CN116523798B - Infrared contrast enhancement method based on local optimization - Google Patents
Infrared contrast enhancement method based on local optimization Download PDFInfo
- Publication number
- CN116523798B CN116523798B CN202310774212.4A CN202310774212A CN116523798B CN 116523798 B CN116523798 B CN 116523798B CN 202310774212 A CN202310774212 A CN 202310774212A CN 116523798 B CN116523798 B CN 116523798B
- Authority
- CN
- China
- Prior art keywords
- image
- local
- contrast
- background layer
- original
- 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 50
- 238000005457 optimization Methods 0.000 title claims abstract description 9
- 230000000903 blocking effect Effects 0.000 claims abstract description 9
- 238000001914 filtration Methods 0.000 claims description 12
- 230000006835 compression Effects 0.000 claims description 11
- 238000007906 compression Methods 0.000 claims description 11
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 abstract description 3
- 230000002401 inhibitory effect Effects 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007704 transition 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
- G06T5/90—Dynamic range modification of images or parts thereof
-
- 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
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
An infrared contrast enhancement method based on local optimization belongs to the technical field of image processing. The method aims at solving the problems of poor local contrast information, local information loss and distortion of global brightness and darkness relationship existing in the existing high-dynamic infrared image processing technology. According to the invention, the original high-dynamic image is segmented, and the local contrast of the image is enhanced by adopting the optimal pulling of the local contrast; inhibiting the blocking effect by performing Gaussian smoothing on parameters among blocks; taking the image compressed by the global contrast as a local brightness guide image to obtain a background layer compressed image with local contrast increased; adding the background layer compressed image and the detail layer image again according to the linear proportion to obtain a final image; the brightness and darkness relationship of the original image is maintained. The method is suitable for the field of image processing, enhances local contrast information under the condition of keeping the global brightness and darkness relationship of the original image, and improves the definition of image features.
Description
Technical Field
The invention relates to an infrared contrast enhancement method based on local optimization, and belongs to the technical field of image processing.
Background
The infrared image has all-weather imaging capability, so that the infrared image is widely applied to the fields of military, security, automatic driving and the like. However, when the infrared image is 14 bits or more, there is a problem in that the general display cannot display while the contrast ratio is low. At present, the problem is generally solved by adopting the following two methods: 1) A global contrast-based compression method; because the method directly compresses the high dynamic image to the low dynamic image on the whole, partial gray scale is necessarily compressed, and the problems of poor local contrast information, local information loss and the like exist. 2) A local contrast degree compression or pull-up method based on local information; because the method involves compression or stretching of different blocks, block effects are easy to occur in transition intervals among the blocks, meanwhile, the brightness of each block is calculated according to the information of the local block, and the problems of global brightness and darkness relation distortion and the like can be caused.
Disclosure of Invention
Aiming at the problems, the main purpose of the invention is to provide a local optimal infrared contrast enhancement method, which enhances the contrast through the optimal pulling of the local contrast; suppressing the blocking effect through parameter Gaussian smoothing among blocks; and realizing the fidelity of the brightness relationship of the original image through the global brightness guide graph. And under the condition of keeping the global brightness and darkness relationship of the original image, the local contrast information is enhanced, the definition of the image characteristics is improved, and the imaging quality of the image is improved.
The invention aims at realizing the following technical scheme:
step one: partitioning original high-dynamic image, and calculating local mean value of each block regionAnd local standard deviation->；
The blocking method comprises a square blocking method, a rectangular blocking method, a round blocking method and a scene-based segmentation blocking method.
Square and rectangular block method, i.e. to sizeIs +.>Is divided into->Blocks, each block having a size of +.>。
For the square block method and the rectangular block method, the partial block size is 25-32768 pixels, or the number of the divided original images is 4-64 blocks.
Office for calculating each block of areaPart average valueAnd local standard deviation->。
Step two: according to the local standard deviation obtained in the step oneCalculating a local gain coefficient:
，
wherein Is a local gain factor of size +.>；/>A constant set to limit the gain coefficient to be too large, which is 100-1000; />Is the dynamic range of the display, +.>N is the number of display bits.
Step three: for the local gain coefficient obtained in the second stepAnd the local mean value obtained in the step oneUp-sampling is carried out to obtain gain factors and average values which are the same as the size of the original image:
，
wherein and />The up-sampled gain coefficient and the up-sampled average parameter are respectively +.>；/>Is a constant for controlling Gaussian weight, which is 1000-10000; />Representing coordinates +.>To block coordinates->Distance of the heart.
Step four: image layering is carried out on the original high-dynamic image to obtain a background layer imageAnd detail layer image；
Layering is carried out by adopting a side protection filter, wherein the side protection filter comprises guide filtering, bilateral filtering and least square filtering; the background layer image obtained after layering isThe detail layer image is +.>The method comprises the steps of carrying out a first treatment on the surface of the Wherein the filter window size is between 3 x 3 and 30 x 30;
step five: for the background layer image obtained in the step fourPerforming global contrast compression to obtain background layer image +.>；
The compression method adopted comprises an adaptive AGC algorithm, a histogram algorithm or a platform histogram method. The resulting map after global contrast compression is. The AGC algorithm has a good effect on the fidelity of the global brightness and darkness relationship, and the histogram algorithm has a relatively good effect on the global contrast;
step six: taking the global contrast compressed image obtained in the fifth step as a local brightness guide image, taking the original image as local information, taking a local gain coefficient as a stretching coefficient, and calculating to obtain a background layer compressed image with local contrast increased;
，
wherein ,an output image after contrast enhancement; />Is a parameter for controlling the local contrast ratio to be between 0.5 and 2; />Is the image to be processed.
Step seven: compressing the background layer image obtained in the step six and the detail layer image obtained in the step fourRe-adding according to the linear proportion to obtain a final image;
，
wherein ,for the final output image +.>The detail enhancement coefficient is 0.5-2; and under the condition of keeping the global brightness and darkness relationship of the original image, the local contrast information is enhanced, the definition of the image characteristics is improved, and the imaging quality of the image is improved.
Advantageous effects
1. The invention discloses an infrared contrast enhancement method based on local optimization, which adopts the optimal pulling of local contrast to enhance the local contrast of an image; inhibiting the blocking effect by performing Gaussian smoothing on parameters among blocks; and improving the definition of the image features.
2. According to the infrared contrast enhancement method based on local optimization, a global contrast compressed image is used as a local brightness guide image, and a background layer compressed image with local contrast increased is obtained; and the compressed image of the background layer and the image of the detail layer are added again according to the linear proportion to obtain a final image, so that the fidelity of the brightness relationship of the original image is realized. And under the condition of keeping the global brightness and darkness relationship of the original image, the local contrast information is enhanced, the definition of the image characteristics is improved, and the imaging quality of the image is improved.
Drawings
FIG. 1 is a flow chart of a locally optimal infrared contrast enhancement method according to the present disclosure;
fig. 2 is an image upsampling schematic diagram based on a locally optimal infrared contrast enhancement method according to the present embodiment;
fig. 3 (a) is a result of processing the original image disclosed in the present embodiment by a conventional AGC method;
fig. 3 (b) shows the result of the treatment by the method according to the present invention disclosed in this example.
Detailed Description
The present invention will be described in detail with reference to the accompanying drawings and examples. The technical problems and the beneficial effects solved by the technical proposal of the invention are also described, and the described embodiment is only used for facilitating the understanding of the invention and does not have any limiting effect.
As shown in fig. 1, the method for enhancing infrared contrast based on local optimization disclosed in this embodiment is implemented and applied on an infrared imaging component with 1024×768 resolution, and specifically comprises the following implementation steps:
step one: the original high dynamic image is segmented and the local mean value and standard deviation are calculated, namely the original image(size 1024×768) into 4×3 blocks, each block having a size of 256×256, and calculating the mean value of each block regionAnd standard deviation->, wherein />. The method for partitioning can be a square block or a round, rectangular or scene segmentation effect.
Step two: the local gain coefficient is calculated according to the local standard deviation, and the calculation formula is as follows:
wherein Is the stretch factor of the local block,/>Is a constant set to limit the gain factor to be too large, here set to 128,/for>Is the dynamic range, here set to 255 (facing 8-bit display), is processed to give +.>The size was 4×3.
Step three: up-sampling the local gain coefficient and the average value to obtain the gain coefficient and the average value with the same size as the original image, wherein the calculation formula is as follows:
wherein and />The up-sampled gain factor and the up-sampled mean parameter are 1024×768 in size. />Is a constant for controlling the Gaussian weight, here 3600,/is taken>Representing coordinates +.>To block coordinates->Distance of the heart.
Step four: image layering is carried out on an original high-dynamic image to obtain a background layer image and a detail layer image, the layering method adopts a side protection filtering algorithm, the side protection filtering algorithm can be guide filtering, bilateral filtering and least square filtering, the guide filtering is adopted for layering in the embodiment, and the obtained background layer image isThe calculation is as follows:
wherein and />Representation->In window->Mean and variance of>Representation window->In this case, the window is 15×15=225, < >>In order to prevent the denominator from being too small or being a value set to 0, a good effect is generally obtained between 10000 and 50000, and 32768 is taken for calculation in this embodiment.
Step five: global contrast compression is carried out on the background layer image by adopting an AGC algorithmThe calculation formula is as follows:
wherein Is the standard deviation of the original image, +.>For the graph to be processedImage (S)/(S)>For the mean value of the image to be processed, +.>Is a constant for preventing excessive gain, here 128 +.>Is the desired image brightness 128,/or->Is the background layer image after global compression.
Step six: the image compressed by the global contrast is used as a local brightness guide image, the original image is local information, the local gain coefficient is used as a stretching coefficient to calculate and obtain a background layer compressed image with the local contrast increased, and the calculation formula is as follows:
wherein ,is a parameter controlling the local contrast, here taken as 1.
Step seven: re-adding the background layer compressed image and the detail layer image according to a certain proportion to obtain a final image;
wherein ,for the final output image +.>For the detail enhancement factor, 1.2 is taken here.
As shown in fig. 3 (a) and as shown in fig. 3 (b), the present example discloses an infrared contrast enhancement method based on local optimization, and the effect diagram before and after the treatment is compared with the diagram, and the original image is treated by the conventional AGC method, so that the mask and the hair on the face of the person have almost no details; and as a result of the treatment by the method provided by the invention, the facial mask and hair characteristics of the human are clear and visible, and the overall and local contrast effects of the image are obviously enhanced.
The foregoing detailed description has set forth the objects, aspects and advantages of the invention in further detail, it should be understood that the foregoing description is only illustrative of the invention and is not intended to limit the scope of the invention, but is to be accorded the full scope of the invention as defined by the appended claims.
Claims (3)
1. An infrared contrast enhancement method based on local optimization is characterized in that: comprises the following steps of the method,
step one: partitioning original high-dynamic image, and calculating local mean value of each block regionAnd local standard deviation->；
Step two: according to the local standard deviation obtained in the step oneCalculating a local gain coefficient:
，
wherein Is a local gain factor of size +.>；/>A constant set to limit the gain coefficient to be too large, which is 100-1000; />Is the dynamic range of the display, +.>N is the number of display bits;
step three: for the local gain coefficient obtained in the second stepAnd the local mean value obtained in the step oneUp-sampling is carried out to obtain gain factors and average values which are the same as the size of the original image:
，
wherein and />The up-sampled gain coefficient and the up-sampled average parameter are respectively +.>；/>Is a constant for controlling Gaussian weight, which is 1000-10000; />Representing coordinates +.>To block coordinates->Distance of the heart;
step four: image layering is carried out on the original high-dynamic image to obtain a background layer imageAnd detail layer image；
Layering is carried out by adopting a side protection filter, wherein the side protection filter comprises guide filtering, bilateral filtering and least square filtering; the background layer image obtained after layering isThe detail layer image is +.>The method comprises the steps of carrying out a first treatment on the surface of the Wherein the filter window size is between 3 x 3 and 30 x 30;
step five: for the background layer image obtained in the step fourPerforming global contrast compression to obtain background layer image +.>；
Step six: taking the global contrast compressed image obtained in the fifth step as a local brightness guide image, taking the original image as local information, taking a local gain coefficient as a stretching coefficient, and calculating to obtain a background layer compressed image with local contrast increased;
，
wherein ,an output image after contrast enhancement; />Is a parameter for controlling the local contrast ratio to be between 0.5 and 2; />Is an image to be processed;
step seven: compressing the background layer image obtained in the step six and the detail layer image obtained in the step fourRe-adding according to the linear proportion to obtain a final image;
，
wherein ,for the final output image +.>The detail enhancement coefficient is 0.5-2; local contrast information is enhanced while preserving the global bright-dark relationship of the original image.
2. A locally optimal infrared contrast enhancement method as claimed in claim 1 wherein: the method for realizing the blocking of the original high-dynamic image comprises the following steps: square block method, rectangular block method, circular block method and scene-based block method;
square and rectangular block method, i.e. to sizeIs +.>Is divided into->Blocks, each block having a size of +.>；
For the square block method and the rectangular block method, the partial block size is 25-32768 pixels, or the number of the divided original images is 4-64 blocks.
3. A locally optimal infrared contrast enhancement method as claimed in claim 2 wherein: in the fifth step, the background layer imageAnd performing global contrast compression, wherein the compression method comprises a self-adaptive AGC algorithm, a histogram algorithm and a platform histogram method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310774212.4A CN116523798B (en) | 2023-06-28 | 2023-06-28 | Infrared contrast enhancement method based on local optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310774212.4A CN116523798B (en) | 2023-06-28 | 2023-06-28 | Infrared contrast enhancement method based on local optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116523798A CN116523798A (en) | 2023-08-01 |
| CN116523798B true CN116523798B (en) | 2023-08-25 |
Family
ID=87396211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310774212.4A Active CN116523798B (en) | 2023-06-28 | 2023-06-28 | Infrared contrast enhancement method based on local optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116523798B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530848A (en) * | 2013-09-27 | 2014-01-22 | 中国人民解放军空军工程大学 | Double exposure implementation method for inhomogeneous illumination image |
| CN104157003A (en) * | 2014-07-18 | 2014-11-19 | 北京理工大学 | Heat image detail enhancement method based on normal distribution adjustment |
| CN109934790A (en) * | 2019-03-27 | 2019-06-25 | 北京理工大学 | Infrared imaging system asymmetric correction method with adaptive threshold |
| CN113870135A (en) * | 2021-09-28 | 2021-12-31 | 国网上海市电力公司 | NSST domain infrared image enhancement method based on longicorn stigma optimization algorithm |
| CN115034985A (en) * | 2022-05-31 | 2022-09-09 | 哈尔滨工程大学 | Underwater image enhancement method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2564373B1 (en) * | 2010-04-26 | 2014-12-17 | Robert Bosch GmbH | Detection and/or enhancement of contrast differences in digital image data |
-
2023
- 2023-06-28 CN CN202310774212.4A patent/CN116523798B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103530848A (en) * | 2013-09-27 | 2014-01-22 | 中国人民解放军空军工程大学 | Double exposure implementation method for inhomogeneous illumination image |
| CN104157003A (en) * | 2014-07-18 | 2014-11-19 | 北京理工大学 | Heat image detail enhancement method based on normal distribution adjustment |
| CN109934790A (en) * | 2019-03-27 | 2019-06-25 | 北京理工大学 | Infrared imaging system asymmetric correction method with adaptive threshold |
| CN113870135A (en) * | 2021-09-28 | 2021-12-31 | 国网上海市电力公司 | NSST domain infrared image enhancement method based on longicorn stigma optimization algorithm |
| CN115034985A (en) * | 2022-05-31 | 2022-09-09 | 哈尔滨工程大学 | Underwater image enhancement method |
Non-Patent Citations (1)
| Title |
|---|
| 《基于IHBF的增强局部对比度红外小目标检测方法》;贺顺等;《红外技术》;1132-1138 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116523798A (en) | 2023-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110599415B (en) | Image contrast enhancement implementation method based on local self-adaptive gamma correction | |
| CN111899205B (en) | Image enhancement method of scene self-adaptive wide dynamic infrared thermal imaging | |
| CN105931201B (en) | A kind of image subjective vision effect reinforcing method based on wavelet transformation | |
| CN111968041A (en) | Self-adaptive image enhancement method | |
| CN109919859B (en) | Outdoor scene image defogging enhancement method, computing device and storage medium thereof | |
| CN111105371B (en) | Enhancement method of low-contrast infrared image | |
| CN108280836B (en) | Image processing method and device | |
| CN111709898B (en) | Infrared image enhancement method and system based on optimized CLAHE | |
| CN111968065B (en) | Self-adaptive enhancement method for image with uneven brightness | |
| Kim et al. | Single image haze removal using hazy particle maps | |
| CN117252773A (en) | Image enhancement method and system based on self-adaptive color correction and guided filtering | |
| CN113592750B (en) | Infrared enhancement method based on gradient histogram | |
| CN114998165A (en) | Histogram transformation based uniform exposure image contrast enhancement method | |
| CN109345479B (en) | Real-time preprocessing method and storage medium for video monitoring data | |
| CN110580690A (en) | image enhancement method for identifying peak value transformation nonlinear curve | |
| CN110111280A (en) | A kind of enhancement algorithm for low-illumination image of multi-scale gradient domain guiding filtering | |
| CN116523798B (en) | Infrared contrast enhancement method based on local optimization | |
| CN112465711A (en) | Degraded image enhancement method for foggy environment | |
| CN116630198A (en) | Multi-scale fusion underwater image enhancement method combining self-adaptive gamma correction | |
| CN113112438B (en) | Image enhancement method based on clipping histogram | |
| CN113256533B (en) | Self-adaptive low-illumination image enhancement method and system based on MSRCR | |
| CN115835036A (en) | Infrared image compression method based on self-adaptive gamma correction | |
| CN112822343B (en) | Night video oriented sharpening method and storage medium | |
| CN109167892B (en) | Video image detail enhancement method and system | |
| CN114820359B (en) | Infrared image global tone mapping method based on human eye vision region division |
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 |