Video noise detection method, terminal device and computer storage medium

Abstract

The present application provides a video noise detection method, a terminal device and a computer storage medium. The video noise detection method includes: obtaining a first basic feature image of a first video frame image in a video, and obtaining a second basic feature image of a second video frame image in a video; determining a noise area based on the first basic feature image and the second basic feature image, and determining a first noise rate of the noise area based on a frame difference map of the noise area; determining a second noise rate based on pixel difference information between the first basic feature image and the second basic feature image; and determining a target noise rate of the video based on the first noise rate and the second noise rate. In the above manner, the video noise detection method of the present application can effectively improve the robustness of video noise detection.

Description

Technical Field

[0001] The present application relates to the technical field of image quality evaluation, and in particular to a video noise detection method, a terminal device and a computer storage medium. Background Art

[0002] Video noise is an important factor affecting image quality. How to detect video noise in order to reasonably evaluate the corresponding image quality is one of the research focuses in this field.

[0003] However, existing video noise detection methods are unable to detect noise in certain extreme cases (such as video noise with extremely high noise levels), or only have good detection effects on some types of noise (such as Gaussian noise), which results in poor detection effects and low robustness of existing video noise detection methods in some cases. Summary of the invention

[0004] The present application provides a video noise detection method, a terminal device and a computer storage medium to improve.

[0005] The present application provides a video noise detection method, which includes:

[0006] Acquire a first basic feature image of a first video frame image in the video, and acquire a second basic feature image of a second video frame image in the video;

[0007] Determine a noise region based on the first basic feature image and the second basic feature image, and determine a first noise rate of the noise region based on a frame difference image of the noise region;

[0008] Determining a second noise rate based on pixel difference information between the first basic feature image and the second basic feature image;

[0009] A target noise rate for the video is determined based on the first noise rate and the second noise rate.

[0010] Wherein, obtaining a first basic feature image of a first video frame image in a video includes:

[0011] Acquire a first texture map of a first video frame image;

[0012] Calculating a first texture degree value of a first video frame image based on the first texture map;

[0013] If the first texture level value is greater than or equal to the preset texture level value, the first texture image is used as the first basic feature image of the first video frame image.

[0014] The video noise detection method further includes:

[0015] If the first texture degree value is less than the preset texture degree value, a first expansion map of the first video frame image is obtained based on the first texture map, and the first expansion map is used as a first basic feature image of the first video frame image.

[0016] Wherein, determining the noise area based on the first basic feature image and the second basic feature image includes:

[0017] Compressing the first basic feature image based on a preset convolution template to obtain a first mask image of the first basic feature image;

[0018] Compressing the second basic feature image based on a preset convolution template to obtain a second mask image of the second basic feature image;

[0019] The overlapping area of ​​the first mask image and the second mask image is taken as the noise area.

[0020] Wherein, determining the first noise rate of the noise area based on the frame difference map of the noise area includes:

[0021] Acquire a first integral image of the first video frame image, and acquire a second integral image of the second video frame image;

[0022] Acquire a frame difference image and a frame difference integral image of the noise region based on the first integral image and the second integral image;

[0023] Based on the frame difference integral map, a first noise rate of the noise region is determined.

[0024] Wherein, determining the first noise rate of the noise area based on the frame difference integral image includes:

[0025] Divide the noise area into several noise area blocks;

[0026] Calculate the variance and smoothness of each noise area block based on the frame difference integral map;

[0027] The first noise rate of the noise region is calculated based on the variance and smoothness of all noise region blocks.

[0028] The first noise rate of the noise area is calculated based on the variance and smoothness of all noise area blocks, including:

[0029] Filter out valid noise region blocks whose smoothness is less than a preset smoothness from all noise region blocks, wherein both the smoothness and the variance of the valid noise region blocks are not 0;

[0030] Based on the smoothness of all effective noise area blocks as weights, the average value of the variance is calculated as the first noise rate of the noise area.

[0031] Wherein, determining the second noise rate based on pixel difference information between the first basic feature image and the second basic feature image includes:

[0032] Recording changed pixel points with different pixel values ​​at the same position in the first mask image and the second mask image;

[0033] Based on the changed pixels, a second noise rate is determined.

[0034] Wherein, determining the second noise rate based on the changed pixel point includes:

[0035] The second noise rate is calculated based on the ratio of the number of changed pixels to the number of pixels of the first video frame image or the second video frame image.

[0036] The present application also provides a terminal device, the terminal device includes a memory and a processor, wherein the memory is coupled to the processor;

[0037] The memory is used to store program data, and the processor is used to execute the program data to implement the above-mentioned video noise detection method.

[0038] The present application also provides a computer storage medium, which is used to store program data. When the program data is executed by a processor, it is used to implement the video noise detection method as described above.

[0039] The beneficial effect of the present application is that the video noise detection method of the present application obtains a frame difference map to obtain a first noise rate based on basic feature images of different frames, and obtains pixel difference information to obtain a second noise rate, and finally obtains a target noise rate of the video based on the first noise rate and the second noise rate to complete the video noise detection. In the above manner, the present application combines the frame difference map and pixel difference information of different frame images to calculate the target noise rate of the video, which can effectively improve the robustness of the video noise detection method. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0041] Figure 1 It is a flow chart of an embodiment of the video noise detection method of the present application;

[0042] Figure 2 It is a structural schematic diagram of an embodiment of the terminal device of the present application;

[0043] Figure 3 It is a structural diagram of an embodiment of the computer storage medium of the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] See also Figure 1 , Figure 1 It is a flowchart of an embodiment of the video noise detection method of the present application.

[0046] The video noise detection method of the present application is applied to a terminal device, wherein the terminal device of the present application can be a server, an electronic device, or a system in which a server and a terminal device cooperate with each other. Accordingly, the various parts included in the electronic device, such as various units, subunits, modules, and submodules, can all be set in the server, can all be set in the terminal device, or can be set in the server and the terminal device respectively.

[0047] The above-mentioned server can be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers, or it can be implemented as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here. In some possible implementations, the video noise detection method of the embodiment of the present application can be implemented by a processor calling a computer-readable instruction stored in a memory.

[0048] like Figure 1 As shown, the video noise detection method of the present application specifically includes the following steps:

[0049] Step S11: obtaining a first basic feature image of a first video frame image in a video, and obtaining a second basic feature image of a second video frame image in the video.

[0050] The first video frame image and the second video frame image may be two adjacent video frame images in the same video stream. The basic features of an image include color features, texture features, shape features, and spatial relationship features. When detecting video noise, it is more appropriate to perform correlation calculations based on the texture features of the image to obtain a detection result.

[0051] Optionally, obtaining a first basic feature image of a first video frame image in a video may specifically include the following steps:

[0052] A first texture map of a first video frame image is obtained.

[0053] Based on the first texture map, a first texture reference value of the first video frame image is determined.

[0054] If the first texture reference value is greater than or equal to the preset texture reference value, execute A. If the first texture reference value is less than the preset texture reference value, execute B.

[0055] A: Use the first texture image as the first basic feature image of the first video frame image.

[0056] B: Obtaining a first expansion map of the first video frame image based on the first texture map, and using the first expansion map as a first basic feature image of the first video frame image.

[0057] When the first texture reference value is high (e.g., the first texture reference value is greater than or equal to the preset texture reference value), the image texture of the first video frame image is relatively complex and has strong rich text characteristics. Therefore, it is necessary to directly use the first texture map as the first basic feature image of the first video frame image to retain more texture features. Rich Text Format (RTF) is a cross-platform document format that is convenient for viewing on different devices and systems. Most word processing software can read and save documents in rich text format. Rich text refers to the fact that files in rich text format are embedded with different control symbols compatible with various applications and operating systems, making the files larger and more complex overall.

[0058] When the first texture reference value is low (e.g., the first texture reference value is less than the preset texture reference value), the image texture of the first video frame image is relatively simple, the image is smooth, and the text information contained is less. Therefore, it is necessary to further obtain a first expansion map of the first video frame image based on the first texture map, and use the first expansion map as the first basic feature image of the first video frame image to highlight the texture features.

[0059] Specifically, obtaining a first texture map of a first video frame image may include the following steps:

[0060] A Gaussian filter is performed on the grayscale image of the first video frame to remove noise.

[0061] The gradient strength and gradient direction of the denoised first video frame image are calculated, wherein the formula for calculating the gradient strength and gradient direction is as follows:

[0062]

[0063]

[0064] In the formula, G is the gradient strength, θ is the gradient direction, and f x is the gradient in the x-axis direction, f yis the gradient in the y-axis direction, and the x-axis and the y-axis are two axes perpendicular to each other in the vertical coordinate system of the first video frame image.

[0065] Based on the gradient intensity and gradient direction, the non-maximum suppression technique is used to obtain the first texture map.

[0066] Further acquiring a first expansion map of the first video frame image based on the first texture map may specifically include the following steps:

[0067] The first texture map is filtered using a sliding window of a preset size to obtain a first dilation map.

[0068] Acquiring the first texture map of the first video frame image may specifically be processing the first video frame image using an edge detection algorithm to obtain the first texture map. Using a sliding window of a preset size to filter the first texture map may specifically be convolving the first texture map using a convolution kernel of a preset size to obtain the first expansion map. The first texture map may specifically be a canny texture map, and the first expansion map may specifically be a canny expansion map.

[0069] The specific formula for calculating the first texture reference value of the first video frame image based on the first texture map may be as follows:

[0070]

[0071] Wherein, CS is the first texture reference value, M is the width of the first video frame image, N is the height of the first video frame image, and C(x, y) is the pixel value of the pixel point (x, y) in the first texture image.

[0072] It should be noted that the specific steps of obtaining the second basic feature image of the second video frame image correspond to the specific steps of obtaining the first basic feature image of the first video frame image, which will not be repeated here.

[0073] Step S12: determining a noise region based on the first basic feature image and the second basic feature image, and determining a first noise rate of the noise region based on a frame difference image of the noise region.

[0074] The noise region can be obtained according to the first basic feature image and the second basic feature image, and then the frame difference image corresponding to the noise region is calculated for use in subsequent calculations. The first noise rate is calculated based on the obtained frame difference image and the noise region for use in subsequent calculations.

[0075] Optionally, determining the noise area based on the first basic feature image and the second basic feature image may specifically include the following steps:

[0076] The first basic feature image is compressed based on a preset convolution template to obtain a first mask image of the first basic feature image.

[0077] The second basic feature image is compressed based on a preset convolution template to obtain a second mask image of the second basic feature image.

[0078] The overlapping area of ​​the first mask image and the second mask image is taken as the noise area.

[0079] Specifically, compressing the first basic feature image based on a preset convolution template to obtain a first mask image of the first basic feature image may specifically include:

[0080] The first texture image is compressed based on a preset convolution template to obtain a first mask image of the first basic feature image, wherein the formula for obtaining the first mask image may be as follows:

[0081] F(x,y)=H(x,y)★C(x,y);

[0082] Where F(x, y) is the first mask image, H(x, y) is the preset convolution template, C(x, y) is the first texture map, and ★ is the convolution operator.

[0083] In the process of compressing the first texture image based on the preset convolution template, the preset convolution template may be a 5*5 convolution template. When performing convolution, if there are more than 8 pixels with grayscale values ​​of 255 (full value) in a 5*5 pixel block range in the first texture image corresponding to the preset convolution template, the pixel points corresponding to the 5*5 pixel block in the first mask image obtained by convolution are assigned a value of 1, otherwise the pixel points corresponding to the 5*5 pixel block are assigned a value of 0.

[0084] It should be noted that the specific steps of compressing the second basic feature image based on the preset convolution template to obtain the second mask image of the second basic feature image correspond to the specific steps of compressing the first basic feature image based on the preset convolution template to obtain the first mask image of the first basic feature image, and will not be repeated here.

[0085] The first mask image and the second mask image obtained by the compression processing of the first texture map can highlight the characteristics of the noise points. Therefore, the overlapping area of ​​the first mask image and the second mask image can be further identified as the noise area. The calculation amount of determining the noise area based on this method is low and the accuracy is high.

[0086] Optionally, determining the first noise rate of the noise region based on the frame difference map of the noise region may specifically include the following steps:

[0087] A first integral image of the first video frame image is obtained, and a second integral image of the second video frame image is obtained.

[0088] A frame difference image and a frame difference integral image of the noise region are obtained based on the first integral image and the second integral image.

[0089] Based on the frame difference integral map, a first noise rate of the noise region is determined.

[0090] Specifically, the frame difference integral map may include an integral map and a square integral map, and the square integral map is a map obtained by squaring each pixel value in the integral map.

[0091] Optionally, determining the first noise rate of the noise region based on the frame difference map of the noise region may specifically include the following steps:

[0092] A first integral image of a noise region in a first video frame image is obtained, and a second integral image of a noise region in a second video frame image is obtained.

[0093] A frame difference image and a frame difference integral image of the noise region are obtained based on the first integral image and the second integral image.

[0094] Based on the frame difference integral map, a first noise rate of the noise region is determined.

[0095] After obtaining the frame difference image and the frame difference integral image of the noise area, further determining the first noise rate of the noise area based on the frame difference integral image may specifically include the following steps:

[0096] The noise area is divided into several noise area blocks.

[0097] The variance and smoothness of each noise region block are calculated based on the frame difference integral map.

[0098] The first noise rate of the noise region is calculated based on the variance and smoothness of all noise region blocks.

[0099] Specifically, the size of each noise area block is the same as the above-mentioned preset convolution template. If the size of the preset convolution template is 5*5, the size of each noise area block is also 5*5.

[0100] Furthermore, calculating the first noise rate of the noise region based on the variance and smoothness of all noise region blocks may specifically include the following steps:

[0101] Filter out valid noise region blocks whose smoothness is less than a preset smoothness from all noise region blocks, wherein both the smoothness and the variance of the valid noise region blocks are not zero.

[0102] Based on the smoothness of all effective noise area blocks as weights, the average value of the variance is calculated as the first noise rate of the noise area.

[0103] Specifically, noise area blocks whose smoothness is less than a preset smoothness and whose smoothness and variance are not 0 can be screened out from all noise area blocks, and the screened noise area blocks are determined as valid noise area blocks. The smoothness of each valid noise area block is used as the weight corresponding to each valid noise area block, and the weighted average of the variances of each valid noise area block is calculated as the first noise rate. The preset smoothness can be 30%, 50%, 60%, or other values, which are not limited here.

[0104] Since the pixel value of any pixel point in the inter-frame integral image is equal to the sum of the pixel values ​​in the rectangular area surrounded by the upper left corner of the frame difference image and the pixel point, after obtaining the inter-frame integral image, the sum of the pixel values ​​in a rectangular area of ​​any size in the frame difference image can be calculated in a constant time, which can greatly reduce the amount of calculation of subsequent calculations based on the inter-frame integral image and improve the speed of video noise detection.

[0105] Step S13: determining a second noise rate based on pixel difference information between the first basic feature image and the second basic feature image.

[0106] The pixel difference information can be obtained by comparing the pixel values ​​of the first basic feature image and the second basic feature image, and the second noise rate is calculated based on the obtained pixel difference information for use in subsequent calculations.

[0107] On the basis of obtaining the first mask image and the second mask image as described above, further determining the second noise rate based on the pixel difference information between the first basic feature image and the second basic feature image may specifically include the following steps:

[0108] Record the changed pixel points with different pixel values ​​at the same position in the first mask image and the second mask image.

[0109] Based on the changed pixels, a second noise rate is determined.

[0110] Furthermore, based on the changed pixel points, determining the second noise rate may specifically include the following steps:

[0111] The second noise rate is calculated based on the ratio of the number of changed pixels to the number of pixels of the first video frame image or the second video frame image.

[0112] Specifically, first, pixel difference information of each pixel point in the video to which the first video frame image and the second video frame image belong may be determined based on the following formula.

[0113]

[0114] In the formula, are all the pixels contained in the first mask image or the second mask image, (x, y) is a pixel with the same position in the i-th mask image (e.g., the first mask image) and the i-1-th mask image (e.g., the second mask image), F i (x,y) is the pixel value of the pixel point (x,y) in the mask image of the i-th frame, is the pixel value of the pixel point (x, y) in the mask image of the i-1th frame.

[0115] The meaning of this formula is that if the pixel value of a pixel point (x, y) in the mask image of the i-th frame is different from that in the mask image of the i-1-th frame, then the pixel point in the S of the i-th frame is i (x, y) is assigned a value of 1. If they are the same, the pixel is set to S in the i-th frame. i (x,y) is assigned the value 0.

[0116] Then, the S of each pixel in each processed frame is determined by the above formula. i (x, y) and then convert each pixel point in each processed frame into S i The sum of (x, y) is divided by the number of processed frames to obtain the pixel average value corresponding to each pixel point, which can be shown as follows:

[0117]

[0118] In the formula, is the pixel average value of the pixel point (x, y), is the pixel (x, y) in each processed frame i The sum of (x, y), T is the number of processed frames, and the number of processed frames can specifically be the frame sequence number of the current frame in the video stream, that is, the number of frames that have been processed in the video stream.

[0119] Finally, the number of pixels whose average pixel value is greater than a preset pixel average value threshold is recorded as the number of noise points.

[0120] The formula for calculating the second noise rate is as follows:

[0121]

[0122] Where K is the number of noise points, is the total number of pixels contained in the first mask image or the second mask image, and Γ is the second noise rate.

[0123] Step S14: Determine a target noise rate of the video based on the first noise rate and the second noise rate.

[0124] A weighted average of the first noise rate and the second noise rate may be calculated as a target noise rate of the video.

[0125] Optionally, the formula for calculating the target noise rate of the video is as follows:

[0126]

[0127] Where σ is the target noise rate, is the first noise rate, Γ is the second noise rate, α and β are the weights of the first noise rate and the second noise rate, respectively. It can be the mean of the variance mentioned above.

[0128] Specifically, the sum of α and β may be 1, or may be greater than 1 or less than 1. It may be set according to actual needs or conditions and is not limited here.

[0129] It should be noted that the above steps S15 and S16 may be performed before the above steps S13 and S14, or may be performed simultaneously with the above steps S13 and S14, which is not limited here.

[0130] The video noise detection method of the present application obtains a frame difference map to obtain a first noise rate based on basic feature images of different frames, and obtains pixel difference information to obtain a second noise rate, and finally obtains the target noise rate of the video based on the first noise rate and the second noise rate to complete the video noise detection. In the above manner, the present application combines the frame difference map and pixel difference information of different frame images to calculate the target noise rate of the video, which can effectively improve the robustness of the video noise detection method. In addition, the complexity of the calculations involved in the present application is relatively low, which can effectively improve the response speed, that is, the sensitivity, of the video noise detection method.

[0131] In order to implement the video noise detection method of the above embodiment, this application proposes a terminal device. Figure 2 , Figure 2 It is a structural diagram of an embodiment of the terminal device of the present application.

[0132] like Figure 2 As shown, the terminal device 20 of the embodiment of the present application includes a processor 21, a memory 22 and a bus 23.

[0133] The processor 21 and the memory 22 are connected to the bus 23 respectively. The memory 22 stores program data. The processor 21 is used to execute the program data to implement the video noise detection method described in the above embodiment.

[0134] In this embodiment, the processor 21 may also be referred to as a CPU (Central Processing Unit). The processor 21 may be an integrated circuit chip having the ability to process signals. The processor 21 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or the processor 21 may also be any conventional processor, etc.

[0135] In order to implement the video noise detection method of the above embodiment, the present application also proposes a computer storage medium. Figure 3 , Figure 3 It is a structural diagram of an embodiment of the computer storage medium of the present application.

[0136] like Figure 3 As shown, the computer storage medium 30 is used to store program data 31. When the program data 31 is executed by the processor, it is used to implement the video noise detection method as described in the above embodiment.

[0137] The present application also provides a computer program product, wherein the computer program product includes a computer program, and the computer program is operable to enable a computer to execute the video noise detection method as described in the embodiment of the present application. The computer program product may be a software installation package.

[0138] The video noise detection method described in the above embodiment of the present application, when implemented in the form of a software functional unit and sold or used as an independent product, can be stored in a device, such as a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or part of the contribution to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0139] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A video noise detection method, characterized in that: The video noise detection method comprises: Acquire a first basic feature image of a first video frame image in a video, and acquire a second basic feature image of a second video frame image in the video; Acquire a first mask image of the first basic feature image and a second mask image of the second basic feature image; taking an overlapping area of ​​the first mask image and the second mask image as a noise area; Acquire a first integral image of the first video frame image, and acquire a second integral image of the second video frame image; Acquire a frame difference integral image of the noise area based on the first integral image and the second integral image; Determining a first noise rate of the noise area based on the frame difference integral image; Recording changed pixel points with different pixel values ​​at the same position in the first mask image and the second mask image; Calculating a second noise rate based on a ratio of the number of changed pixels to the number of pixels of the first video frame image or the second video frame image; Determining a target noise rate of the video based on the first noise rate and the second noise rate; The step of obtaining a first basic feature image of a first video frame image in a video includes: Acquire a first texture map of the first video frame image; Determining a first texture reference value of the first video frame image based on the first texture map; If the first texture reference value is greater than or equal to a preset texture reference value, using the first texture image as a first basic feature image of the first video frame image; If the first texture reference value is less than the preset texture reference value, obtaining a first expansion map of the first video frame image based on the first texture map, and using the first expansion map as a first basic feature image of the first video frame image; The acquiring a first mask image of the first basic feature image and a second mask image of the second basic feature image includes: Compressing the first basic feature image based on a preset convolution template to obtain a first mask image of the first basic feature image; Compressing the second basic feature image based on a preset convolution template to obtain a second mask image of the second basic feature image; The determining, based on the frame difference integral map, a first noise rate of the noise area comprises: Dividing the noise area into a plurality of noise area blocks; Calculating the variance and smoothness of each noise area block based on the frame difference integral map; Calculating a first noise rate of the noise region based on variance and smoothness of all noise region blocks; The step of acquiring a first expansion map of the first video frame image based on the first texture map includes: The first texture map is filtered using a sliding window of a preset size to obtain the first dilation map.

2. The video noise detection method according to claim 1, characterized in that: The formula for determining the first texture reference value of the first video frame image based on the first texture map is as follows: In the formula, is the first texture reference value, is the width of the first video frame image, is the height of the first video frame image, is the pixel point in the first texture map The pixel value of .

3. The video noise detection method according to claim 1, characterized in that: The step of calculating the first noise rate of the noise region based on the variance and smoothness of all noise region blocks comprises: Screening out valid noise region blocks whose smoothness is less than a preset smoothness from all noise region blocks, wherein both the smoothness and the variance of the valid noise region blocks are not 0; Based on the smoothness of all effective noise region blocks as weights, an average value of the variance is calculated as the first noise rate of the noise region.

4. A terminal device, characterized in that: The terminal device includes a memory and a processor, wherein the memory is coupled to the processor; The memory is used to store program data, and the processor is used to execute the program data to implement the video noise detection method according to any one of claims 1 to 3.

5. A computer storage medium, characterized in that: The computer storage medium is used to store program data, and when the program data is executed by the processor, it is used to implement the video noise detection method according to any one of claims 1 to 3.

Images