Video processing method, device, equipment and computer storage medium

Abstract

Embodiments of the present invention relate to the field of multimedia playback technology and disclose a video processing method, comprising: determining discontinuous regions within consecutive video frames; the discontinuous regions being regions where image features of adjacent frames are discontinuous; determining feature information of the consecutive frames; generating multiple video frames based on the feature information; and enhancing the discontinuous regions based on the video frames to obtain processed videos. Through the above-described methods, embodiments of the present invention improve the video viewing experience.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of computer data processing, and in particular to a video processing method, apparatus, device, and computer storage medium. Background Art

[0002] Current videos generally focus on collecting and processing areas with medium light intensity.

[0003] During the process of implementing the embodiments of the present invention, the inventors of this application discovered that in existing video processing technologies, there are areas with drastic changes in luminosity, and image texture details are easily obscured by changes in luminosity, thereby causing visual discontinuity and affecting the user's viewing experience. Summary of the Invention

[0004] In view of the above problems, embodiments of the present invention provide a video processing method, apparatus, device, and computer for solving the problem of poor video viewing experience in the prior art.

[0005] According to one aspect of an embodiment of the present invention, a video processing method is provided, the method comprising:

[0006] Determining discontinuous regions within consecutive frames of a video; the discontinuous regions are regions where image features of adjacent frames are discontinuous;

[0007] determining feature information of the consecutive frames;

[0008] generating a plurality of video frames according to the feature information;

[0009] The discontinuous area is enhanced according to the video frame to obtain a processed video.

[0010] In an optional manner, the feature information includes frequency domain feature information; the video frame includes an approximate video frame; the approximate video frame is a video frame in which the frequency domain feature information in the front-back direction of the continuous frames satisfies a preset feature value range.

[0011] In an optional manner, the frequency domain feature information includes grayscale value gradient change information; and the method further includes:

[0012] Screening at least two comparison reference frames in the front-back direction of the continuous frames according to the grayscale value gradient change information and the characteristic value interval to obtain a frame to be approximated;

[0013] Approximation processing is performed on the frame to be approximated to obtain the approximate video frame.

[0014] In an optional manner, the video frame includes an overlay video frame; the overlay video frame is a key frame containing texture detail information of the continuous frames.

[0015] In an optional manner, the feature information includes frequency domain feature information; the discontinuous area includes a plurality of target area points; and the method further includes:

[0016] Determining at least one key frame corresponding to the target area point from adjacent areas of the target area point according to the frequency domain feature information;

[0017] generating a transparent image corresponding to the target area point according to the frequency domain feature information;

[0018] The transparent image is superimposed on the key frame of the target area point to obtain the superimposed video frame.

[0019] In an optional manner, the frequency domain feature information includes grayscale value gradient change information; the method includes:

[0020] Dividing the continuous frames into a high light area and a low light area according to the gray value gradient change information;

[0021] determining a detail component relationship between the highlight area and the low light area;

[0022] The transparent image is generated according to the detail component relationship and the endpoint output information of the highlight area and the low light area.

[0023] In an optional manner, the discontinuous region includes a plurality of target region points; the feature information includes frequency domain feature information; the video frame includes an approximate video frame and an overlay video frame; wherein the approximate video frame is a video frame in which a change in the frequency domain feature information in a front-to-back direction of the continuous frame meets a preset condition; the overlay video frame is a key frame containing texture detail information of the continuous frame; and the method further includes:

[0024] determining a best frame from the approximate video frame and the superimposed video frame;

[0025] The target area point is subjected to frame replacement or frame supplementation processing according to the optimal frame to obtain the processed video.

[0026] According to another aspect of an embodiment of the present invention, there is provided a video processing apparatus, comprising:

[0027] A first determining module is configured to determine a discontinuous region within consecutive frames of a video; the discontinuous region is a region where image features of adjacent frames are discontinuous;

[0028] A second determining module, configured to determine feature information of the consecutive frames;

[0029] A generating module, configured to generate a plurality of video frames according to the feature information;

[0030] The processing module is used to perform enhancement processing on the discontinuous area according to the video frame to obtain a processed video.

[0031] According to another aspect of an embodiment of the present invention, there is provided a video processing device, comprising: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus;

[0032] The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of any one of the embodiments of the video processing method.

[0033] According to another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores at least one executable instruction, and the executable instruction enables a video processing device to perform the operation of any one of the embodiments of the video processing method.

[0034] The embodiment of the present invention determines the discontinuous areas within the continuous frames of the video; the discontinuous areas are areas where the image features of adjacent frames are discontinuous, thereby locating the frame position where the viewing experience is not smooth. The feature information of the continuous frames is then determined; multiple video frames are generated based on the feature information; and finally, the discontinuous areas are enhanced based on the video frames to obtain a processed video. This is different from the existing technology that only focuses on enhancing the medium-luminosity area, resulting in an unsmooth video viewing experience in areas with large luminosity changes. The embodiment of the present invention can optimize the smoothness and fluidity of the video frame, ensure clear details, and improve the video viewing experience.

[0035] The above description is only an overview of the technical solutions of the embodiments of the present invention. In order to more clearly understand the technical means of the embodiments of the present invention, they can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiments of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are specifically listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] The accompanying drawings are only used to illustrate the embodiments and are not to be considered as limiting the present invention. In addition, the same reference symbols are used to represent the same components throughout the drawings. In the drawings:

[0037] Figure 1 A schematic diagram showing a flow chart of a video processing method provided by an embodiment of the present invention is shown;

[0038] Figure 2 A schematic flow chart of a video processing method provided by another embodiment of the present invention is shown;

[0039] Figure 3A schematic flow chart of a video processing method provided by another embodiment of the present invention is shown;

[0040] Figure 4 A schematic structural diagram of a video processing device provided by an embodiment of the present invention is shown;

[0041] Figure 5 A schematic structural diagram of a video processing device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0042] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention can be implemented in various forms and should not be limited to the embodiments set forth herein.

[0043] Figure 1 The flowchart of the video processing method provided by the embodiment of the present invention is shown, and the method is executed by a computer processing device. The computer processing device may include a mobile phone, a laptop computer, etc. Figure 1 As shown, the method includes the following steps:

[0044] Step 10: Determine discontinuous regions within continuous frames of the video; the discontinuous regions are regions where image features of adjacent frames are discontinuous.

[0045] In one embodiment of the present invention, the type of the video may be a movie, a stop-motion animation, a cartoon, a dynamic image, etc. Continuous frames refer to a plurality of image frames that are continuous in time sequence in the video.

[0046] Continuous frame acquisition can capture video images based on a set timeline length. For example, if you read a 2-minute short video and select continuous frames for the segment to be processed, assuming the timeline length is set to 4 seconds, for a video set with a frame rate of 30fps, 120 continuous frames can be captured within the 4-second timeline. Image features can include brightness, clarity, and other characteristics. Discontinuities in these features can lead to discontinuities in the video viewing experience, such as flickering brightness or specific areas of the screen being blurry and clear at times.

[0047] For example, the discontinuous area may be an area with a dramatic change in luminosity. The large change in luminosity masks the texture details of the image, thereby causing a discontinuous experience such as a blurred image.

[0048] Step 20: Determine feature information of the consecutive frames.

[0049] In one embodiment of the present invention, considering that in the usual time domain and space domain states, the image / video frame hides a lot of information, in the frequency domain state, it is easier to reveal the high-frequency and low-frequency areas distributed in the video frame, and it is also convenient to analyze the local details of the image.

[0050] Therefore, the feature information can be the frequency domain feature information after the frequency domain transformation of continuous frames, so as to better reflect the image detail characteristics of the continuous frames, facilitate the subsequent corresponding enhancement processing based on the feature information, and repair the blurred, overexposed, dark and other difficult-to-process images and videos, thereby improving the visual experience.

[0051] In yet another embodiment of the present invention, the frequency domain transform may be a Fourier transform.

[0052] The continuous frame images are subjected to Fourier transformation from the spatial domain to the frequency domain to obtain two-dimensional coordinate information. The transformation process is as follows:

[0053] Perform a two-dimensional discrete Fourier transform according to the following formula:

[0054]

[0055] Among them, the image size of continuous frames is set to M×N, that is, the total number of pixels is M×N; u is the frequency domain variable in the M direction, u=0,1,2,…,M-1; v is the frequency domain variable in the N direction, v=0,1,2,…,N-1; (x,y) is the spatial domain image variable; f(x,y) is the grayscale value of point (x,y).

[0056] The above formula is used to discretize continuous frame images into two-dimensional signals, which are then converted into gradient changes on two-dimensional coordinates using a two-dimensional Fourier transform. The two-dimensional coordinates are decomposed into two independent one-dimensional coordinate grayscale value changes. The grayscale value changes of the two one-dimensional coordinates are superimposed to obtain the gradient changes of the two-dimensional coordinates in the frequency domain. After the Fourier transform, the horizontal coordinate is the frequency of the separated sinusoidal signal, and the vertical coordinate corresponds to the weighted density, i.e., the amplitude value.

[0057] Step 30: Generate multiple video frames according to the feature information.

[0058] In one embodiment of the present invention, when processing discontinuous regions based on feature information, noise removal can be performed on the discontinuous regions to produce a clearer image. Furthermore, detail supplementation can be performed on the discontinuous regions, thereby making the image more continuous and including more of the previously discontinuous features. During detail supplementation, approximate video frames with less spectral variation than continuous frames can be used as supplementary frames.

[0059] Therefore, in one embodiment of the present invention, the video frame includes an approximate video frame; the approximate video frame is a video frame whose frequency domain feature information in the front-back direction of the continuous frames satisfies a preset feature value range.

[0060] The preset eigenvalue interval may be limited by an upper eigenvalue limit and a lower eigenvalue limit.

[0061] In one embodiment of the present invention, the frequency domain feature information includes grayscale value gradient change information; step 30 further includes:

[0062] Step 301: screening at least two comparison reference frames in the front-back direction of the continuous frames according to the grayscale value gradient change information and the characteristic value interval to obtain a frame to be approximated.

[0063] In one embodiment of the present invention, an upper threshold and a lower threshold of grayscale gradient change information may be set, and a comparison reference frame having a grayscale gradient change value between the upper threshold and the lower threshold is determined as a frame to be approximated.

[0064] Step 302: performing approximation processing on the frame to be approximated to obtain the approximate video frame.

[0065] In one embodiment of the present invention, the approximation process may include at least one of similarity transformation, changing RGB channels, and smoothness processing.

[0066] In one embodiment of the present invention, each frame to be approximated is analyzed separately to determine the area of ​​the target image and its position, a rectangular grid of a specified size with a preset value is segmented in the target image area, and a marker point is selected. The position of the marker point in the target image area can be determined by bilinear interpolation, and each preset rectangular grid is deformed using a similarity transformation matrix.

[0067] The formula for similarity transformation is as follows:

[0068]

[0069] The similarity transformation matrix is:

[0070]

[0071] Where (x′, y′) is the coordinate of the original image point;

[0072] (x i ,y i ) is the coordinate of the set mark point;

[0073] is the transformation matrix set, where a1=b2, a2=-b1;

[0074] (x, y are the target image coordinates to be set;

[0075] (w cx , w cy ) is the target image center.

[0076] In one embodiment of the present invention, the process of changing the RGB channels includes at least the following:

[0077] Each of the RGB channels (0-255) has 256 levels, and the three channels can produce a total of 16,777,216 colors. The reference frame is subjected to approximate color adjustment. Similarly, the target image area can be divided into rectangular grids of a specified size with a preset value. By separating the colors of the rectangular grid area according to the set pattern, a three-channel separated color combination is formed. Then, an approximate color is taken for each color in the color combination to generate multiple three-channel separated approximate colors. By combining and extracting the effective approximate colors, multiple approximate color combinations can be obtained to optimize the approximate video frame.

[0078] In one embodiment of the present invention, the smoothing process for the frame to be approximated may be performed by using methods such as mean filtering, box filtering, Gaussian filtering, median filtering, bilateral filtering, and 2D filtering.

[0079] Considering that the texture details in discontinuous areas will be masked by changes in luminosity, noise or other discontinuous image features, resulting in visual blur and inconsistency, it is necessary to supplement the texture details of the images in continuous frames.

[0080] Therefore, in yet another embodiment of the present invention, the video frame in step 30 includes an overlay video frame; the overlay video frame is a key frame containing texture detail information of the consecutive frames.

[0081] In another embodiment of the present invention, considering that the key frames include more image information, it is necessary to first capture and determine the key frames, and generate a transparent image containing the engraved texture details, and then superimpose the transparent image on the key frames of the target area points, thereby reducing the blurred areas in the continuous frames and removing noise.

[0082] Therefore, in another embodiment of the present invention, the characteristic information includes frequency domain characteristic information; the discontinuous area includes a plurality of target area points; step 30 further includes:

[0083] Step 303: Determine at least one key frame corresponding to the target area point from adjacent areas of the target area point according to the frequency domain feature information.

[0084] In one embodiment of the present invention, the key frame determination process can include performing gradient coding on the image of the adjacent region based on the grayscale gradient change information to obtain a feature vector corresponding to the adjacent region; determining the key frame from the adjacent region based on the feature vector, and selecting the key frame based on the grayscale gradient change amount and the gradient coding.

[0085] Among them, the gradient encoding is to take the local square block (2 n ×2 n ) / n takes an integer between 2 and 10, inclusive. The pixels are arranged in ascending and descending order. The clockwise direction can be set as the specified direction. One-dimensional feature vectors are extracted for the two-dimensional blocks. Z two-dimensional blocks correspond to Z one-dimensional feature vectors. The appropriate key frames are determined by the Z feature vectors.

[0086] Step 304: Generate a transparent image corresponding to the target area point according to the frequency domain feature information.

[0087] In one embodiment of the present invention, the frequency domain feature information includes grayscale value gradient change information; step 304 further includes:

[0088] Step 3041: Divide the continuous frames into a high-light area and a low-light area according to the grayscale value gradient change information.

[0089] In one embodiment of the present invention, continuous frame images are divided into a high-frequency area and a low-frequency area according to the grayscale value gradient change and a preset change threshold.

[0090] Step 3042: Determine the detail component relationship between the highlight area and the low light area.

[0091] In one embodiment of the present invention, the detail component relationship is used to characterize the linear relationship between the frequency domain features of the high and low light areas. The detail component relationship includes at least one of a horizontal detail component relationship, a vertical detail component relationship, and a diagonal detail component relationship.

[0092] Step 3043: Generate the transparent image according to the detail component relationship, the endpoint output information of the highlight area and the low light area.

[0093] In one embodiment of the present invention, the linear relationship between the highlight area and the low light area of ​​the distribution area and the output value at the endpoint of the low light area are processed, and the output value at the endpoint of the highlight area is output, and compiled to obtain a transparent image.

[0094] The transparent image is a high-frequency image derived from the linear relationship between high and low light areas, depicting the details of the original keyframe. The transparent image is used to parametrically compensate for the graphic details between the high and low light areas, thus reflecting the visual details of the real environment.

[0095] Step 305: superimpose the transparent image on the key frame of the target area point to obtain the superimposed video frame.

[0096] In one embodiment of the present invention, by superimposing a transparent image on a key frame, the details of the key frame image are supplemented, thereby achieving an effect of enhancing the visual experience.

[0097] Step 40: performing enhancement processing on the discontinuous region according to the video frame to obtain a processed video.

[0098] In one embodiment of the present invention, the enhancement process may be frame interpolation or frame replacement. Considering that approximating video frames can make an image clearer and less noisy, while superimposing video frames can reflect more texture details of the image, the video frame with the best processed effect can be selected from the approximating video frames and the superimposed video frames. The processed video effect can be determined based on the feature continuity between the video frames.

[0099] Therefore, in one embodiment of the present invention, the discontinuous area includes multiple target area points; the feature information includes frequency domain feature information; the video frame includes an approximate video frame and an overlaid video frame; wherein the approximate video frame is a video frame in which the change of the frequency domain feature information in the front-to-back direction of the continuous frame meets a preset condition; the overlaid video frame is a key frame containing texture detail information of the continuous frame.

[0100] In order to further improve the smoothness of the processed video, approximate video frames and superimposed video frames can be generated simultaneously, and the video frame with the best effect after enhancement processing (ie, the best frame) can be enhanced to further improve the effect of video enhancement processing.

[0101] Step 40 further includes: Step 401: determining an optimal frame from the approximate video frame and the superimposed video frame.

[0102] In one embodiment of the present invention, when there are both approximate video frames and superimposed video frames, the video frame with the best effect after enhancement processing (ie, the best frame) can be selected to further improve the effect of the video enhancement processing.

[0103] Specifically, the approximate video frame, the superimposed video frame, and the original video frame may be combined to obtain a corresponding processed video, and then the target frame may be selected from the approximate video frame and the superimposed video frame according to the smoothness of the processed video.

[0104] The smoothness level may be the smoothness level of the image features of the processed video, which is used to reflect whether the video viewing experience is smooth and continuous.

[0105] In one embodiment of the present invention, the degree of smoothness may also be determined by visually comparing the combined videos and determining the degree of smoothness based on motion vector information of the forward and backward reference fields.

[0106] Step 402: performing frame replacement or frame supplementation processing on the target area point according to the optimal frame to obtain the processed video.

[0107] In one embodiment of the present invention, the best frame is added to the target area point for frame supplementation, or the video frame of the target area point is replaced, and after processing, the processed video is marked with the processed area.

[0108] Through a distributed sorting algorithm, a sequence of specified length is generated to mark and record the processing area; by reading the marked records, the video frames after frame replacement or frame supplementation can be retrieved and mapped to the user space for display, thereby improving the user's video viewing experience.

[0109] In another embodiment of the present invention, the video processing process can refer to Figure 2 .

[0110] like Figure 2 As shown, firstly, a first video set to be processed is read, continuous frames of a preset timeline length are selected from the first video set, and regions with discontinuous image features are determined in the continuous frames as discontinuous regions.

[0111] Subsequently, the continuous frames are Fourier transformed from the spatial domain to the frequency domain to obtain the relevant features of the continuous frames. Then, multiple video frames are generated based on the relevant features, and the best frame is selected and loaded into the corresponding area point of the discontinuous area.

[0112] The process of generating video frames and selecting the best frame can be referred to Figure 3 ,like Figure 3 As shown, the grayscale gradient change after Fourier transform of consecutive frames is calculated and gradient encoding is performed. Subsequently, at least two reference frames for comparison in the front-to-back direction of the corresponding regional point in the discontinuous region are taken to generate an approximate video frame. Simultaneously, a transparent image generated by gradient encoding is taken for the corresponding regional point and superimposed on the key frame of the corresponding regional point to obtain a superimposed video frame.

[0113] The approximate video frame and the superimposed video frame are respectively combined with the original continuous frames to perform smoothness evaluation, and the above-mentioned best frame is determined from the approximate video frame and the superimposed video frame according to the smoothness.

[0114] Finally, the best frame is loaded into the corresponding area point of the discontinuous area, and the frame is replaced or supplemented to obtain a continuous frame that completes the continuous processing.

[0115] For example Figure 2As shown, the continuous frames that have completed the continuous processing are subjected to Fourier inverse transform from the frequency domain to the spatial domain to obtain a second video set that is output to the client for playback.

[0116] The video processing method provided by the embodiment of the present invention determines the discontinuous areas within the continuous frames of the video; the discontinuous areas are areas where the image features of adjacent frames are discontinuous, thereby locating the frame position where the viewing experience is not smooth. The feature information of the continuous frames is then determined; multiple video frames are generated based on the feature information; finally, the discontinuous areas are enhanced based on the video frames to obtain a processed video. This is different from the existing technology that only focuses on enhancing the medium luminance area, resulting in an unsmooth video viewing experience in areas with large luminance changes. The video processing method provided by the embodiment of the present invention can optimize the smoothness and fluency of the video frames, ensure clear details, and improve the video viewing experience.

[0117] Figure 4 FIG. 1 shows a schematic diagram of the structure of a video processing device provided by an embodiment of the present invention. Figure 4 As shown, the device 50 includes: a first determination module 501 , a second determination module 502 , a generation module 503 and a processing module 504 .

[0118] The first determining module 501 is configured to determine a discontinuous region within consecutive frames of a video; the discontinuous region is a region where image features of adjacent frames are discontinuous;

[0119] A second determining module 502 is configured to determine feature information of the consecutive frames;

[0120] A generating module 503 is configured to generate a plurality of video frames according to the feature information;

[0121] The processing module 504 is configured to perform enhancement processing on the discontinuous region according to the video frame to obtain a processed video.

[0122] The operation process of the video processing device provided in the embodiment of the present invention is substantially the same as that of the aforementioned method embodiment, and will not be described in detail.

[0123] The video processing device provided by the embodiment of the present invention determines the discontinuous areas within the continuous frames of the video; the discontinuous areas are areas where the image features of adjacent frames are discontinuous, thereby locating the frame position where the viewing experience is not smooth. Then, the feature information of the continuous frames is determined; multiple video frames are generated based on the feature information; finally, the discontinuous areas are enhanced based on the video frames to obtain a processed video. This is different from the existing technology that only focuses on enhancing the medium luminance area, resulting in an unsmooth video viewing experience in areas with large luminance changes. The video processing device provided by the embodiment of the present invention can optimize the smoothness and fluency of the video frames, ensure clear details, and improve the video viewing experience.

[0124] Figure 5 The schematic diagram of the structure of the video processing device provided by the embodiment of the present invention is shown. The specific embodiment of the present invention does not limit the specific implementation of the video processing device.

[0125] like Figure 5 As shown, the video processing device may include: a processor (processor) 602 , a communications interface (Communications Interface) 604 , a memory (memory) 406 , and a communication bus 408 .

[0126] Processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. Communication interface 404 is used to communicate with other devices, such as clients or other server network elements. Processor 402 is used to execute program 410, which may specifically perform the steps described above in the embodiment of the video processing method.

[0127] Specifically, the program 410 may include program code including computer-executable instructions.

[0128] Processor 402 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the video processing device may be processors of the same type, such as one or more CPUs, or may be processors of different types, such as one or more CPUs and one or more ASICs.

[0129] The memory 406 is used to store the program 410. The memory 406 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0130] The program 410 may be specifically called by the processor 402 to enable the video processing device to perform the following operations:

[0131] Determining discontinuous regions within consecutive frames of a video; the discontinuous regions are regions where image features of adjacent frames are discontinuous;

[0132] determining feature information of the consecutive frames;

[0133] generating a plurality of video frames according to the feature information;

[0134] The discontinuous area is enhanced according to the video frame to obtain a processed video.

[0135] The operation process of the video processing device provided in the embodiment of the present invention is substantially the same as that of the aforementioned method embodiment, and will not be described in detail.

[0136] The video processing device provided by the embodiment of the present invention determines the discontinuous areas within the continuous frames of the video; the discontinuous areas are areas where the image features of adjacent frames are discontinuous, thereby locating the frame position where the viewing experience is not smooth. Then, the feature information of the continuous frames is determined; multiple video frames are generated based on the feature information; finally, the discontinuous areas are enhanced based on the video frames to obtain a processed video. This is different from the existing technology that only focuses on enhancing the medium luminance area, resulting in an unsmooth video viewing experience in areas with large luminance changes. The video processing device provided by the embodiment of the present invention can optimize the smoothness and fluency of the video frames, ensure clear details, and improve the video viewing experience.

[0137] An embodiment of the present invention provides a computer-readable storage medium storing at least one executable instruction. When the executable instruction is executed on a video processing device, the video processing device executes the video processing method in any of the above method embodiments.

[0138] The executable instructions may be specifically used to enable the video processing device to perform the following operations:

[0139] Determining discontinuous regions within consecutive frames of a video; the discontinuous regions are regions where image features of adjacent frames are discontinuous;

[0140] determining feature information of the consecutive frames;

[0141] generating a plurality of video frames according to the feature information;

[0142] The discontinuous area is enhanced according to the video frame to obtain a processed video.

[0143] The operation process of the executable instructions stored in the computer storage medium provided in the embodiment of the present invention is roughly the same as that of the aforementioned method embodiment and will not be repeated here.

[0144] The executable instructions stored in the computer storage medium provided by the embodiment of the present invention determine the discontinuous areas within the continuous frames of the video; the discontinuous areas are areas where the image features of adjacent frames are discontinuous, thereby locating the frame position where the viewing experience is not smooth. Then, the feature information of the continuous frames is determined; multiple video frames are generated based on the feature information; finally, the discontinuous areas are enhanced based on the video frames to obtain a processed video. This is different from the existing technology that only focuses on enhancing the medium luminance area, resulting in an unsmooth video viewing experience in areas with large luminance changes. The executable instructions stored in the computer storage medium provided by the embodiment of the present invention can optimize the smoothness and fluency of the video frames, ensure clear details, and improve the video viewing experience.

[0145] An embodiment of the present invention provides a video processing device for executing the above-mentioned video processing method.

[0146] An embodiment of the present invention provides a computer program, which can be called by a processor to enable a video processing device to execute the video processing method in any of the above method embodiments.

[0147] An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed on a computer, the computer executes the video processing method in any of the above method embodiments.

[0148] The algorithm or demonstration provided herein are not inherently relevant to any particular computer, virtual system or other equipment. Various general-purpose systems may also be used together with the teachings based on this. According to the above description, it is apparent that the structure required for constructing this type of system. In addition, the embodiment of the present invention is not directed to any specific programming language yet. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the above description of specific languages ​​is for the purpose of disclosing the best mode of the present invention.

[0149] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0150] Similarly, it should be understood that in order to streamline the present invention and facilitate understanding of one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the embodiments of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim.

[0151] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and set in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed so far can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0152] It should be noted that the above embodiments illustrate rather than limit the invention, and that alternative embodiments may be devised by a person skilled in the art without departing from the scope of the appended claims. In the claims, any reference signs placed between brackets should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. In a unit claim enumerating several means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third etc. does not indicate any order. These words may be interpreted as names. The steps in the above embodiments should not be understood as limiting the order of execution unless otherwise specified.

Claims

1. A video processing method, characterized in that: The method comprises: Determining discontinuous regions within consecutive frames of a video; the discontinuous regions are regions where image features of adjacent frames are discontinuous; Determining feature information of the continuous frames; the feature information includes frequency domain feature information; the video frame includes an approximate video frame; the approximate video frame is a video frame where the frequency domain feature information in the front-back direction of the continuous frames satisfies a preset feature value range; the frequency domain feature information includes grayscale value gradient change information; Generating a plurality of video frames according to the feature information includes: screening at least two comparison reference frames in the front-back direction of the continuous frames according to the grayscale value gradient change information and the feature value interval to obtain frames to be approximated; performing approximation processing on the frames to be approximated to obtain the approximate video frames; The discontinuous area is enhanced according to the video frame to obtain a processed video.

2. The method according to claim 1, characterized in that The video frame includes a superimposed video frame; the superimposed video frame is a key frame superimposed with texture detail information of the continuous frames.

3. The method according to claim 2, characterized in that The feature information includes frequency domain feature information; the discontinuous area includes a plurality of target area points; and generating a plurality of video frames according to the feature information includes: Determining at least one key frame corresponding to the target area point from adjacent areas of the target area point according to the frequency domain feature information; generating a transparent image corresponding to the target area point according to the frequency domain feature information; The transparent image is superimposed on the key frame of the target area point to obtain the superimposed video frame.

4. The method according to claim 3, characterized in that The frequency domain feature information includes grayscale value gradient change information; and generating a transparent image corresponding to the target area point according to the frequency domain feature information includes: Dividing the continuous frames into a high light area and a low light area according to the grayscale value gradient change information; determining a detail component relationship between the highlight area and the low light area; The transparent image is generated according to the detail component relationship and the endpoint output information of the highlight area and the low light area.

5. The method according to claim 1, characterized in that The discontinuous region includes a plurality of target region points; the feature information includes frequency domain feature information; the video frame includes an approximate video frame and an overlay video frame; wherein the approximate video frame is a video frame in which a change in the frequency domain feature information in a front-to-back direction of the continuous frame satisfies a preset condition; the overlay video frame is a key frame on which texture detail information of the continuous frame is overlaid; and the enhancing process of the discontinuous region according to the video frame to obtain a processed video includes: determining a best frame from the approximate video frame and the superimposed video frame; The target area point is subjected to frame replacement or frame supplementation processing according to the optimal frame to obtain the processed video.

6. A video processing device, characterized in that: The device comprises: A first determining module is configured to determine a discontinuous region within consecutive frames of a video; the discontinuous region is a region where image features of adjacent frames are discontinuous; a second determining module for determining feature information of the continuous frames; the feature information including frequency domain feature information; the video frames including approximate video frames; the approximate video frames being video frames whose frequency domain feature information in a front-to-back direction of the continuous frames satisfies a preset feature value range; the frequency domain feature information including grayscale value gradient change information; a generating module, configured to generate a plurality of video frames based on the feature information, comprising: screening at least two comparison reference frames in a front-to-back direction of the continuous frames based on the grayscale value gradient change information and the feature value interval to obtain frames to be approximated; and performing approximation processing on the frames to be approximated to obtain the approximate video frames; The processing module is used to perform enhancement processing on the discontinuous area according to the video frame to obtain a processed video.

7. A video processing device, characterized in that: include: A processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other via the communication bus; The memory is used to store at least one executable instruction, and the executable instruction enables the processor to perform the operation of the video processing method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that The storage medium stores at least one executable instruction. When the executable instruction is executed on the video processing device, the video processing device executes the operation of the video processing method according to any one of claims 1 to 5.

Images