Video coding cross-component prediction method and system based on Gaussian process regression

Abstract

The invention discloses a video coding cross-component prediction method and system based on Gaussian process regression, and the method comprises the steps: obtaining a reference pixel of a reconstruction block from a brightness component, and enabling the reference pixel to serve as the input of a cross-component prediction model; according to the reference pixel, reference area selection is completed through a codec, and then a first reconstruction pixel is selected according to the reference area; according to a given first threshold value, a prediction model can be established for brightness pixels with different intensities according to the size of the first threshold value and the current pixel intensity, and then a second reconstruction pixel is selected through the prediction model; constructing a Gaussian regression model according to the first reconstructed pixel and the second reconstructed pixel; and performing cross-component prediction on the current coding unit according to the Gaussian regression model to obtain a video coding cross-component prediction result. According to the embodiment of the invention, the prediction accuracy can be improved, the problem of correlation between brightness and chromaticity in a video coding process is solved, and the method can be widely applied to the technical field of computers.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a video coding cross-component prediction method and system based on Gaussian process regression. Background Art

[0002] Traditional cross-component linear regression models, such as the Cross-Component Linear Model (CCLM), can only capture simple linear relationships when dealing with the relationship between brightness and chrominance components, and have difficulty dealing with complex nonlinear relationships. In the video encoding process, there is a correlation problem between brightness and chrominance. How to deeply capture the complex relationship between brightness and chrominance components in video signals has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to propose a video coding cross-component prediction method and system based on Gaussian process regression, which can improve the accuracy of prediction and solve the correlation problem between brightness and chrominance in the video coding process.

[0004] To achieve the above object, an embodiment of the present invention provides a video coding cross-component prediction method based on Gaussian process regression, comprising the following steps:

[0005] Obtaining reference pixels of the reconstructed block from the luminance component, wherein the reference pixels are used as input of a cross-component prediction model;

[0006] According to the reference pixel, a reference area is selected by a codec, and then a first reconstructed pixel is selected according to the reference area;

[0007] According to a given first threshold, a prediction model can be established for brightness pixels of different intensities according to the first threshold value and the current pixel intensity, and then a second reconstructed pixel is selected through the prediction model;

[0008] Constructing a Gaussian regression model according to the first reconstructed pixels and the second reconstructed pixels;

[0009] The current coding unit is cross-component predicted according to the Gaussian regression model to obtain a video coding cross-component prediction result.

[0010] In some embodiments, obtaining reference pixels of the reconstructed block from the luminance component comprises the following steps:

[0011] Get the brightness reconstruction buffer and the chrominance reconstruction buffer. In the YUV420 format, if the chrominance area corresponds to multiple brightness blocks, take the brightness coding unit corresponding to the center point;

[0012] The top and left luminance reconstructed pixels are downsampled to match the corresponding chrominance components;

[0013] When downsampling the luminance reference pixel, the selection of the sampling filter is determined by the sequence parameter set or the code stream syntax.

[0014] In some embodiments, the step of selecting a reference area by a codec based on the reference pixel comprises the following steps:

[0015] Specify the width and height of the reference area, use the n rows on the top and left of the reference area for pixel reconstruction, and perform pixel expansion from the current coding unit of size WxH to ​​obtain reconstructed brightness pixels.

[0016] The reference region is selected using the reconstructed brightness pixels from the top or left.

[0017] In some embodiments, according to the given first threshold, a prediction model can be established for brightness pixels of different intensities according to the first threshold value and the current pixel intensity, including the following steps:

[0018] In the implementation process of selecting the reference area, the mean value of the brightness component is calculated as the first threshold, and the brightness component is divided into two parts according to the first threshold: a part lower than or equal to the first threshold and a part higher than the first threshold;

[0019] The brightness components of the two parts are used to train a Gaussian regression model; wherein the part lower than or equal to the first threshold is used to train to obtain a first model, and the part higher than the first threshold is used to train to obtain a second model;

[0020] In the process of cross-component prediction, the corresponding model is selected for prediction according to the current brightness pixel of the statement; specifically: if the brightness value of the current pixel is lower than or equal to the first threshold, the first model is used for prediction; if the brightness value of the current pixel is higher than the first threshold, the second model is used for prediction.

[0021] In some embodiments, constructing a Gaussian regression model according to the first reconstructed pixel and the second reconstructed pixel comprises the following steps:

[0022] The expression of the Gaussian process regression model is determined as: C = f(Y) = GP(μ(Y), k(Y, Y')), where μ(Y) is the mean function, k(Y, Y') is the covariance function, Y is the brightness pixel, and C is the juxtaposed chrominance pixel; GP() represents the Gaussian process;

[0023] According to the Gaussian process regression model, the Gaussian process is initialized and configured, and the initialization result of the mean function and the initialization result of the covariance function are determined;

[0024] According to the Gaussian process regression model, the Gaussian process model is conditioned, and then the posterior distribution of the Gaussian process is updated according to the result of the conditional processing.

[0025] In some embodiments, the step of performing conditional processing of the Gaussian process model according to the Gaussian process regression model, and then updating the posterior distribution of the Gaussian process according to the result of the conditional processing, comprises the following steps:

[0026] According to the newly added sample points, the mean function is updated according to the observed data. The update formula of the mean function is: μ post (Y) = μ prior (Y)+K y,Y (K Y,Y +σ 2 I) -1 (C-μ prior (Y)), where μ post (Y) represents the updated mean function; μ prior (T) represents the prior mean function; K y,Y Represents the covariance matrix of the new sample point y and the existing sample point Y; K Y,Y represents the covariance matrix between existing sample points Y; σ represents the noise parameter; I represents the unit matrix; C represents the new observation value;

[0027] When there is no observation data, the covariance matrix is ​​a diagonal matrix: when new sample points are included in the model, the covariance matrix is ​​updated using the Cholesky decomposition method; when there is new observation data, the new sample points are included in the model by updating the Cholesky decomposition matrix;

[0028] The expression of the autocovariance a of the new sample point is a=k(y,y)+σ, where k(y,y) is the autocovariance of the new sample y and σ is the noise parameter.

[0029] The expression of the covariance vector b of the new sample point and the existing sample point is: b = [k(y, y1), k(y, y2), ..., k(y, y n )] T , where y n is the brightness value of the existing sample point;

[0030] In the process of updating the Cholesky decomposition matrix L, the expression of the autocovariance term a′ of the new sample point is: Then update the matrix L as:

[0031] L 11 =a′

[0032] L 12 = -a′·b·L

[0033] L 21 =-L·b T ·a′

[0034] L 22 =L+L·b T ·a′·b·L

[0035] Among them, b T ·L·b is the inner product of the covariance vector of the existing sample point and the new sample point.

[0036] In some embodiments, performing cross-component prediction on the current coding unit according to the Gaussian regression model comprises the following steps:

[0037] Use the updated mean function to perform pixel prediction, calculate the covariance matrix between the new sample point Y* and the existing sample point Y, and calculate the covariance matrix between the existing sample points Y;

[0038] Determine the mean function with predicted values ​​and obtain the result of cross-component prediction;

[0039] Among them, the expression of the mean function with predicted value is:

[0040]

[0041] The expression of the prediction result across components is:

[0042] predC=μ ppst (Y * )

[0043] Among them, μ post () represents the mean function with predicted value; μ prior () represents the prior mean function; Represents the predicted point Y * The covariance matrix with the existing sample points Y; K Y，Y represents the covariance matrix between existing sample points Y; σ represents the noise parameter; I represents the identity matrix; C represents the new observation value; predC represents the prediction result across components.

[0044] Another aspect of the embodiment of the present invention further provides a video coding cross-component prediction system based on Gaussian process regression, including:

[0045] The first module is used to obtain reference pixels of the reconstructed block from the luminance component, and the reference pixels are used as input of the cross-component prediction model:

[0046] A second module is used to select a reference area through a codec according to the reference pixel, and then select a first reconstructed pixel according to the reference area;

[0047] The third module is used to establish a prediction model for brightness pixels of different intensities according to a given first threshold value and the current pixel intensity, and then select a second reconstructed pixel through the prediction model;

[0048] A fourth module, configured to construct a Gaussian regression model according to the first reconstructed pixels and the second reconstructed pixels;

[0049] The fifth module is used to perform cross-component prediction on the current coding unit according to the Gaussian regression model to obtain a cross-component prediction result of video coding.

[0050] To achieve the above objective, another aspect of an embodiment of the present invention provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned method when executing the computer program.

[0051] To achieve the above objective, another aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method is implemented.

[0052] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the above method.

[0053] The embodiments of the present invention include at least the following beneficial effects: The present invention provides a method and system for cross-component prediction of video coding based on Gaussian process regression, the scheme obtains reference pixels of the reconstructed block from the luminance component, and the reference pixels are used as the input of the cross-component prediction model; according to the reference pixels, the reference area selection is completed by the codec, and then the first reconstructed pixel is selected according to the reference area; according to a given first threshold, a prediction model can be established for luminance pixels of different intensities according to the first threshold value and the current pixel intensity, and then the second reconstructed pixel is selected through the prediction model; according to the first reconstructed pixel and the second reconstructed pixel, a Gaussian regression model is constructed; according to the Gaussian regression model, the current coding unit is cross-component predicted to obtain the video coding cross-component prediction result. The embodiments of the present invention can improve the accuracy of prediction and solve the correlation problem between luminance and chrominance in the video coding process. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a schematic diagram of an implementation environment provided by an embodiment of the present invention;

[0055] Figure 2 is a flow chart of the overall steps provided by an embodiment of the present invention;

[0056] Figure 3 is a flowchart of specific implementation steps provided by an embodiment of the present invention;

[0057] Figure 4 is a schematic diagram of a coding region provided by an embodiment of the present invention;

[0058] Figure 5 is an example diagram of a reference area selected in an embodiment of the present invention;

[0059] Figure 6 It is an example of multi-model expansion based on brightness pixel intensity provided by an embodiment of the present invention;

[0060] Figure 7 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present invention. They are only examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the attached claims.

[0062] It is understood that the terms "first", "second", etc. used in the present invention may be used herein to describe various concepts, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0063] The terms "at least one", "multiple", "each", "any", etc. used in the present invention, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0064] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0065] Before describing the embodiments of the present invention in detail, some related technologies involved in the embodiments of the present invention are first described as follows:

[0066] 1. Cross-Component Linear Model (CCLM) Cross-Component Linear Model:

[0067] Cross-Component Linear Model (CCLM) is a method used for chrominance prediction in video coding, which obtains chrominance values ​​based on linear transformation of reconstructed luminance pixels.

[0068] The specific implementation of CCLM involves the following process:

[0069] 1. Use the reconstructed luma component values ​​(obtained through the downsampling process) to predict the chroma values.

[0070] 2. The prediction function is defined as pred_C(i,j)=α*rec_L'(i,j)+β, where pred_C is the predicted chrominance value and rec_L' represents the reconstructed value of the luminance component.

[0071] 3. The determination of coefficients α and β depends on the brightness and chrominance values ​​of the adjacent coding units (CU), which can be calculated by the following formula:

[0072] α=(Ya-Yb) / (Xa-Xb),

[0073] β=Yb-α*Xb,

[0074] Among them, Ya is the maximum brightness pixel value that has been downsampled, Xa is the chrominance value corresponding to Ya, Yb is the minimum brightness pixel value that has been downsampled, and Xb is the chrominance value corresponding to Yb.

[0075] In addition to using all the upper and left luminance reference pixels to calculate the linear model parameters, CCLM also provides two additional modes, called LMA and LML modes. The LMA mode uses only the upper reference pixels, while the LML mode uses only the left reference pixels. This increases the flexibility of predicting chrominance and allows adaptation to different video content. The calculation of the linear model parameters not only occurs at the encoder end, but the decoder also performs the same operation. Therefore, the values ​​of α and β do not need to be recorded in the bitstream, reducing additional bitstream overhead.

[0076] 2. Convolutional Cross-Component Model (CCCM) convolutional cross-component model:

[0077] Convolutional Cross-Component Model (CCCM) is a convolutional model for chrominance prediction, similar to Cross-Component Linear Model (CCLM), which is based on the idea of ​​predicting chrominance pixels from reconstructed luma pixels. CCCM takes into account the relationship between luma and chroma components and uses a downsampled version of the luma reconstruction block to match the size of the chroma block.

[0078] The basic steps of the module are as follows:

[0079] 1. Before predicting the chroma pixels, the luma reconstruction block is downsampled to match the size of the chroma block.

[0080] 2. Apply a 7-tap convolution filter to process the luma samples and calculate the chroma predicted pixels.

[0081] The specific prediction function is expressed in the following form:

[0082] predChromaVal=c0 C+c1 N+c2 S+c3 E+c4 W+c5 P+c6 B

[0083] Among them, C is the brightness sample at the corresponding position of the current chrominance sample, N, S, E, W are the adjacent samples of the current brightness sample, and P is a nonlinear term calculated as follows:

[0084] P=(C*C+midVal)>>bitDepth

[0085] where midVal is a bias term representing a scalar offset between the input and output, typically set to the mid-chroma value.

[0086] 3. Calculate the filter coefficients c_n by minimizing the mean square error (MSE) between the predicted and reconstructed chrominance samples. This can be done by solving equations using numerical methods such as LDL decomposition.

[0087] Similar to CCLM, CCCM provides the option to use a single model or a multi-model variant. The multi-model variant uses two models, one derived for samples above the average brightness reference value and another for the remaining samples (below the average brightness reference value). The multi-model CCCM mode can be selected if the prediction unit (PU) has at least 128 reference samples available.

[0088] The reference region consists of 2 or 6 rows of chroma samples above and to the left of the PU. How many neighbor samples are used by the single model CCCM to derive the CCCM model parameters is determined by the template cost. For the multi-model CCCM mode, the two candidate models use 6 rows of neighboring luma samples or luma samples that coincide with the current chroma block position to derive the average, dividing the samples into two groups. The cost is calculated by applying the candidate CCP (2 or 6 rows) on the template and calculating the total absolute difference (SAD) between the CCP predicted samples and the reconstructed samples in the template.

[0089] The video coding cross-component prediction method and system based on Gaussian process regression provided by the embodiment of the present invention relate to the field of computer technology. The video coding cross-component prediction method based on Gaussian process regression provided by the embodiment of the present invention can be applied to a terminal, can also be applied to a server, and can also be software running in a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, and a car terminal, etc., but is not limited to this; the server side can be configured as an independent physical server, or a server cluster or distributed system composed of multiple physical servers, and can also be configured to provide cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The cloud server of basic cloud computing services, the server can also be a node server in a blockchain network; the software can be an application that implements a video coding cross-component prediction method based on Gaussian process regression, etc., but is not limited to the above forms.

[0090] The present invention can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present invention can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present invention can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0091] like Figure 1 FIG. 1 is a schematic diagram of an implementation environment provided by an embodiment of the present invention. Figure 1The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected to a network wirelessly or wired to complete data transmission and exchange.

[0092] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big data and artificial intelligence platforms.

[0093] In addition, the server 101 can also be a node server in the blockchain network. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanism, and encryption algorithm.

[0094] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal 102 may also be a vehicle-mounted terminal of various device types described above, but is not limited thereto. The terminal 102 and the server 101 may be directly or indirectly connected via wired or wireless communication, which is not limited in this embodiment of the present invention.

[0095] Based on the example Figure 1 In the implementation environment shown, an embodiment of the present invention provides a video coding cross-component prediction method based on Gaussian process regression. The following is explained using the application of the video coding cross-component prediction method based on Gaussian process regression in the server 101 as an example. It can be understood that the method can also be applied to the terminal 102.

[0096] Reference Figure 2 , Figure 2 The flowchart of the Gaussian process regression-based video coding cross-component prediction method applied to the server provided by the embodiment of the present invention, the execution subject of the method can be any of the aforementioned computer devices (including servers or terminals). Figure 2 , the method may include the following steps:

[0097] Obtaining reference pixels of the reconstructed block from the luminance component, wherein the reference pixels are used as input of a cross-component prediction model;

[0098] According to the reference pixel, a reference area is selected by a codec, and then a first reconstructed pixel is selected according to the reference area;

[0099] According to a given first threshold, a prediction model can be established for brightness pixels of different intensities according to the first threshold value and the current pixel intensity, and then a second reconstructed pixel is selected through the prediction model;

[0100] Constructing a Gaussian regression model according to the first reconstructed pixels and the second reconstructed pixels;

[0101] The current coding unit is cross-component predicted according to the Gaussian regression model to obtain a video coding cross-component prediction result.

[0102] In some embodiments, obtaining reference pixels of the reconstructed block from the luminance component comprises the following steps:

[0103] Get the brightness reconstruction buffer and the chrominance reconstruction buffer. In the YUV420 format, if the chrominance area corresponds to multiple brightness blocks, take the brightness coding unit corresponding to the center point;

[0104] The top and left luminance reconstructed pixels are downsampled to match the corresponding chrominance components;

[0105] When downsampling the luminance reference pixel, the selection of the sampling filter is determined by the sequence parameter set or the code stream syntax.

[0106] In some embodiments, the step of selecting a reference area by a codec based on the reference pixel comprises the following steps:

[0107] Specify the width and height of the reference area, use the n rows on the top and left of the reference area for pixel reconstruction, and perform pixel expansion from the current coding unit of size WxH to ​​obtain reconstructed brightness pixels.

[0108] The reference region is selected using the reconstructed brightness pixels from the top or left.

[0109] In some embodiments, according to the given first threshold, a prediction model can be established for brightness pixels of different intensities according to the first threshold value and the current pixel intensity, including the following steps:

[0110] In the implementation process of selecting the reference area, the mean value of the brightness component is calculated as the first threshold, and the brightness component is divided into two parts according to the first threshold: a part lower than or equal to the first threshold and a part higher than the first threshold;

[0111] The brightness components of the two parts are used to train a Gaussian regression model; wherein the part lower than or equal to the first threshold is used to train to obtain a first model, and the part higher than the first threshold is used to train to obtain a second model;

[0112] In the process of cross-component prediction, the corresponding model is selected for prediction according to the current brightness pixel of the statement; specifically: if the brightness value of the current pixel is lower than or equal to the first threshold, the first model is used for prediction; if the brightness value of the current pixel is higher than the first threshold, the second model is used for prediction.

[0113] In some embodiments, constructing a Gaussian regression model according to the first reconstructed pixel and the second reconstructed pixel comprises the following steps:

[0114] The expression of the Gaussian process regression model is determined as: C = f(Y) = GP(μ(Y), k(Y, Y')), where μ(Y) is the mean function, k(Y, Y') is the covariance function, Y is the brightness pixel, and C is the juxtaposed chrominance pixel; GP() represents the Gaussian process;

[0115] According to the Gaussian process regression model, the Gaussian process is initialized and configured, and the initialization result of the mean function and the initialization result of the covariance function are determined;

[0116] According to the Gaussian process regression model, the Gaussian process model is conditioned, and then the posterior distribution of the Gaussian process is updated according to the result of the conditional processing.

[0117] In some embodiments, the step of performing conditional processing of the Gaussian process model according to the Gaussian process regression model, and then updating the posterior distribution of the Gaussian process according to the result of the conditional processing, comprises the following steps:

[0118] According to the newly added sample points, the mean function is updated according to the observed data. The update formula of the mean function is: μ post (Y) = μ prior (Y)+K y，Y (K Y，Y +σ 2 I) -1 (C-μ prior (Y)), where μ post (Y) represents the updated mean function; μ prior (Y) represents the prior mean function; K y，Y Represents the covariance matrix of the new sample point y and the existing sample point Y; K Y，Y represents the covariance matrix between existing sample points Y; σ represents the noise parameter; I represents the unit matrix; C represents the new observation value;

[0119] When there is no observation data, the covariance matrix is ​​a diagonal matrix: when new sample points are included in the model, the covariance matrix is ​​updated using the Cholesky decomposition method; when there is new observation data, the new sample points are included in the model by updating the Cholesky decomposition matrix;

[0120] The expression of the autocovariance a of the new sample point is a=k(y, y)+σ, where k(y, y) is the autocovariance of the new sample y and σ is the noise parameter.

[0121] The expression of the covariance vector b of the new sample point and the existing sample point is: b = [k(y, y1), k(y, y2), ..., k(y, y n )] T , where y n is the brightness value of the existing sample point;

[0122] In the process of updating the Cholesky decomposition matrix L, the expression of the autocovariance term a′ of the new sample point is: Then update the matrix L as:

[0123] L 11 =a′

[0124] L 12 = -a′·b·L

[0125] L 21 =-L·b T ·a′

[0126] L 22 =L+L·b T ·a′·b·L

[0127] Among them, b T ·L·b is the inner product of the covariance vector of the existing sample point and the new sample point.

[0128] In some embodiments, performing cross-component prediction on the current coding unit according to the Gaussian regression model comprises the following steps:

[0129] Use the updated mean function to perform pixel prediction, calculate the covariance matrix between the new sample point Y* and the existing sample point Y, and calculate the covariance matrix between the existing sample points Y;

[0130] Determine the mean function with predicted values ​​and obtain the result of cross-component prediction;

[0131] Among them, the expression of the mean function with predicted value is:

[0132]

[0133] The expression of the prediction result across components is:

[0134] predC=μ post (Y * )

[0135] Among them, μpost () represents the mean function with predicted value; μ prior () represents the prior mean function; Represents the predicted point Y * The covariance matrix with the existing sample points Y; K Y,Y represents the covariance matrix between existing sample points Y; σ represents the noise parameter; I represents the identity matrix; C represents the new observation value; predC represents the prediction result across components.

[0136] The following describes the specific implementation process of the present invention in detail by taking a specific application scenario as an example:

[0137] The cross-component prediction method based on Gaussian process regression described in the embodiment of the present invention is mainly used in the intra-frame image reconstruction process in video coding. The method predicts the chrominance component through the reconstructed luminance component, thereby achieving efficient cross-component prediction. Figure 3 As shown, on the encoder and decoder sides, the method sequentially executes the same S100, S200, S300, S400, and S500 processes to ensure the consistency and accuracy of the encoding and decoding prediction algorithm.

[0138] A.S100 obtains the reference area

[0139] The main responsibility of the S100 module is to obtain the reference pixels of the reconstructed block from the luminance (Luma) component. These reference pixels are used to predict the cross-component prediction model input of the chrominance (Chroma) component. In this process:

[0140] 1. Get the brightness reconstruction buffer and the chrominance reconstruction buffer. The current encoding context is as follows: Figure 4 In the YUV420 format, if the chroma area corresponds to multiple luminance blocks, the luminance coding unit (Luma CU) corresponding to the center point is taken.

[0141] 2. To ensure that the luma block has the same width and height as the chroma block, the top and left luma reconstructed pixels can be downsampled to match the corresponding chroma components. When downsampling the luma reference pixels, the sampling filter selection can be indicated by the sequence parameter set (SPS) or specified by the code stream syntax.

[0142] B.S200 reference area selection

[0143] The S200 module will complete the coding area selection implemented by the codec. The use of reference pixels follows the method that can be selected as follows Figure 5 As shown, including:

[0144] 1. The reference area can specify a certain width and height value, and use n rows of pixels on the top and left to reconstruct the pixels. At the same time, the current coding unit (CU) of size WxH can be expanded to a certain extent, such as 0 pixels, W pixels, or H pixels.

[0145] In the implementation, the reference area consists of 2 or 6 rows of chroma samples above and to the left of the PU, aligned with the reference area obtained by the CCCM method.

[0146] 2. The reference area can be selected in the following ways, such as Figure 5 As shown:

[0147] Only the top or left reconstructed brightness pixels are used, which are called Top (T, top mode) and Left (L, left mode), respectively. All top and left reference pixels are used, which is recorded as LT (Left & Top) mode.

[0148] C.S300 multi-model expansion

[0149] In addition to using S200 reference area templates in different directions, this algorithm is also applicable to multi-model expansion implementation. According to the specified given threshold, a prediction model can be established for brightness pixels of different intensities based on the threshold size and the current pixel intensity, which can further improve the accuracy of model prediction.

[0150] 1. In the process of obtaining the reference area in S200, the mean value of the brightness component can be calculated and used as a threshold (modelThr). The brightness component is divided into two parts according to the threshold: a part lower than or equal to the threshold (Model 1) and a part higher than the threshold (Model 2), such as Figure 6 As shown, the abscissa (Colocated Luma Value) represents the brightness value, and the ordinate (Chroma Value) represents the chromaticity value.

[0151] 2. In the prediction model training process of S400, two models are trained based on the threshold value.

[0152] 1) For Model 1, only samples whose brightness component is lower than or equal to the threshold are used to train the Gaussian process regression model.

[0153] 2) For Model 2, only samples with brightness components above the threshold are used to train the Gaussian process regression model.

[0154] 3. In the cross-component prediction process of S500, the corresponding model is selected for the current brightness pixel of the statement for prediction.

[0155] 1) If the brightness value of the current pixel is lower than or equal to the threshold modelThr, Model 1 is used for prediction.

[0156] 2) If the brightness value of the current pixel is higher than the threshold modelThr, Model 2 is used for prediction.

[0157] D. Training of the S400 Gaussian process regression model

[0158] A Gaussian regression model may be established based on the reconstructed pixels selected by S200 and S300.

[0159] Gaussian Process Regression (GPR) is a non-parametric regression method based on Bayesian inference. The core idea is to model the spatial relationship between components as a random process. Any finite-dimensional distribution of this process is a Gaussian distribution. Using the mean function of the Gaussian random process, we can perform prediction and output of chrominance pixels based on the input luminance pixels.

[0160] The training process of the Gaussian regression model is the process of conditioning new samples. The Gaussian process regression model can continuously update its posterior distribution based on the input cross-component pixel pairs [Luma, Chroma] and capture the data fitting relationship.

[0161] Let Y be the brightness pixel and C be the collocated chrominance pixel. The Gaussian process regression model can be expressed as

[0162] C=f(Y)=GP(μ(Y),k(Y,Y'))

[0163] Among them, μ(Y) is the mean function, and k(Y,Y') is the covariance function (or kernel function) used to describe the similarity between different input points.

[0164] 1. Gaussian process initialization

[0165] 1) Initialization of the mean function

[0166] The mean function is usually set to a constant or zero, representing an a priori assumption about the input data.

[0167] μ(Y)=0

[0168] Or take the chromaticity mean of the template area as the mean function, that is,

[0169]

[0170] Where N is the number of pixels in the template area.

[0171] 2) Kernel function definition

[0172]

[0173] Used to measure the similarity of brightness pixels.

[0174] 2. Conditioning of Gaussian Process Model

[0175] Conditioning is the training process of the Gaussian model, which updates the posterior distribution of the Gaussian process through new data (Y, C).

[0176] 2.1 Update the mean function

[0177] As new sample points are added, the mean function will be updated according to the observed data. Specifically, the update formula of the mean function is:

[0178] μ post (Y) = μ prior (Y)+K y，Y (K Y,Y +σ 2 I) -1 (C-μ prior (Y)

[0179] Where: μ_prior(Y) is the prior mean function. K_{y, Y} is the covariance matrix between the new sample point y and the existing sample point Y. K_{Y, Y} is the covariance matrix between the existing sample points Y. σ is the noise parameter. I is the identity matrix. C is the new observation.

[0180] 2.2 Update the covariance matrix

[0181] When there is no observed data, the covariance matrix is ​​a diagonal matrix. When new sample points are included in the model, the Cholesky decomposition method can be used to update the covariance matrix K to achieve efficient solution. That is,

[0182] K=L·L T

[0183] When there is new observation data (y, c), the new sample points can be incorporated into the model by updating the Cholesky decomposition matrix L. There are:

[0184] 1) Autocovariance of new sample points

[0185] a=k(y,y)+σ

[0186] Where k(y, y) is the autocovariance of the new sample y and σ is the noise parameter.

[0187] 2) Covariance vector of new sample points and existing sample points

[0188] b=[k(y,y1),k(y,y2),…,k(y,yn )] T

[0189] Among them, y_i is the brightness value of the existing sample point.

[0190] 3) Update the Cholesky decomposition matrix L

[0191] Let the autocovariance term of the new sample point be

[0192]

[0193] Among them, b T ·L·b is the inner product of the covariance vector of the existing sample point and the new sample point.

[0194] The L matrix can be updated:

[0195] L 11 =a′

[0196] L 12 = -a′·b·L

[0197] L 21 =-L·b T ·a′

[0198] L 22 =L+L·b T ·a′·b·L

[0199] For each reconstructed cross-component pixel pair [Luma, Chroma] selected by S200 and S300, it will be used as a training sample to perform the above-mentioned Gaussian process regression model training process, which enables the Gaussian process model to continuously adapt to new observation data and achieve more accurate predictions.

[0200] In implementation, Gaussian process regression models can be trained for the chrominance components Cb and Cr respectively.

[0201] E.S500 uses Gaussian process regression for cross-component prediction

[0202] The Gaussian process model established in S400 can perform cross-component prediction on the current Cu. For the reconstructed luminance pixel Y* of the current Cu, it is used as the input of the Gaussian process model to predict its collocated chrominance value. When the downsampling method of the luminance component is adopted, it should be consistent with the operation in S100.

[0203] In the pixel prediction process, the updated mean function can be used for prediction.

[0204] 1. Calculate the covariance matrix K_{Y*, Y} of the new sample point Y* and the existing sample point Y.

[0205] 2. Calculate the covariance matrix K_{Y,Y} between the existing sample points Y.

[0206] Mean function with predicted values

[0207]

[0208] Taking this as the result of cross-component prediction, we have

[0209] predC=μ post (Y * )

[0210] At the same time, the prediction value is clipped to ensure that it falls within the valid pixel intensity range [0, 2 bitdepth -1], for example, in a 10-bit YUV sequence, the effective range of pixel intensity extends from 0 to 1023. That is,

[0211] predC′=min(max(predC, 0), 1023).

[0212] C. Solution Implementation

[0213] The cross-component prediction method described in the embodiment of the present invention is applicable to intra-frame prediction and inter-frame prediction modules of video coding, and can be applied to video coding reference software platforms such as VTM, ECM, AV1, HPM, etc. It is applicable to the encoding and decoding of sequences such as YUV420 and YUV444.

[0214] The encoding and decoding methods described in the embodiments of the present invention can be evaluated for quality using indicators such as bpp, PSNR, SSIM, VMAF, and BDRate.

[0215] In intra-frame prediction, the method of the embodiment of the present invention can be enabled through a flag in the bitstream. When the flag is positive, it means that this module is enabled in intra-frame prediction to perform a chrominance prediction process based on Gaussian process regression.

[0216] In summary, in view of the problems existing in the prior art, this embodiment proposes a video coding cross-component prediction method based on Gaussian process regression, which aims to solve the correlation problem between brightness and chrominance in the video coding process. The algorithm can deeply capture the complex relationship between brightness and chrominance components in the video signal. By modeling under the framework of random processes, the algorithm not only provides a high degree of interpretability, but also can achieve more accurate results in the prediction process.

[0217] This embodiment designs a novel cross-component prediction algorithm. Traditional cross-component linear regression models such as CCLM and CCCM can only capture simple linear relationships when dealing with the relationship between brightness and chrominance components, and it is difficult to deal with complex nonlinear relationships. Gaussian process regression, as a powerful nonlinear modeling tool, can accurately capture and predict the complex nonlinear relationship between brightness and chrominance, and adapt to different types of data distribution and noise characteristics, thereby providing more accurate prediction results.

[0218] Another aspect of the embodiment of the present invention further provides a video coding cross-component prediction system based on Gaussian process regression, including:

[0219] A first module is used to obtain reference pixels of a reconstructed block from a luminance component, wherein the reference pixels are used as input of a cross-component prediction model;

[0220] A second module is used to select a reference area through a codec according to the reference pixel, and then select a first reconstructed pixel according to the reference area;

[0221] The third module is used to establish a prediction model for brightness pixels of different intensities according to a given first threshold value and the current pixel intensity, and then select a second reconstructed pixel through the prediction model;

[0222] A fourth module, configured to construct a Gaussian regression model according to the first reconstructed pixels and the second reconstructed pixels;

[0223] The fifth module is used to perform cross-component prediction on the current coding unit according to the Gaussian regression model to obtain a cross-component prediction result of video coding.

[0224] It can be understood that the contents of the above method embodiments are all applicable to the present system embodiments, the functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0225] An embodiment of the present invention further provides an electronic device, the electronic device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the above-mentioned video coding cross-component prediction method based on Gaussian process regression when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0226] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0227] See also Figure 7 , Figure 7 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0228] The processor 701 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention.

[0229] The memory 702 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 702, and the processor 701 calls and executes the video coding cross-component prediction method based on Gaussian process regression in the embodiment of the present invention;

[0230] Input / output interface 703, used to implement information input and output;

[0231] Communication interface 704, used to realize communication interaction between the device and other devices, which can be realized through wired mode (such as USB, network cable, etc.) or wireless mode (such as mobile network, WIFI, Bluetooth, etc.);

[0232] A bus 705 that transmits information between the various components of the device (e.g., the processor 701, the memory 702, the input / output interface 703, and the communication interface 704);

[0233] The processor 701 , the memory 702 , the input / output interface 703 and the communication interface 704 are connected to each other in communication within the device via a bus 705 .

[0234] An embodiment of the present invention further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the video coding cross-component prediction method based on Gaussian process regression is implemented.

[0235] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0236] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0237] It should be noted that in various specific embodiments of the present invention, when it comes to the need to perform relevant processing based on data related to user identity or characteristics such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first, and the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiment of the present invention needs to obtain the user's sensitive personal information, it will obtain the user's separate permission or consent through a pop-up window or jump to a confirmation page, and after clearly obtaining the user's separate permission or consent, it will obtain the necessary user-related data for the normal operation of the embodiment of the present invention.

[0238] The embodiments described in the embodiments of the present invention are intended to more clearly illustrate the technical solutions of the embodiments of the present invention, and do not constitute a limitation on the technical solutions provided by the embodiments of the present invention. Those skilled in the art can appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present invention are also applicable to similar technical problems.

[0239] Those skilled in the art will appreciate that the technical solutions shown in the figures do not limit the embodiments of the present invention and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0240] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0241] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0242] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0243] It should be understood that in the present invention, "at least one (item)" refers to one or more, and "plurality" refers to two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can represent: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0244] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0245] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0246] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0247] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including multiple instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store programs.

[0248] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the embodiments of the present invention is not limited thereby. Any modification, equivalent substitution and improvement made by those skilled in the art without departing from the scope and essence of the embodiments of the present invention shall be within the scope of the rights of the embodiments of the present invention.

Claims

1. A video coding cross-component prediction method based on Gaussian process regression, characterized in that: The following steps are involved: Obtaining reference pixels of the reconstructed block from the luminance component, wherein the reference pixels are used as input of a cross-component prediction model; According to the reference pixel, a reference area is selected by a codec, and then a first reconstructed pixel is selected according to the reference area; According to a given first threshold, a prediction model can be established for brightness pixels of different intensities according to the first threshold value and the current pixel intensity, and then a second reconstructed pixel is selected through the prediction model; Constructing a Gaussian regression model according to the first reconstructed pixels and the second reconstructed pixels; The current coding unit is cross-component predicted according to the Gaussian regression model to obtain a video coding cross-component prediction result.

2. The method for cross-component prediction of video coding based on Gaussian process regression according to claim 1, characterized in that: The step of obtaining reference pixels of the reconstructed block from the brightness component comprises the following steps: Get the brightness reconstruction buffer and the chrominance reconstruction buffer. In the YUV420 format, if the chrominance area corresponds to multiple brightness blocks, take the brightness coding unit corresponding to the center point; The top and left luminance reconstructed pixels are downsampled to match the corresponding chrominance components; When downsampling the luminance reference pixel, the selection of the sampling filter is determined by the sequence parameter set or the code stream syntax.

3. The video coding cross-component prediction method based on Gaussian process regression according to claim 1, characterized in that: The step of selecting a reference area by using a codec according to the reference pixel comprises the following steps: Specify the width and height of the reference area, use the n rows on the top and left of the reference area for pixel reconstruction, and perform pixel expansion from the current coding unit of size WxH to ​​obtain reconstructed brightness pixels. The reference region is selected using the reconstructed brightness pixels from the top or left.

4. The video coding cross-component prediction method based on Gaussian process regression according to claim 1, characterized in that: According to the given first threshold, a prediction model can be established for brightness pixels of different intensities according to the first threshold value and the current pixel intensity, including the following steps: In the implementation process of selecting the reference area, the mean value of the brightness component is calculated as the first threshold, and the brightness component is divided into two parts according to the first threshold: a part lower than or equal to the first threshold and a part higher than the first threshold; The brightness components of the two parts are used to train a Gaussian regression model; wherein the part lower than or equal to the first threshold is used to train to obtain a first model, and the part higher than the first threshold is used to train to obtain a second model; In the process of cross-component prediction, the corresponding model is selected for prediction according to the current brightness pixel of the statement; specifically: if the brightness value of the current pixel is lower than or equal to the first threshold, the first model is used for prediction; if the brightness value of the current pixel is higher than the first threshold, the second model is used for prediction.

5. The method for cross-component prediction of video coding based on Gaussian process regression according to claim 1, characterized in that: The constructing of a Gaussian regression model according to the first reconstructed pixel and the second reconstructed pixel comprises the following steps: The expression of the Gaussian process regression model is determined as: C = f(Y) = GP(μ(Y), k(Y, Y')), where μ(Y) is the mean function, k(Y, Y') is the covariance function, Y is the brightness pixel, and C is the juxtaposed chrominance pixel; GP() represents the Gaussian process; According to the Gaussian process regression model, the Gaussian process is initialized and configured, and the initialization result of the mean function and the initialization result of the covariance function are determined; According to the Gaussian process regression model, the Gaussian process model is conditioned, and then the posterior distribution of the Gaussian process is updated according to the result of the conditional processing.

6. The method for cross-component prediction of video coding based on Gaussian process regression according to claim 5, characterized in that: The step of performing conditional processing of the Gaussian process model according to the Gaussian process regression model, and then updating the posterior distribution of the Gaussian process according to the result of the conditional processing, comprises the following steps: According to the newly added sample points, the mean function is updated according to the observed data. The update formula of the mean function is: μ post (Y) = μ prior (Y)+K y,Y (K Y,Y +σ 2 I) -1 (C-μ prior (Y)), where μ post (Y) represents the updated mean function; μ prior (Y) represents the prior mean function; K y,Y Represents the covariance matrix of the new sample point y and the existing sample point Y; K Y,Y represents the covariance matrix between existing sample points Y; σ represents the noise parameter; I represents the unit matrix; C represents the new observation value; When there is no observation data, the covariance matrix is ​​a diagonal matrix: when new sample points are included in the model, the covariance matrix is ​​updated using the Cholesky decomposition method; when there is new observation data, the new sample points are included in the model by updating the Cholesky decomposition matrix; The expression of the autocovariance a of the new sample point is a=k(y,y)+σ, where k(y,y) is the autocovariance of the new sample y and σ is the noise parameter. The expression of the covariance vector b between the new sample point and the existing sample point is: b = [k(y,y1),k(y,y2),…,k(y,y n )] T , where y n is the brightness value of the existing sample point; In the process of updating the Cholesky decomposition matrix L, the expression of the autocovariance term a′ of the new sample point is: Then update the matrix L as: L 11 =a ′ L 12 =-a ′ ·b·L L 21 =-L·b T ·a ′ L 22 =L+L·b T ·a ′ ·b·Y Among them, b T ·L·b is the inner product of the covariance vector of the existing sample point and the new sample point.

7. The method for cross-component prediction of video coding based on Gaussian process regression according to claim 1, characterized in that: The performing cross-component prediction on the current coding unit according to the Gaussian regression model comprises the following steps: Use the updated mean function to perform pixel prediction, calculate the covariance matrix between the new sample point Y* and the existing sample point Y, and calculate the covariance matrix between the existing sample points Y; Determine the mean function with predicted values ​​and obtain the result of cross-component prediction; Among them, the expression of the mean function with predicted value is: The expression of the prediction result across components is: beforeC=μ post (Y * ) Among them, μ post () represents the mean function with predicted value; μ prior () represents the prior mean function; Represents the predicted point Y * The covariance matrix with the existing sample points Y; K Y,Y represents the covariance matrix between existing sample points Y; σ represents the noise parameter; I represents the identity matrix; C represents the new observation value; predC represents the prediction result across components.

8. A video coding cross-component prediction system based on Gaussian process regression, characterized in that: include: A first module is used to obtain reference pixels of a reconstructed block from a luminance component, wherein the reference pixels are used as input of a cross-component prediction model; A second module is used to select a reference area through a codec according to the reference pixel, and then select a first reconstructed pixel according to the reference area; The third module is used to establish a prediction model for brightness pixels of different intensities according to a given first threshold value and the current pixel intensity, and then select a second reconstructed pixel through the prediction model; A fourth module, configured to construct a Gaussian regression model according to the first reconstructed pixels and the second reconstructed pixels; The fifth module is used to perform cross-component prediction on the current coding unit according to the Gaussian regression model to obtain a cross-component prediction result of video coding.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images