model of the present invention
Within enclosing.
Claims (1)
1. an All-weather traffic image enhancement method based on luminance reference drift, it is characterised in that comprise the following steps:
Step 1: obtain original traffic image；
Step 2: original traffic image is transformed into HSV color space from rgb color space；
Step 3: extract the luminance component channel data of HSV color space traffic image；
Step 4: obtain brightness flop curve according to the entire change of illumination, obtains brightness according to the real-time change of illumination the most anti-
Feedback, obtains monitoring the luminance reference value in moment after both are weighted；
Described luminance reference value, the luminance reference value in its evening is definite value, and the luminance reference value on daytime regards crossing towards not
With the Gauss distribution becoming multi-form；The process that specifically determines of described luminance reference value is:
The mean flow rate in evening is held essentially constant, and the luminance reference value in evening is set to definite value, it may be assumed that L (t)=c；
The luminance reference value on daytime regard crossing towards difference, crossing, north-south, moment at noon video scene is the brightest, morning
Dark with dusk scene, the change of luminance reference value is arrived low the most again, and whole process Gaussian function represents:
L (t)=l0*exp(-(t-μ)2/2σ2)
Wherein l0For the luminance reference value in illumination the strongest moment, μ is brightness curve average, and σ is the standard deviation of brightness curve, the choosing of σ
Select according to following principle: setting daytime is from moment t0To t1, then t0To t1Include process on whole daytime, and the horizontal stroke of Gauss distribution
Axle interval (μ-2.58 σ, μ+2.58 σ) occupies more than 99.7% ratio of whole distribution, so σ=(t1-t0)/(2.58*2)；
East and West direction crossing exists along the situation of backlight, if camera is exposed to the west, the morning frontlighting, image entirety is the brightest, in order to make image exist
One rational brightness range, luminance reference should reduce, afternoon backlight, image is the brightest, in shadow region in illumination direct projection region
Territory is very dark, and in monitoring, car plate and other useful information of vehicle body all concentrate on shadow region, so luminance reference should improve；Phase
Otherwise when machine is towards east, this impact along backlight describes with along BLC function:
COM (t)=λ sin (w (t-ts))*c0
Wherein λ is penalty coefficient, when camera is exposed to the west on the occasion of, towards being negative value during east, w is the angular frequency of penalty function, tsMend for light
The initial time repaid, if teThe end time compensated for light, then w=2 π/(te-ts)；c0For standard of compensation value；
By above-mentioned, it is appreciated that luminance reference curve L (t) of East and West direction crossing t image can be expressed as:
Step 5: according to luminance reference value, luminance component channel data is divided into high luminance area and low-light level district, respectively to highlighted
Degree district and each intensity level in low-light level district calculate its corresponding drift parameter, and then, each intensity level is multiplied by the drift ginseng of correspondence
The intensity level that number is new after being strengthened；
Described strengthened after new intensity level, it implements process and is: the region on the left of luminance reference value is defined as low bright
Degree region, the region on the right side of luminance reference value is defined as high-brightness region, first asks for brightness of image averageIts
In, i is brightness value, s (i) be brightness value be the pixel count of i, mpLuminance mean value for image；Then the skew of low-light level district is asked for
ParameterOffset parameter with high-brightness regionWherein, l0For the step 4 gained image acquisition moment
Luminance reference value, mpFor the luminance mean value of image, α is the drift parameter on the left of luminance reference value, and β is on the right side of luminance reference value
Drift parameter；To on the left of luminance reference value and the intensity level of right side area be multiplied by respectively drift parameter α and β obtain enhanced newly
Intensity level；
Step 6: by new luminance level component and original chromatic component and saturation component combination and be transformed into rgb color space
Obtain the coloured image that original traffic image finally strengthens.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310689070.8A CN103632351B (en) | 2013-12-16 | 2013-12-16 | All-weather traffic image enhancement method based on brightness datum drift |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310689070.8A CN103632351B (en) | 2013-12-16 | 2013-12-16 | All-weather traffic image enhancement method based on brightness datum drift |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103632351A CN103632351A (en) | 2014-03-12 |
| CN103632351B true CN103632351B (en) | 2017-01-11 |
Family
ID=50213368
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310689070.8A Active CN103632351B (en) | 2013-12-16 | 2013-12-16 | All-weather traffic image enhancement method based on brightness datum drift |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103632351B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104112290A (en) * | 2014-06-19 | 2014-10-22 | 中国科学院深圳先进技术研究院 | RGB color image processing method and system |
| CN104184974B (en) * | 2014-09-03 | 2018-02-09 | 北京时代奥视科技股份有限公司 | The screening technique and device of video luminance signal display methods and anomalous video signal |
| CN104778674B (en) * | 2015-04-30 | 2018-01-12 | 武汉大学 | A kind of suitable backlight traffic image self-adapting enhancement method based on time series |
| CN105303543A (en) * | 2015-10-23 | 2016-02-03 | 努比亚技术有限公司 | Image enhancement method and mobile terminal |
| CN105574820A (en) * | 2015-12-04 | 2016-05-11 | 南京云石医疗科技有限公司 | Deep learning-based adaptive ultrasound image enhancement method |
| CN106791471B (en) * | 2016-12-29 | 2021-07-20 | 宇龙计算机通信科技(深圳)有限公司 | Image optimization method, image optimization device and terminal |
| CN107292898B (en) * | 2017-05-04 | 2019-09-10 | 浙江工业大学 | A kind of license plate shadow Detection and minimizing technology based on HSV |
| CN108600631B (en) * | 2018-05-16 | 2021-03-12 | Oppo广东移动通信有限公司 | Image processing method, image processing device, computer-readable storage medium and electronic equipment |
| CN108629329B (en) * | 2018-05-17 | 2021-04-23 | Oppo广东移动通信有限公司 | Image processing method and device, electronic equipment and computer readable storage medium |
| CN112581400B (en) * | 2020-12-22 | 2024-05-31 | 安徽圭目机器人有限公司 | Gaussian standard deviation and contrast ratio based tuned image enhancement method |
| CN114298935B (en) * | 2021-12-27 | 2024-06-04 | 重庆港宇高科技开发有限公司 | Image enhancement method, device and computer readable storage medium |
| CN115841431B (en) * | 2023-02-06 | 2023-05-05 | 淄博市临淄区交通运输事业服务中心 | Traffic transportation image enhancement method based on video monitoring |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101982825A (en) * | 2010-11-04 | 2011-03-02 | 杭州海康威视系统技术有限公司 | Method and device for processing video image under intelligent transportation monitoring scene |
| CN102231206A (en) * | 2011-07-14 | 2011-11-02 | 浙江理工大学 | Colorized night vision image brightness enhancement method applicable to automotive assisted driving system |
-
2013
- 2013-12-16 CN CN201310689070.8A patent/CN103632351B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101982825A (en) * | 2010-11-04 | 2011-03-02 | 杭州海康威视系统技术有限公司 | Method and device for processing video image under intelligent transportation monitoring scene |
| CN102231206A (en) * | 2011-07-14 | 2011-11-02 | 浙江理工大学 | Colorized night vision image brightness enhancement method applicable to automotive assisted driving system |
Non-Patent Citations (2)
| Title |
|---|
| 夜间交通视频图像增强方法研究和应用;张铿等;《交通信息与安全》;20130220;83-86 * |
| 智能交通系统中运动目标检测方法的研究;高大山;《中国优秀硕士学位论文全文数据库（电子期刊）》;20040229;第2.2.1-2.2.2节，第3.2.5节，附图2-1 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103632351A (en) | 2014-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103632351B (en) | All-weather traffic image enhancement method based on brightness datum drift | |
| CN102129673B (en) | Color digital image enhancing and denoising method under random illumination | |
| CN102231206B (en) | Colorized night vision image brightness enhancement method applicable to automotive assisted driving system | |
| CN106897981A (en) | A kind of enhancement method of low-illumination image based on guiding filtering | |
| CN103593830B (en) | A kind of low illumination level video image enhancement | |
| CN102693532B (en) | The automatic local directed complete set of image shadow and highlight | |
| CN104778674B (en) | A kind of suitable backlight traffic image self-adapting enhancement method based on time series | |
| CN102509272B (en) | Color image enhancement method based on color constancy | |
| CN103714520B (en) | Digital video image strengthening system and its method are realized based on FPGA | |
| CN101170642B (en) | A dynamically video image processing method | |
| CN109447910A (en) | A kind of low-luminance color image enchancing method based on fuzzy theory | |
| CN102496152B (en) | Self-adaptive image contrast enhancement method based on histograms | |
| CN105046663A (en) | Human visual perception simulation-based self-adaptive low-illumination image enhancement method | |
| CN104349070A (en) | High dynamic range image exposure time control method | |
| CN101783963A (en) | Nighttime image enhancing method with highlight inhibition | |
| CN108416754A (en) | A kind of more exposure image fusion methods automatically removing ghost | |
| CN107909562A (en) | A kind of Fast Image Fusion based on Pixel-level | |
| Zheng et al. | Infrared traffic image enhancement algorithm based on dark channel prior and gamma correction | |
| CN104268843A (en) | Image self-adaptation enhancing method based on histogram modification | |
| CN106169182A (en) | A kind of method synthesizing several different exposure images | |
| CN110570360A (en) | Retinex-based robust and comprehensive low-quality illumination image enhancement method | |
| CN110473152A (en) | Based on the image enchancing method for improving Retinex algorithm | |
| CN110706172A (en) | Low-illumination color image enhancement method based on adaptive chaotic particle swarm optimization | |
| CN113822826B (en) | Low-illumination image brightness enhancement method | |
| CN110223262A (en) | A kind of rapid image fusion method based on Pixel-level |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |