Video quality evaluation method, device, electronic device and storage medium

Abstract

The embodiments of the present application provide a video quality evaluation method, device, electronic device and computer-readable storage medium. The video quality evaluation method includes obtaining an original video and a super-resolution video; the super-resolution video is a video obtained by super-resolution reconstruction of the original video; determining a preset resolution according to the resolution of the original video and the resolution of the super-resolution video; adjusting the resolution of the original video to the preset resolution to obtain a first video, and / or; adjusting the resolution of the super-resolution video to the preset resolution to obtain a second video; calculating the similarity between the first video and the second video, and determining the quality evaluation result of the super-resolution video according to the similarity. The embodiments of the present application realize the evaluation of the quality of the super-resolution video after super-resolution reconstruction, and timely discover the super-resolution video with low quality.

Description

Technical Field

[0001] The present application relates to the field of image and video processing technology. Specifically, the present application relates to a video quality evaluation method, device, electronic device and storage medium. Background Art

[0002] Super-resolution is to improve the resolution of the original image through hardware or software methods. The process of obtaining a high-resolution image through a series of low-resolution images is called super-resolution reconstruction. Single image super-resolution refers to the use of a low-resolution image to reconstruct its corresponding high-resolution image; correspondingly, video super-resolution uses multiple related low-resolution video frames to reconstruct their corresponding high-resolution video frames.

[0003] The prior art usually uses the structural similarity SSIM algorithm to evaluate the similarity of images. The SSIM algorithm has three important parameters: brightness, contrast, and structure. These three parameters are also the basis for people to subjectively judge whether two images are similar, that is, the SSIM algorithm is an algorithm that judges the similarity of images based on people's subjective perspective. The premise of using the SSIM algorithm is that the resolution of the images is consistent. In order to improve the clarity of images or videos, the prior art will perform super-resolution reconstruction on pictures or videos. The clarity of the super-resolution reconstructed pictures or videos will be improved, but the super-resolution reconstructed pictures or videos may be distorted, that is, the quality of the pictures or videos may change, and the quality of the super-resolution pictures or videos needs to be detected. However, the resolution of the super-resolution reconstructed pictures or videos is different from that of the initial pictures or videos. Pictures or videos with different resolutions cannot be compared for similarity through the SSIM algorithm, that is, the quality of the super-resolution video cannot be evaluated. Summary of the invention

[0004] In view of the shortcomings of the existing methods, the present application proposes a super-resolution video quality method, device, electronic device and storage medium to solve the technical problem that the existing technology cannot judge the quality of super-resolution video.

[0005] In a first aspect, an embodiment of the present application provides a video quality evaluation method, comprising:

[0006] Obtaining original video and super-resolution video; super-resolution video is a video obtained by super-resolution reconstruction of the original video;

[0007] Determine a preset resolution according to the resolution of the original video and the resolution of the super-resolution video;

[0008] adjusting the resolution of the original video to a preset resolution to obtain a first video, and / or;

[0009] adjusting the resolution of the super-resolution video to the resolution to obtain a second video;

[0010] The similarity between the first video and the second video is calculated, and the quality evaluation result of the super-resolution video is determined according to the similarity.

[0011] In a possible implementation, adjusting the resolution of the original video to a resolution to obtain the first video, and / or adjusting the resolution of the super-resolution video to a preset resolution to obtain the second video, includes:

[0012] When the preset resolution is equal to the resolution of the super-resolution video, determining a first scaling ratio for adjusting the resolution of the original video to the resolution of the super-resolution video according to the resolution of the original video and the resolution of the super-resolution video;

[0013] The original video is scaled according to a preset interpolation algorithm and a first scaling ratio to obtain a first video corresponding to the original video.

[0014] In a possible implementation, adjusting the resolution of the original video to a resolution to obtain the first video, and / or adjusting the resolution of the super-resolution video to a preset resolution to obtain the second video, includes:

[0015] When the preset resolution is equal to the resolution of the original video, determining a second scaling ratio for adjusting the resolution of the super-resolution video to the resolution of the original video according to the resolution of the original video and the resolution of the super-resolution video;

[0016] The super-resolution video is scaled according to a preset interpolation algorithm and a second scaling ratio to obtain a second video corresponding to the super-resolution video.

[0017] In a possible implementation, adjusting the resolution of the original video to a resolution to obtain the first video, and / or adjusting the resolution of the super-resolution video to a preset resolution to obtain the second video, includes:

[0018] When the preset resolution is not equal to the resolution of the original video and is not equal to the resolution of the super-resolution video, determining, according to the resolution of the original video and the resolution of the super-resolution video, a third scaling ratio for adjusting the resolution of the original video to the preset resolution and a fourth scaling ratio for adjusting the resolution of the super-resolution video to the preset resolution;

[0019] According to a preset interpolation algorithm and a third scaling ratio and a fourth scaling ratio, the original video and the super-resolution video are scaled respectively to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video.

[0020] In a possible implementation, the preset interpolation algorithm includes at least one or a combination of bicubic interpolation, biquadratic interpolation, and bilinear interpolation;

[0021] In a possible implementation, calculating the similarity between the first video and the second video includes:

[0022] The similarity between video frames of the same number of frames in the first video and the second video is determined, and the similarity between the first video and the second video is determined based on the similarities between all targeted video frames.

[0023] In a possible implementation, determining the similarity between video frames of the same number of frames in the first video and the second video includes:

[0024] Extracting video frames with the same number of frames from the first video and the second video respectively;

[0025] Decoding video frames of the same number of frames of the first video and the second video to obtain image data of the video frames; the image data includes at least one of a spectral three-value YUV and a spectral standard value RGB;

[0026] The similarity between video frames of the same frame number in the first video and the second video is calculated based on the image data of the video frames.

[0027] In a second aspect, an embodiment of the present application provides a video quality evaluation device, including:

[0028] The acquisition module is used to acquire the original video and the super-resolution video; the super-resolution video is the video obtained by super-resolution reconstruction of the original video;

[0029] A preset resolution determination module, used to determine the preset resolution according to the resolution of the original video and the resolution of the super-resolution video;

[0030] A first video and a second video obtaining module, configured to adjust the resolution of the original video to a preset resolution to obtain the first video, and / or to adjust the resolution of the super-resolution video to a resolution to obtain the second video;

[0031] The video similarity calculation module is used to calculate the similarity between the first video and the second video, and determine the quality evaluation result of the super-resolution video according to the similarity.

[0032] In a possible implementation, the first video and the second video obtaining module include:

[0033] A first scaling ratio determination submodule, configured to determine, when the preset resolution is equal to the resolution of the super-resolution video, a first scaling ratio for adjusting the resolution of the original video to the resolution of the super-resolution video according to the resolution of the original video and the resolution of the super-resolution video;

[0034] The first scaling submodule is used to scale the original video according to a preset interpolation algorithm and a first scaling ratio to obtain a first video corresponding to the original video.

[0035] In a possible implementation, the first video and the second video obtaining module include:

[0036] A second scaling ratio determination submodule, configured to determine, when the preset resolution is equal to the resolution of the original video, a second scaling ratio for adjusting the resolution of the super-resolution video to the resolution of the original video according to the resolution of the original video and the resolution of the super-resolution video;

[0037] The second scaling submodule is used to scale the super-resolution video according to a preset interpolation algorithm and a second scaling ratio to obtain a second video corresponding to the super-resolution video.

[0038] In a possible implementation, the first video and the second video obtaining module include:

[0039] A third scaling ratio and a fourth scaling ratio determination submodule, for determining, when the preset resolution is not equal to the resolution of the original video and not equal to the resolution of the super-resolution video, a third scaling ratio for adjusting the resolution of the original video to the preset resolution and a fourth scaling ratio for adjusting the resolution of the super-resolution video to the preset resolution according to the resolution of the original video and the resolution of the super-resolution video;

[0040] The third scaling submodule is used to scale the original video and the super-resolution video according to a preset interpolation algorithm and a third scaling ratio and a fourth scaling ratio, respectively, to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video.

[0041] In a possible implementation, the preset interpolation algorithm includes at least one or a combination of bicubic interpolation, biquadratic interpolation, and bilinear interpolation;

[0042] In a possible implementation, calculating the similarity between the first video and the second video includes:

[0043] The video similarity determination submodule is used to determine the similarity between video frames of the same number of frames in the first video and the second video, and determine the similarity between the first video and the second video based on the similarity between all targeted video frames.

[0044] In a possible implementation, the video similarity determination submodule includes:

[0045] A video frame extraction unit, used to extract video frames with the same number of frames from the first video and the second video respectively;

[0046] A decoding unit, used to decode the video frames of the same frame number of the first video and the second video to obtain image data of the video frames; the image data includes at least one of a spectral three-value YUV and a spectral standard RGB value;

[0047] The video frame similarity calculation unit is used to calculate the similarity between the video frames of the same number of frames in the first video and the second video based on the image data of the video frames.

[0048] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method provided in the first aspect are implemented.

[0049] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect.

[0050] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. When a processor of a computer device reads the computer instructions from the computer-readable storage medium, the processor executes the computer instructions, so that the computer device executes the steps of implementing the method provided in the first aspect.

[0051] The beneficial technical effects brought about by the technical solution provided by the embodiment of the present application include: the embodiment of the present application obtains an original video and a super-resolution video; the super-resolution video is a video obtained after super-resolution reconstruction of the original video; the resolution of the original video and / or the super-resolution video is adjusted to the same resolution to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video; the similarity between the first video and the second video is calculated, and the quality evaluation result of the super-resolution video is determined according to the similarity, thereby evaluating the quality of the super-resolution video after super-resolution reconstruction and timely discovering the super-resolution video with low quality.

[0052] Additional aspects and advantages of the present application will be partially given in the following description, which will become apparent from the following description, or will be understood through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0054] Figure 1 A schematic diagram of comparing the similarity of two images provided in an embodiment of the present application;

[0055] Figure 2 A schematic diagram of a video quality evaluation method provided in an embodiment of the present application;

[0056] Figure 3It exemplarily shows a flow chart of determining the similarity between video frames of the same reality in a first video and a second video;

[0057] Figure 4 A flowchart of another video quality evaluation method provided in an embodiment of the present application;

[0058] Figure 5 A schematic diagram of the structure of a video quality assessment device provided in an embodiment of the present application;

[0059] Figure 6 A schematic diagram of the structure of an electronic device for video quality evaluation provided in an embodiment of the present application. DETAILED DESCRIPTION

[0060] The present application is described in detail below, and examples of embodiments of the present application are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar components or components with the same or similar functions. In addition, if the detailed description of the known technology is unnecessary for the features of the present application shown, it will be omitted. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0061] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0062] Those skilled in the art will appreciate that, unless expressly stated otherwise, the singular forms "a", "an", "" and "the" used herein may also include the plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other elements, or there may be intermediate elements. In addition, "connected" or "coupled" as used herein may include wireless connections or wireless couplings. The term "and / or" as used herein includes all or any unit and all combinations of one or more associated listed items.

[0063] First, several terms involved in this application are introduced and explained:

[0064] Structural Similarity (SSIM) is an indicator to measure the similarity between two images. It is used to measure the similarity of images and can also be used to judge the quality of compressed images. SSIM uses two images, one is an uncompressed image without distortion, and the other is a distorted image.

[0065] like Figure 1 As shown, it exemplarily shows a schematic diagram of similarity comparison between two images, where x is the original image without distortion, y is the distorted image after processing, the resolution of image x and image y is the same, and brightness, contrast and structure are three important parameters when SSIM calculates similarity. These three parameters are also the basis for people to subjectively judge whether two images are similar, that is, to measure the brightness and contrast of image x and image y, and then compare the brightness, contrast and structure of image x and image y to finally obtain the similarity.

[0066] The SSIM algorithm is used for similarity calculation. The formula corresponding to the SSIM algorithm is as follows:

[0067] SSIM(x,y)=[l(x,y)] α c[(x,y)] β s[(x,y)] γ (1)

[0068]

[0069]

[0070]

[0071] Where l(x,y) compares the brightness of x and y, c(x,y) compares the contrast of x and y, s(x,y) compares the structure of x and y, α>0, β>0 and γ>0 are parameters for adjusting the relative importance of l(x,y), c(x,y) and s(x,y), and μ x and μ y , δ x and δ y are the mean and standard deviation of x and y respectively, δ xy is the covariance of x and y, C1, C2 and C3 are all constants, which are used to maintain the stability of l(x,y), c(x,y) and s(x,y). The larger the value of the structural similarity index, the higher the similarity between the two images.

[0072] If two identical images are used to perform SSIM similarity calculation, then μ x =μ y , δ x =δ y, then SSIM = 1, and the parameters are set to α = β = γ = 1, and C3 = C2 / 2 to simplify, we get

[0073]

[0074] Usually C1=(K1*L)^2, C2=(K2*L)^2, C3=C2 / 2, generally K1=0.01, K2=0.03, L is the grayscale level of the image (for 8-bit grayscale image, L=255).

[0075] Super-resolution (SR) is to improve the resolution of the original image through hardware or software methods. The process of obtaining a high-resolution image through a series of low-resolution images is super-resolution reconstruction. Single image super-resolution refers to the use of a low-resolution image to reconstruct its corresponding high-resolution image; Correspondingly, video super-resolution is the use of multiple related low-resolution video frames to reconstruct their corresponding high-resolution video frames. In a large number of electronic image application fields, people often expect to obtain high-resolution (HR) images. High resolution means that the pixel density in the image is high and can provide more details, which are indispensable in many practical applications. For example, high-resolution medical images are very helpful for doctors to make correct diagnoses; using high-resolution satellite images, it is easy to distinguish similar objects from similar objects; if high-resolution images can be provided, the performance of pattern recognition in computer vision will be greatly improved.

[0076] Downsampling means decimation. For a sample value sequence, sampling is performed once every few sample values. The new sequence obtained in this way is the downsampling of the original sequence. When processing an image, downsampling will reduce the resolution of the image.

[0077] Upsampling is the reverse process of downsampling, also known as upsampling or interpolating.

[0078] YUV, spectral standard value, "Y" represents brightness (Luminance or Luma), which is the grayscale value, and "U" and "V" represent chrominance (Chrominance or Chroma), which is used to describe the color and saturation of the image and is used to specify the color of the pixel.

[0079] RGB means the three primary colors of red, green and blue, R=Red, G=Green, B=Blue.

[0080] The inventor of the present application conducted research and found that the prior art usually uses the structural similarity SSIM algorithm to evaluate the similarity of images. The SSIM algorithm has three important parameters: brightness, contrast and structure. These three parameters are also the basis for people to subjectively judge whether two images are similar, that is, the SSIM algorithm is an algorithm for judging the similarity of images based on people's subjective perspective. The premise of using the SSIM algorithm is that the resolution of the image is consistent. In order to improve the clarity of the image or video, the prior art will perform super-resolution reconstruction on the picture or video. The clarity of the super-resolution reconstructed picture or video will be improved, but the quality of the super-resolution reconstructed picture or video may change, and the quality of the super-resolution picture or video needs to be detected. The prior art uses the SSIM algorithm to detect the similarity of two pictures or videos, but the resolution of the super-resolution reconstructed picture or video is different from that of the initial picture or video. Pictures or videos with different resolutions cannot be compared for similarity through the SSIM algorithm, so it is impossible to judge the similarity between the super-resolution reconstructed picture or video and the original picture or video, and it is impossible to judge the quality of the super-resolution reconstructed picture or video.

[0081] The video quality evaluation method, device, electronic device and storage medium provided in this application are intended to solve the above technical problems in the prior art.

[0082] The technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems are described in detail below with specific embodiments.

[0083] The present application embodiment provides a video quality evaluation method, such as Figure 1 As shown, it exemplarily shows a flow chart of a video quality evaluation method provided in an embodiment of the present application, the method comprising:

[0084] Step S201, obtaining the original video and the super-resolution video;

[0085] Among them, the super-resolution video is the video obtained by super-resolution reconstruction of the original video;

[0086] In the embodiment of the present application, the original video refers to an undistorted, unprocessed video, and the super-resolution video refers to a video obtained by super-resolution reconstruction of the original video. Super-resolution reconstruction of the original video is actually a process of upsampling the original video. The resolution of the super-resolution video obtained after the super-resolution reconstruction of the original video is higher than the original video. Therefore, the clarity of the super-resolution video is higher than that of the original video.

[0087] It should be emphasized that although the clarity of the super-resolution video is higher than that of the original video, the super-resolution video is a distorted video. After super-resolution reconstruction, the original video becomes a distorted video, that is, the video quality of the super-resolution video may change, and there is a difference in quality from the original video.

[0088] Specifically, for example, if the resolution of the original video is 500×500, the resolution of the super-resolution video obtained after super-resolution reconstruction is 750×750. The resolution of 500×500 means that the number of horizontal pixels is 500 and the number of vertical pixels is 500. The higher the resolution, the more pixels there are, and the more precise the sensed image is. When the screen size is the same, the higher the resolution, the finer and more delicate the display effect will be.

[0089] Step S202: determining a preset resolution according to the resolution of the original video and the resolution of the super-resolution video.

[0090] Image resolution refers to the ability of a measurement or display system to distinguish details. It can be used for measurements in the fields of time, space, etc. In daily language, resolution is often used to refer to the clarity of an image. The higher the resolution, the better the image quality and the more details it can show. However, in contrast, the more information is recorded, the larger the file will be.

[0091] Since the points, lines and surfaces on the screen are composed of pixels, the more pixels the monitor can display, the finer the picture, and the more information can be displayed in the same screen area, so resolution is one of the very important performance indicators. The entire image can be imagined as a large chessboard, and the resolution is expressed as the number of intersections of all longitude and latitude lines. Display resolution is the number of pixels displayed on the screen. A resolution of 160×128 means 160 horizontal pixels and 128 vertical pixels. The higher the resolution, the more pixels there are, and the more precise the image sensed. When the screen size is the same, the higher the resolution, the finer and more delicate the display effect.

[0092] In the embodiment of the present application, the resolutions of the original video and the super-resolution video are not equal. However, the premise for similarity comparison is that the resolutions of the two images or videos are the same. If the similarities of the two images or videos for similarity comparison are different, the similarity comparison cannot be performed. Therefore, it is necessary to determine the preset resolution and adjust the resolution of the original video and the resolution of the super-resolution video to the preset resolution.

[0093] Step S203: adjusting the resolution of the original video to a preset resolution to obtain a first video, and / or adjusting the resolution of the super-resolution video to a preset resolution to obtain a second video.

[0094] The embodiment of the present application can adjust the resolution of at least one of the original video and the super-resolution video so that the two are at the same resolution, that is, adjust the two to a preset resolution. After adjusting the resolution, a first video corresponding to the original video and a second video corresponding to the super-resolution video are obtained.

[0095] It is worth noting that adjusting the original video and the super-resolution video to the preset resolution should not change the quality of the video, or the change is very small, that is, adjusting the original video and the super-resolution video to the same resolution does not cause the original video or the super-resolution video to be distorted again, or the distortion is very small and can be ignored.

[0096] Step S204, calculating the similarity between the first video and the second video, and determining a quality evaluation result of the super-resolution video according to the similarity.

[0097] The quality evaluation result of the embodiment of the present application is determined based on the similarity between the first video and the second video. If the similarity value is larger, it indicates that the super-resolution video is more similar to the original video, and the corresponding quality evaluation result of the super-resolution video is that the super-resolution video quality is high.

[0098] Similarly, if the similarity value is smaller, it means that the super-resolution video and the original video are less similar, there is a large difference between the super-resolution video and the original video, and the corresponding super-resolution video quality evaluation result is that the super-resolution video quality is low.

[0099] The embodiments of the present application do not limit how to divide the quality evaluation results of the super-resolution video into levels and grades. For example, it can be divided into ultra-high, high, medium, low and ultra-low levels, or it can be divided into level 1, level 2, level 3...9 levels. The higher the level, the higher the quality of the super-resolution video.

[0100] In the embodiment of the present application, after adjusting the resolution of the original video and / or the super-resolution video to the same resolution, a first video corresponding to the original video and a second video corresponding to the super-resolution video are obtained. The resolutions of the first video and the second video are consistent, and the similarity between the two can be calculated. If the value of the similarity between the two is larger, it indicates that the quality of the super-resolution video is higher.

[0101] The embodiment of the present application obtains an original video and a super-resolution video; the super-resolution video is a video obtained by super-resolution reconstruction of the original video; a preset resolution is determined according to the resolution of the original video and the resolution of the super-resolution video; the resolution of the original video is adjusted to the preset resolution to obtain a first video, and / or; the resolution of the super-resolution video is adjusted to the preset resolution to obtain a second video; the similarity between the first video and the second video is calculated, and a quality evaluation result of the super-resolution video is determined according to the similarity, so as to evaluate the quality of the super-resolution video after super-resolution reconstruction and timely discover the super-resolution video with low quality.

[0102] The embodiment of the present application provides a possible implementation method, which adjusts the resolution of the original video to a resolution to obtain a first video, and / or adjusts the resolution of the super-resolution video to a preset resolution to obtain a second video, including:

[0103] When the preset resolution is equal to the resolution of the super-resolution video, a first scaling ratio for adjusting the resolution of the original video to the resolution of the super-resolution video is determined according to the resolution of the original video and the resolution of the super-resolution video.

[0104] The preset resolution in the embodiment of the present application can be any resolution. When the preset resolution is equal to the resolution of the super-resolution video, there is no need to adjust the resolution of the super-resolution video. The second video is the super-resolution video. It is only necessary to adjust the resolution of the original video to the preset resolution.

[0105] In the embodiment of the present application, the resolution of the super-resolution video is higher than the resolution of the original video. When the preset resolution is equal to the resolution of the super-resolution video, there is no need to adjust it to be equal to the resolution of the super-resolution video. It is only necessary to increase the resolution of the original video to the resolution of the super-resolution video. According to the resolution of the original video and the resolution of the super-resolution video, a first scaling ratio for adjusting the resolution of the original video to the resolution of the super-resolution video is determined, and the first scaling ratio = resolution of the super-resolution video / resolution of the original video.

[0106] Specifically, for example, if the resolution of the existing original video is 500×500 and the resolution of the super-resolution video is 750×750, the first scaling ratio can be calculated as follows: resolution of the super-resolution video / resolution of the original video=1.5.

[0107] The original video is scaled according to a preset interpolation algorithm and a first scaling ratio to obtain a first video corresponding to the original video.

[0108] The embodiment of the present application can achieve video scaling through a preset interpolation algorithm. When scaling the video, the preset interpolation algorithm can increase or decrease the resolution of the video without causing video distortion, that is, the preset interpolation algorithm does not change the quality of the video. The preset interpolation algorithm includes but is not limited to: bicubic interpolation, biquadratic interpolation, and bilinear interpolation.

[0109] The embodiment of the present application scales the original video using a preset interpolation algorithm and a first scaling ratio to obtain a first video corresponding to the original video. At this time, the resolution of the first video is equal to the resolution of the super-resolution video.

[0110] Specifically, continuing with the above example, the original video is scaled according to a preset interpolation algorithm and a first scaling ratio, and the first scaling ratio is 1.5. The preset interpolation algorithm can be used to increase the resolution of the original video to 1.5 times the resolution of the original video to obtain the first video corresponding to the original video. At this time, the second video is a super-resolution video.

[0111] In fact, the process of improving the resolution of the original video through a preset interpolation algorithm is the process of upsampling the original video. The resolution of the original video is improved by upsampling. The embodiment of the present application does not limit other methods of improving the resolution of the original video.

[0112] The embodiment of the present application provides a possible implementation method, which adjusts the resolution of the original video to a resolution to obtain a first video, and / or adjusts the resolution of the super-resolution video to a preset resolution to obtain a second video, including:

[0113] When the preset resolution is equal to the resolution of the original video, a second scaling ratio for adjusting the resolution of the super-resolution video to the resolution of the original video is determined according to the resolution of the original video and the resolution of the super-resolution video.

[0114] In the embodiment of the present application, the resolution of the original video is lower than the resolution of the super-resolution video. When the preset resolution is equal to the resolution of the original video, there is no need to adjust the original video. It is only necessary to reduce the resolution of the super-resolution video to the resolution of the original video. According to the resolution of the original video and the resolution of the super-resolution video, a second scaling ratio is determined for adjusting the resolution of the super-resolution video to the resolution of the original video. The second scaling ratio = resolution of the original video / resolution of the super-resolution video.

[0115] Specifically, for example, if the resolution of the existing original video is 500×500 and the resolution of the super-resolution video is 750×750, the second scaling ratio can be calculated as follows: resolution of the original video / resolution of the super-resolution video=2 / 3.

[0116] The super-resolution video is scaled according to a preset interpolation algorithm and a second scaling ratio to obtain a second video corresponding to the super-resolution video.

[0117] In addition to improving the resolution of the original video through a preset interpolation algorithm, the embodiments of the present application can also reduce the resolution of the super-resolution video by shrinking the super-resolution video through a preset interpolation algorithm, and reduce the resolution of the super-resolution video to the resolution of the original video, so that the two have the same resolution.

[0118] The super-resolution video is scaled according to a preset interpolation algorithm and a second scaling ratio, so that a resolution of the scaled super-resolution video is the same as a resolution of the original video.

[0119] Specifically, continuing with the above example, the super-resolution video is scaled according to a preset interpolation algorithm and a second scaling ratio, and the second scaling ratio is 2 / 3. The preset interpolation algorithm can be used to reduce the resolution of the super-resolution video to 2 / 3 times of the original resolution to obtain the second video corresponding to the super-resolution video. At this time, the first video is the original video.

[0120] In fact, reducing the resolution of the super-resolution video by using a preset interpolation algorithm is the process of downsampling the super-resolution video. The resolution of the super-resolution video is reduced by downsampling. The embodiments of the present application do not limit other methods of reducing the resolution of the super-resolution video.

[0121] The embodiment of the present application provides a possible implementation method, which adjusts the resolution of the original video to a resolution to obtain a first video, and / or adjusts the resolution of the super-resolution video to a preset resolution to obtain a second video, including:

[0122] When the preset resolution is not equal to the resolution of the original video and is not equal to the resolution of the super-resolution video, a third scaling ratio for adjusting the resolution of the original video to the preset resolution and a fourth scaling ratio for adjusting the resolution of the super-resolution video to the preset resolution are determined based on the resolution of the original video and the resolution of the super-resolution video.

[0123] In an embodiment of the present application, when the preset resolution is equal to the resolution of the original video or equal to the resolution of the super-resolution video, it is only necessary to scale one of the original video or the super-resolution video, and there is no need to scale the other video; when the preset resolution is the resolution of the super-resolution video, it is only necessary to adjust the resolution of the original video to the resolution of the super-resolution video to obtain a first video corresponding to the original video, without scaling the super-resolution video, and the second video at this time is the super-resolution video; when the preset resolution is the resolution of the original video, it is only necessary to adjust the resolution of the super-resolution video to the resolution of the original video to obtain a second video corresponding to the super-resolution video, without scaling the original video, and the first video at this time is the original video.

[0124] In addition, when the preset resolution is not equal to the resolution of the original video and is not equal to the resolution of the super-resolution video, it is necessary to adjust the resolution of the original video and the resolution of the super-resolution video at the same time to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video.

[0125] If the preset resolution is greater than the resolution of the original video and smaller than the resolution of the super-resolution video, then the resolution of the original video needs to be increased and the resolution of the super-resolution video needs to be reduced; if the preset resolution is smaller than the resolution of the original video, then both the resolution of the original video and the resolution of the super-resolution video need to be reduced; if the preset resolution is greater than the resolution of the super-resolution video, then both the resolution of the super-resolution video and the resolution of the original video need to be increased.

[0126] According to the resolution of the original video and the preset resolution, a third scaling ratio is determined for adjusting the resolution of the original video to the preset resolution, where the third scaling ratio=preset resolution / resolution of the original video.

[0127] According to the resolution of the super-resolution video and the preset resolution, a fourth scaling ratio for adjusting the resolution of the super-resolution video to the preset resolution is determined, where the fourth scaling ratio=preset resolution / resolution of the super-resolution video.

[0128] Specifically, if the resolution of the existing original video is 500×500, the resolution of the super-resolution video is 750×750, and if the preset resolution is 600×600, the third scaling ratio corresponding to the original video = 6 / 5, and the original video is scaled by the preset interpolation algorithm and the third scaling ratio to increase the resolution of the original video to the preset resolution, and the fourth scaling ratio corresponding to the super-resolution video = 3 / 4, and the super-resolution video is scaled by the preset interpolation algorithm and the fourth scaling ratio to reduce the resolution of the super-resolution video to the preset resolution.

[0129] According to a preset interpolation algorithm and a third scaling ratio and a fourth scaling ratio, the original video and the super-resolution video are scaled respectively to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video.

[0130] An embodiment of the present application provides a possible implementation method, and the preset interpolation algorithm includes at least one or a combination of bicubic interpolation, biquadratic interpolation and bilinear interpolation.

[0131] The preset interpolation methods in the embodiments of the present application include but are not limited to bicubic interpolation, biquadratic interpolation and bilinear interpolation. Any interpolation method that can reduce the resolution of the super-resolution video while ensuring that the video quality is not changed is within the protection scope of the embodiments of the present application.

[0132] The embodiment of the present application scales the original video or the super-resolution video through a preset interpolation algorithm, thereby adjusting the resolution of the original video and the resolution of the super-resolution video to a unified resolution, so that the two can be compared for similarity.

[0133] The present application embodiment provides a possible implementation method for calculating the similarity between a first video and a second video, including:

[0134] The similarity between video frames of the same number of frames in the first video and the second video is determined, and the similarity between the first video and the second video is determined based on the similarities between all targeted video frames.

[0135] In the embodiment of the present application, the first video is a video obtained by adjusting the resolution of the original video, and the second video is a video obtained by adjusting the resolution of the super-resolution video. The resolution of the first video is the same as that of the second video. To calculate the similarity between the first video and the second video, video frames of the same number of frames of the first video and the second video can be distinguishably extracted, the video frames are decoded to obtain YUV and RGB of the video frames, the YUV or RGB is introduced into the SSIM algorithm formula, the similarity between the video frames of the same number of frames is calculated, and then the similarities of all video frames are weighted averaged to obtain the similarity between the first video and the second video. The similarity between the first video and the second video is the similarity between the super-resolution video and the original video.

[0136] The present application embodiment provides a possible implementation method, such as Figure 3 As shown, it exemplarily shows a flow chart of determining the similarity between video frames of the same frame number in the first video and the second video, and determining the similarity between video frames of the same frame number in the first video and the second video includes:

[0137] Step S301 , extracting video frames with the same number of frames from the first video and the second video respectively.

[0138] In the embodiment of the present application, the similarity between the first video and the second video is determined based on the similarity between video frames with the same frame number in the first video and the second video. Therefore, to calculate the similarity between the first video and the second video, it is necessary to first distinguish and extract the same real video frames of the first video and the second video from the first video and the second video.

[0139] Step S302, decoding video frames of the same frame number of the first video and the second video to obtain image data of the video frames; the image data includes at least one of spectral three-value YUV and spectral standard value RGB.

[0140] After extracting video frames with the same frame number of the first video and the second video, the embodiment of the present application decodes the video frames with the same frame number of the first video and the second video, and obtains image data of the video frames after decoding, wherein the image data includes at least one of spectral three-value YUV and spectral standard value RGB.

[0141] YUV and RGB have the same role and are used to obtain the brightness, contrast and structure of video frames.

[0142] The YUV and RGB obtained by decoding the video frame are used for subsequent similarity calculation. YUV and RGB include three parameters: brightness, contrast and structure. Substituting these three parameters into the SSIM algorithm formula can calculate the similarity of video frames with the same frame number.

[0143] Step S303: Calculate the similarity between video frames of the same number of frames in the first video and the second video based on the image data of the video frames.

[0144] After decoding the video frames, the embodiment of the present application obtains the image data of the video frames, that is, the brightness, contrast and structure of each video frame are obtained, and the brightness, contrast and structure of the video frames with the same frame number of the first video and the second video are substituted into the above formulas (1), (2), (3) and (4) to calculate the similarity S(i) between the video frames with the same frame number, where i is the number of the video frame and is a positive integer.

[0145] By performing weighted averaging on the similarities of all the same video frames, the similarity S between the first video and the second video is obtained, that is, the similarity between the super-resolution video and the original video, S = 1 / N*∑S(i), where N is the number of video frames that need to be evaluated by the SSIM algorithm, and i is the number of video frames.

[0146] The embodiment of the present application determines the similarity between video frames of the same number of frames in the first video and the second video, and determines the similarity between the first video and the second video based on the similarities between all targeted video frames, thereby reducing the error in the determined similarity between the first video and the second video.

[0147] like Figure 4 As shown, it exemplarily shows a process diagram of a video quality evaluation method, such as Figure 4 As shown, the whole process includes: step S401, obtaining the original video and the super-resolution video, the super-resolution video is the video obtained after the super-resolution reconstruction of the original video; step S402 determines the preset resolution according to the resolution of the original video and the resolution of the super-resolution video; step S403, adjusting the resolution of the original video to the preset resolution to obtain the first video, and / or; adjusting the resolution of the super-resolution video to the resolution to obtain the second video; step S404, decoding the first video to obtain each video frame corresponding to the first video; step S404', decoding the second video to obtain each video frame corresponding to the second video; step S405, calculating the similarity between video frames of the same frame number; step S406, performing weighted average processing on the similarity between all video frames to obtain the average similarity, and determining the average similarity as the similarity between the first video and the second video.

[0148] Based on the same inventive concept, the embodiment of the present application provides a video quality evaluation device 50, the structural framework diagram of the device is as follows: Figure 5 As shown, including:

[0149] The acquisition module 501 is used to acquire the original video and the super-resolution video; the super-resolution video is the video obtained by super-resolution reconstruction of the original video;

[0150] A preset resolution determination module 502, used to determine a preset resolution according to the resolution of the original video and the resolution of the super-resolution video;

[0151] The first video and second video obtaining module 503 is used to adjust the resolution of the original video to a preset resolution to obtain the first video, and / or to adjust the resolution of the super-resolution video to a resolution to obtain the second video;

[0152] The video similarity calculation module 504 is used to calculate the similarity between the first video and the second video, and determine the quality evaluation result of the super-resolution video according to the similarity.

[0153] The embodiment of the present application provides a possible implementation method. In a possible implementation method, the first video and the second video obtaining module include:

[0154] A first scaling ratio determination submodule, configured to determine, when the preset resolution is equal to the resolution of the super-resolution video, a first scaling ratio for adjusting the resolution of the original video to the resolution of the super-resolution video according to the resolution of the original video and the resolution of the super-resolution video;

[0155] The first scaling submodule is used to scale the original video according to a preset interpolation algorithm and a first scaling ratio to obtain a first video corresponding to the original video.

[0156] The embodiment of the present application provides a possible implementation method, wherein the first video and the second video obtaining module include:

[0157] A second scaling ratio determination submodule, configured to determine, when the preset resolution is equal to the resolution of the original video, a second scaling ratio for adjusting the resolution of the super-resolution video to the resolution of the original video according to the resolution of the original video and the resolution of the super-resolution video;

[0158] The second scaling submodule is used to scale the super-resolution video according to a preset interpolation algorithm and a second scaling ratio to obtain a second video corresponding to the super-resolution video.

[0159] The embodiment of the present application provides a possible implementation method, wherein the first video and the second video obtaining module include:

[0160] A third scaling ratio and a fourth scaling ratio determination submodule, for determining, when the preset resolution is not equal to the resolution of the original video and not equal to the resolution of the super-resolution video, a third scaling ratio for adjusting the resolution of the original video to the preset resolution and a fourth scaling ratio for adjusting the resolution of the super-resolution video to the preset resolution according to the resolution of the original video and the resolution of the super-resolution video;

[0161] The third scaling submodule is used to scale the original video and the super-resolution video according to a preset interpolation algorithm and a third scaling ratio and a fourth scaling ratio, respectively, to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video.

[0162] The embodiment of the present application provides a possible implementation method, wherein the preset interpolation algorithm includes at least one or a combination of bicubic interpolation, biquadratic interpolation and bilinear interpolation;

[0163] The present application embodiment provides a possible implementation method for calculating the similarity between a first video and a second video, including:

[0164] The video similarity determination submodule is used to determine the similarity between video frames of the same number of frames in the first video and the second video, and determine the similarity between the first video and the second video based on the similarity between all targeted video frames.

[0165] The embodiment of the present application provides a possible implementation method, the video similarity determination submodule includes:

[0166] A video frame extraction unit, used to extract video frames with the same number of frames from the first video and the second video respectively;

[0167] A decoding unit, used to decode the video frames of the same frame number of the first video and the second video to obtain image data of the video frames; the image data includes at least one of a spectral three-value YUV and a spectral standard RGB value;

[0168] The video frame similarity calculation unit is used to calculate the similarity between the video frames of the same number of frames in the first video and the second video based on the image data of the video frames.

[0169] The video quality assessment device of this embodiment can execute any video quality assessment method provided in the embodiments of the present application, and the implementation principles are similar and will not be repeated here.

[0170] Based on the same inventive concept, an embodiment of the present application provides an electronic device, which includes: a memory and a processor.

[0171] The memory is communicatively connected to the processor.

[0172] At least one computer program is stored in the memory and is used to implement various optional implementations of any video quality assessment method provided in the embodiments of the present application when executed by the processor.

[0173] Those skilled in the art will appreciate that the electronic equipment provided by the embodiments of the present application can be specially designed and manufactured for the desired purpose, or can also include known devices in a general-purpose computer. These devices have computer programs stored therein, which are selectively activated or reconstructed. Such computer programs can be stored in a device (e.g., computer) readable medium or in a medium suitable for storing electronic instructions and coupled to any type of bus respectively.

[0174] Compared with the prior art, the present invention can achieve the following: by acquiring an original video and a super-resolution video; the super-resolution video is a video obtained by super-resolution reconstruction of the original video; determining a preset resolution according to the resolution of the original video and the resolution of the super-resolution video; adjusting the resolution of the original video to the preset resolution to obtain a first video, and / or; adjusting the resolution of the super-resolution video to the preset resolution to obtain a second video; calculating the similarity between the first video and the second video, and determining a quality evaluation result of the super-resolution video according to the similarity, thereby evaluating the quality of the super-resolution video after super-resolution reconstruction and timely discovering super-resolution videos with low quality.

[0175] Figure 6 It is a block diagram of an exemplary electronic device 600 according to an embodiment of the present application. Figure 6 The electronic device 500 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0176] like Figure 6 As shown, the present application provides an electronic device 600 in an optional embodiment. The electronic device 600 can be in the form of a general-purpose computing device. The components of the electronic device 600 may include but are not limited to: one or more processors 601, a storage system 602, and a bus 603 connecting different system components (including the storage system 602 and the processor 601).

[0177] Bus 603 represents one or more of a variety of bus structures, including, for example, but not limited to, Industrial Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0178] The electronic device 600 typically includes a variety of computer system readable media, which can be any available media that can be accessed by the electronic device 600, including volatile media and non-volatile media, removable media or non-removable media.

[0179] The storage system 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 6021 and / or cache memory 6022. The electronic device 600 may further include other removable / non-removable, volatile / non-volatile computer system storage media (such as Figure 6 By way of example only, the storage system may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, and is often referred to as a "hard drive"). Although Figure 6 Although not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a floppy disk) and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 603 via one or more data medium interfaces. The storage system 602 may include at least one program product, wherein the program product has at least one program module 6024 configured to perform multiple functions of various embodiments of the present application.

[0180] A program / utility 6025 having at least one program module 6024 may be stored, for example, in the storage system 602, such program modules 6024 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, and each or some combination of these examples may include an implementation of a network environment. The program modules 6024 generally perform the functions and / or methods of the embodiments described herein.

[0181] The electronic device 600 may also communicate with a display 610 and one or more other external devices 620 (e.g., a keyboard, a pointing device, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 600 and / or any device that enables the computer system 20 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed through an input / output (I / O) interface 604. In addition, the electronic device 600 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network (e.g., the Internet)) through a network adapter 605. Figure 6 As shown in FIG. 6 , the network adapter 605 can communicate with other modules of the electronic device 600 via the bus 603. It should be understood that although Figure 6 Not shown, but other hardware and / or software modules may be used in conjunction with the computer system, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0182] It should be noted that Figure 6 The schematic diagram of the computing system that can be used to implement various embodiments of the present application is only schematically shown. Those skilled in the art can understand that the electronic device 600 can be implemented by introducing additional computing devices.

[0183] The embodiment of the present application provides a computer-readable storage medium, which, compared with the prior art, obtains an original video and a super-resolution video; the super-resolution video is a video obtained after super-resolution reconstruction of the original video; a preset resolution is determined according to the resolution of the original video and the resolution of the super-resolution video; the resolution of the original video is adjusted to the preset resolution to obtain a first video, and / or; the resolution of the super-resolution video is adjusted to the preset resolution to obtain a second video; the similarity between the first video and the second video is calculated, and a quality evaluation result of the super-resolution video is determined according to the similarity, thereby evaluating the quality of the super-resolution video after super-resolution reconstruction and timely discovering the super-resolution video with low quality.

[0184] The present application embodiment provides a computer-readable storage medium applicable to various optional implementations of any of the above-mentioned video quality evaluation methods, which will not be described in detail here.

[0185] By applying the embodiments of the present application, at least the following beneficial effects can be achieved: an original video and a super-resolution video are obtained; the super-resolution video is a video obtained by super-resolution reconstruction of the original video; a preset resolution is determined according to the resolution of the original video and the resolution of the super-resolution video; the resolution of the original video is adjusted to the preset resolution to obtain a first video, and / or; the resolution of the super-resolution video is adjusted to the preset resolution to obtain a second video; the similarity between the first video and the second video is calculated, and a quality evaluation result of the super-resolution video is determined according to the similarity, so as to evaluate the quality of the super-resolution video after super-resolution reconstruction and timely discover the super-resolution video with low quality.

[0186] Those skilled in the art will appreciate that the various operations, methods, steps, measures, and schemes in the processes discussed in this application may be alternated, altered, combined, or deleted. Further, other steps, measures, and schemes in the various operations, methods, and processes discussed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted. Further, the steps, measures, and schemes in the prior art that are similar to those disclosed in this application may also be alternated, altered, rearranged, decomposed, combined, or deleted.

[0187] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0188] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0189] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0190] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0191] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0192] The above are only some implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A video quality evaluation method, characterized in that: include: Get the original video and super-resolution video; The super-resolution video is a video obtained by performing super-resolution reconstruction on the original video; Determining a preset resolution according to the resolution of the original video and the resolution of the super-resolution video; adjusting the resolution of the original video to the preset resolution to obtain a first video, and / or; Adjusting the resolution of the super-resolution video to the preset resolution to obtain a second video; Calculating the similarity between the first video and the second video, and determining a quality evaluation result of the super-resolution video according to the similarity; said adjusting the resolution of the original video to the preset resolution to obtain the first video, and / or; Adjusting the resolution of the super-resolution video to the preset resolution to obtain a second video includes: When the preset resolution is equal to the resolution of the super-resolution video, determining a first scaling ratio for adjusting the resolution of the original video to the resolution of the super-resolution video according to the resolution of the original video and the resolution of the super-resolution video; Scaling the original video according to a preset interpolation algorithm and the first scaling ratio to obtain a first video corresponding to the original video; The step of adjusting the resolution of the original video to the preset resolution to obtain the first video, and / or adjusting the resolution of the super-resolution video to the preset resolution to obtain the second video, comprises: When the preset resolution is equal to the resolution of the original video, determining a second scaling ratio for adjusting the resolution of the super-resolution video to the resolution of the original video according to the resolution of the original video and the resolution of the super-resolution video; The super-resolution video is scaled according to a preset interpolation algorithm and the second scaling ratio to obtain a second video corresponding to the super-resolution video.

2. The video quality evaluation method according to claim 1, characterized in that: said adjusting the resolution of the original video to the preset resolution to obtain the first video, and / or; Adjusting the resolution of the super-resolution video to the preset resolution to obtain a second video includes: When the preset resolution is not equal to the resolution of the original video and is not equal to the resolution of the super-resolution video, determining, according to the resolution of the original video and the resolution of the super-resolution video, a third scaling ratio for adjusting the resolution of the original video to the preset resolution and a fourth scaling ratio for adjusting the resolution of the super-resolution video to the preset resolution; According to a preset interpolation algorithm and the third scaling ratio and the fourth scaling ratio, the original video and the super-resolution video are scaled respectively to obtain a first video corresponding to the original video and a second video corresponding to the super-resolution video.

3. The video quality assessment method according to any one of claims 1 to 2, characterized in that: The preset interpolation algorithm includes at least one or a combination of bicubic interpolation, biquadratic interpolation and bilinear interpolation.

4. The video quality assessment method according to claim 1, characterized in that: The calculating the similarity between the first video and the second video includes: The similarity between video frames of the same number of frames in the first video and the second video is determined, and the similarity between the first video and the second video is determined based on the similarities between all targeted video frames.

5. The video quality evaluation method according to claim 4, characterized in that: Determining the similarity between video frames of the same number of frames in the first video and the second video includes: Extracting video frames with the same number of frames from the first video and the second video respectively; Decoding video frames of the same number of frames of the first video and the second video to obtain image data of the video frames; the image data includes at least one of a spectral three-value YUV and a spectral standard RGB value; The similarity between the video frames of the same frame number in the first video and the second video is calculated based on the image data of the video frames.

6. A video quality evaluation device using the video quality evaluation method according to any one of claims 1 to 5, characterized in that: include: An acquisition module is used to acquire original video and super-resolution video; The super-resolution video is a video obtained by performing super-resolution reconstruction on the original video; A preset resolution determination module, used to determine a preset resolution according to the resolution of the original video and the resolution of the super-resolution video; A first video and a second video obtaining module, configured to adjust the resolution of the original video to the preset resolution to obtain the first video, and / or to adjust the resolution of the super-resolution video to the preset resolution to obtain the second video; The video similarity calculation module is used to calculate the similarity between the first video and the second video, and determine the quality evaluation result of the super-resolution video according to the similarity.

7. An electronic device, characterized in that: include: processor; A memory, communicatively connected to the processor; At least one program is stored in the memory and configured to be executed by the processor, wherein the at least one program is configured to: implement the video quality assessment method according to any one of claims 1 to 5.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer-readable storage medium is characterized in that when the computer program is executed by an electronic device, the video quality assessment method according to any one of claims 1 to 5 is implemented.

Images