CN114286088A - Video screen splash detection method, device and storage medium applied to graphic processor - Google Patents
Video screen splash detection method, device and storage medium applied to graphic processor Download PDFInfo
- Publication number
- CN114286088A CN114286088A CN202111573720.3A CN202111573720A CN114286088A CN 114286088 A CN114286088 A CN 114286088A CN 202111573720 A CN202111573720 A CN 202111573720A CN 114286088 A CN114286088 A CN 114286088A
- Authority
- CN
- China
- Prior art keywords
- value
- screen
- data
- channel
- image
- 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.)
- Pending
Links
Images
Abstract
The application provides a video screen splash detection method, equipment and a storage medium applied to a graphic processor, wherein the method comprises the following steps: acquiring original data of a video; acquiring an image to be detected after the image is rendered by a graphics processor; carrying out color space transformation on an image to be detected to obtain transformed data; and detecting whether the screen is blurred according to the transformed data and the original data. The method provided by the application can effectively complete the detection of various screen-blooming phenomena such as line shape, color cast, tearing dislocation and the like by performing color space transformation on the image to be detected and detecting whether the screen is blooming or not according to the transformed data and the original data.
Description
Technical Field
The present application relates to the field of image processing technologies, and in particular, to a video splash screen detection method, device, and storage medium for a graphics processor.
Background
When the player separates, decodes, renders, and scans the video file to be output to the display, if a GPU (Graphics Processing Unit) has errors such as decoding and rendering, the display will be torn, misaligned, and color-shifted, as shown in fig. 1.
In the existing method for searching the screen splash, the number difference of straight lines between a reference image and an image to be detected and the color cast value of RGB (Red Green Blue) data are obtained through image detection, so that the purpose of detecting the screen splash is achieved.
However, the types of the screen-patterned patterns which can be detected by the existing scheme are single, the screen-patterned phenomenon is diversified, and the screen-patterned patterns not only have the common linear strip-shaped screen, but also have irregular screen-patterned patterns such as color cast, tearing and dislocation.
Disclosure of Invention
In order to solve one of the technical defects, the application provides a video splash screen detection method, video splash screen detection equipment and a storage medium which are applied to a graphic processor.
In a first aspect of the present application, a video screen splash detection method applied to a graphics processor is provided, the method including:
acquiring original data of a video;
acquiring an image to be detected after the image is rendered by a graphics processor;
carrying out color space transformation on the image to be detected to obtain transformed data;
and detecting whether the screen is displayed according to the transformed data and the original data.
Optionally, the acquiring raw data of the video includes:
acquiring a video file;
decoding the video file;
and determining the decoded data as original data.
Optionally, the color space of the image to be detected is an RGB space;
the color space transformation is carried out on the image to be detected to obtain transformed data, and the method comprises the following steps:
and converting the space of the data of the image to be detected into a YUV space according to the space conversion relation, and determining the data of the image to be detected after the space conversion as converted data.
Optionally, the spatial transformation relationship includes:
Y＝0.299*R+0.587*G+0.114*B；
U＝-0.147*R-0.289*G+0.436*B；
V＝0.615*R-0.515*G-0.100*B；
wherein R is the value of R channel in RGB space before conversion, G is the value of G channel in RGB space before conversion, B is the value of B channel in RGB space before conversion, Y is the value of Y channel in YUV space after conversion, U is the value of U channel in YUV space after conversion, and V is the value of V channel in YUV space after conversion.
Optionally, the detecting whether to screen up according to the transformed data and the original data includes:
determining a difference matrix according to the U channel value and the V channel value of the transformed data and the U channel value and the V channel value of the original data;
carrying out binarization processing on the difference matrix to obtain a difference matrix M1 after binarization processing;
determining the number of hue differences according to M1;
and detecting whether the screen is blurred according to the number of the hue differences.
Optionally, the detecting whether to screen according to the number of hue differences includes:
if the number of the hue differences is not less than the screen-blooming threshold value, determining that the detection result is the screen-blooming;
and if the number of the hue differences is smaller than the screen-blooming threshold value, detecting whether the screen is blooming or not according to the Y channel value of the transformed data and the Y channel value of the original data.
Optionally, the detecting whether to screen up according to the Y channel value of the transformed data and the Y channel value of the original data includes:
determining a deviation value between a Y channel value of the transformed data and a Y channel value of the original data;
according to the deviation value, performing binarization processing on the difference matrix by adopting a local structure similarity method to obtain a two-dimensional coordinate matrix M2;
taking coordinate information in M2 as an area starting point, and respectively intercepting areas in a preset range from a Y channel value of the transformed data and a Y channel value of the original data;
calculating a structural similarity index according to the intercepted area;
if the structural similarity index is not smaller than the similarity threshold, determining that the detection result is a screen splash;
and if the structural similarity index is smaller than the similarity threshold value, determining that the detection result is a non-screen-splash result.
Optionally, the calculating a structural similarity index according to the intercepted area includes:
wherein SSIM (x, y) is a structural similarity index, x, y are truncated regions, and muxIs the average value of x, μyIs the average value of the values of y,
is the variance of x and is the sum of the differences,
variance of y, σxyIs the covariance of x and y, c1，c2Is a constant.
In a second aspect of the present application, there is provided an electronic device comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method according to the first aspect.
In a third aspect of the present application, there is provided a computer readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the method according to the first aspect as described above.
The application provides a video screen splash detection method, equipment and a storage medium applied to a graphic processor, wherein the method comprises the following steps: acquiring original data of a video; acquiring an image to be detected after the image is rendered by a graphics processor; carrying out color space transformation on an image to be detected to obtain transformed data; and detecting whether the screen is blurred according to the transformed data and the original data. The method provided by the application can effectively complete the detection of various screen-blooming phenomena such as line shape, color cast, tearing dislocation and the like by performing color space transformation on the image to be detected and detecting whether the screen is blooming or not according to the transformed data and the original data.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic view of a blooming phenomenon;
fig. 2 is a schematic flowchart of a video splash screen detection method applied to a graphics processor according to an embodiment of the present disclosure;
fig. 3 is a flowchart illustrating a method for detecting whether to screen according to transformed data and original data according to an embodiment of the present application.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following further detailed description of the exemplary embodiments of the present application with reference to the accompanying drawings makes it clear that the described embodiments are only a part of the embodiments of the present application, and are not exhaustive of all embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In the process of implementing the present application, the inventor finds that, in the existing screen splash retrieval method, the number difference of the straight lines between the reference image and the image to be detected and the color cast value of the RGB data are obtained through image detection, so as to achieve the purpose of detecting the screen splash phenomenon. However, the types of the screen-patterned patterns which can be detected by the existing scheme are single, the screen-patterned phenomenon is diversified, and the screen-patterned patterns not only have the common linear strip-shaped screen, but also have irregular screen-patterned patterns such as color cast, tearing and dislocation.
In view of the foregoing problems, embodiments of the present application provide a video splash detection method, device, and storage medium for a graphics processor, where the method includes: acquiring original data of a video; acquiring an image to be detected after the image is rendered by a graphics processor; carrying out color space transformation on an image to be detected to obtain transformed data; and detecting whether the screen is blurred according to the transformed data and the original data. The method provided by the application can effectively complete the detection of various screen-blooming phenomena such as line shape, color cast, tearing dislocation and the like by performing color space transformation on the image to be detected and detecting whether the screen is blooming or not according to the transformed data and the original data.
Referring to fig. 2, an implementation flow of the video splash screen detection method applied to a Graphics Processing Unit (GPU) provided by this embodiment is as follows:
101, raw data of a video is acquired.
In particular, the method comprises the following steps of,
1. and acquiring the video file.
2. The video file is decoded.
3. The decoded data is determined as the original data.
The color space of the decoded data is the YUV (luminance chrominance) space.
And 102, acquiring an image to be detected after the image is rendered by the graphics processor.
And 103, performing color space transformation on the image to be detected to obtain transformed data.
The color space of the image to be detected is an RGB space, so that the step can convert the space of the data of the image to be detected into a YUV space according to the space conversion relation during specific implementation, and determine the data of the image to be detected after the space conversion as converted data.
That is, all the transformed data in this step are data in YUV space.
Wherein, the spatial conversion relation is as follows:
Y＝0.299*R+0.587*G+0.114*B。
U＝-0.147*R-0.289*G+0.436*B。
V＝0.615*R-0.515*G-0.100*B。
wherein R is the value of R channel in RGB space before conversion, G is the value of G channel in RGB space before conversion, B is the value of B channel in RGB space before conversion, Y is the value of Y channel in YUV space after conversion, U is the value of U channel in YUV space after conversion, and V is the value of V channel in YUV space after conversion.
For example, if the image to be detected is R2G2B2, the data of the image to be detected after the space transformation is Y2U2V2, and the transformed data is Y2U2V 2.
Wherein the content of the first and second substances,
Y2＝0.299*R2+0.587*G2+0.114*B2。
U2＝-0.147*R2-0.289*G2+0.436*B2。
V2＝0.615*R2-0.515*G2-0.100*B2。
and 104, detecting whether the screen is displayed according to the transformed data and the original data.
Because the transformed data and the original data are YUV space data, the implementation process of the step is as follows:
1. and determining a difference matrix according to the U channel value and the V channel value of the transformed data and the U channel value and the V channel value of the original data.
2. And (4) carrying out binarization processing on the difference matrix to obtain a difference matrix M1 after binarization processing.
3. The number of hue differences was determined according to M1.
4. And detecting whether the screen is blurred according to the number of the hue differences.
For example,
and if the number of the hue differences is not less than the screen-blooming threshold value, determining that the detection result is the screen-blooming.
And if the number of the hue differences is smaller than the screen-blooming threshold value, detecting whether the screen is blooming or not according to the Y channel value of the transformed data and the Y channel value of the original data.
I.e., 1) determining a deviation value between the Y-channel value of the transformed data and the Y-channel value of the original data. 2) And (4) carrying out binarization processing on the difference matrix by adopting a local structure similarity method according to the deviation value to obtain a two-dimensional coordinate matrix M2. 3) And taking the coordinate information in the M2 as a starting point of the region, and respectively cutting out the region of a preset range (such as 100 x 100) from the Y channel value of the transformed data and the Y channel value of the original data. 4) And calculating a structural similarity index according to the intercepted area. 5) And if the structural similarity index is not less than the similarity threshold, determining that the detection result is a screen splash. And if the structural similarity index is smaller than the similarity threshold value, determining that the detection result is a non-screen-splash result.
Wherein the index of structural similarity
Wherein SSIM (x, y) is a structural similarity index, x, y are truncated regions, and muxIs the average value of x, μyIs the average value of the values of y,
is the variance of x and is the sum of the differences,
variance of y, σxyIs the covariance of x and y, c1，c2Is a constant.
Taking FIG. 3 as an example, if the transformed data is Y2U2V2 and the original data is Y1U1V1, then
1. Calculating a difference matrix of U2V2 and U1V1, carrying out binarization processing on the difference matrix to obtain M1, counting to obtain the number of hue differences N1, judging whether the number of hue differences is less than a set threshold value, and judging that the image to be detected has a screen-blooming phenomenon if the number of hue differences is greater than the set threshold value.
2. And if the difference value N1 is smaller than the set threshold value, comparing the Y1 and the Y2 data to obtain a brightness information deviation value. According to the deviation numerical value, a local structure similarity method is adopted to carry out binarization processing on the difference matrix to obtain a two-dimensional coordinate matrix M2 of pixel points with larger differences, the coordinate information in M2 is taken as a region starting point, 100 × 100 regions R1 and R2 are respectively intercepted from Y1 and Y2, the structure similarity index SSIM of R1 and R2 is calculated, whether the value is smaller than a set threshold value or not is judged, if the value is larger than the set threshold value, the phenomenon of screen splash of the image to be detected is judged, and if the value is larger than the set threshold value, the phenomenon of screen splash of the image to be detected is judged.
In the video screen splash detection method applied to the graphic processor provided by this embodiment, the chromaticity deviation value and the structural similarity index of the image to be detected and the original data are obtained by performing color space transformation on the image to be detected and then comparing the UV data and the Y data with the original data.
The invention uses color space transformation to detect the video screen splash, achieves the aim of detecting on color saturation and image texture respectively by comparing the difference of YUV data, solves the problem of poor detection effect under the condition of color cast screen splash based on RGB data difference comparison, and can effectively cover the detection of line, color cast, tearing and other screen splash types.
The embodiment provides a video screen splash detection method applied to a graphic processor, which is used for acquiring original data of a video; acquiring an image to be detected after the image is rendered by a graphics processor; carrying out color space transformation on an image to be detected to obtain transformed data; and detecting whether the screen is blurred according to the transformed data and the original data. According to the method provided by the embodiment, the color space transformation is carried out on the image to be detected, whether the screen is patterned or not is detected according to the transformed data and the original data, and the detection of various screen-patterned phenomena such as line shape, color cast, tearing dislocation and the like can be effectively finished.
Based on the same inventive concept of a video splash screen detection method applied to a graphics processor, the present embodiment provides an electronic device, including: memory, processor, and computer programs.
Wherein the computer program is stored in the memory and configured to be executed by the processor to implement the video splash screen detection method applied to the graphics processor shown in fig. 2 described above.
In particular, the method comprises the following steps of,
raw data of a video is acquired.
And acquiring the image to be detected after the image processor renders.
And carrying out color space transformation on the image to be detected to obtain transformed data.
And detecting whether the screen is blurred according to the transformed data and the original data.
Optionally, the obtaining raw data of the video includes:
and acquiring the video file.
The video file is decoded.
A color space of the decoded data is determined.
The decoded data is determined as the original data.
Optionally, the color space of the image to be detected is an RGB space.
The method for carrying out color space transformation on an image to be detected to obtain transformed data comprises the following steps:
and converting the space of the data of the image to be detected into a YUV space according to the space conversion relation, and determining the data of the image to be detected after the space conversion as converted data.
Optionally, the spatial transformation relationship comprises:
Y＝0.299*R+0.587*G+0.114*B。
U＝-0.147*R-0.289*G+0.436*B。
V＝0.615*R-0.515*G-0.100*B。
wherein R is the value of R channel in RGB space before conversion, G is the value of G channel in RGB space before conversion, B is the value of B channel in RGB space before conversion, Y is the value of Y channel in YUV space after conversion, U is the value of U channel in YUV space after conversion, and V is the value of V channel in YUV space after conversion.
Optionally, detecting whether to screen up according to the transformed data and the original data includes:
and determining a difference matrix according to the U channel value and the V channel value of the transformed data and the U channel value and the V channel value of the original data.
And (4) carrying out binarization processing on the difference matrix to obtain a difference matrix M1 after binarization processing.
The number of hue differences was determined according to M1.
And detecting whether the screen is blurred according to the number of the hue differences.
Optionally, detecting whether to screen according to the number of hue differences includes:
and if the number of the hue differences is not less than the screen-blooming threshold value, determining that the detection result is the screen-blooming.
And if the number of the hue differences is smaller than the screen-blooming threshold value, detecting whether the screen is blooming or not according to the Y channel value of the transformed data and the Y channel value of the original data.
Optionally, detecting whether to screen up according to the Y channel value of the transformed data and the Y channel value of the original data, includes:
a deviation value between the Y-channel value of the transformed data and the Y-channel value of the original data is determined.
And (4) carrying out binarization processing on the difference matrix by adopting a local structure similarity method according to the deviation value to obtain a two-dimensional coordinate matrix M2.
And taking the coordinate information in the M2 as an area starting point, and respectively intercepting areas in preset ranges from the Y channel value of the transformed data and the Y channel value of the original data.
And calculating a structural similarity index according to the intercepted area.
And if the structural similarity index is not less than the similarity threshold, determining that the detection result is a screen splash.
And if the structural similarity index is smaller than the similarity threshold value, determining that the detection result is a non-screen-splash result.
Optionally, calculating a structural similarity index according to the intercepted area includes:
wherein SSIM (x, y) is a structural similarity index, x, y are truncated regions, and muxIs the average value of x, μyIs the average value of the values of y,
is a square of xThe difference is that the number of the first and second,
variance of y, σxyIs the covariance of x and y, c1，c2Is a constant.
The electronic device provided by the embodiment, wherein the computer program is executed by the processor to acquire the original data of the video; acquiring an image to be detected after the image is rendered by a graphics processor; carrying out color space transformation on an image to be detected to obtain transformed data; and detecting whether the screen is blurred according to the transformed data and the original data. The embodiment can effectively complete the detection of various screen-blooming phenomena such as line shape, color cast, tearing dislocation and the like by carrying out color space transformation on the image to be detected and detecting whether the screen is blooming or not according to the transformed data and the original data.
The present embodiment provides a computer on which a computer program is stored, based on the same inventive concept of a video splash screen detection method applied to a graphic processor. The computer program is executed by the processor to implement the video splash detection method applied to the graphics processor shown in fig. 2 described above.
In particular, the method comprises the following steps of,
raw data of a video is acquired.
And acquiring the image to be detected after the image processor renders.
And carrying out color space transformation on the image to be detected to obtain transformed data.
And detecting whether the screen is blurred according to the transformed data and the original data.
Optionally, the obtaining raw data of the video includes:
and acquiring the video file.
The video file is decoded.
A color space of the decoded data is determined.
The decoded data is determined as the original data.
Optionally, the color space of the image to be detected is an RGB space.
The method for carrying out color space transformation on an image to be detected to obtain transformed data comprises the following steps:
and converting the space of the data of the image to be detected into a YUV space according to the space conversion relation, and determining the data of the image to be detected after the space conversion as converted data.
Optionally, the spatial transformation relationship comprises:
Y＝0.299*R+0.587*G+0.114*B。
U＝-0.147*R-0.289*G+0.436*B。
V＝0.615*R-0.515*G-0.100*B。
wherein R is the value of R channel in RGB space before conversion, G is the value of G channel in RGB space before conversion, B is the value of B channel in RGB space before conversion, Y is the value of Y channel in YUV space after conversion, U is the value of U channel in YUV space after conversion, and V is the value of V channel in YUV space after conversion.
Optionally, detecting whether to screen up according to the transformed data and the original data includes:
and determining a difference matrix according to the U channel value and the V channel value of the transformed data and the U channel value and the V channel value of the original data.
And (4) carrying out binarization processing on the difference matrix to obtain a difference matrix M1 after binarization processing.
The number of hue differences was determined according to M1.
And detecting whether the screen is blurred according to the number of the hue differences.
Optionally, detecting whether to screen according to the number of hue differences includes:
and if the number of the hue differences is not less than the screen-blooming threshold value, determining that the detection result is the screen-blooming.
And if the number of the hue differences is smaller than the screen-blooming threshold value, detecting whether the screen is blooming or not according to the Y channel value of the transformed data and the Y channel value of the original data.
Optionally, detecting whether to screen up according to the Y channel value of the transformed data and the Y channel value of the original data, includes:
a deviation value between the Y-channel value of the transformed data and the Y-channel value of the original data is determined.
And (4) carrying out binarization processing on the difference matrix by adopting a local structure similarity method according to the deviation value to obtain a two-dimensional coordinate matrix M2.
And taking the coordinate information in the M2 as an area starting point, and respectively intercepting areas in preset ranges from the Y channel value of the transformed data and the Y channel value of the original data.
And calculating a structural similarity index according to the intercepted area.
And if the structural similarity index is not less than the similarity threshold, determining that the detection result is a screen splash.
And if the structural similarity index is smaller than the similarity threshold value, determining that the detection result is a non-screen-splash result.
Optionally, calculating a structural similarity index according to the intercepted area includes:
wherein SSIM (x, y) is a structural similarity index, x, y are truncated regions, and muxIs the average value of x, μyIs the average value of the values of y,
is the variance of x and is the sum of the differences,
variance of y, σxyIs the covariance of x and y, c1，c2Is a constant.
The present embodiment provides a computer-readable storage medium on which a computer program is executed by a processor to acquire raw data of a video; acquiring an image to be detected after the image is rendered by a graphics processor; carrying out color space transformation on an image to be detected to obtain transformed data; and detecting whether the screen is blurred according to the transformed data and the original data. The embodiment can effectively complete the detection of various screen-blooming phenomena such as line shape, color cast, tearing dislocation and the like by carrying out color space transformation on the image to be detected and detecting whether the screen is blooming or not according to the transformed data and the original data.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The scheme in the embodiment of the application can be implemented by adopting various computer languages, such as object-oriented programming language Java and transliterated scripting language JavaScript.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (10)
1. A video screen splash detection method applied to a graphics processor is characterized by comprising the following steps:
acquiring original data of a video;
acquiring an image to be detected after the image is rendered by a graphics processor;
carrying out color space transformation on the image to be detected to obtain transformed data;
and detecting whether the screen is displayed according to the transformed data and the original data.
2. The method of claim 1, wherein the obtaining raw data of a video comprises:
acquiring a video file;
decoding the video file;
and determining the decoded data as original data.
3. The method according to claim 1, characterized in that the color space of the image to be detected is an RGB space;
the color space transformation is carried out on the image to be detected to obtain transformed data, and the method comprises the following steps:
and converting the space of the data of the image to be detected into a YUV space according to the space conversion relation, and determining the data of the image to be detected after the space conversion as converted data.
4. The method of claim 3, wherein the spatially transforming the relationship comprises:
Y＝0.299*R+0.587*G+0.114*B；
U＝-0.147*R-0.289*G+0.436*B；
V＝0.615*R-0.515*G-0.100*B；
wherein R is the value of R channel in RGB space before conversion, G is the value of G channel in RGB space before conversion, B is the value of B channel in RGB space before conversion, Y is the value of Y channel in YUV space after conversion, U is the value of U channel in YUV space after conversion, and V is the value of V channel in YUV space after conversion.
5. The method of claim 4, wherein detecting whether to screen up based on the transformed data and the raw data comprises:
determining a difference matrix according to the U channel value and the V channel value of the transformed data and the U channel value and the V channel value of the original data;
carrying out binarization processing on the difference matrix to obtain a difference matrix M1 after binarization processing;
determining the number of hue differences according to M1;
and detecting whether the screen is blurred according to the number of the hue differences.
6. The method of claim 5, wherein said detecting whether to screen up based on said number of hue differences comprises:
if the number of the hue differences is not less than the screen-blooming threshold value, determining that the detection result is the screen-blooming;
and if the number of the hue differences is smaller than the screen-blooming threshold value, detecting whether the screen is blooming or not according to the Y channel value of the transformed data and the Y channel value of the original data.
7. The method of claim 6, wherein the detecting whether to screen up according to the Y-channel value of the transformed data and the Y-channel value of the original data comprises:
determining a deviation value between a Y channel value of the transformed data and a Y channel value of the original data;
according to the deviation value, performing binarization processing on the difference matrix by adopting a local structure similarity method to obtain a two-dimensional coordinate matrix M2;
taking coordinate information in M2 as an area starting point, and respectively intercepting areas in a preset range from a Y channel value of the transformed data and a Y channel value of the original data;
calculating a structural similarity index according to the intercepted area;
if the structural similarity index is not smaller than the similarity threshold, determining that the detection result is a screen splash;
and if the structural similarity index is smaller than the similarity threshold value, determining that the detection result is a non-screen-splash result.
8. The method of claim 7, wherein calculating the structural similarity indicator from the truncated region comprises:
wherein SSIM (x, y) is a structural similarity index, x, y are truncated regions, and muxIs the average value of x, μyIs the average value of the values of y,
is the variance of x and is the sum of the differences,
variance of y, σxyIs the covariance of x and y, c1，c2Is a constant.
9. An electronic device, comprising:
a memory;
a processor; and
a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-8.
10. A computer-readable storage medium, having stored thereon a computer program; the computer program is executed by a processor to implement the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111573720.3A CN114286088A (en) | 2021-12-21 | 2021-12-21 | Video screen splash detection method, device and storage medium applied to graphic processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111573720.3A CN114286088A (en) | 2021-12-21 | 2021-12-21 | Video screen splash detection method, device and storage medium applied to graphic processor |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114286088A true CN114286088A (en) | 2022-04-05 |
Family
ID=80873571
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111573720.3A Pending CN114286088A (en) | 2021-12-21 | 2021-12-21 | Video screen splash detection method, device and storage medium applied to graphic processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114286088A (en) |
-
2021
- 2021-12-21 CN CN202111573720.3A patent/CN114286088A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111028213B (en) | Image defect detection method, device, electronic equipment and storage medium | |
| US11113795B2 (en) | Image edge processing method, electronic device, and computer readable storage medium | |
| CN110189349B (en) | Image processing method and device | |
| CN109600605B (en) | Detection method of 4K ultra-high-definition video, electronic device and computer program product | |
| CN111223032A (en) | Watermark embedding method, watermark extracting method, watermark embedding device, watermark extracting equipment and data processing method | |
| CN105681775A (en) | White balance method and device | |
| CN108615030B (en) | Title consistency detection method and device and electronic equipment | |
| JP2006332908A (en) | Color image display apparatus, color image display method, program, and recording medium | |
| KR101428923B1 (en) | System and Method for Automatic Extraction of Component Packaging Regions in PCB | |
| CN112348946A (en) | Print processing method, print processing apparatus, electronic device, and storage medium | |
| CN113487473B (en) | Method and device for adding image watermark, electronic equipment and storage medium | |
| US7920755B2 (en) | Video content detector | |
| CN111163301B (en) | Color adjustment method, device and computer readable storage medium | |
| KR20120015980A (en) | Method, system and computer program product for object color correction | |
| CN114066823A (en) | Method for detecting color block and related product thereof | |
| CN112700456A (en) | Image area contrast optimization method, device, equipment and storage medium | |
| CN109859303B (en) | Image rendering method and device, terminal equipment and readable storage medium | |
| CN110298812B (en) | Image fusion processing method and device | |
| CN114286088A (en) | Video screen splash detection method, device and storage medium applied to graphic processor | |
| CN117011114A (en) | Watermark embedding method and device for virtual desktop, electronic equipment and storage medium | |
| US8090145B2 (en) | System and method for analyzing and marking film | |
| CN111415367A (en) | Method and device for removing image background | |
| CN111953986A (en) | Image processing method and device | |
| CN107452039B (en) | Method and device for compressing RGB color space | |
| CN111340677A (en) | Video watermark detection method and device, electronic equipment and computer readable medium |
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 |