Sample value adaptive compensation method and device based on integrated circuit, equipment and storage medium

By using a preset sliding window in the integrated circuit to process the target pixel data of the sample value adaptive compensation algorithm in parallel, the problem of processing delay of the sample value adaptive compensation algorithm is solved, and the system's operating speed and computing efficiency are improved.

CN118921473APending Publication Date: 2024-11-08PENG CHENG LAB
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411050198.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-08

AI Technical Summary

Technical Problem

In the prior art, there is a large delay in the processing of sample adaptive compensation algorithms in integrated circuits, resulting in a decrease in the system operation speed.

Method used

The preset sliding window reads multiple target pixel data of the target encoding unit from the target memory, and performs parallel processing in the calculation core to reduce the individual processing of pixels and improve processing efficiency.

Benefits of technology

The parallel acceleration of the adaptive compensation algorithm for sample values ​​in integrated circuits is realized, which improves the calculation speed, reduces resource consumption, and improves the operating speed of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118921473A_ABST
    Figure CN118921473A_ABST
Patent Text Reader

Abstract

The invention discloses a sample value adaptive compensation method and device based on an integrated circuit, equipment and a storage medium, relates to the technical field of video coding, and discloses the sample value adaptive compensation method based on the integrated circuit. Comprising the following steps: reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window; temporarily storing the pixel data corresponding to each target pixel point to a target register, and determining a plurality of to-be-processed pixel points in a target middle area of the target register and the pixel data corresponding to each to-be-processed pixel point; and carrying out parallel sample value self-adaptive compensation processing on pixel data corresponding to each pixel point to be processed through the calculation kernel. By means of the mode, parallel acceleration of the sample value self-adaptive compensation algorithm in the integrated circuit is achieved, the calculation speed of the sample value self-adaptive compensation algorithm in the integrated circuit is increased, and meanwhile excessive resource consumption is not increased.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of video coding technology, and in particular to a sample value adaptive compensation method, device, equipment and storage medium based on an integrated circuit. Background Art

[0002] Audio Video Coding Standard, Gen3 (AVS3) is the third-generation audio and video codec standard independently developed by my country. It is the world's first audio and video codec technical standard for the 8K ultra-high-definition industry. The Sample Adaptive Offset (SAO) algorithm is an important component of the AVS3 coding standard, which affects the quality of the reconstructed image and the coding performance. The SAO algorithm is implemented for integrated circuits and is called the SAO module. The SAO module processes the largest coding unit (LCU) as a unit, and processes an image corresponding to an LCU, about 4096 pixels, each time it works. The input of SAO is usually an original image of the size of an LCU and a reconstructed image of the size of an LCU. In the implementation of integrated circuits, if each pixel is processed one by one, the time delay is at least 4096 cycles, which greatly reduces the operating speed of the entire encoder system.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of the present application is to provide a sample value adaptive compensation method, device, equipment and storage medium based on integrated circuits, aiming to solve the technical problem in the prior art that there is a large delay in the SAO algorithm processing pixels in the LCU, which greatly reduces the operating speed of the system.

[0005] To achieve the above object, the present application proposes a sample value adaptive compensation method based on integrated circuit, the method comprising:

[0006] Reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window;

[0007] Temporarily storing pixel data corresponding to each target pixel point in a target register, and determining a plurality of pixels to be processed in a target middle area of ​​the target register and pixel data corresponding to each pixel point to be processed;

[0008] The pixel data corresponding to each pixel point to be processed is subjected to parallel sample value adaptive compensation processing through the calculation kernel.

[0009] In one embodiment, the step of reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window includes:

[0010] When the current position of the preset sliding window is the starting edge position of the target coding unit, aligning the edge position of the preset sliding window with the unit edge of the target coding unit;

[0011] Pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory according to the alignment result.

[0012] In one embodiment, the step of reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window includes:

[0013] When the current position of the preset sliding window is the terminal edge position of the target coding unit, determining the adjacent coding unit of the target coding unit according to the terminal edge position;

[0014] splicing the target coding unit and the adjacent coding unit to obtain a spliced ​​coding unit;

[0015] The pixel data corresponding to the plurality of target pixel points of the splicing coding unit are read from the target memory through the preset sliding window.

[0016] In one embodiment, the step of reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window includes:

[0017] When the current position of the preset sliding window is the direction edge position of the target coding unit, obtaining the target traversal path;

[0018] Determining a target traversal position of the preset sliding window according to the target traversal path;

[0019] The preset sliding window is moved to the target traversal position according to the target traversal path, and pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory through the preset sliding window.

[0020] In one embodiment, before reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window, the method further includes:

[0021] Obtain pixel data corresponding to each pixel point of the target coding unit;

[0022] Merge and store pixel data corresponding to a preset number of pixel points to obtain a memory address of each pixel point;

[0023] The pixel data corresponding to each pixel point is stored according to the memory address of each pixel point.

[0024] In one embodiment, after performing parallel sample adaptive compensation processing on the pixel data corresponding to each pixel point to be processed by the computing kernel, the method further includes:

[0025] Retaining pixel data corresponding to each target pixel point in the preset sliding window to obtain pixel data corresponding to a plurality of retained pixel points;

[0026] Determine the moving distance by using a plurality of reserved pixel points and the window size of the preset sliding window;

[0027] Moving the preset sliding window according to the target sliding direction and the moving distance, and reading pixel data corresponding to a plurality of filling pixel points of the target coding unit from the target memory through the moved preset sliding window;

[0028] Pixel data corresponding to a plurality of target pixels are obtained according to pixel data corresponding to a plurality of reserved pixels and pixel data corresponding to a plurality of filled pixels.

[0029] In one embodiment, the performing of parallel sample adaptive compensation processing on the pixel data corresponding to each pixel point to be processed by the computing kernel includes:

[0030] The pixel data corresponding to each pixel point to be processed are statistically analyzed in parallel by the calculation kernel to obtain the statistical results of each pixel point to be processed;

[0031] Decision output is performed based on the statistical results of each pixel to be processed to obtain the target output decision;

[0032] A filtering calculation is performed based on the target output decision to complete the sample value adaptive compensation processing of each pixel point to be processed.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a sample value adaptive compensation device based on an integrated circuit, and the sample value adaptive compensation device based on an integrated circuit includes: a reading module, used to read pixel data corresponding to multiple target pixel points of a target coding unit from a target memory through a preset sliding window;

[0034] A storage module, used for temporarily storing pixel data corresponding to each target pixel point in a target register, and determining a plurality of pixels to be processed in a target middle area of ​​the target register and pixel data corresponding to each pixel to be processed;

[0035] The processing module is used to perform parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through the calculation kernel.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a sample value adaptive compensation device based on an integrated circuit, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the sample value adaptive compensation method based on an integrated circuit as described above.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the sample value adaptive compensation method based on integrated circuits as described above are implemented.

[0038] The present application provides a sample value adaptive compensation method based on an integrated circuit. The present application reads pixel data corresponding to multiple target pixel points of a target coding unit from a target memory through a preset sliding window; temporarily stores the pixel data corresponding to each target pixel point in a target register, and determines multiple pixel points to be processed in the target middle area of ​​the target register and the pixel data corresponding to each pixel point to be processed; and performs parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through a calculation kernel. In the above manner, multiple target pixel points are read through a preset sliding window, and multiple pixel points to be processed in the middle area of ​​the register are subjected to parallel sample value adaptive compensation processing through a calculation kernel, thereby realizing parallel acceleration of the sample value adaptive compensation algorithm in the integrated circuit, improving the calculation speed of the sample value adaptive compensation algorithm in the integrated circuit, and at the same time not increasing excessive resource consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0041] Figure 1 A flowchart diagram of the first embodiment of the sample value adaptive compensation method based on integrated circuit of the present application;

[0042] Figure 2 A register diagram of a sample value adaptive compensation method based on an integrated circuit provided in Embodiment 1 of the present application;

[0043] Figure 3A schematic diagram of sliding window initialization of a sample value adaptive compensation method based on an integrated circuit provided in Embodiment 1 of the present application;

[0044] Figure 4 A schematic diagram of a traversal path of a sample value adaptive compensation method based on an integrated circuit provided in Embodiment 1 of the present application;

[0045] Figure 5 A schematic diagram of memory storage of a sample adaptive compensation method based on an integrated circuit provided in Embodiment 1 of the present application;

[0046] Figure 6 Schematic diagram of pixel merging and storage of the sample value adaptive compensation method based on integrated circuit provided in the first embodiment of the present application

[0047] Figure 7 A flow chart of the second embodiment of the sample value adaptive compensation method based on integrated circuit provided in the present application;

[0048] Figure 8 A schematic diagram of horizontal sliding of a sample adaptive compensation method based on an integrated circuit provided in Embodiment 2 of the present application;

[0049] Fig. 9 A schematic diagram before vertical sliding of the sample adaptive compensation method based on integrated circuit provided in the second embodiment of the present application;

[0050] Fig.10 A schematic diagram of a vertical sliding method of a sample adaptive compensation method based on an integrated circuit provided in the second embodiment of the present application;

[0051] Fig.11 This is a schematic diagram of the module structure of a sample value adaptive compensation device based on an integrated circuit according to an embodiment of the present application;

[0052] Fig.12 Schematic diagram of the device structure of the hardware operating environment involved in the sample value adaptive compensation method based on integrated circuit in the embodiment of the present application.

[0053] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0054] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0055] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0056] The main solution of the embodiment of the present application is: reading pixel data corresponding to multiple target pixel points of the target coding unit from the target memory through a preset sliding window; temporarily storing the pixel data corresponding to each target pixel point in the target register, and determining multiple pixel points to be processed in the target middle area of ​​the target register and the pixel data corresponding to each pixel point to be processed; performing parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through the computing kernel.

[0057] At present, the SAO module processes the image corresponding to the largest coding unit (LCU) in units, and processes an image corresponding to an LCU, which is about 4096 pixels, each time it works. The input of SAO is usually an original image of the size of an LCU and a reconstructed image of the size of an LCU. In the implementation of integrated circuits, if each pixel is processed one by one, the time delay (Latency) is at least 4096 cycles, which greatly reduces the operating speed of the entire encoder system.

[0058] The present application reads multiple target pixel points through a preset sliding window, and performs parallel sample value adaptive compensation processing on multiple pixel points to be processed in the middle area of ​​the register through a computing kernel, thereby realizing parallel acceleration of the sample value adaptive compensation algorithm in the integrated circuit, improving the calculation speed of the sample value adaptive compensation algorithm in the integrated circuit, and at the same time not increasing excessive resource consumption.

[0059] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a sample value adaptive compensation device based on an integrated circuit, etc. The following takes the sample value adaptive compensation device based on an integrated circuit as an example to illustrate this embodiment and the following embodiments.

[0060] Based on this, the embodiment of the present application provides a sample value adaptive compensation method based on an integrated circuit, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the sample adaptive compensation method based on integrated circuit of the present application.

[0061] In this embodiment, the method described includes steps S10 to S30:

[0062] Step S10, reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window.

[0063] It should be noted that the preset sliding window refers to the sliding window set in this embodiment. The size of the preset sliding window can be (M+2)×(N+2) or other sizes. This embodiment does not limit this. However, in this embodiment, the size of (M+2)×(N+2) is used as an example for explanation. In this embodiment, the SAO module includes a group of memories for storing original pixels and reconstructed pixels, and a register CACHE of a preset size. The size of the register CACHE is (M+2)×(N+2). Figure 2 shown.

[0064] It is understood that the target coding unit refers to the maximum coding unit currently being processed by the SAO algorithm, and there are multiple maximum coding units on an image. The target memory refers to the memory in the SAO module that stores original pixels and reconstructed pixels.

[0065] In a specific implementation, there is a preset sliding window in the target coding unit, and the pixel data in the window will be read from the target memory. The pixel data corresponding to each pixel point of the target coding unit read by the preset sliding window is the pixel data corresponding to multiple target pixel points. In this embodiment, the pixel data corresponding to the pixel points of the (M+2)×(N+2) area in the target coding unit will be read from the memory each time through the preset sliding window.

[0066] It should be noted that, in this embodiment, the pixel data corresponding to the M+2 consecutive pixel points in the vertical direction in the target coding unit are merged and stored in one memory address, so M+2 pixel data can be obtained from the memory for each clock beat. Combined with the data access characteristics of the sliding window, the time delay for accessing the memory can be reduced.

[0067] In a feasible implementation manner, step S10 may further include steps A11 to A12:

[0068] Step A11: when the current position of the preset sliding window is the starting edge position of the target coding unit, align the edge position of the preset sliding window with the unit edge of the target coding unit.

[0069] It should be noted that when the current position of the preset sliding window is obtained as the starting edge position of the target coding unit, it means that the SAO algorithm processing will start on the target coding unit. In this embodiment, the starting edge position can be any one of the upper left corner, upper right corner, lower left corner, and lower right corner of the target coding unit, or other positions, which is not limited in this embodiment.

[0070] It is understandable that when the current position of the preset sliding window is the starting edge position of the target coding unit, initialization is required, that is, the edge position of the preset sliding window is further aligned with the unit edge of the target coding unit. In this embodiment, the unit edge refers to the four edges of the target coding unit. For example, the upper left corner is used as the starting edge position for explanation. At the beginning, the SAO module reads the pixel data of the upper left corner (M+2)×(N+2) area from the target memory through the preset sliding window and stores it in the CACHE composed of registers, such as Figure 3 At this time, the left edge of the preset sliding window is aligned with the left edge of the LCU, and the upper edge of the preset sliding window is aligned with the upper edge of the LCU. This process is regarded as initialization of the CACHE.

[0071] Step A12, reading pixel data corresponding to multiple target pixel points of the target coding unit from the target memory according to the alignment result.

[0072] It should be noted that when the alignment result is that the edge position of the preset sliding window is aligned with the unit edge of the target coding unit, the pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory through the preset sliding window.

[0073] In a feasible implementation manner, step S10 may further include steps B11 to B13:

[0074] Step B11: when the current position of the preset sliding window is the terminal edge position of the target coding unit, determine the adjacent coding unit of the target coding unit according to the terminal edge position.

[0075] It should be noted that when the current position of the preset sliding window is the end edge position of the target coding unit, it means that the traversal of the target coding unit has been completed through the preset sliding window. In this embodiment, the end edge position can be any one of the upper left corner, upper right corner, lower left corner, and lower right corner of the target coding unit, or other positions, which are not limited in this embodiment. At this time, the maximum coding unit adjacent to the target coding unit is determined, and the maximum coding unit adjacent to the target coding unit is the adjacent coding unit of the target coding unit.

[0076] Step B12: splicing the target coding unit and the adjacent coding unit to obtain a spliced ​​coding unit.

[0077] It should be noted that the target coding unit and a plurality of adjacent coding units are spliced ​​to obtain a plurality of spliced ​​coding units.

[0078] Step B13, reading pixel data corresponding to a plurality of target pixel points of the splicing coding unit from the target memory through the preset sliding window.

[0079] It should be noted that the pixel data corresponding to multiple target pixel points of the spliced ​​coding unit are read from the target memory through a preset sliding window, thereby ensuring that each pixel point at the edge position of the target coding unit can be located in the central area of ​​the target register CACHE, and the size of the central area of ​​the target register CACHE is M×N.

[0080] In a feasible implementation manner, step S10 may further include steps C11 to C13:

[0081] Step C11, when the current position of the preset sliding window is the directional edge position of the target coding unit, obtain the target traversal path.

[0082] It should be noted that when the current position of the preset sliding window is the direction edge position of the target coding unit, it means that the preset sliding window has reached the unit edge of the target coding unit, but has not completed the traversal of the target coding unit. At this time, the target traversal path is obtained. In this embodiment, the direction edge position can be any position of the four edges of the target coding unit, and this embodiment is not limited to this. The target traversal path can be an S-shaped driving path, such as Figure 4 shown.

[0083] Step C12: determining the target traversal position of the preset sliding window according to the target traversal path.

[0084] It should be noted that the next traversal position of the preset sliding window is determined according to the target traversal path and the current position of the preset sliding window, and the next traversal position of the preset sliding window is the target traversal position.

[0085] Step C13, moving the preset sliding window to the target traversal position according to the target traversal path, and reading pixel data corresponding to multiple target pixel points of the target coding unit from the target memory through the preset sliding window.

[0086] It should be noted that the preset sliding window is moved to the target traversal position according to the target traversal path, and the pixel positions corresponding to multiple target Siangsu points of the target coding unit are read from the target memory through the preset sliding window.

[0087] In a feasible implementation manner, before step S10, steps D11 to D13 may also be included:

[0088] Step D11, obtaining pixel data corresponding to each pixel point of the target coding unit.

[0089] Step D12, merging and storing pixel data corresponding to a preset number of pixel points to obtain a memory address of each pixel point.

[0090] Step D13, storing pixel data corresponding to each pixel point according to the memory address of each pixel point.

[0091] It should be noted that one component of an image pixel × occupies one byte in the memory. The form of distributed memory in hardware is flexible, and the data bit width of RAM can be selected. Then, if the data of multiple pixels are bundled together and stored in one address, the access efficiency of data can be improved. Therefore, the pixel data corresponding to each pixel point of the target coding unit is obtained.

[0092] It is understandable that the pixel data corresponding to the preset number of pixel points are combined and stored, and the pixel data of the preset number of pixel points are combined and stored in a RAM address, so as to obtain the memory address of each pixel point, and the pixel data corresponding to each pixel point is stored according to the memory address of each pixel point. In this embodiment, the preset number of pixel points can be M+2 consecutive pixel points in the vertical direction.

[0093] In the specific implementation, for ease of understanding, an example of pixel merging is given below. Figure 5 In the memory shown, the four image pixel data of a single component (0, 0), (1, 0), (2, 0), (3, 0) are stored together in RAM address 0x0. The same applies to other pixels. Then, when the system accesses this memory, it accesses address 0x0 and can obtain four pixel data in one clock beat. Reading RAM addresses 0x0, 0x1, 0x2, 0x3, 0x4, and 0x5 in sequence can obtain Figure 6 The 4×6 pixel data shown consumes 5 clock beats. In contrast, the storage method of storing 1 pixel in 1 RAM address requires 24 clock beats to read the same 4×6 pixels.

[0094] Step S20, temporarily storing the pixel data corresponding to each target pixel point in a target register, and determining a plurality of to-be-processed pixel points in a target middle area of ​​the target register and the pixel data corresponding to each to-be-processed pixel point.

[0095] It should be noted that the pixel data corresponding to each target pixel point in the (M+2)×(N+2) area in the target coding unit is read through a preset sliding window, and the pixel data corresponding to each target pixel point read each time is temporarily stored in the target register CACHE.

[0096] It can be understood that after completing the temporary storage of the pixel data corresponding to each target pixel point read each time, the M×N target pixel points in the middle area of ​​the target register CACHE are determined. In this embodiment, the M×N target pixel points in the middle area of ​​the target register CACHE are multiple pixels to be processed, such as Figure 3 As shown in, (0,0), (0,1), (0,2), (0,3), (0,4), (0,5), (1,0), (1,1), (1,2), (1,3), (1,4), (1,5), (2,0), (2,1), (2,2), (2,3), (2,4), (2,5), (3,0), (3,1), (3,2), (3,3), (3,4), (3,5) are multiple target pixels, and the M×N pixels to be processed in the middle area of ​​the target register CACHE are: (1,1), (1,2), (1,3), (1,4), (2,1), (2,2), (2,3), (2,4).

[0097] Step S30 , performing parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed by the calculation kernel.

[0098] It should be noted that the calculation kernel of the SAO module performs parallel sample adaptive compensation processing on the pixel data corresponding to each pixel to be processed. In this embodiment, the SAO algorithm uses 5 different strategies to examine the pixels one by one, and then decides on a filtering strategy, and finally filters the pixels. The SAO algorithm is divided into 3 processes: statistical stage, decision stage, and filter calculation stage. In the statistical stage, the algorithm performs 5 different types of feature statistics on each pixel. In the decision stage, the algorithm examines the cost and benefits of filtering the pixels corresponding to the 5 statistical methods, and finally generates a decision and outputs the decision. In the filter calculation stage, the algorithm performs filter calculations on the pixels according to the decisions made, and outputs the calculation results as the results of SAO.

[0099] Step E11, performing parallel feature statistics on the pixel data corresponding to each pixel point to be processed by using a calculation kernel to obtain a statistical result of each pixel point to be processed.

[0100] Step E12, making a decision output based on the statistical results of each pixel to be processed to obtain a target output decision.

[0101] Step E13, performing filtering calculation based on the target output decision to complete the sample value adaptive compensation processing of each pixel point to be processed.

[0102] It should be noted that the computing kernel of the SAO module performs parallel feature statistics on the pixel data corresponding to each pixel to be processed, makes a decision output based on the statistical results of each pixel to be processed, and finally performs filtering calculation based on the target output decision to complete the sample value adaptive compensation processing of each pixel to be processed.

[0103] The present embodiment provides a sample value adaptive compensation method based on an integrated circuit. The present embodiment reads pixel data corresponding to multiple target pixel points of a target coding unit from a target memory through a preset sliding window; temporarily stores the pixel data corresponding to each target pixel point in a target register, and determines multiple pixel points to be processed in the target middle area of ​​the target register and the pixel data corresponding to each pixel point to be processed; and performs parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through a calculation kernel. In the above manner, multiple target pixel points are read through a preset sliding window, and multiple pixel points to be processed in the middle area of ​​the register are subjected to parallel sample value adaptive compensation processing through a calculation kernel, thereby realizing parallel acceleration of the sample value adaptive compensation algorithm in the integrated circuit, improving the calculation speed of the sample value adaptive compensation algorithm in the integrated circuit, and at the same time not increasing excessive resource consumption.

[0104] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 7 After step S30, the sample value adaptive compensation method based on integrated circuit further includes steps S31 to S34:

[0105] Step S31, retaining pixel data corresponding to each target pixel point in the preset sliding window to obtain pixel data corresponding to a plurality of retained pixel points.

[0106] It should be noted that after the computing kernel completes processing of multiple pixels to be processed, the target sliding direction of the preset sliding window is determined. The rule for determining the target sliding direction is to move away from the left and right edges of the currently touched LCU. If the left side of the LCU is currently touched, the direction is to the right. The direction does not change until the next time the sliding window touches the left and right edges of the LCU. The significance of this step is that the basic logic of the horizontal left sliding window and the horizontal right sliding window is the same, but the directions are opposite. After determining the direction, part of the sliding window logic can be shared.

[0107] It is understandable that when sliding the window, it is necessary to retain pixel data corresponding to a preset number of target pixels based on the target sliding direction to obtain pixel data corresponding to multiple retained pixels. In this embodiment, if the target sliding direction is right, first move the (M+2)×2 pixels on the right side of the window horizontally to the (M+2)×2 area on the left side, and then read the (M+2)×N pixels in sequence in the memory to fill the right side, such as Figure 8 As shown in the figure. When the target sliding direction is left, the pixel translation direction and data filling position are reversed from the above process. This sliding window operation only needs to read (M+2)×N pixels from the target memory, reducing memory access.

[0108] In the specific implementation, when the target sliding direction is vertical sliding at this time, the preset sliding window slides vertically M units, firstly moves the 2×(N+2) pixels of the lower 2 rows in the window upward by M rows, and then reads the M×(N+2) pixels of the corresponding position in the target memory. Fig. 9 As shown, after sliding Fig.10 shown.

[0109] Step S32: determining the moving distance by using a plurality of retained pixels and the window size of the preset sliding window.

[0110] Step S33, moving the preset sliding window according to the target sliding direction and the moving distance, and reading pixel data corresponding to multiple filling pixel points of the target coding unit from the target memory through the moved preset sliding window.

[0111] Step S34, obtaining pixel data corresponding to a plurality of target pixel points according to the pixel data corresponding to a plurality of reserved pixel points and the pixel data corresponding to a plurality of filled pixel points.

[0112] It should be noted that the moving distance of the preset sliding window is determined by the plurality of retained pixels and the window size of the preset sliding window, and the preset sliding window is moved according to the target sliding direction and the moving distance. The pixel data corresponding to the plurality of pixels that have not been read in the target coding unit are read from the target memory through the moved preset sliding window. In this embodiment, the plurality of pixels that have not been read before and are read through the moved preset sliding window are the plurality of filling pixels.

[0113] It can be understood that the pixel data corresponding to the plurality of reserved pixels and the pixel data corresponding to the plurality of filled pixels are summarized, that is, the pixel data corresponding to the plurality of target pixels read through the preset window each time. Figure 8For example, when the target sliding direction is right, the target pixel points read by the preset sliding window last time are (0,0), (0,1), (0,2), (0,3), (0,4), (0,5), (1,0), (1,1), (1,2), (1,3), (1,4), (1,5), (2,0), (2,1), (2,2), (2,3), (2,4), (2,5), (3,0), (3,1), (3,2), (3,3), (3,4), (3,5). At this time, the multiple retained pixel points are the (M+2)×2 pixels on the right side of the window, namely: (0,4), (0,5), (1,4), (1,5), (2,4), (2,5), (3,4), (3,5). After moving the preset sliding window The obtained filling pixels are (0, 6), (0, 7), (0, 8), (0, 9), (1, 6), (1, 7), (1, 8), (1, 9), (2, 6), (2, 7), (2, 8), (2, 9), (3, 6), (3, 7), (3, 8), (3, 9). The target pixel points read at this time are (0, 4), (0, 5) , (1, 4), (1, 5), (2, 4), (2, 5), (3, 4), (3, 5), (0, 6), (0, 7), (0, 8), (0, 9), (1, 6), (1, 7), (1, 8), (1, 9), (2, 6), (2, 7), (2, 8), (2, 9), (3, 6), (3, 7), (3, 8), (3, 9).

[0114] In a specific implementation, the preset sliding window is moved according to the target sliding direction and the target traversal path, and the pixel data corresponding to each pixel point of the LCU in the target memory is read through the preset sliding window until the LCU traversal is completed.

[0115] This embodiment retains the pixel data corresponding to each target pixel point in the preset sliding window to obtain pixel data corresponding to multiple retained pixel points; determines the moving distance by the multiple retained pixel points and the window size of the preset sliding window; moves the preset sliding window according to the target sliding direction and the moving distance, and reads the pixel data corresponding to multiple filling pixel points of the target coding unit from the target memory through the moved preset sliding window; obtains the pixel data corresponding to multiple target pixel points based on the pixel data corresponding to the multiple retained pixel points and the pixel data corresponding to the multiple filling pixel points. In the above manner, the complete traversal of the LCU is guaranteed and the memory access is reduced.

[0116] Exemplarily, in order to help understand the implementation process of the sample value adaptive compensation method based on integrated circuit obtained by combining this embodiment with the above-mentioned embodiment 1, specifically:

[0117] In this embodiment, the SAO module includes a group of memories for storing original pixels and reconstructed pixels and a register CACHE of size (M+2)×(N+2). It is assumed that there is a sliding window in the LCU, and the pixel data in the window will be read from the memory and temporarily stored in the CACHE. And when the window is updated, the data is updated by sliding. There is a computing kernel that can perform statistical calculations on M×N pixels in parallel. The pixel data of an LCU is stored in the memory as follows: M+2 consecutive pixels in the vertical direction are merged and stored in a memory address. In this way, M+2 pixel data can be obtained from the memory for each clock beat, and combined with the data access characteristics of the sliding window, the time delay for accessing the memory can be reduced.

[0118] The method of this embodiment specifically includes the following steps: Step 1: Initialization. At the beginning, the module reads the pixel data of the upper left corner (M+2)×(N+2) area from the memory and stores it in the CACHE composed of registers. At this time, the left edge of the sliding window is aligned with the left edge of the LCU, and the upper edge of the sliding window is aligned with the upper edge of the LCU. This process is regarded as the initialization of the CACHE. The calculation kernel of the SAO module performs statistical calculations on the M×N pixels in the center of the (M+2)×(N+2) CACHE.

[0119] Step 2: Determine the direction of the horizontal sliding of the sliding window. The rule for determining the sliding direction is to move away from the left and right edges of the currently touched LCU. Currently touching the left side of the LCU, the direction is to the right. The direction does not change until the next time the sliding window touches the left or right edge of the LCU. The significance of the above steps is that the basic logic of the horizontal left sliding window and the horizontal right sliding window is the same, but the direction is opposite. After determining the direction, part of the sliding window logic can be shared.

[0120] Step 3: Horizontal sliding window. The sliding window slides horizontally by N pixel units. Specifically, when the sliding window direction is right, first move the (M+2)×2 pixels on the right side of the window horizontally to the (M+2)×2 area on the left side. Then read the (M+2)×N pixels in sequence from the memory to fill the right side. When the sliding window direction is left, the pixel translation direction and data filling position are reversed from the above process. This sliding window operation only needs to read (M+2)×N pixels from the memory, reducing memory access. Calculate the middle M×N pixels.

[0121] Repeat step 3 until the sliding window touches the left and right edges of the LCU.

[0122] Step 4: Slide the window vertically. Slide the window vertically M units. First, move the 2×(N+2) pixels in the lower 2 rows of the window upward by M rows, then read the M×(N+2) pixels in the corresponding position in the memory and fill them in the lower part. Calculate the middle M×N pixels.

[0123] Repeat steps 2 to 4 above, traversing the entire LCU content in an S-shaped manner until the sliding window passes through all pixels from one corner of the LCU where it was initialized to the other corner. At this point, all non-boundary pixels in the target LCU have been processed by the kernel calculation, and then the sliding window reads part of the pixel data of the LCU adjacent to the current LCU and combines it with the boundary pixels of the current LCU, thereby ensuring that the boundary pixels of the current LCU can be in the center of the CACHE, so that the boundary pixels are processed by the calculation kernel.

[0124] The (M+2)×(N+2) size window proposed in the above method allows the parallel processing of the middle M×N pixels for the pixel data in the window, and then the window is traversed through the pixels of the entire LCU by sliding. Assuming that M and N are 1 and 8 respectively, that is, 8 pixels are calculated in parallel, the calculation time of one LCU can be reduced from about 4096 cycles to about 512 cycles. The SAO module implemented in this way can greatly improve the real-time performance of the encoder, thereby achieving certain technical indicators, such as: 60fps. Moreover, the specific parameters can be adjusted according to performance requirements and resource requirements to balance resource costs and performance benefits, and improve the calculation speed of the SAO algorithm in the integrated circuit without increasing excessive resource consumption.

[0125] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the sample value adaptive compensation method based on integrated circuits of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0126] The present application also provides a sample value adaptive compensation device based on integrated circuit, please refer to Fig.11 , the sample value adaptive compensation device based on integrated circuit comprises:

[0127] A reading module 10, configured to read pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window;

[0128] The storage module 20 is used to temporarily store the pixel data corresponding to each target pixel point in a target register, and determine a plurality of pixels to be processed in the target middle area of ​​the target register and the pixel data corresponding to each pixel to be processed;

[0129] The processing module 30 is used to perform parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through a calculation kernel.

[0130] Optionally, the reading module 10 is further used for:

[0131] When the current position of the preset sliding window is the starting edge position of the target coding unit, the edge position of the preset sliding window is aligned with the unit edge of the target coding unit; and pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory according to the alignment result.

[0132] Optionally, the reading module 10 is further used for:

[0133] When the current position of the preset sliding window is the terminal edge position of the target coding unit, the adjacent coding unit of the target coding unit is determined according to the terminal edge position; the target coding unit and the adjacent coding unit are spliced ​​to obtain a spliced ​​coding unit; and pixel data corresponding to multiple target pixel points of the spliced ​​coding unit are read from the target memory through the preset sliding window.

[0134] Optionally, the reading module 10 is further used for:

[0135] When the current position of the preset sliding window is the directional edge position of the target coding unit, a target traversal path is obtained; the target traversal position of the preset sliding window is determined according to the target traversal path; the preset sliding window is moved to the target traversal position according to the target traversal path, and pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory through the preset sliding window.

[0136] Optionally, the reading module 10 is further used for:

[0137] Obtain pixel data corresponding to each pixel point of the target coding unit; merge and store pixel data corresponding to a preset number of pixel points to obtain a memory address of each pixel point; and store pixel data corresponding to each pixel point according to the memory address of each pixel point.

[0138] Optionally, the processing module 30 is further used for:

[0139] The pixel data corresponding to each target pixel point in the preset sliding window is retained to obtain pixel data corresponding to multiple retained pixel points; the moving distance is determined by the multiple retained pixel points and the window size of the preset sliding window; the preset sliding window is moved according to the target sliding direction and the moving distance, and the pixel data corresponding to multiple filling pixel points of the target coding unit are read from the target memory through the moved preset sliding window; the pixel data corresponding to multiple target pixel points are obtained according to the pixel data corresponding to the multiple retained pixel points and the pixel data corresponding to the multiple filling pixel points.

[0140] Optionally, the processing module 30 is further used for:

[0141] The pixel data corresponding to each pixel to be processed are subjected to parallel feature statistics through the calculation kernel to obtain the statistical results of each pixel to be processed; a decision output is performed based on the statistical results of each pixel to be processed to obtain a target output decision; a filtering calculation is performed based on the target output decision to complete the sample value adaptive compensation processing of each pixel to be processed.

[0142] The sample value adaptive compensation device based on integrated circuit provided by the present application adopts the sample value adaptive compensation method based on integrated circuit in the above embodiment, which can solve the technical problem that there is a large delay in the SAO algorithm processing pixels in the LCU in the prior art, which greatly reduces the operating speed of the system. Compared with the prior art, the beneficial effects of the sample value adaptive compensation device based on integrated circuit provided by the present application are the same as the beneficial effects of the sample value adaptive compensation method based on integrated circuit provided by the above embodiment, and the other technical features of the sample value adaptive compensation device based on integrated circuit are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0143] The present application provides a sample value adaptive compensation device based on an integrated circuit, and the sample value adaptive compensation device based on an integrated circuit includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the sample value adaptive compensation method based on the integrated circuit in the above-mentioned embodiment 1.

[0144] Reference below Fig.12 , which shows a schematic diagram of the structure of a sample adaptive compensation device based on an integrated circuit suitable for implementing the embodiment of the present application. The sample adaptive compensation device based on an integrated circuit in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.12 The sample value adaptive compensation device based on integrated circuit shown is only an example and should not bring any limitation to the function and scope of use of the embodiments of the present application.

[0145] like Fig.12As shown, the sample adaptive compensation device based on integrated circuit may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the sample adaptive compensation device based on integrated circuit are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the sample adaptive compensation device based on an integrated circuit to communicate with other devices wirelessly or by wire to exchange data. Although the sample adaptive compensation device based on an integrated circuit with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0146] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0147] The sample value adaptive compensation device based on integrated circuit provided by the present application adopts the sample value adaptive compensation method based on integrated circuit in the above embodiment, which can solve the technical problem that there is a large delay in the SAO algorithm processing pixels in the LCU in the prior art, which greatly reduces the operating speed of the system. Compared with the prior art, the beneficial effects of the sample value adaptive compensation device based on integrated circuit provided by the present application are the same as the beneficial effects of the sample value adaptive compensation method based on integrated circuit provided by the above embodiment, and the other technical features of the sample value adaptive compensation device based on integrated circuit are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0148] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0149] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0150] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the sample value adaptive compensation method based on integrated circuits in the above-mentioned embodiment.

[0151] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0152] The computer-readable storage medium may be included in the sample value adaptive compensation device based on an integrated circuit; or may exist independently without being assembled into the sample value adaptive compensation device based on an integrated circuit.

[0153] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by a sample value adaptive compensation device based on an integrated circuit, the sample value adaptive compensation device based on the integrated circuit: reads pixel data corresponding to multiple target pixel points of a target coding unit from a target memory through a preset sliding window; temporarily stores the pixel data corresponding to each target pixel point to a target register, and determines multiple pixel points to be processed in a target middle area of ​​the target register and the pixel data corresponding to each pixel point to be processed; and performs parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through a computing kernel.

[0154] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0155] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0156] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0157] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned sample adaptive compensation method based on integrated circuits, and can solve the technical problem that the SAO algorithm in the prior art processes pixels within the LCU with a large delay, which greatly reduces the operating speed of the system. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the sample adaptive compensation method based on integrated circuits provided by the above-mentioned embodiments, and will not be repeated here.

[0158] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned integrated circuit-based sample value adaptive compensation method when executed by a processor.

[0159] The computer program product provided by the present application can solve the technical problem in the prior art that the SAO algorithm processes pixels in the LCU with a large delay, which greatly reduces the operating speed of the system. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the sample adaptive compensation method based on integrated circuits provided in the above embodiment, and will not be repeated here.

[0160] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A sample value adaptive compensation method based on integrated circuit, characterized in that: The sample value adaptive compensation method based on integrated circuit includes: Reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window; Temporarily storing pixel data corresponding to each target pixel point in a target register, and determining a plurality of pixels to be processed in a target middle area of ​​the target register and pixel data corresponding to each pixel point to be processed; The pixel data corresponding to each pixel point to be processed is subjected to parallel sample value adaptive compensation processing through the calculation kernel.

2. The method according to claim 1, characterized in that The step of reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window includes: When the current position of the preset sliding window is the starting edge position of the target coding unit, aligning the edge position of the preset sliding window with the unit edge of the target coding unit; Pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory according to the alignment result.

3. The method according to claim 1, characterized in that The step of reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window includes: When the current position of the preset sliding window is the terminal edge position of the target coding unit, determining the adjacent coding unit of the target coding unit according to the terminal edge position; splicing the target coding unit and the adjacent coding unit to obtain a spliced ​​coding unit; The pixel data corresponding to the plurality of target pixel points of the splicing coding unit are read from the target memory through the preset sliding window.

4. The method according to claim 1, characterized in that The step of reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window includes: When the current position of the preset sliding window is the direction edge position of the target coding unit, obtaining the target traversal path; Determining a target traversal position of the preset sliding window according to the target traversal path; The preset sliding window is moved to the target traversal position according to the target traversal path, and pixel data corresponding to multiple target pixel points of the target coding unit are read from the target memory through the preset sliding window.

5. The method according to claim 1, characterized in that Before reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window, the method further includes: Obtain pixel data corresponding to each pixel point of the target coding unit; Merge and store pixel data corresponding to a preset number of pixel points to obtain a memory address of each pixel point; The pixel data corresponding to each pixel point is stored according to the memory address of each pixel point.

6. The method according to any one of claims 1 to 5, characterized in that After the pixel data corresponding to each pixel point to be processed are processed by the computing kernel in parallel with the sample value adaptive compensation processing, the method further includes: Retaining pixel data corresponding to each target pixel point in the preset sliding window to obtain pixel data corresponding to a plurality of retained pixel points; Determine the moving distance by using a plurality of reserved pixel points and the window size of the preset sliding window; Moving the preset sliding window according to the target sliding direction and the moving distance, and reading pixel data corresponding to a plurality of filling pixel points of the target coding unit from the target memory through the moved preset sliding window; Pixel data corresponding to a plurality of target pixels are obtained according to pixel data corresponding to a plurality of reserved pixels and pixel data corresponding to a plurality of filled pixels.

7. The method according to any one of claims 1 to 5, characterized in that The method of performing parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed by the calculation kernel includes: The pixel data corresponding to each pixel point to be processed are statistically analyzed in parallel by the calculation kernel to obtain the statistical results of each pixel point to be processed; Decision output is performed based on the statistical results of each pixel to be processed to obtain the target output decision; A filtering calculation is performed based on the target output decision to complete the sample value adaptive compensation processing of each pixel point to be processed.

8. A sample value adaptive compensation device based on integrated circuit, characterized in that: The sample value adaptive compensation device based on integrated circuit comprises: A reading module, used for reading pixel data corresponding to a plurality of target pixel points of a target coding unit from a target memory through a preset sliding window; A storage module, used for temporarily storing pixel data corresponding to each target pixel point in a target register, and determining a plurality of pixels to be processed in a target middle area of ​​the target register and pixel data corresponding to each pixel to be processed; The processing module is used to perform parallel sample value adaptive compensation processing on the pixel data corresponding to each pixel point to be processed through the calculation kernel.

9. A sample value adaptive compensation device based on integrated circuit, characterized in that: The integrated circuit-based sample value adaptive compensation device includes: a memory, a processor, and an integrated circuit-based sample value adaptive compensation program stored in the memory and executable on the processor, wherein the integrated circuit-based sample value adaptive compensation program is configured to implement the integrated circuit-based sample value adaptive compensation method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores a sample value adaptive compensation program based on an integrated circuit, and when the sample value adaptive compensation program based on an integrated circuit is executed by a processor, the sample value adaptive compensation method based on an integrated circuit as described in any one of claims 1 to 7 is implemented.