CN111476736B - Image defogging method, terminal and system - Google Patents
Image defogging method, terminal and system Download PDFInfo
- Publication number
- CN111476736B CN111476736B CN202010289876.8A CN202010289876A CN111476736B CN 111476736 B CN111476736 B CN 111476736B CN 202010289876 A CN202010289876 A CN 202010289876A CN 111476736 B CN111476736 B CN 111476736B
- Authority
- CN
- China
- Prior art keywords
- image
- color
- dark
- channel
- 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 36
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 230000009466 transformation Effects 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000006243 chemical reaction Methods 0.000 claims abstract description 9
- 239000003086 colorant Substances 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 40
- 238000004590 computer program Methods 0.000 claims description 16
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000002834 transmittance Methods 0.000 claims description 5
- 238000011084 recovery Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 7
- 230000007547 defect Effects 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/10—Image enhancement or restoration by non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20064—Wavelet transform [DWT]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application discloses an image defogging method, which comprises the following steps: converting the hazy image from an RGB color space to an LAB color space to obtain the hazy image of the LAB color space; performing wavelet transformation denoising treatment on L, A, B color channels of the foggy image of the LAB color space to obtain L, A, B denoised color channels; according to the transmissivity distribution, carrying out dark primary color prior method treatment on the L-color channel; and combining the processed L, A, B color channels to obtain an LAB image, converting the LAB image into an RGB image, and outputting the defogged image. The application is based on the requirements of atomizing aerial images and needing to carry out clear treatment, takes color space conversion as a basis, utilizes the advantage of more centralized information by wavelet transformation, overcomes the defect of high complexity of prior computation of dark primary colors, and ensures that the aerial images are defogged rapidly and thoroughly under the condition of uneven low-altitude haze. Compared with the classical dark primary prior algorithm, the method has the advantages of low calculation complexity and higher calculation speed.
Description
Technical Field
The present application relates to image processing technologies, and in particular, to an image defogging method, terminal, and system.
Background
Modern unmanned aerial vehicles are increasingly used to obtain image information, video information and position information mainly through task equipment, and post-processing of image data is becoming more critical. In the actual process, the unmanned aerial vehicle is affected by more atmospheric environment due to higher shooting position, and particularly has poor imaging effect under foggy weather, thereby affecting tracking of targets, investigation of terrains and the like. Therefore, the defogging technology research for the unmanned aerial vehicle image has great significance.
The image defogging technology at the present stage mainly comprises two directions: image enhancement and image restoration, respectively. The image enhancement defogging technology mainly improves the contrast of an image through some algorithms, enhances the details of the image, and mainly comprises a defogging technology based on histogram equalization, a defogging algorithm based on the Retinex theory and a defogging algorithm based on wavelet change.
The defogging technology for image restoration is to estimate scene depth by establishing an atmospheric scattering model and to remove the defogging effect by inverting the image imaging process. Among these, best is the dark channel prior algorithm proposed by He Kaiming et al, the transmissivity is estimated through the minimum filtering, and the transmissivity can be optimized by utilizing the technologies such as soft matting or bilateral filtering, so that a better experimental result can be obtained, but the algorithm has higher computational complexity.
Disclosure of Invention
Aiming at the problem that the existing unmanned aerial vehicle ground information processing terminal cannot further process a foggy image, the embodiment of the application provides an image defogging method, a terminal and a system.
In order to achieve the above purpose, the technical scheme of the application is as follows:
in a first aspect, an embodiment of the present application provides an image defogging method, including:
converting the hazy image from an RGB color space to an LAB color space to obtain the hazy image of the LAB color space;
performing wavelet transformation denoising treatment on L, A, B color channels of the foggy image of the LAB color space to obtain L, A, B denoised color channels;
and processing the L-color channel image by a dark primary color prior method according to the transmissivity distribution. Calculating an atmospheric light value in an L color channel, selecting the first 0.1% pixel point with the maximum brightness value in the dark primary color calculated by the L color channel, calculating the transmissivity by taking the maximum value of the pixel points corresponding to the original image as the value A, and finally obtaining a new L color channel through recovery calculation
Combining the processed L, A, B color channels to obtain an LAB image;
further, the LAB image is converted into an RGB image and output for display.
In a second aspect, an embodiment of the present application provides an image defogging system, including:
the color conversion module is used for converting the hazy image from an RGB color space to an LAB color space to obtain the hazy image of the LAB color space;
the wavelet transformation denoising processing module is used for respectively carrying out wavelet transformation denoising processing on L, A, B color channels of the foggy image in the LAB color space to obtain L, A, B denoised color channels;
and the dark primary color prior processing module is used for carrying out dark primary color prior method processing on the L-color channel image according to the transmissivity distribution, and outputting a new L-color channel image.
The merging module is used for merging the processed L, A, B color channels to obtain an LAB image;
in a third aspect, an embodiment of the present application provides an image defogging terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the image defogging method when executing the computer program.
A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the above-mentioned image defogging method.
Compared with the prior art, the application has the beneficial effects that:
the application is based on the requirements of atomizing aerial images and needing to carry out clear processing, takes color space conversion as a basis, utilizes the advantage of wavelet transformation to enable information to be more concentrated, overcomes the defect of high complexity of prior computation of dark primary colors, enables aerial images to be defogged rapidly under the condition of uneven low-altitude haze, enables defogging to be more thorough, and has lower computation complexity and higher computation speed than the classical prior algorithm of the dark primary colors.
Drawings
FIG. 1 is a flowchart of an image defogging method according to an embodiment of the present application;
FIG. 2 is an original hazy image;
FIG. 3a is an L-component image of a foggy image;
FIG. 3b is an A-component image of a foggy image;
FIG. 3c is a B-component image of a hazy image;
FIG. 3d is an L component histogram;
FIG. 3e is a component A histogram;
FIG. 3f is a B component histogram;
FIG. 4 is a final image after defogging;
FIG. 5 is a schematic diagram of the image defogging system according to the embodiment of the present application;
fig. 6 is a schematic diagram of the composition of an image defogging terminal according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the drawings and detailed description.
Examples:
referring to fig. 1, the image defogging method provided in this embodiment includes the following steps:
101. converting the hazy image into an LAB color space from an RGB color space as shown in figure 2 to obtain the hazy image of the LAB color space; in LAB mode, the hazy portion can be better distinguished.
102. And performing wavelet transform denoising treatment on L, A, B color channels of the foggy image of the LAB color space to obtain L, A, B denoised color channels. The details are sharpened by wavelet transforms on the three color channels L, a, B, respectively, so that the contrast can be more finely tuned, as shown in particular in fig. 3a-3 f.
The wavelet transform has a good locality in the time-frequency domain, its varying-scale nature being such that the wavelet transform has a "concentrated" capability on the determined signal. After wavelet transformation of the image containing noise, the image noise and the signal noise show different characteristics: the energy of the signal is mainly concentrated on some bright lines, while the value of most coefficients approaches 0; the distribution of noise is opposite to that of signals, the coefficients of the noise are uniformly distributed in the whole scale space, the amplitude difference is not large (the noise can be smoothed in a large scale), and the characteristic provides a basis for denoising images based on wavelet transformation.
103. And processing the L-color channel image by a dark primary prior method according to the transmissivity distribution to obtain new L-color channel data.
104. The processed L, A, B three color channels are combined to obtain a LAB image and converted to an RGB image, as shown in fig. 4.
Therefore, the method is based on the requirements of atomizing aerial images and needing to carry out clear treatment, takes color space conversion as a basis, utilizes the advantage of more centralized information by wavelet transformation, overcomes the defect of high complexity of prior computation of dark primary colors, and ensures that aerial images with uneven low-altitude haze are defogged rapidly and thoroughly. Compared with the classical dark primary prior algorithm, the algorithm has low computational complexity and higher operation speed, and compared with the classical soft matting dark color prior defogging algorithm, the algorithm provided by the application has the advantage that the operation time is shortened by about 1/3.
As a preferable mode of this embodiment, wavelet transform denoising is performed on the subcomponents of the L, A, B three color channels by a thresholding method. That is, the wavelet transform technique is used to denoise the transformed color space components by a thresholding method, which can preserve local information such as edges and details of the image. The main theoretical basis of the wavelet threshold denoising method is that the wavelet coefficient amplitude of the signal is larger than the coefficient amplitude of noise after wavelet decomposition. The specific treatment process comprises the following steps: carrying out wavelet decomposition on the noise-containing signal on each scale, and reserving all decomposition values under a large scale; for the decomposition value under the small scale, a threshold value is set, the wavelet coefficient with the amplitude lower than the threshold value is set to be zero, and the wavelet coefficient higher than the threshold value is completely reserved. And finally, reconstructing the wavelet coefficient obtained after the processing by utilizing inverse wavelet transformation to recover an effective signal. Wherein the large and small dimensions of the present application are relative terms and do not represent specific dimensional limitations.
Specifically, the dark primary prior processing is performed on the L-color channel image according to the transmittance distribution, and the image after defogging is output in the conversion format includes:
according to the dark primary prior theory, for a foggless image J (x), the dark primary prior rule is:
wherein J is dark (x) Color values of the dark channel map for J (x); j (J) c (y) is the color value of one of the three channels r, g and b in J (x); Ω (x) is a block region centered on x; c represents any one color channel of r, g and b;
the transmittance t (x) is calculated as:
the result is obtained after normalization treatment of the dark channel with the fog image; the function of omega variable reduces the color value of the dark channel diagram, and 0 < omega is less than or equal to 1;
after the dark channel prior algorithm and the transmissivity are estimated, the restored image is:
wherein t is 0 Is the lower limit value of the transmissivity; a isGlobal atmospheric light; i (x) represents a foggy image;
according to the method, an atmospheric light value is calculated in an L color channel, a first 0.1% pixel point with the largest brightness value is selected from dark primary colors calculated by the L color channel, then the maximum value corresponding to the pixel points in an original image is used as a value A, the maximum value is substituted into a transmissivity calculation formula t (x), and finally a new L color channel is obtained through recovery calculation.
And combining the L color channel, the A channel and the B channel values to form a new defogged image, and further converting the new defogged image into an RGB image for output and display.
Therefore, through the algorithm processing steps, the haze with uneven distribution is further refined by using the dark channel rule, the defect of high complexity of dark primary color priori calculation is overcome, compared with the classical soft matting dark color priori defogging algorithm, the algorithm provided by the application has the advantages that the operation time is shortened by about 1/3, the defogging of the aerial image under the condition of low-altitude haze is rapid, the defogging is more complete, and local information such as edges, details and the like of the aerial image is well reserved.
Example 2:
referring to fig. 5, the image defogging system provided in this embodiment includes:
the color conversion module 701 is configured to convert the hazy image from an RGB color space to a LAB color space, and obtain a hazy image in the LAB color space;
the wavelet transform denoising processing module 702 is configured to perform wavelet transform denoising processing on three L, A, B color channels of the foggy image in the LAB color space, so as to obtain three L, A, B denoised color channels;
and the dark primary prior processing module 703 is configured to perform dark primary prior processing on the L color channel image according to the transmittance distribution, so as to obtain a new L color channel.
The merging module 704 is configured to merge the processed L, A, B color channels to obtain an LAB image, and further convert the LAB image into an RGB image;
therefore, the system is based on the requirements of atomizing aerial images and needing to carry out clear processing, takes color space conversion as a basis, utilizes the advantage of more centralized information by wavelet transformation, overcomes the defect of high complexity of prior computation of dark primary colors, and enables aerial images to be defogged rapidly and thoroughly under the condition of uneven low-altitude haze.
Since the color conversion module 701, the wavelet transform denoising processing module 702, the dark primary prior processing module 703, and the combining module 704 correspond to the steps 101-104 of embodiment 1, the working principles of the respective modules will not be described in detail in this embodiment.
Example 3:
referring to fig. 6, the image defogging terminal provided in this embodiment includes a processor 801, a memory 802, and a computer program 803, such as an image defogging program, stored in the memory 802 and executable on the processor 801. The processor 801, when executing the computer program 803, implements the steps of embodiment 1 described above, such as the steps shown in fig. 1. Alternatively, the processor 801 implements the functions of the respective modules in the above-described embodiment 2 when executing the computer program 803.
By way of example, the computer program 803 may be partitioned into one or more modules that are stored in the memory 802 and executed by the processor 801 to perform the present application. The one or more modules may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program 803 in the image defogging terminal.
The image defogging processing terminal can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The image defogging terminal may include, but is not limited to, a processor 801, a memory 802. It will be appreciated by those skilled in the art that fig. 6 is merely an example of an image defogging terminal and does not constitute a limitation of the image defogging terminal, and may include more or less components than illustrated, or may combine certain components, or different components, e.g., the image defogging terminal may further include an input and output device, a network access device, a bus, etc.
The processor 801 may be a central processing unit (Central Processing Unit, CPU), but may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (FieldProgrammable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 802 may be an internal storage element of the image defogging processing terminal, for example, a hard disk or a memory of the image defogging processing terminal. The memory 802 may also be an external storage device of the image defogging terminal, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like. Further, the memory 802 may also include both an internal storage unit and an external storage device of the image defogging processing terminal. The memory 802 is used to store the computer program and other programs and data required for the image defogging processing terminal. The memory 802 may also be used to temporarily store data that has been output or is to be output.
Example 4:
the present embodiment provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the method described in embodiment 1.
The computer readable medium can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer readable medium may even be paper or another suitable medium upon which the program is printed, such as by optically scanning the paper or other medium, then editing, interpreting, or otherwise processing as necessary, and electronically obtaining the program, which is then stored in a computer memory.
The above embodiments are only for illustrating the technical concept and features of the present application, and are intended to enable those skilled in the art to understand the content of the present application and implement the same, and are not intended to limit the scope of the present application. All equivalent changes or modifications made in accordance with the essence of the present application are intended to be included within the scope of the present application.
Claims (8)
1. An image defogging method, comprising:
converting the hazy image from an RGB color space to an LAB color space to obtain the hazy image of the LAB color space;
performing wavelet transformation denoising treatment on L, A, B color channels of the foggy image of the LAB color space to obtain L, A, B denoised color channels;
dark primary color prior processing is carried out on the brightness component L color channel;
combining the processed L, A, B color channels to obtain an LAB image;
converting the LAB image into an RGB image and outputting the defogged image;
the dark primary prior processing of the luminance component L color channel includes:
according to the dark primary prior theory, for a foggless image J (x), the dark primary prior rule is:
wherein J is dark (x) Is J (x)) Color values of the dark channel map; j (J) c (y) is the color value of one of the three channels r, g and b in J (x); Ω (x) is a block region centered on x; c represents any one color channel of r, g and b;
the transmittance t (x) is calculated as:
the result is obtained after normalization treatment of the dark channel with the fog image; the function of omega variable reduces the color value of the dark channel diagram, and 0 < omega is less than or equal to 1;
after the dark channel prior algorithm and the transmissivity are estimated, the restored image is:
wherein t is 0 Is the lower limit value of the transmissivity; a is global atmospheric light; i (x) represents a foggy image;
according to the method, an atmospheric light value is calculated in an L color channel, a first 0.1% pixel point with the largest brightness value is selected from dark primary colors calculated by the L color channel, then the maximum value corresponding to the pixel points in an original image is used as a value A, the maximum value is substituted into a transmissivity calculation formula t (x), and finally a new L color channel is obtained through recovery calculation.
2. The image defogging method of claim 1, wherein the sub-components of the L, A, B three color channels are subjected to wavelet transform denoising processing by a thresholding method.
3. The image defogging method according to claim 2, wherein the wavelet transform denoising processing of the subcomponents of the L, A, B three color channels by using a thresholding method comprises:
carrying out wavelet decomposition on the noise-containing signal on each scale, and reserving all decomposition values under a large scale; and setting a threshold value for the decomposition value under the small scale, setting the wavelet coefficient with the amplitude lower than the threshold value to zero, completely retaining the wavelet coefficient higher than the threshold value, and finally reconstructing the wavelet coefficient obtained after processing by using inverse wavelet transformation to recover an effective signal.
4. An image defogging system, comprising:
the color conversion module is used for converting the hazy image from an RGB color space to an LAB color space to obtain the hazy image of the LAB color space;
the wavelet transformation denoising processing module is used for respectively carrying out wavelet transformation denoising processing on L, A, B color channels of the foggy image in the LAB color space to obtain L, A, B denoised color channels;
the dark primary color prior processing module is used for carrying out dark primary color prior method processing on the L-color channel image according to the transmissivity distribution;
the merging module is used for merging the processed L, A, B color channels to obtain an LAB image;
the dark primary prior processing module performs dark primary prior processing on the brightness component L color channel, including:
according to the dark primary prior theory, for a foggless image J (x), the dark primary prior rule is:
wherein J is dark (x) Color values of the dark channel map for J (x); j (J) c (y) is the color value of one of the three channels r, g and b in J (x); Ω (x) is a block region centered on x; c represents any one color channel of r, g and b;
the transmittance t (x) is calculated as:
the result is obtained after normalization treatment of the dark channel with the fog image; the function of omega variable reduces the color value of the dark channel diagram, and 0 < omega is less than or equal to 1;
after the dark channel prior algorithm and the transmissivity are estimated, the restored image is:
wherein t is 0 Is the lower limit value of the transmissivity; a is global atmospheric light; i (x) represents a foggy image;
and calculating an atmospheric light value in the L color channel, selecting the first 0.1% pixel point with the maximum brightness value in the dark primary color obtained by calculating the L color channel, substituting the maximum value of the pixel point corresponding to the original image as the value of A into a transmissivity calculation formula t (x), and finally obtaining a new L color channel by recovery calculation.
5. The image defogging system of claim 4, wherein the wavelet transform denoising processing module performs wavelet transform denoising processing on the subcomponents of the L, A, B three color channels by using a thresholding method.
6. The image defogging system of claim 5, wherein thresholding the sub-components of the L, A, B color channels comprises:
carrying out wavelet decomposition on the noise-containing signal on each scale, and reserving all decomposition values under a large scale; and setting a threshold value for the decomposition value under the small scale, setting the wavelet coefficient with the amplitude lower than the threshold value to zero, completely retaining the wavelet coefficient higher than the threshold value, and finally reconstructing the wavelet coefficient obtained after processing by using inverse wavelet transformation to recover an effective signal.
7. An image defogging terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any of the claims 1 to 3 when executing the computer program.
8. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010289876.8A CN111476736B (en) | 2020-04-14 | 2020-04-14 | Image defogging method, terminal and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010289876.8A CN111476736B (en) | 2020-04-14 | 2020-04-14 | Image defogging method, terminal and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111476736A CN111476736A (en) | 2020-07-31 |
| CN111476736B true CN111476736B (en) | 2023-09-22 |
Family
ID=71751850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010289876.8A Active CN111476736B (en) | 2020-04-14 | 2020-04-14 | Image defogging method, terminal and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111476736B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113538267B (en) * | 2021-07-09 | 2023-10-20 | 广东职业技术学院 | Unmanned aerial vehicle foggy image definition method, system, computer and storage medium |
| CN113763488A (en) * | 2021-07-21 | 2021-12-07 | 广东工业大学 | Remote sensing image demisting degree method combining dark channel pre-inspection algorithm and U-Net |
| CN115471429B (en) * | 2022-10-31 | 2023-04-07 | 航天宏图信息技术股份有限公司 | Remote sensing image defogging method and device based on global color migration |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955905A (en) * | 2014-05-13 | 2014-07-30 | 北京邮电大学 | Rapid wavelet transformation and weighted image fusion single-image defogging method |
| CN106157267A (en) * | 2016-07-12 | 2016-11-23 | 中国科学技术大学 | A kind of image mist elimination absorbance optimization method based on dark channel prior |
| CN108765336A (en) * | 2018-05-25 | 2018-11-06 | 长安大学 | Image defogging method based on dark bright primary colors priori with auto-adaptive parameter optimization |
| CN109544467A (en) * | 2018-10-23 | 2019-03-29 | 江苏理工学院 | A method of based on enhancing color image contrast under LAB model |
-
2020
- 2020-04-14 CN CN202010289876.8A patent/CN111476736B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955905A (en) * | 2014-05-13 | 2014-07-30 | 北京邮电大学 | Rapid wavelet transformation and weighted image fusion single-image defogging method |
| CN106157267A (en) * | 2016-07-12 | 2016-11-23 | 中国科学技术大学 | A kind of image mist elimination absorbance optimization method based on dark channel prior |
| CN108765336A (en) * | 2018-05-25 | 2018-11-06 | 长安大学 | Image defogging method based on dark bright primary colors priori with auto-adaptive parameter optimization |
| CN109544467A (en) * | 2018-10-23 | 2019-03-29 | 江苏理工学院 | A method of based on enhancing color image contrast under LAB model |
Non-Patent Citations (1)
| Title |
|---|
| 方周.基于暗原色理论的雾天图像清晰化方法研究.《中国优秀硕士学位论文全文数据库信息科技辑》.2016,(第4期),I138-955. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111476736A (en) | 2020-07-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111476736B (en) | Image defogging method, terminal and system | |
| Singh et al. | Single image dehazing using gradient channel prior | |
| Park et al. | Low-light image enhancement using variational optimization-based retinex model | |
| Xiao et al. | Fast image dehazing using guided joint bilateral filter | |
| Li et al. | Edge-preserving decomposition-based single image haze removal | |
| Guo et al. | An efficient fusion-based defogging | |
| Gopalan et al. | A blur-robust descriptor with applications to face recognition | |
| Li et al. | Single image haze removal using content‐adaptive dark channel and post enhancement | |
| Im et al. | Single image-based ghost-free high dynamic range imaging using local histogram stretching and spatially-adaptive denoising | |
| WO2015192115A1 (en) | Systems and methods for automated hierarchical image representation and haze removal | |
| Xu et al. | Single image haze removal using light and dark channel prior | |
| Xie et al. | Single image dehazing using kernel regression model and dark channel prior | |
| Shu et al. | Alternating minimization algorithm for hybrid regularized variational image dehazing | |
| Yu et al. | Underwater image enhancement based on color-line model and homomorphic filtering | |
| Zhu et al. | Underwater image enhancement based on colour correction and fusion | |
| Shi et al. | A joint deep neural networks-based method for single nighttime rainy image enhancement | |
| Pandey et al. | A fast and effective vision enhancement method for single foggy image | |
| Li et al. | Efficient burst raw denoising with variance stabilization and multi-frequency denoising network | |
| Wang et al. | A convex single image dehazing model via sparse dark channel prior | |
| Kumar et al. | Dynamic stochastic resonance and image fusion based model for quality enhancement of dark and hazy images | |
| Cao et al. | Remote sensing image recovery and enhancement by joint blind denoising and dehazing | |
| Lian et al. | Learning intensity and detail mapping parameters for dehazing | |
| Liu et al. | Joint dehazing and denoising for single nighttime image via multi-scale decomposition | |
| Yang et al. | Multi-scale underwater image enhancement with optimized homomorphic filter and RGB color correction | |
| Thomas et al. | Effectual single image dehazing with color correction transform and dark channel prior |
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 |