CN111800584B - High dynamic range image processing method, device and computer readable storage medium - Google Patents
High dynamic range image processing method, device and computer readable storage medium Download PDFInfo
- Publication number
- CN111800584B CN111800584B CN202010798824.3A CN202010798824A CN111800584B CN 111800584 B CN111800584 B CN 111800584B CN 202010798824 A CN202010798824 A CN 202010798824A CN 111800584 B CN111800584 B CN 111800584B
- Authority
- CN
- China
- Prior art keywords
- luminance
- picture
- brightness
- dynamic range
- component
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/741—Circuitry for compensating brightness variation in the scene by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/76—Circuitry for compensating brightness variation in the scene by influencing the image signals
Abstract
The invention discloses a high dynamic range image processing method, a device and a computer readable storage medium, wherein the method comprises the steps of counting the number of pixel points of brightness components in a bright area in a selected picture, weighting and summing the pixel points to obtain S1, counting the number of pixel points of brightness components in a dark area, weighting and summing the pixel points to obtain S2, and weighting and summing the brightness components of the whole picture to obtain S3; substituting k1 into S1/S3 to a (y11, y12, y13) into a (k1, x11, x12, x13) to suppress the luminance in the bright area, and substituting the result of k2 into S2/S3 into a (y21, y22, y23) into B (k2, x21, x22, x23) to increase the luminance in the dark area; and after the brightness of the bright area of the picture is suppressed and the brightness of the dark area of the picture is improved, outputting a high dynamic range image of the picture. The dynamic range and image details are expanded by using a single picture, so that the time delay from the beginning of shooting to the generation of the picture is reduced, and the dynamic range and the image details can be expanded for the shot picture.
Description
Technical Field
The present invention relates to the field of high dynamic range image processing technologies, and in particular, to a high dynamic range image processing method and apparatus, and a computer-readable storage medium.
Background
Dynamic Range (Dynamic Range) is used in many fields to represent the ratio of the maximum value to the minimum value of a variable. In digital images, the dynamic range, also called contrast, represents the ratio between the maximum gray value and the minimum gray value within the range in which the image can be displayed. For a natural scene in the real world, the dynamic range represents the ratio of the brightest illumination intensity to the darkest illumination intensity. In most of the current color digital images, R, G, B each channel uses one byte of 8 bits to store, that is, the representation range of each channel is 0 to 255 gray levels, where 0 to 255 is the dynamic range of the image. Since the dynamic range in the same scene in the real world varies greatly, we call High Dynamic Range (HDR), and the dynamic range on a normal picture is Low Dynamic Range (LDR).
High Dynamic Range Images (HDRI) are a type of image that can represent a wide variation in brightness in an actual scene, and therefore, can better represent the optical characteristics of bright and dark areas in the scene. The range of pixel values to be represented by a high dynamic range image is typically large, sometimes requiring hundreds of thousands or even millions. High dynamic range images require more data bits per color channel than conventional images because of its linear encoding and the need to represent an even larger range of values from the range of luminance visible to the human eye.
Currently, there are three main types of methods for acquiring HDR images: the first category is simulated light and composite images based on physical lighting models, and the source of early HDR images is mainly this category; the second type is to use a plurality of common dynamic range images (LDRI) with different exposure levels to calculate the actual brightness of high dynamic state to obtain HDR images (multiple exposure method, multi-target exposure synthesis); the third category is to take HDR images directly with special hardware devices. The first type is artificially synthesized images which cannot process natural images, the third type needs special equipment, the second type can synthesize HDR images only by a plurality of images with different exposure quantities shot by a common camera, and the existing HDR images are usually obtained by the second type.
However, since a plurality of ordinary dynamic range images (LDRI) with different exposure levels are used to calculate the actual luminance of the high dynamic range to obtain the HDR image, and a plurality of pictures need to be taken, a time delay from the start of taking to the generation of the picture is large, and the process of expanding the dynamic range and the image details of the taken picture cannot be performed.
Disclosure of Invention
In view of the above, an object of the present invention is to provide a method, an apparatus and a computer readable storage medium for processing a high dynamic range image, so as to solve the technical problems that capturing multiple pictures causes a long delay from the beginning of capturing to the generation of an HDR image, and the captured pictures cannot be processed to expand the dynamic range and the image details. The technical scheme adopted by the invention for solving the technical problems is as follows:
according to a first aspect of the present invention, there is provided a high dynamic range image processing method, the method comprising:
in a selected picture, counting the number of pixels of the brightness component in the bright area, weighting and summing the number of pixels of the brightness component in the dark area to S1, weighting and summing the number of pixels of the brightness component in the dark area to S2, and weighting and summing the brightness component of the whole picture to S3;
substituting k1 into S1/S3 to a (y11, y12, y13) into a (k1, x11, x12, x13) to suppress the luminance in the bright area, and substituting the result of k2 into S2/S3 into a (y21, y22, y23) into B (k2, x21, x22, x23) to increase the luminance in the dark area;
and after the brightness of the bright area of the picture is suppressed and the brightness of the dark area of the picture is improved, outputting a high dynamic range image of the picture.
According to a second aspect of the present invention, there is provided a high dynamic range image processing apparatus, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the computer program, when executed by the processor, implementing the steps of the high dynamic range image processing method described above.
According to a third aspect of the present invention, there is also provided a computer-readable storage medium having stored thereon a high dynamic range image processing program which, when executed by a processor, implements the steps of the above-described high dynamic range image processing method.
According to the high dynamic range image processing method, the high dynamic range image processing device and the computer readable storage medium, the bright area and the dark area on a single picture are divided, the brightness of the bright area is suppressed by the brightness suppression function, the brightness of the dark area is increased by the brightness increase function, and the high dynamic range image of the picture is obtained. The dynamic range and image details are expanded by using a single picture, so that the time delay from the beginning of shooting to the generation of the picture is reduced, and the dynamic range and the image details can be expanded for the shot picture.
Drawings
FIG. 1 is a flowchart of a high dynamic range image processing method according to embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a conventional high dynamic range image principle for obtaining a picture from a plurality of pictures;
FIG. 3 is a schematic diagram of a high dynamic range image principle for obtaining a picture from a single picture according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a high dynamic range image processing apparatus according to embodiment 2 of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention clearer and clearer, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, an embodiment of the present invention provides a high dynamic range image processing method, including:
and S101, counting the number of pixel points of the brightness component in the bright area in the selected picture, weighting and summing the pixel points to obtain S1, counting the number of pixel points of the brightness component in the dark area, weighting and summing the pixel points to obtain S2, and weighting and summing the brightness component of the whole picture to obtain S3.
Specifically, before the step of selecting one picture, the method further includes:
setting a brightness threshold L1 of a bright area and a brightness threshold L2 of a dark area, wherein pixel points with brightness values larger than L1 in the picture are considered to belong to the bright area, and pixel points with brightness values smaller than L2 are considered to belong to the dark area; the pixel value range of the pixel points is 0,1 and 2.
The counting the number of the pixels of the brightness component in the bright area and performing weighted summation to obtain S1, the counting the number of the pixels of the brightness component in the dark area and performing weighted summation to obtain S2, and the performing weighted summation to obtain S3 of the brightness component of the whole picture specifically includes:
counting pixel values larger than L1 in the picture as (L1+1), (L1+2) and (L1+3) · n, wherein the corresponding weighted values are W (L1+1), W (L1+2) and W (L1+3) · Wn, and the pixel values of the brightness component of the statistical light region are respectively (L1+1), (L1+2) and (L1+3) · n, and the number of pixel points of the brightness component of the statistical light region is respectively CNT (L1+1), CNT (L1+2) and CNT (L1+3) · CNTn;
counting pixel values smaller than L2 in the picture to be 0,1,2.. once. (L2-1), wherein the corresponding weights are W0, W1 and W2.. W (L2-1), and the number of pixel points of the brightness component of the dark area to be 0,1,2.. once. (L2-1) is CNT0, CNT1 and CNT2.. once.. CNT (L2-1);
then S1 ═ CNT (L1+1) × W (L1+1) + CNT (L1+2) × W (L1+2) + CNT (L1+3) × W (L1+3) +.
S2＝CNT0*W0+CNT1*W1+CNT2*W2+......+CNT(L2-1)*W(L2-1)；
S3＝CNT0*W0+CNT1*W1+CNT2*W2+......+CNTN*Wn；
Where n is the maximum pixel value of the luminance and chrominance components.
S102, substituting k1 into S1/S3 to a (y11, y12, y13) to a (k1, x11, x12, x13) to suppress the luminance in the bright area, and substituting the result of k2 into S2/S3 into a luminance boost function (y21, y22, y23) to B (k2, x21, x22, x23) to boost the luminance in the dark area.
Wherein the luma compression function (y11, y12, y13) is a (k1, x11, x12, x13), y11 is a compressed luma, y12 is a compressed first chroma component, and y13 is a compressed second chroma component; x11 is the pre-compression luminance, x12 is the pre-compression first chrominance component, and x13 is the pre-compression second chrominance component. In the luminance boost function (y21, y22, y23) ═ B (k2, x21, x22, x23), y21 is the boosted luminance, y22 is the first chrominance component after boosting, y23 is the second chrominance component after boosting, x21 is the luminance before boosting, x22 is the first chrominance component before boosting, and x23 is the second chrominance component before boosting.
In one embodiment, the luminance suppressing function (y11, y12, y13) is a (k1, x11, x12, x13) and the luminance boosting function (y21, y22, y23) is B (k2, x21, x22, x 23);
the luminance suppression function (y11, y12, y13) ═ a (k1, x11, x12, x13) is:
y11＝max(0,(x11–(k1×(x11/n)×Δd)))；
y12＝max(0,(x12–(k1×(x12/n)×Δd)))；
y13＝max(0,(x13–(k1×(x13/n)×Δd)))；
the luminance boost function (y21, y22, y23) ═ B (k2, x21, x22, x23) is:
y21＝min(n,(x1+(k2×(1-(x21/n))×Δu)))；
y22＝min(n,(x2+(k2×(1-(x22/n))×Δu)))；
y23＝min(n,(x3+(k2×(1-(x23/n))×Δu)))；
where n is the maximum pixel value of the luminance and chrominance components, Δ d is the compression factor, and Δ u is the lifting factor.
S103, after brightness suppression is carried out on the bright area and brightness improvement is carried out on the dark area of the picture, a high dynamic range image of the picture is output.
As shown in fig. 2, the effect of providing more dynamic range and image details is achieved by taking multiple pictures and combining the multiple pictures into one picture. Specifically, multiple photos P1, P2 and P3 are taken at preset time intervals by taking the same scene at the same viewing angle or position. . . Pm, by photographs P1, P2, P3. . . Pm synthesizes a high dynamic range image Ph. Because a plurality of pictures need to be shot, the time delay from the beginning of shooting to the generation of the pictures is large, and the shot pictures cannot be processed by expanding the dynamic range and the image details.
As shown in fig. 3, a picture P1 is taken of the same scene, and a pixel point in the picture P1 with a brightness value greater than L1 is considered to belong to a bright area and a pixel point with a brightness value less than L2 is considered to belong to a dark area according to a preset brightness threshold L1 and a preset brightness threshold L2 for the picture P1; and counting the number of pixels of the brightness component in the light area, weighting and summing the pixels to obtain S1, counting the number of pixels of the brightness component in the dark area, weighting and summing the pixels to obtain S2, and weighting and summing the brightness component of the whole picture to obtain S3.
Specifically, pixel values greater than L1 in the statistical picture P1 include (L1+1), (L1+2), (L1+3) · n, and corresponding to weighted values of W (L1+1), W (L1+2), and W (L1+3) · Wn, and the pixel values of the luminance component of the statistical light region are (L1+1), (L1+2), and the pixel numbers of L1+3) · n are respectively CNT (L1+1), CNT (L1+2), and CNT (L1+3) · CNTn;
the statistical picture P1 has pixel values smaller than L2, which are 0,1,2.. once. (L2-1), and correspond to weights W0, W1, and W2.. W (L2-1), and the number of pixels of the luminance component in the statistical dark area, which are 0,1,2.. once. (L2-1), is CNT0, CNT1, and CNT2.. once.. CNT (L2-1), respectively;
then S1 ═ CNT (L1+1) × W (L1+1) + CNT (L1+2) × W (L1+2) + CNT (L1+3) × W (L1+3) +.
S2＝CNT0*W0+CNT1*W1+CNT2*W2+......+CNT(L2-1)*W(L2-1)；
S3＝CNT0*W0+CNT1*W1+CNT2*W2+......+CNTN*Wn；
Where n is the maximum pixel value of the luminance and chrominance components.
Then, the luminance suppression function (y11, y12, y13) is substituted with k1 to S1/S3 to a (k1, x11, x12, x13) to suppress the luminance in the dark area, and the luminance boosting function (y21, y22, y23) is substituted with k2 to S2/S3 to B (k2, x21, x22, x23) to boost the luminance in the dark area. After the brightness suppression and the brightness boost for the bright and dark areas of the picture P1, the high dynamic range image Ph of the picture P1 is output.
Example 2
As shown in fig. 4, the hardware structure of the high dynamic range image processing apparatus according to the embodiment of the present invention, specifically, the high dynamic range image processing apparatus 20 at least includes a processor 21, a memory 22 and a data bus 23. The data bus 23 is used for implementing connection communication between the processor 21 and the memory 22, and the memory 22 is a computer-readable storage medium that can store at least one computer program, which can be read, compiled and executed by the processor 21, so as to implement the corresponding processing flow. In the present embodiment, the memory 22 is used as a computer readable storage medium, in which a high dynamic range image processing program is stored, and the program is executable by the processor 21, so as to implement the following steps of the high dynamic range image processing method:
in a selected picture, counting the number of pixels of the brightness component in the bright area, weighting and summing the number of pixels of the brightness component in the dark area to S1, weighting and summing the number of pixels of the brightness component in the dark area to S2, and weighting and summing the brightness component of the whole picture to S3;
substituting k1 into S1/S3 to a (y11, y12, y13) into a (k1, x11, x12, x13) to suppress the luminance in the bright area, and substituting the result of k2 into S2/S3 into a (y21, y22, y23) into B (k2, x21, x22, x23) to increase the luminance in the dark area;
and after the brightness of the bright area of the picture is suppressed and the brightness of the dark area of the picture is improved, outputting a high dynamic range image of the picture.
Example 3
An embodiment of the present invention further provides a computer-readable storage medium, where a high dynamic range image processing program is stored on the computer-readable storage medium, and when the high dynamic range image processing program is executed by a processor, the steps of the high dynamic range image processing method are implemented.
According to the high dynamic range image processing method, the high dynamic range image processing device and the computer readable storage medium, the bright area and the dark area on a single picture are divided, the brightness of the bright area is suppressed by the brightness suppression function, the brightness of the dark area is increased by the brightness increase function, and the high dynamic range image of the picture is obtained. The dynamic range and image details are expanded by using a single picture, so that the time delay from the beginning of shooting to the generation of the picture is reduced, and the dynamic range and the image details can be expanded for the shot picture.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better embodiment. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a computer-readable storage medium (such as ROM/RAM, magnetic disk, optical disk), and includes instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device) to execute the method for allocating resources in a D2D communication system according to the embodiments of the present invention.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings, and are not to be construed as limiting the scope of the invention. Any modifications, equivalents and improvements which may occur to those skilled in the art without departing from the scope and spirit of the present invention are intended to be within the scope of the claims.
Claims (5)
1. A method of high dynamic range image processing, the method comprising:
in a selected picture, counting the number of pixels of the brightness component in the bright area, weighting and summing the number of pixels of the brightness component in the dark area to S1, weighting and summing the number of pixels of the brightness component in the dark area to S2, and weighting and summing the brightness component of the whole picture to S3;
substituting k1 into S1/S3 to a (y11, y12, y13) into a (k1, x11, x12, x13) to suppress the luminance in the bright area, and substituting the result of k2 into S2/S3 into a (y21, y22, y23) into B (k2, x21, x22, x23) to increase the luminance in the dark area; the luminance compression function (y11, y12, y13) is a (k1, x11, x12, x13), y11 is compressed luminance, y12 is compressed first chrominance component, and y13 is compressed second chrominance component; x11 is the pre-compression luminance, x12 is the pre-compression first chrominance component, and x13 is the pre-compression second chrominance component; in the luminance boost function (y21, y22, y23) ═ B (k2, x21, x22, x23), y21 is the boosted luminance, y22 is the first chrominance component after boosting, y23 is the second chrominance component after boosting, x21 is the luminance before boosting, x22 is the first chrominance component before boosting, and x23 is the second chrominance component before boosting;
after the brightness of the bright area of the picture is suppressed and the brightness of the dark area of the picture is improved, outputting a high dynamic range image of the picture;
before the step of selecting a picture, the method further comprises:
setting the luminance suppressing functions (y11, y12, y13) ═ a (k1, x11, x12, x13) and the luminance boost functions (y21, y22, y23) ═ B (k2, x21, x22, x 23);
the luminance suppression function (y11, y12, y13) ═ a (k1, x11, x12, x13) is:
y11＝max(0,(x11–(k1×(x11/n)×Δd)))；
y12＝max(0,(x12–(k1×(x12/n)×Δd)))；
y13＝max(0,(x13–(k1×(x13/n)×Δd)))；
the luminance boost function (y21, y22, y23) ═ B (k2, x21, x22, x23) is:
y21＝min(n,(x1+(k2×(1-(x21/n))×Δu)))；
y22＝min(n,(x2+(k2×(1-(x22/n))×Δu)))；
y23＝min(n,(x3+(k2×(1-(x23/n))×Δu)))；
where n is the maximum pixel value of the luminance and chrominance components, Δ d is the compression factor, and Δ u is the lifting factor.
2. The high dynamic range image processing method of claim 1, wherein said step of selecting a picture is preceded by the method further comprising:
setting a brightness threshold L1 of a bright area and a brightness threshold L2 of a dark area, wherein pixel points with brightness values larger than L1 in the picture are considered to belong to the bright area, and pixel points with brightness values smaller than L2 are considered to belong to the dark area; the pixel value range of the pixel points is 0,1 and 2.
3. The method according to claim 2, wherein the counting the number of pixels of the luminance component in the light region and performing weighted summation S1, the counting the number of pixels of the luminance component in the dark region and performing weighted summation S2, and the performing weighted summation S3 of the luminance component of the entire picture specifically comprises:
counting pixel values larger than L1 in the picture as (L1+1), (L1+2) and (L1+3) · n, wherein the corresponding weighted values are W (L1+1), W (L1+2) and W (L1+3) · Wn, and the pixel values of the brightness component of the statistical light region are respectively (L1+1), (L1+2) and (L1+3) · n, and the number of pixel points of the brightness component of the statistical light region is respectively CNT (L1+1), CNT (L1+2) and CNT (L1+3) · CNTn;
counting pixel values smaller than L2 in the picture to be 0,1,2.. once. (L2-1), wherein the corresponding weights are W0, W1 and W2.. W (L2-1), and the number of pixel points of the brightness component of the dark area to be 0,1,2.. once. (L2-1) is CNT0, CNT1 and CNT2.. once.. CNT (L2-1);
then S1 ═ CNT (L1+1) × W (L1+1) + CNT (L1+2) × W (L1+2) + CNT (L1+3) × W (L1+3) +.
S2＝CNT0*W0+CNT1*W1+CNT2*W2+......+CNT(L2-1)*W(L2-1)；
S3＝CNT0*W0+CNT1*W1+CNT2*W2+......+CNTN*Wn；
Where n is the maximum pixel value of the luminance and chrominance components.
4. A high dynamic range image processing apparatus, characterized in that the apparatus comprises a memory, a processor and a computer program stored on the memory and executable on the processor, which computer program, when executed by the processor, carries out the steps of the high dynamic range image processing method according to any one of claims 1 to 3.
5. A computer-readable storage medium having stored thereon a high dynamic range image processing program which, when executed by a processor, implements the steps of the high dynamic range image processing method of any one of items 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010798824.3A CN111800584B (en) | 2020-08-11 | 2020-08-11 | High dynamic range image processing method, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010798824.3A CN111800584B (en) | 2020-08-11 | 2020-08-11 | High dynamic range image processing method, device and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111800584A CN111800584A (en) | 2020-10-20 |
| CN111800584B true CN111800584B (en) | 2022-04-29 |
Family
ID=72833953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010798824.3A Active CN111800584B (en) | 2020-08-11 | 2020-08-11 | High dynamic range image processing method, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111800584B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103795991A (en) * | 2014-02-08 | 2014-05-14 | 厦门美图之家科技有限公司 | High-dynamic-range image generating method based on single image |
| CN103971330A (en) * | 2013-02-05 | 2014-08-06 | 腾讯科技（深圳）有限公司 | Image enhancing method and device |
| CN108805873A (en) * | 2017-04-28 | 2018-11-13 | 南宁富桂精密工业有限公司 | Image processing method and device |
| CN110738603A (en) * | 2018-07-18 | 2020-01-31 | 中国商用飞机有限责任公司 | image gray scale processing method, device, computer equipment and storage medium |
| CN110766621A (en) * | 2019-10-09 | 2020-02-07 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
| CN111093039A (en) * | 2018-10-24 | 2020-05-01 | 北京图森智途科技有限公司 | Exposure evaluation value calculation method, exposure parameter adjustment method and imaging equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5802520B2 (en) * | 2011-11-11 | 2015-10-28 | 株式会社 日立産業制御ソリューションズ | Imaging device |
| US9460497B2 (en) * | 2012-09-21 | 2016-10-04 | Htc Corporation | Image enhancement methods and systems using the same |
| CN110581956A (en) * | 2019-08-26 | 2019-12-17 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
-
2020
- 2020-08-11 CN CN202010798824.3A patent/CN111800584B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103971330A (en) * | 2013-02-05 | 2014-08-06 | 腾讯科技（深圳）有限公司 | Image enhancing method and device |
| CN103795991A (en) * | 2014-02-08 | 2014-05-14 | 厦门美图之家科技有限公司 | High-dynamic-range image generating method based on single image |
| CN108805873A (en) * | 2017-04-28 | 2018-11-13 | 南宁富桂精密工业有限公司 | Image processing method and device |
| CN110738603A (en) * | 2018-07-18 | 2020-01-31 | 中国商用飞机有限责任公司 | image gray scale processing method, device, computer equipment and storage medium |
| CN111093039A (en) * | 2018-10-24 | 2020-05-01 | 北京图森智途科技有限公司 | Exposure evaluation value calculation method, exposure parameter adjustment method and imaging equipment |
| CN110766621A (en) * | 2019-10-09 | 2020-02-07 | Oppo广东移动通信有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111800584A (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104980652B (en) | Image processing apparatus and image processing method | |
| CN109801240B (en) | Image enhancement method and image enhancement device | |
| US10565742B1 (en) | Image processing method and apparatus | |
| CN112565636B (en) | Image processing method, device, equipment and storage medium | |
| KR101998531B1 (en) | Real-time video enhancement methods, terminals, and non-transitory computer readable storage media | |
| CN112532855B (en) | Image processing method and device | |
| CN108335272B (en) | Method and device for shooting picture | |
| CN111242860B (en) | Super night scene image generation method and device, electronic equipment and storage medium | |
| CN112381743A (en) | Image processing method, device, equipment and storage medium | |
| WO2023273868A1 (en) | Image denoising method and apparatus, terminal, and storage medium | |
| CN111209775A (en) | Signal lamp image processing method, device, equipment and storage medium | |
| CN110807735A (en) | Image processing method, image processing device, terminal equipment and computer readable storage medium | |
| JP2011223221A (en) | Photographing device and image integration program | |
| CN106803920B (en) | Image processing method and device and intelligent conference terminal | |
| JP4879363B1 (en) | Image processing system | |
| JP2018182376A (en) | Image processing apparatus | |
| CN110581957A (en) | image processing method, image processing device, storage medium and electronic equipment | |
| CN114245035A (en) | Video generation method and device, equipment and medium | |
| CN111800584B (en) | High dynamic range image processing method, device and computer readable storage medium | |
| CN111800583B (en) | High dynamic range image partition processing method and device and computer readable storage medium | |
| CN115187487A (en) | Image processing method and device, electronic device and storage medium | |
| JP2016010121A (en) | Image processing apparatus and image processing method | |
| Gil Rodríguez et al. | High quality video in high dynamic range scenes from interlaced dual-iso footage | |
| WO2016200480A1 (en) | Color filter array scaler | |
| WO2012172728A1 (en) | Image processing system |
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 |