Video picture optimization method and device, equipment and medium

Abstract

The invention discloses a video picture optimization method and device, equipment and a medium, and the method comprises the steps: analyzing a to-be-displayed target video frame obtained in real time, determining the picture quality, the picture scene and the element region of the picture element of the target video frame, and storing the picture configuration data, the picture quality and the picture scene of a user into the element region of the picture element; inputting a model subjected to picture optimization training, outputting parameters for optimization and the confidence coefficient of the corresponding parameters, and for any picture partition for dividing the picture of the target video frame, optimizing the picture partition according to the element areas of all picture elements, the parameters and the confidence coefficient of the corresponding parameters, the method comprises the following steps: optimizing a picture partition according to the picture partition, obtaining an optimized picture partition, obtaining an optimized target video frame according to the optimized picture partition, and playing and displaying the optimized target video frame. According to the invention, the optimization of the video picture is automatically realized, the accuracy and adaptability of picture optimization are improved, the video optimization effect is improved, and thus the user experience is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, and in particular to a video picture optimization method, device, equipment and medium. BACKGROUND

[0002] With the rapid development of digital video technology and the popularity of display devices, users have higher and higher requirements for video playback quality. In the video playback process, visual parameters such as the color tone, brightness and contrast of the picture directly affect the user's viewing experience. Traditional video display systems usually use fixed color tone settings, such as cold color tone, warm color tone or standard color tone mode. These settings remain constant throughout the video playback process. However, video content is diverse and complex, and when playing these contents using fixed color tone settings, problems such as picture color distortion, detail loss and insufficient contrast often occur, which seriously affects the user's viewing experience.

[0003] There are several improvement attempts in the prior art, but there are still certain limitations. First, adjustment based on preset modes. Most display devices provide preset display modes, such as "standard mode", "movie mode", "game mode", etc. These modes adjust the display effect through preset color parameters, and users can manually select the corresponding mode according to the viewing content. However, this method has limited optimization effect and requires manual adjustment by the user. Second, automatic brightness adjustment based on ambient light sensors. Some high-end display devices integrate ambient light sensors that can detect the intensity of ambient light and automatically adjust the screen brightness. However, this method mainly focuses on brightness adjustment and has limited optimization effect, and requires manual adjustment by the user. Third, manual adjustment based on user preferences. Users can manually adjust parameters such as color tone, saturation and contrast through the settings menu of the display device. Although this method is flexible, it still requires frequent manual operation by the user, resulting in poor user experience.

[0004] Therefore, how to automatically optimize the video picture, improve the accuracy of optimization, and improve the user experience has become a problem to be solved. SUMMARY

[0005] The embodiments of the present application provide a video picture optimization method, device, equipment and medium to solve the problem of how to automatically optimize the video picture, improve the accuracy of optimization, and improve the user experience.

[0006] A video picture optimization method comprises: real-time obtaining a target video frame to be displayed from a video source, analyzing the picture of the target video frame, and determining the picture quality, picture scene and element region of the contained picture elements of the target video frame; obtain picture configuration data of the user, input the picture configuration data, the picture quality and the picture scene into a model which has been trained for picture optimization, and output parameters for picture optimization of the target video frame and confidence of corresponding parameters through the model which has been trained for picture optimization; divide the picture of the target video frame into regions to obtain picture partitions, optimize any picture partition according to element regions, parameters and confidence of corresponding parameters of all picture elements, and obtain an optimized picture partition; obtain an optimized target video frame according to all optimized picture partitions, and display the optimized target video frame.

[0007] A video picture optimization device comprises: a picture analysis module configured to obtain a target video frame to be displayed from a video source in real time, analyze a picture of the target video frame, and determine picture quality, picture scene and element regions of picture elements contained in the target video frame; a model prediction module configured to obtain picture configuration data of the user, input the picture configuration data, the picture quality and the picture scene into a model which has been trained for picture optimization, and output parameters for picture optimization of the target video frame and confidence of corresponding parameters through the model which has been trained for picture optimization; a picture optimization module configured to divide the picture of the target video frame into regions to obtain picture partitions, optimize any picture partition according to element regions, parameters and confidence of corresponding parameters of all picture elements, and obtain an optimized picture partition; a picture display module configured to obtain an optimized target video frame according to all optimized picture partitions, and display the optimized target video frame.

[0008] A computer device comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the above-mentioned video picture optimization method when executing the computer program.

[0009] A computer readable storage medium stores a computer program, and the computer program is executable on a processor to implement the above-mentioned video picture optimization method.

[0010] The video picture optimization method, device, computer device and storage medium described above, by analyzing the target video frame to be displayed obtained in real time, determining the picture quality, picture scene and element region of the picture elements contained by the target video frame, inputting the picture configuration data of the user, picture quality and picture scene into the model which has been trained for picture optimization, outputting the parameters for picture optimization of the target video frame and the confidence of the corresponding parameters, dividing the target video frame to obtain picture partitions, optimizing any picture partition according to the element region of all picture elements, parameters and the confidence of the corresponding parameters, obtaining the optimized picture partition, obtaining the optimized target video frame according to all optimized picture partitions, and playing and displaying the optimized target video frame.

[0011] Among them, by analyzing the content of the target video frame in real time, the picture quality, picture scene and element region of the picture elements are recognized, and through the model which has been trained for picture optimization, the corresponding optimization parameters and their confidence are generated, on this basis, the picture partitions of the target video frame are taken as units for fine optimization, the optimized target video frame is obtained for playing and displaying, the optimization of the video picture is automatically realized, the accuracy and adaptability of the picture optimization are improved, the effect of the video optimization is improved, and the user experience is improved. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the description of the embodiments of the present application. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0013] Figure 1 is an application environment diagram of the video picture optimization method in an embodiment of the present application; Figure 2 is a flowchart of the video picture optimization method in an embodiment of the present application; Figure 3 is another flowchart of the video picture optimization method in an embodiment of the present application; Figure 4 is another flowchart of the video picture optimization method in an embodiment of the present application; Figure 5 is another flowchart of the video picture optimization method in an embodiment of the present application; Figure 6 is a schematic diagram of the video picture optimization device in an embodiment of the present application; Figure 7 is a schematic diagram of the computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0014] The technical solutions in the embodiments of the present application will be apparently and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all the other embodiments obtained by a person of ordinary skill in the art without any creative work fall within the protection scope of the present application.

[0015] The video picture optimization method provided by the embodiments of the present application can be applied in an application environment as shown in Figure 1 . Specifically, the video picture optimization method is applied in a video picture optimization system, which includes a client and a server as shown in Figure 1 . The client and the server communicate through a network, and are used to solve the problem of how to automatically realize optimization of a video picture, improve the accuracy of optimization, and improve user experience. The client, also known as a user end, is a program that provides local services for clients corresponding to the server. The client can be installed on, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, and portable wearable devices. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0016] In an embodiment, as shown in Figure 2 , a video picture optimization method is provided. Taking the server in Figure 1 as an example, the method includes the following steps: Step S201: Real-time acquisition of a target video frame to be displayed from a video source, analysis of a picture of the target video frame, determination of picture quality, a picture scene, and an element region of a picture element contained in the target video frame.

[0017] Step S202: Acquisition of picture configuration data of a user, input of the picture configuration data, the picture quality, and the picture scene into a model that has been trained for picture optimization, and output of parameters for picture optimization of the target video frame and a confidence degree of the corresponding parameters by the model that has been trained for picture optimization.

[0018] In this embodiment, the target video frame can refer to a video frame to be played and displayed and requiring picture optimization, the video source can refer to the source of the target video frame, such as a real-time video stream and a video file stored on a disk, etc., the picture quality can refer to the quality of the picture displayed by the target video frame, the picture scene can refer to the scene to which the picture displayed by the target video frame belongs, such as indoor, outdoor, daytime, nighttime, sunny day and rainy day, etc., the picture element can refer to an independently identifiable entity in the picture displayed by the target video frame, such as text, face and object, etc., and the element region can refer to the region occupied by the picture element in the picture of the target video frame.

[0019] The picture configuration data can refer to the picture optimization parameter data combined with the user preference, and the model that has been trained for picture optimization can refer to a deep learning model that has been trained for picture optimization parameter prediction. The model is trained to predict the optimization parameters based on the picture configuration data, the picture quality and the picture scene. The parameters can refer to the parameters for picture optimization of the target video frame, which can include parameters such as hue, saturation and contrast.

[0020] Specifically, the target video frame to be displayed is obtained from the video source in real time, the picture of the target video frame is analyzed to determine the picture quality, the picture scene and the element region of the picture element contained by the target video frame, the picture configuration data of the user, the picture quality and the picture scene are input into the model that has been trained for picture optimization, and the parameters for picture optimization of the target video frame and the confidence of the corresponding parameters are output by the model that has been trained for picture optimization.

[0021] Step S203: The picture of the target video frame is divided into regions to obtain picture partitions. For any picture partition, the picture partition is optimized according to the element region of all picture elements, the parameters and the confidence of the corresponding parameters to obtain an optimized picture partition.

[0022] Step S204: The optimized target video frame is obtained according to all optimized picture partitions, and the optimized target video frame is played and displayed.

[0023] In this embodiment, the picture partition can refer to a sub-region obtained by dividing the picture of the target video frame.

[0024] Specifically, the picture of the target video frame is divided to obtain picture partitions. For any picture partition, the picture partition is optimized according to the element region of all picture elements, the parameters and the confidence of the corresponding parameters to obtain an optimized picture partition. The optimized target video frame is obtained according to all optimized picture partitions, and the optimized target video frame is played and displayed.

[0025] In the embodiment, by analyzing the content of the target video frame in real time, the picture quality, the picture scene and the element region of the picture element of the target video frame are recognized, and the model trained by the picture optimization is used to generate the targeted optimization parameter and the confidence, and on this basis, the fine optimization is performed on the picture partition of the target video frame to obtain the optimized target video frame for playing and displaying, so that the optimization of the video picture is automatically realized, the accuracy and adaptability of the picture optimization are improved, the effect of the video optimization is improved, and the user experience is improved.

[0026] In an embodiment, as shown in Figure 3 A video picture optimization method is provided. The step S201 of analyzing the picture of the target video frame to determine the picture scene of the target video frame includes the following steps: Step S301: For any pixel in the picture of the target video frame, the hue value of the pixel is determined.

[0027] Step S302: According to the hue values of all the pixels, the hue distribution feature of the target video frame is determined.

[0028] Step S303: According to the hue distribution feature, the scene of the picture of the target video frame is identified to obtain the picture scene.

[0029] In the embodiment, the hue distribution feature can be feature data representing the hue distribution trend of the pixels in the target video frame.

[0030] Specifically, for any pixel in the picture of the target video frame, the hue value of the pixel is calculated, the hue histogram is generated according to the hue values of all the pixels, the hue distribution feature is identified by analyzing the hue histogram, and the picture scene of the target video frame is determined based on the hue distribution feature.

[0031] Optionally, the picture of the target video frame is analyzed to determine the picture quality of the target video frame, including: for any pixel in the picture of the target video frame, the brightness value, the gradient value and the first chroma value of the pixel are determined, the maximum brightness value and the minimum brightness value are determined from all the brightness values, the contrast score of the target video frame is determined according to the maximum brightness value and the minimum brightness value, the sharpness score of the target video frame is determined according to the gradient values of all the pixels in the target video frame, the second chroma value of each pixel in the reference video frame is obtained, the color accuracy score of the target video frame is determined according to the first chroma value of all the pixels in the target video frame and the second chroma value of all the pixels in the reference video, and the picture quality is obtained according to the contrast score, the sharpness score and the color accuracy score.

[0032] The first chroma value can be a chroma value of a pixel in the target video frame, the second chroma value can be a chroma value of a pixel in the reference video frame, the chroma value is a LAB (L channel-brightness, A channel-green and red axis, B channel-blue and yellow axis) value, the reference video frame can be a video frame with a standard chroma, the contrast score can be a score for measuring the overall brightness of the target video frame, the sharpness score can be a score for measuring the edge definition of the object in the target video frame, and the color accuracy score can be a score for measuring the closeness of the color of the target video frame to the standard color.

[0033] That is, the maximum brightness value and the minimum brightness value are subtracted to obtain a difference result, and the maximum brightness value and the minimum brightness value are added to obtain a sum result, the difference result and the sum result are divided to obtain the contrast score. The closer the contrast score is to 1, the higher the contrast is, and there are very bright and very dark areas in the picture. The closer the contrast score is to 0, the lower the contrast is, and the overall picture is gray and lacks brightness levels. The average of all pixel gradient values in the target video frame is calculated to obtain the sharpness score. The larger the sharpness score is, the higher the overall sharpness of the picture is.

[0034] For any pixel in the target video frame, the second chroma value of the corresponding pixel color in the reference video frame is determined, the difference between the first chroma value and the second chroma value of the pixel in the three dimensions of brightness, red-green chroma and yellow-blue chroma is calculated respectively, each of the obtained difference values is squared, the three squared results are added, and the square root of the sum is taken to obtain the color accuracy score of the pixel. The average of the color accuracy scores of all pixels in the target video frame is calculated to obtain the color accuracy score of the target video frame. The smaller the color accuracy score is, the higher the color accuracy is.

[0035] Optionally, the picture of the target video frame is analyzed to determine the element region of the picture element contained in the target video frame, including: analyzing the picture of the target video frame by optical character recognition technology to determine the text element contained in the target video frame and the element region corresponding to the text element; analyzing the picture of the target video frame by a preset target recognition algorithm to determine the face element contained in the target video frame, the element region corresponding to the face element, the article element and the element region corresponding to the article element.

[0036] That is, the text in the picture of the target video frame and the region occupied by the corresponding text are recognized by optical character recognition technology, and the face, article, region occupied by the face and region occupied by the article in the picture of the target video frame are recognized by a preset target recognition algorithm (an algorithm for recognizing articles and faces).

[0037] In the embodiment, the scene of the picture is recognized by analyzing the color tone distribution characteristics of the picture, and multiple quality indexes such as contrast, sharpness and color accuracy are calculated. The key visual elements and the corresponding element regions are located based on the optical character recognition and target recognition algorithm, the basic situation of the target video frame is objectively evaluated, an objective data basis is provided for subsequent picture optimization, the pertinence of picture optimization is ensured, and the effect of picture optimization is improved.

[0038] In an embodiment, as shown in Figure 4 A video picture optimization method is provided. In step S203, for any picture partition, the picture partition is optimized according to the element regions, parameters and confidence degrees of the corresponding parameters of all picture elements, to obtain an optimized picture partition, including the following steps. Step S401: For any picture partition, the element regions contained in the picture partition are determined according to the element regions of all picture elements, and the region proportion of the picture elements in the picture partition is determined according to the picture partition and the element regions contained in the picture partition.

[0039] Step S402: The weight of the picture partition is determined according to the region proportion, the picture partition is optimized according to the weight, all parameters and the confidence degrees of the corresponding parameters, and an optimized picture partition is obtained.

[0040] In the embodiment, the region proportion can refer to the proportion of the element regions in the corresponding region of the picture partition, and the weight can refer to a value representing the importance of the picture partition determined according to the region proportion.

[0041] Specifically, for any picture partition, the element regions in the picture partition are determined, the region proportion of the picture elements in the picture partition is determined according to the element regions in the picture partition and the corresponding region of the picture partition, the weight of the picture partition is determined according to the region proportion, the picture partition is optimized according to the weight, all parameters and the confidence degrees of the corresponding parameters, and an optimized picture partition is obtained.

[0042] Optionally, the picture partition is optimized according to the weight, all parameters and the confidence degrees of the corresponding parameters to obtain an optimized picture partition, including: for any parameter, the initial optimization intensity of the parameter is determined according to the confidence degree of the parameter, the target optimization intensity is obtained by adjusting the initial optimization intensity according to the weight, and the picture partition is picture-optimized according to the target optimization intensity of all parameters and the corresponding parameters to obtain an optimized picture partition.

[0043] The initial optimization intensity can refer to the parameter optimization intensity determined based on the confidence degree, and the target optimization intensity can refer to the parameter optimization intensity adjusted by the weight.

[0044] That is, for any parameter, according to the confidence of the parameter, the initial optimization intensity of the parameter is determined (an aggressive strategy is adopted when the confidence is high, and a conservative strategy is adopted when the confidence is low), the initial optimization intensity of the parameter is adjusted according to the weight of the picture partition to obtain the target optimization intensity, and the picture partition is optimized according to all parameters and the target optimization intensity of the corresponding parameter to obtain the optimized picture partition.

[0045] In the embodiment, by calculating the area proportion of picture elements in each picture partition and dynamically allocating optimization weights according to the area proportion, the initial optimization intensity corresponding to the confidence of the model output parameter is adjusted according to the weight, adaptive picture optimization based on the importance of the partition content is realized, the accuracy and adaptability of picture optimization are improved, and the effect of video optimization is improved.

[0046] In an embodiment, as shown in Figure 5 A video picture optimization method is provided, and the step S204 of obtaining the optimized target video frame according to all optimized picture partitions includes the following steps: Step S501: performing spatial dimension smoothing processing on all optimized picture partitions to obtain an optimized target video frame.

[0047] Step S502: obtaining a previous video frame corresponding to the optimized target video frame, performing time dimension smoothing processing on the previous video frame corresponding to the optimized target video frame and the optimized target video frame, and playing and displaying the optimized target video frame.

[0048] Specifically, spatial smoothing is performed among all optimized picture partitions to realize smooth transition among different optimized picture partitions, blur the boundaries between the partitions, determine a previous video frame of the target video frame, obtain a video frame corresponding to the previous video frame, and perform time smoothing on the optimized target video frame and the video frame corresponding to the previous video frame to avoid flicker caused by sudden changes in brightness, color, or details between frames.

[0049] In the embodiment, by introducing a spatial and time dual smoothing mechanism, the block effect and boundary traces caused by partition optimization are eliminated in the spatial dimension, the uniformity and naturalness of the whole picture are ensured, the shaking and flicker of the picture between frames are effectively inhibited in the time dimension, the coherence and stability of the video picture playback are ensured, and the user experience is improved.

[0050] It should be understood that the size of the serial number of each step in the above embodiments does not mean the order of execution, the execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0051] In an embodiment, a video frame optimization apparatus is provided, which corresponds to the video frame optimization method in the above-mentioned embodiments. As shown in the figure, the video frame optimization apparatus comprises a frame analysis module 61, a model prediction module 62, a frame optimization module 63 and a frame display module 64. The functions of each module are described in detail as follows: Figure 6 The frame analysis module 61 is configured to acquire a target video frame to be displayed from a video source in real time, analyze the frame of the target video frame, and determine the frame quality, the frame scene and the element region of the contained frame elements of the target video frame. The model prediction module 62 is configured to acquire the frame configuration data of a user, input the frame configuration data, the frame quality and the frame scene into a model that has been trained for frame optimization, and output the parameters for frame optimization of the target video frame and the confidence of the corresponding parameters through the model that has been trained for frame optimization. The frame optimization module 63 is configured to divide the frame of the target video frame into regions to obtain frame partitions, and for any frame partition, optimize the frame partition according to the element region of all frame elements, the parameters and the confidence of the corresponding parameters to obtain an optimized frame partition. The frame display module 64 is configured to obtain an optimized target video frame according to all optimized frame partitions, and play and display the optimized target video frame. Optionally, the frame analysis module 61 comprises:

[0052] A tone determination unit configured to determine the tone value of any pixel in the frame of the target video frame. A feature determination unit configured to determine the tone distribution feature of the target video frame according to the tone values of all pixels. A scene recognition unit configured to recognize the frame scene of the frame of the target video frame according to the tone distribution feature to obtain the frame scene.

[0053] Optionally, the frame analysis module 61 comprises: A pixel determination unit configured to determine the brightness value, the gradient value and the first chroma value of any pixel in the frame of the target video frame. A contrast determination unit configured to determine the maximum brightness value and the minimum brightness value from all brightness values, and determine the contrast score of the target video frame according to the maximum brightness value and the minimum brightness value. A sharpness determination unit configured to determine the sharpness score of the target video frame according to the gradient values of all pixels in the target video frame. ​a color determination unit configured to obtain second chrominance values of each pixel in a reference video frame, and determine a color accuracy score of the target video frame according to the first chrominance values of all pixels in the target video frame and the second chrominance values of all pixels in the reference video frame; a quality determination unit configured to obtain the picture quality according to the contrast score, the sharpness score and the color accuracy score.

[0054] Optionally, the picture analysis module 61 comprises: a text recognition unit configured to analyze the picture of the target video frame by an optical character recognition technology, and determine text elements contained in the target video frame and element regions of the corresponding text elements; a target recognition unit configured to analyze the picture of the target video frame by a preset target recognition algorithm, and determine face elements contained in the target video frame, element regions of the corresponding face elements, article elements and element regions of the corresponding article elements.

[0055] Optionally, the picture optimization module 63 comprises: a proportion determination unit configured to determine, for any picture partition, element regions contained in the picture partition according to element regions of all picture elements, and determine a region proportion of picture elements in the picture partition according to the picture partition and the element regions contained in the picture partition; a partition optimization unit configured to determine a weight of the picture partition according to the region proportion, and optimize the picture partition according to the weight, all parameters and confidences of the corresponding parameters to obtain an optimized picture partition.

[0056] Optionally, the partition optimization unit comprises: an initial determination subunit configured to determine, for any parameter, an initial optimization intensity of the parameter according to a confidence of the parameter; an adjustment subunit configured to adjust the initial optimization intensity according to the weight to obtain a target optimization intensity; a parameter optimization subunit configured to optimize the picture partition according to all parameters and target optimization intensities of the corresponding parameters to obtain the optimized picture partition.

[0057] Optionally, the picture display module 64 comprises: a spatial smoothing unit configured to perform smoothing processing on all optimized picture partitions in a spatial dimension to obtain the optimized target video frame; a time smoothing unit, configured to obtain a previous video frame corresponding to the target video frame, perform smoothing on the previous video frame corresponding to the target video frame and the target video frame in a time dimension, and display the target video frame.

[0058] The specific definitions of the video picture optimization apparatus can refer to the definitions of the video picture optimization method, which are not repeated here. Each module in the video picture optimization apparatus can be realized by software, hardware, or a combination thereof. Each module can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory in the computer device in software form, so that the processor can call and execute the operations of each module.

[0059] In an embodiment, a computer device is provided, which can be a server, and the internal structure diagram thereof can be as shown in Figure 7 The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store target video frames. The network interface of the computer device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement a video picture optimization method.

[0060] In an embodiment, a computer device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor implements the video picture optimization method in the above embodiments when executing the computer program, such as Figure 2 as shown in S201-S204, or Figures 3 to 5 For brevity, the functions of the modules / units in this embodiment are not repeated here. Alternatively, the processor implements the functions of the modules / units in the video picture optimization apparatus, such as Figure 6 the functions of the picture analysis module 61, the model prediction module 62, the picture optimization module 63, and the picture display module 64 as shown in

[0061] In an embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the video picture optimization method in the above embodiments, such as Figure 2 as shown in S201-S204, or Figures 3 to 5As shown in FIG. 1, the video picture optimization apparatus 100 includes a picture analysis module 61, a model prediction module 62, a picture optimization module 63 and a picture display module 64. The functions of the picture analysis module 61, the model prediction module 62, the picture optimization module 63 and the picture display module 64 are not repeated here for the sake of brevity. Alternatively, the processor implements the functions of the modules / units in the embodiment of the video picture optimization apparatus when executing the computer program, for example, Figure 6 The functions of the picture analysis module 61, the model prediction module 62, the picture optimization module 63 and the picture display module 64 are not repeated here for the sake of brevity.

[0062] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing the relevant hardware, and the computer program can be stored in a non-volatile computer readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned embodiments. Any reference to memory, storage, database or other medium used in the embodiments provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct RAM bus dynamic RAM (DRDRAM) and memory bus dynamic RAM (RDRAM) and the like.

[0063] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above.

[0064] The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, but not limit it; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for video picture optimization, characterized by, The method comprises the following steps: real-time obtaining a target video frame to be displayed from a video source, analyzing a picture of the target video frame, determining a picture quality, a picture scene and an element region of a picture element contained in the target video frame; obtaining picture configuration data of a user, inputting the picture configuration data, the picture quality and the picture scene into a model which has been trained for picture optimization, and outputting parameters for picture optimization of the target video frame and a confidence degree of the corresponding parameters through the model which has been trained for picture optimization; dividing a picture of the target video frame into regions to obtain picture partitions, and optimizing any picture partition according to the element region of all picture elements, the parameters and the confidence degree of the corresponding parameters to obtain an optimized picture partition; obtaining an optimized target video frame according to all optimized picture partitions, and playing and displaying the optimized target video frame.

2. The method of claim 1, wherein, The step of analyzing the picture of the target video frame to determine the picture scene of the target video frame comprises the following steps: determining a hue value of any pixel in the picture of the target video frame; determining a hue distribution feature of the target video frame according to the hue values of all pixels; performing scene recognition on the picture of the target video frame according to the hue distribution feature to obtain the picture scene.

3. The method of claim 1, wherein, The step of analyzing the picture of the target video frame to determine the picture quality of the target video frame comprises the following steps: determining a luminance value, a gradient value and a first chroma value of any pixel in the picture of the target video frame; determining a maximum luminance value and a minimum luminance value from all luminance values, and determining a contrast score of the target video frame according to the maximum luminance value and the minimum luminance value; determining a sharpness score of the target video frame according to the gradient values of all pixels in the target video frame; obtaining a second chroma value of each pixel in a reference video frame, and determining a color accuracy score of the target video frame according to the first chroma values of all pixels in the target video frame and the second chroma values of all pixels in the reference video; determining the picture quality according to the contrast score, the sharpness score and the color accuracy score.

4. The method of Claim 1, wherein, The step of analyzing the picture of the target video frame to determine the element region of the picture element contained in the target video frame comprises the following steps: analyzing the picture of the target video frame through an optical character recognition technology to determine a text element and an element region of the corresponding text element contained in the target video frame; analyzing the picture of the target video frame through a preset target recognition algorithm to determine a face element, an element region of the corresponding face element, an article element and an element region of the corresponding article element contained in the target video frame.

5. The method of Claim 1, wherein, The step of optimizing any picture partition according to the element region of all picture elements, the parameters and the confidence degree of the corresponding parameters to obtain an optimized picture partition comprises the following steps: For any picture partition, according to element regions of all picture elements, determine element regions contained in the picture partition, according to the picture partition and the element regions contained in the picture partition, determine a region proportion of picture elements in the picture partition; According to the region proportion, determine a weight of the picture partition, according to the weight, all parameters and confidence degrees of corresponding parameters, optimize the picture partition to obtain an optimized picture partition.

6. The method of video picture optimization of claim 5, wherein, According to the weight, all parameters and confidence degrees of corresponding parameters, optimize the picture partition to obtain an optimized picture partition, including: For any parameter, according to the confidence degree of the parameter, determine an initial optimization intensity of the parameter; According to the weight, adjust the initial optimization intensity to obtain a target optimization intensity; According to all parameters and target optimization intensities of corresponding parameters, perform picture optimization on the picture partition to obtain the optimized picture partition.

7. The method of Claim 1, wherein, According to all optimized picture partitions, obtain an optimized target video frame, and display the optimized target video frame, including: Smooth all optimized picture partitions in a spatial dimension to obtain the optimized target video frame; Obtain a previous video frame corresponding to the target video frame, smooth the previous video frame corresponding to the optimized target video frame and the optimized target video frame in a time dimension, and display the optimized target video frame.

8. A video picture optimization apparatus, characterized by comprising: Including: A picture analysis module is configured to acquire a target video frame to be displayed from a video source in real time, analyze a picture of the target video frame, and determine picture quality, a picture scene and element regions of picture elements contained in the target video frame; A model prediction module is configured to acquire picture configuration data of a user, input the picture configuration data, the picture quality and the picture scene into a model that has been trained for picture optimization, and output parameters for picture optimization of the target video frame and confidence degrees of corresponding parameters through the model that has been trained for picture optimization; A picture optimization module is configured to divide a picture of the target video frame into picture partitions, optimize any picture partition according to element regions of all picture elements, parameters and confidence degrees of corresponding parameters, and obtain an optimized picture partition. A picture display module is configured to obtain an optimized target video frame from all optimized picture partitions, and display the optimized target video frame.

9. A computer device, comprising: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the video picture optimization method of any one of claims 1-7 when executing the computer program.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the video picture optimization method of any one of claims 1-7.

Images