CN113724147B - Color image turbulence removing system and method based on space-time information reconstruction - Google Patents
Color image turbulence removing system and method based on space-time information reconstruction Download PDFInfo
- Publication number
- CN113724147B CN113724147B CN202110801270.2A CN202110801270A CN113724147B CN 113724147 B CN113724147 B CN 113724147B CN 202110801270 A CN202110801270 A CN 202110801270A CN 113724147 B CN113724147 B CN 113724147B
- Authority
- CN
- China
- Prior art keywords
- time domain
- background model
- model
- module
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000004044 response Effects 0.000 claims abstract description 15
- 238000009792 diffusion process Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 26
- 230000002123 temporal effect Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003707 image sharpening Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
- G06T5/94—Dynamic range modification of images or parts thereof based on local image properties, e.g. for local contrast enhancement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Color Image Communication Systems (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
Abstract
A color image turbulence removing system and method based on space-time information reconstruction, the method includes: for any pixel, a time domain background model of each pixel is built and obtained by utilizing the characteristic that the pixel points in adjacent areas have similar time distribution; carrying out histogram statistics on the time domain background model of each pixel point, obtaining the gray value of each pixel point in the corresponding time domain background model, and obtaining the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the largest frequency occurrence; acquiring the brightness marks of the pixel points through the statistical information of the histogram, and selecting the maximum or minimum value from the corresponding time domain background model as the output response of the current value; and randomly updating the output response of the current value into each adjacent domain of the corresponding time domain background model by adopting an updating strategy of random adjacent domain diffusion. The invention can realize stable display of image quality in turbulent environment, eliminate image distortion caused by turbulent environment and improve image contrast.
Description
Technical Field
The invention relates to a visible light color imaging system, in particular to a color image turbulence removing system and method based on space-time information reconstruction.
Background
Atmospheric turbulence can cause non-uniformity in air density, resulting in different optical refractive indices of portions of the hot air mass, thereby causing direct light rays passing through the hot air mass to deflect, bend and scatter, and further resulting in distortion and blurring of the observed object scene, i.e., turbulence effects. At present, domestic researches on the phenomenon are basically in a blank state, and a traditional image deblurring method is partially adopted for migration research.
Because of the existence of multi-scale vortex in the atmospheric turbulence, for the turbulence effect, the phase distortion and the amplitude of the light wave during transmission are different, and the change of the light wave is irregular, the modeling calibration of the turbulence fuzzy video image is difficult to carry out through a fixed model, but in practical application, the observation and the research of a target are seriously influenced, so that the turbulence removing technology requirement of the color image is increasingly urgent.
Disclosure of Invention
In view of the technical drawbacks and technical shortcomings existing in the prior art, embodiments of the present invention provide a color image turbulence removing system and method based on temporal-spatial information reconstruction, which overcome or at least partially solve the above problems, and the specific scheme is as follows:
As a first aspect of the present invention, there is provided a color image turbulence removal system based on temporal-spatial information reconstruction, the system comprising a temporal background modeling module, a histogram statistics module, a maximum/minimum filtering module, and a temporal model updating module:
The time domain background modeling module is used for establishing a time domain background model of each pixel point by utilizing the characteristic that the pixel points of adjacent areas have similar time distribution for any pixel;
The histogram statistics module is used for carrying out histogram statistics on the time domain background model of each pixel point, acquiring the gray value of each pixel point in the corresponding time domain background model, and acquiring the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the most frequency occurrence;
The maximum/minimum value filtering module is used for obtaining the brightness marks of the pixel points through the histogram statistical information, and selecting the maximum value or the minimum value from the corresponding time domain background model as the output response of the current value;
The time domain model updating module is used for randomly updating the output response of the current value into each adjacent domain of the corresponding time domain background model by adopting an updating strategy of random adjacent domain diffusion.
Further, the system further comprises a color space conversion module, wherein the color space conversion module is used for converting the RGB color image into a Lab color space image before the time domain background modeling module performs time domain modeling, separating brightness and chromaticity, respectively processing a brightness channel and a chromaticity channel in the Lab space, combining the processed channels, and finally converting the Lab color space into the RGB color space.
Further, the system also comprises a Laplacian airspace enhancing module, wherein the Laplacian airspace enhancing module is used for carrying out airspace enhancement on the time domain modeled image before the time domain model updating module carries out the updating strategy, so that the layering sense and the detail information of the image are improved.
Further, the Laplace operator airspace enhancement module specifically performs airspace enhancement processing on the image through the Laplace divalent operator.
Further, the time domain model updating module specifically updates the time domain background model of each pixel point by a random sampling factor, and specifically comprises the following steps:
let the random sampling factor be phi, let the random sampling factor default to 16, denoted by phi 0;
if the random sampling factor phi is fixed, the time domain background model is indicated The larger the standard deviation delta is, the more complex the time domain information is, the more obvious the turbulence fluctuation is, and the smaller the random sampling factor phi is, so as to improve the updating probability of the model; the smaller the standard deviation delta, the smaller the sample fluctuation in the time domain model, i.e. the smaller the complexity of the time domain.
Further, the decision of the random sampling factor phi (x, y) of the pixel point p (x, y) is specifically as follows:
As a second aspect of the present invention, there is provided a color image turbulence removing method based on spatiotemporal information reconstruction, the method comprising:
For any pixel, a time domain background model of each pixel is built and obtained by utilizing the characteristic that the pixel points in adjacent areas have similar time distribution;
Carrying out histogram statistics on the time domain background model of each pixel point, obtaining the gray value of each pixel point in the corresponding time domain background model, and obtaining the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the largest frequency occurrence;
Acquiring the brightness marks of the pixel points through the statistical information of the histogram, and selecting the maximum or minimum value from the corresponding time domain background model as the output response of the current value;
And randomly updating the output response of the current value into each adjacent domain of the corresponding time domain background model by adopting an updating strategy of random adjacent domain diffusion.
Further, the method further comprises: before the time domain background modeling module performs time domain modeling, converting the RGB color image into a Lab color space image, separating brightness and chromaticity, respectively processing a brightness channel and a chromaticity channel in the Lab space, merging the processed channels, and finally converting the Lab color space into the RGB color space.
Further, the method further comprises: before the time domain model updating module performs updating strategy, spatial domain enhancement is performed on the time domain modeled image, and layering sense and detail information of the image are improved.
Further, the time domain model updating module specifically updates the time domain background model of each pixel point by a random sampling factor, and specifically comprises the following steps:
let the random sampling factor be phi, let the random sampling factor default to 16, denoted by phi 0;
if the random sampling factor phi is fixed, the time domain background model is indicated The larger the standard deviation delta is, the more complex the time domain information is, the more obvious the turbulence fluctuation is, and the smaller the random sampling factor phi is, so as to improve the updating probability of the model; the smaller the standard deviation delta, the smaller the sample fluctuation in the time domain model, i.e. the smaller the complexity of the time domain.
The invention has the following beneficial effects:
1) Eliminating the heat wave effect: and (3) taking the influence of air temperature, air flow, humidity and the like on imaging into consideration, constructing a time domain and space domain information model, fully mining the real information of the target, and overcoming the image heat wave effect caused by pseudo information imaging.
2) Image contrast is improved: because the time domain information is modeled, histogram statistics is carried out on the time domain information, bright/dark marking is carried out on pixels, selective output is carried out, and therefore contrast is improved.
3) The image detail is rich: and carrying out image sharpening operation by using a Laplacian operator in the airspace, and improving image details.
4) The color is more saturated: the luminance and chromaticity of the target object are respectively adjusted by utilizing the luminance and chromaticity separation characteristics of the Lab color space.
Drawings
FIG. 1 is a block diagram of a color image turbulence removal system based on temporal and spatial information reconstruction according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating color space conversion according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of modeling a time domain background according to an embodiment of the present invention;
FIG. 4 is a histogram statistical diagram provided in an embodiment of the present invention;
FIG. 5 is a schematic diagram of a Laplace core according to an embodiment of the present invention;
Fig. 6 is a flowchart of a method for removing turbulence in a color image based on spatial-temporal information reconstruction according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, as a first embodiment of the present invention, there is provided a color image turbulence removing system based on space-time information reconstruction, the system including 6 functional modules, respectively: the system comprises a color space conversion module, a time domain background modeling module, a histogram statistics module, a maximum/minimum value filtering module, a Laplacian airspace enhancement module and a time domain model updating module.
The color space conversion module is used for converting the color space into Lab color space, separating brightness and chromaticity aiming at two characteristics of low brightness and low saturation of the turbulence image, and respectively adjusting the brightness and the chromaticity of the image. The luminance channel and the chrominance channel are processed in the Lab space respectively, the processed channels are combined, and finally the Lab color space is converted into the RGB color space, as shown in FIG. 2.
The time domain background modeling module is used for establishing a time domain background model of each pixel point by utilizing the characteristic that the pixel points of adjacent areas have similar time distribution for any pixel.
The time domain background modeling is a process of establishing a background model, for any pixel, by utilizing the characteristic that adjacent area pixel points have similar time distribution, randomly selecting the pixel points in the eight neighborhood range as initial sample values of the background model, and enabling the sample set size of each pixel to be N (N is generally 20), wherein the background model of the pixel point p (x, y) is as follows:
M(x,y)＝{p1(x,y),p2(x,y),…,pi(x,y),…,pN(x,y)}
wherein p i (x, y) is a pixel point randomly selected in eight neighborhoods of the pixel p (x, y)
As shown in fig. 3, the temporal background modeling is divided into 2 parts, where one part circularly stores 20 frames of gray value information for each image point, and the other part circularly updates the 8 neighborhood of each image point, that is, updates the temporal model of the 8 neighborhood when updating the pixel of each image point.
The histogram statistics module is used for carrying out histogram statistics on the time domain background model of each pixel point, obtaining the gray value of each pixel point in the corresponding time domain background model, and obtaining the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the largest frequency occurrence.
In the above embodiment, histogram statistics are performed on the time domain model of each pixel, as shown in fig. 4. The minimum gray value, the average value, the maximum gray value and the gray value with the largest occurrence frequency of the pixel point in the time domain can be obtained through the histogram, and the invention defines a distance judgment standard for the lighting and darkness of an image as follows:
Wherein, the bright and dark marks are 1, namely bright and dark marks are 0, namely dark, MAX represents the minimum gray value, MEAN represents the gray average value, and MIN represents the maximum gray value.
The maximum/minimum value filtering module is used for obtaining the brightness marks of the image points through the histogram statistical information, selecting the maximum or minimum value from the corresponding time domain background model as the output response of the current value, namely:
That is, when the light-dark flag is 1, the maximum value p max (x, y) is selected as the output response p (x, y) of the current value in the corresponding time-domain background model, and when the light-dark flag is 0, the maximum value p min (x, y) is selected as the output response p (x, y) of the current value in the corresponding time-domain background model.
The time domain model updating module is used for randomly updating the time domain model into the eight adjacent domains of the corresponding pixel points by adopting an updating strategy of random adjacent domain diffusion.
Let the random sampling factor be phi (by default 16, denoted by phi 0), the update procedure of the temporal background model M (x, y) for each pixel p (x, y) is as follows:
If the random sampling factor phi is fixed, the time domain model is shown to be Probability updates of (c) are provided. The standard deviation delta of the sample in the time domain model can reflect the complexity of the background, and the larger the standard deviation delta is, the more complex the time domain information is, the more obvious the turbulence fluctuation is, and the smaller the random sampling factor phi is so as to improve the updating probability of the model; the smaller the standard deviation delta, the smaller the sample fluctuation in the time domain model, i.e. the smaller the complexity of the time domain.
Then the decision of the random sampling factor phi (x, y) for pixel point p (x, y) is as follows:
The Laplace operator airspace enhancement module is used for carrying out airspace enhancement on the time-domain-modeled image before the time-domain model updating module carries out updating strategy, and improving layering sense and detail information of the image
The image is subjected to spatial enhancement processing by adopting a Laplace divalent operator, and Laplace transformation of the image is defined as the sum of second derivatives, and specifically comprises the following steps:
In its simplest form, it can use a3 x 3 kernel approximation as shown in fig. 5, with contrast enhanced by subtracting its Laplace from a pair of images.
As shown in fig. 6, as a second aspect of the present invention, there is also provided a color image turbulence removing method based on temporal-spatial information reconstruction, the method comprising:
For any pixel, a time domain background model of each pixel is built and obtained by utilizing the characteristic that the pixel points in adjacent areas have similar time distribution;
Carrying out histogram statistics on the time domain background model of each pixel point, obtaining the gray value of each pixel point in the corresponding time domain background model, and obtaining the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the largest frequency occurrence;
Acquiring the brightness marks of the pixel points through the statistical information of the histogram, and selecting the maximum or minimum value from the corresponding time domain background model as the output response of the current value;
And randomly updating the output response of the current value into each adjacent domain of the corresponding time domain background model by adopting an updating strategy of random adjacent domain diffusion.
Wherein the method further comprises: before the time domain background modeling module performs time domain modeling, converting an RGB color image into a Lab color space image, separating brightness and chromaticity, respectively processing a brightness channel and a chromaticity channel in the Lab space, merging the processed channels, and finally converting the Lab color space into an RGB color space; before the time domain model updating module performs updating strategy, spatial domain enhancement is performed on the time domain modeled image, and layering sense and detail information of the image are improved.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (8)
1. A color image turbulence removing system based on space-time information reconstruction, which is characterized by comprising a time domain background modeling module, a histogram statistics module, a maximum/minimum value filtering module and a time domain model updating module:
The time domain background modeling module is used for establishing a time domain background model of each pixel point by utilizing the characteristic that the pixel points of adjacent areas have similar time distribution for any pixel;
The histogram statistics module is used for carrying out histogram statistics on the time domain background model of each pixel point, acquiring the gray value of each pixel point in the corresponding time domain background model, and acquiring the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the most frequency occurrence;
The maximum/minimum value filtering module is used for obtaining the brightness marks of the pixel points through the histogram statistical information, and selecting the maximum value or the minimum value from the corresponding time domain background model as the output response of the current value;
the time domain model updating module is used for randomly updating the output response of the current value into each adjacent domain of the corresponding time domain background model by adopting an updating strategy of random adjacent domain diffusion;
the time domain model updating module specifically updates the time domain background model of each pixel point by a random sampling factor, and specifically comprises the following steps:
let the random sampling factor be phi, let the random sampling factor default to 16, denoted by phi 0;
if the random sampling factor phi is fixed, the time domain background model is indicated The larger the standard deviation delta is, the more complex the time domain information is, the more obvious the turbulence fluctuation is, and the smaller the random sampling factor phi is, so as to improve the updating probability of the model; the smaller the standard deviation delta, the smaller the sample fluctuation in the time domain model, i.e. the smaller the complexity of the time domain.
2. The color image turbulence removal system based on temporal and spatial information reconstruction of claim 1, further comprising a color space conversion module for converting the RGB color image into a Lab color space image, separating luminance and chrominance, processing the luminance channel and the chrominance channel respectively in the Lab space, merging the processed channels, and finally converting the Lab color space into the RGB color space before the temporal background modeling module performs the temporal modeling.
3. The color image turbulence removing system based on space-time information reconstruction according to claim 1, further comprising a laplacian airspace enhancing module, wherein the laplacian airspace enhancing module is used for carrying out airspace enhancement on the time-modeled image before the time-domain model updating module carries out updating strategy, so that layering sense and detail information of the image are improved.
4. A color image turbulence removing system based on space-time information reconstruction as claimed in claim 3, wherein the laplace operator airspace enhancing module specifically performs airspace enhancing processing on the image through the laplace divalent operator.
5. The color image turbulence removal system based on temporal and spatial information reconstruction of claim 1, wherein,
The decision of the random sampling factor phi (x, y) of the pixel point p (x, y) is specifically as follows:
6. A method for color image turbulence removal based on spatial-temporal information reconstruction, the method comprising:
For any pixel, a time domain background model of each pixel is built and obtained by utilizing the characteristic that the pixel points in adjacent areas have similar time distribution;
Carrying out histogram statistics on the time domain background model of each pixel point, obtaining the gray value of each pixel point in the corresponding time domain background model, and obtaining the minimum value, the average value and the maximum value of the gray in the corresponding time domain background model and the gray value with the largest frequency occurrence;
Acquiring the brightness marks of the pixel points through the statistical information of the histogram, and selecting the maximum or minimum value from the corresponding time domain background model as the output response of the current value;
randomly updating the output response of the current value into each adjacent domain of the corresponding time domain background model by adopting an updating strategy of random adjacent domain diffusion;
the updating strategy of the time domain background model of each pixel point is carried out by a random sampling factor, and the method comprises the following steps:
let the random sampling factor be phi, let the random sampling factor default to 16, denoted by phi 0;
if the random sampling factor phi is fixed, the time domain background model is indicated The larger the standard deviation delta is, the more complex the time domain information is, the more obvious the turbulence fluctuation is, and the smaller the random sampling factor phi is, so as to improve the updating probability of the model; the smaller the standard deviation delta, the smaller the sample fluctuation in the time domain model, i.e. the smaller the complexity of the time domain.
7. The method for color image turbulence removal based on temporal and spatial information reconstruction of claim 6, further comprising: before the time domain background modeling module performs time domain modeling, converting the RGB color image into a Lab color space image, separating brightness and chromaticity, respectively processing a brightness channel and a chromaticity channel in the Lab space, merging the processed channels, and finally converting the Lab color space into the RGB color space.
8. The method for color image turbulence removal based on temporal and spatial information reconstruction of claim 6, further comprising: before the time domain model updating module performs updating strategy, spatial domain enhancement is performed on the time domain modeled image, and layering sense and detail information of the image are improved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110801270.2A CN113724147B (en) | 2021-07-15 | 2021-07-15 | Color image turbulence removing system and method based on space-time information reconstruction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110801270.2A CN113724147B (en) | 2021-07-15 | 2021-07-15 | Color image turbulence removing system and method based on space-time information reconstruction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113724147A CN113724147A (en) | 2021-11-30 |
| CN113724147B true CN113724147B (en) | 2024-08-20 |
Family
ID=78673382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110801270.2A Active CN113724147B (en) | 2021-07-15 | 2021-07-15 | Color image turbulence removing system and method based on space-time information reconstruction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724147B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103493094A (en) * | 2011-01-28 | 2014-01-01 | 法国电力公司 | Processing of image data comprising effects of turbulence in a liquid medium |
| CN107492076A (en) * | 2017-08-03 | 2017-12-19 | 重庆大学 | A kind of freeway tunnel scene vehicle shadow disturbance restraining method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5362878B2 (en) * | 2012-05-09 | 2013-12-11 | 株式会社日立国際電気 | Image processing apparatus and image processing method |
| US9355439B1 (en) * | 2014-07-02 | 2016-05-31 | The United States Of America As Represented By The Secretary Of The Navy | Joint contrast enhancement and turbulence mitigation method |
| CN110223242B (en) * | 2019-05-07 | 2021-08-10 | 北京航空航天大学 | Video turbulence removal method based on time-space domain residual error generation countermeasure network |
-
2021
- 2021-07-15 CN CN202110801270.2A patent/CN113724147B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103493094A (en) * | 2011-01-28 | 2014-01-01 | 法国电力公司 | Processing of image data comprising effects of turbulence in a liquid medium |
| CN107492076A (en) * | 2017-08-03 | 2017-12-19 | 重庆大学 | A kind of freeway tunnel scene vehicle shadow disturbance restraining method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113724147A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shi et al. | Let you see in sand dust weather: A method based on halo-reduced dark channel prior dehazing for sand-dust image enhancement | |
| CN110148095B (en) | Underwater image enhancement method and enhancement device | |
| Shi et al. | Normalised gamma transformation‐based contrast‐limited adaptive histogram equalisation with colour correction for sand–dust image enhancement | |
| Huang et al. | An efficient visibility enhancement algorithm for road scenes captured by intelligent transportation systems | |
| CN105761227A (en) | Underwater image enhancement method based on dark channel prior algorithm and white balance | |
| Wang et al. | Variational single nighttime image haze removal with a gray haze-line prior | |
| CN102722868B (en) | Tone mapping method for high dynamic range image | |
| CN103714520B (en) | Digital video image strengthening system and its method are realized based on FPGA | |
| CN105046663A (en) | Human visual perception simulation-based self-adaptive low-illumination image enhancement method | |
| Zheng et al. | Infrared traffic image enhancement algorithm based on dark channel prior and gamma correction | |
| CN110473152B (en) | Image enhancement method based on improved Retinex algorithm | |
| CN105809643A (en) | Image enhancing method based on self-adaptive block channel stretching | |
| Gao et al. | Sandstorm image enhancement based on YUV space | |
| CN111127340B (en) | Image defogging method | |
| Gu et al. | A Low‐Light Image Enhancement Method Based on Image Degradation Model and Pure Pixel Ratio Prior | |
| CN108711160B (en) | Target segmentation method based on HSI (high speed input/output) enhanced model | |
| CN106023110B (en) | A kind of Hi-Fi image defogging method | |
| CN112435184B (en) | Image recognition method for haze days based on Retinex and quaternion | |
| CN110969584B (en) | Low-illumination image enhancement method | |
| CN109639994A (en) | Embedded onboard camera exposure time dynamic adjusting method | |
| CN106296626B (en) | A kind of night video enhancement method based on gradient fusion | |
| CN108550124B (en) | Illumination compensation and image enhancement method based on bionic spiral | |
| CN113724147B (en) | Color image turbulence removing system and method based on space-time information reconstruction | |
| CN107203979B (en) | Low-illumination image enhancement method | |
| Su et al. | Image enhancement and brightness equalization algorithms in low illumination environment based on multiple frame sequences |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |