WO2024055525A1 - 一种视频图像数据存储的方法、装置、设备及可读介质 - Google Patents

一种视频图像数据存储的方法、装置、设备及可读介质 Download PDF

Info

Publication number
WO2024055525A1
WO2024055525A1 PCT/CN2023/077995 CN2023077995W WO2024055525A1 WO 2024055525 A1 WO2024055525 A1 WO 2024055525A1 CN 2023077995 W CN2023077995 W CN 2023077995W WO 2024055525 A1 WO2024055525 A1 WO 2024055525A1
Authority
WO
WIPO (PCT)
Prior art keywords
pixel
data
ddr
row
row vector
Prior art date
Application number
PCT/CN2023/077995
Other languages
English (en)
French (fr)
Inventor
贾学强
伍峰
熊子涵
丁微微
李志�
Original Assignee
苏州元脑智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州元脑智能科技有限公司 filed Critical 苏州元脑智能科技有限公司
Publication of WO2024055525A1 publication Critical patent/WO2024055525A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/71Indexing; Data structures therefor; Storage structures
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7847Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management

Definitions

  • the present application relates to the field of storage, and in particular, to a method, device, equipment and readable medium for video image data storage.
  • DDR Double Data Rate, full name DDR SDRAM, referred to as DDR, double rate synchronous dynamic random access memory
  • DDR has the advantages of fast access speed, small size, and low price compared to SRAM (Static Random-Access Memory, SRAM static random access memory) when used as a cache. Therefore, it has become a major component in modern digital devices and is mainly responsible for the temporary storage of data. access.
  • this application proposes a method, device, equipment and readable medium for video image data storage.
  • a video image data storage method proposed by this application uses the similarity of the video image data and the circuit characteristics of DDR to change the data polarity storage, and converts the video image data into more "1" high levels during storage. Store to reduce power consumption during storage.
  • one aspect of the embodiments of the present application provides a method for storing video image data.
  • the method includes the following steps: obtaining a pixel matrix of the video image and setting reference pixels in the row vector pixels; Logical operations are performed on the pixels starting from the pixels adjacent to the reference pixel and traversed in row vector order of the pixel matrix to write the corresponding result of each pixel in the pixel matrix into DDR.
  • the method further includes: writing the data of the reference pixel of the row vector pixel into the DDR, and updating the previous data of the reference pixel in the DDR with the data of the reference pixel of the current row vector pixel. , so that the data of the reference pixel in the DDR is adapted to the current row vector pixel.
  • the method further includes: performing the opposite logical operation on the data of the pixels stored in the DDR in sequence according to the writing order of the DDR, so as to restore the data of the pixels stored in the DDR to the original data and read out.
  • logical operations are performed on the row vector pixels starting from the pixels adjacent to the reference pixel and traversed in the order of the row vector of the pixel matrix to convert the pixels of each pixel in the pixel matrix into
  • Writing the corresponding results to DDR includes: sequentially performing XOR and then inversion operations on the row vector pixels starting from the pixels adjacent to the reference pixel, and traversing in the order of the row vector of the pixel matrix.
  • the method further includes: performing inversion and XOR operation on the pixel data stored in the DDR in sequence according to the writing order of the DDR, so as to restore the pixel data stored in the DDR to the original data and read out.
  • obtaining the pixel matrix of the video image and setting reference pixels in the row vector pixels includes: obtaining the row vector group and column vector group of the pixel matrix of the video image, and obtaining the row vector order of the pixel matrix and column vector order; set the first column pixel of the current row vector pixel as the reference pixel of the current row vector pixel, and set it in sequence according to the row vector order to adapt to the logical operation of the current row vector pixel.
  • the method further includes: performing a logical operation on the data of the reference pixel of the current row vector pixel and the previous data of the reference pixel in the DDR; Write to DDR, and update the data of the reference pixel in DDR to the data of the reference pixel of the current row vector pixel.
  • performing a logical operation on the data of the reference pixel point of the current row vector pixel point and the previous data of the reference pixel point in the DDR includes: comparing the data of the reference pixel point of the current row vector pixel point with the previous data of the reference pixel point in the DDR.
  • the previous data of the reference pixel is XORed and then inverted.
  • logical operations are performed on the row vector pixels starting from the pixels adjacent to the reference pixel and traversed in the order of the row vector of the pixel matrix to convert the pixels of each pixel in the pixel matrix into
  • Writing the corresponding results to DDR includes: performing logical operations with the data of the previous pixel in the current row vector pixel in column vector order and writing the corresponding results into DDR; traversing each pixel matrix in row vector order pixels and write their corresponding results into DDR.
  • the data of the previous pixel is sequentially processed in column vector order.
  • Logical operations and writing the corresponding results to the DDR include: performing an XOR operation on the current row vector pixels in sequence with the data of the previous pixels in column vector order and then inverting the data and writing the corresponding results to the DDR.
  • the device includes the following modules: a first module configured to obtain a pixel matrix of the video image and set reference pixels in the row vector pixels. point; the second module is configured to perform logical operations on the row vector pixel points starting from the pixel points adjacent to the reference pixel point and traverse according to the row vector order of the pixel point matrix to convert each pixel point matrix The corresponding result of the pixel is written into DDR.
  • the device further includes: a third module configured to write the data of the reference pixel of the row vector pixel into the DDR, and update the data of the reference pixel of the current row vector pixel in the DDR.
  • the previous data of the reference pixel is used to adapt the data of the reference pixel in the DDR to the current row vector pixel.
  • the device further includes: a fourth module configured to perform the opposite logical operation on the data of the pixels stored in the DDR in sequence according to the writing order of the DDR, so as to convert the data of the pixels stored in the DDR. The data is restored to the original data and read out.
  • Another aspect of the embodiment of the present application also provides a computer device, including at least one processor; and a memory.
  • the memory stores computer instructions that can be run on the processor. When the instructions are executed by the processor, any one of the above methods is implemented. step.
  • the non-volatile readable storage medium stores a computer program that implements any of the above method steps when executed by a processor.
  • This application has at least the following beneficial effects:
  • This application proposes a video image data storage method, device, equipment and readable medium, wherein the video image data storage method proposed by this application utilizes the similarity of video image data and DDR Changing the circuit characteristics of data polarity storage can effectively reduce the energy consumption of the DDR reading and writing process on the premise of ensuring correct data reading and writing, and the effect of reducing power consumption is particularly obvious for large data volume application scenarios. For product power consumption requirements Higher occasions have practical significance.
  • Figure 1 shows a schematic diagram of an embodiment of a video image data storage method provided by this application
  • Figure 2 shows a schematic diagram of another embodiment of a video image data storage method provided by this application.
  • Figure 3 shows a schematic diagram of another embodiment of a video image data storage method provided by the present application.
  • Figure 4 shows a schematic diagram of another embodiment of a video image data storage method provided by this application.
  • Figure 5 shows a schematic diagram of an embodiment of a video image data storage device provided by this application
  • Figure 6 shows a schematic diagram of another embodiment of a video image data storage device provided by this application.
  • Figure 7 shows a schematic diagram of another embodiment of a video image data storage device provided by this application.
  • Figure 8 shows a schematic diagram of an embodiment of a computer device provided by this application.
  • Figure 9 shows a schematic diagram of an embodiment of a non-volatile readable storage medium provided by this application.
  • Video image data consists of a frame of data, and each frame of data is composed of pixel elements.
  • the pixel data includes RGB (Red, Green, Blue, a color system that represents various colors through the changes and superpositions of R, G, and B. ).
  • the adjacent pixel data (horizontally and vertically) of each frame of data generally have continuity, that is, when the video image is accessed by DDR, a large amount of adjacent data will be similar.
  • DDR4 has a new feature compared to the previous generation of DDR.
  • DDR4 uses a new driving standard, namely POD (Pseudo Open-Drain).
  • POD Pulseudo Open-Drain
  • the receiver terminates the signal to VDD, not VDD/2.
  • SSTL STUB SERIES TERMINATED LOGIC
  • POD consume current.
  • DDR4 uses a lower voltage than DDR3, which compensates to a certain extent for the greater current consumption caused by DDR4 being connected to VDD.
  • DDR transmits a 1 the POD consumes no energy while driving high.
  • the DBI Data Bus Inversion, a method of changing data polarity storage in DDR, which can be used to reduce power consumption
  • the two pixel data are A and B respectively, A and B will be XORed to get C.
  • the XORed value of two similar data will have more ‘0’s in C.
  • DBI is performed on the C value to obtain D with more ‘1’ values.
  • DDR is accessed, D is transmitted, and more ‘1’ values are transmitted, thereby reducing power consumption. After the transmission is completed, D changes to C according to the DBI status. After XORing A and C, the original pixel data B is restored.
  • FIG. 1 shows a schematic diagram of an embodiment of a video image data storage method provided in this application.
  • a video image data storage method according to the embodiment of the present application includes the following steps:
  • FIG. 2 shows a schematic diagram of another embodiment of a video image data storage method provided in this application.
  • a video image data storage method according to the embodiment of the present application includes the following steps:
  • FIG. 3 shows a schematic diagram of another embodiment of a video image data storage method provided in this application.
  • a video image data storage method according to the embodiment of the present application includes the following steps:
  • Figure 4 shows a schematic diagram of another embodiment of a video image data storage method provided by this application.
  • the image data When transmitting, the order is x0y0, x1y0,...,x1919y0,x0y1,x1y1,...,x1919y1,...,x0y1079,x1y1079,...,x1919y1079.
  • For the first row of pixel data record the data of pixel x0y0 as D[x0y0], use it as the reference data of the first row of data, write it to DDR, and cache it in RAM (Random Access Memory) , recorded as Reg0. Perform XOR calculation on the data D[x1y0] of pixel point x1y0 and the data D[x0y0] of pixel point x0y0, record the result as D ⁇ [x1y0], then invert the bitwise to get D ⁇ [x1y0], and write it into DDR middle.
  • the data D[x2y0] of the pixel point x2y0 is XORed with the data D[x1y0] of the pixel point x1y0.
  • the data D[x2y1] of the pixel point x2y1 is XORed with the data D[x1y1] of the pixel point x1y1, and the result is recorded as D ⁇ [x2y1], and then the bitwise inversion is performed to obtain D ⁇ [x2y1] and written into the DDR .
  • D ⁇ [x1919y1] is obtained, and then bitwise inversion is obtained to obtain D ⁇ [x1919y1] and written into DDR.
  • the data D[x2y2] of the pixel point x2y2 is XORed with the data D[x1y2] of the pixel point x1y2, and the result is recorded as D ⁇ [x2y2], and then the bitwise inversion is performed to obtain D ⁇ [x2y2] and written into the DDR .
  • D ⁇ [x1919y2] is obtained, and then bitwise inversion is obtained to obtain D ⁇ [x1919y2] and written into DDR.
  • all 1080 rows of data are calculated sequentially and then written into the DDR.
  • the XOR operation of adjacent data can effectively reduce the number of 1's in the data. Then using the DBI feature to perform bitwise inversion, the number of 1's in the data will be smaller than the original number.
  • the data is significantly increased, which can effectively reduce the energy consumption of DDR reading and writing.
  • this method is not limited to a DDR storage method of video image data, but can be extended to similar DDR use areas, which can effectively improve and reduce DDR power consumption, and has practical significance for occasions with high product power consumption requirements.
  • FIG. 5 shows a schematic diagram of an embodiment of a video image data storage device provided by this application.
  • a device for storing video image data provided by this application includes: a first module 011 configured to obtain a pixel matrix of a video image and set reference pixels in row vector pixels; a second module 012, configured to perform logical operations in the row vector pixels starting from the pixels adjacent to the reference pixel and traverse in the order of the row vector of the pixel matrix to convert the corresponding pixels of each pixel in the pixel matrix The result is written to DDR.
  • FIG. 6 shows a schematic diagram of another embodiment of a video image data storage device provided by this application.
  • a device for storing video image data provided by this application includes: a first module 011 configured to obtain a pixel matrix of a video image and set reference pixels in row vector pixels; a second module 012, configured to perform logical operations in the row vector pixels starting from the pixels adjacent to the reference pixel and traverse in the order of the row vector of the pixel matrix to convert the corresponding pixels of each pixel in the pixel matrix The result is written into DDR; the third module 013 is configured to write the data of the reference pixel of the row vector pixel into the DDR, and update the reference pixel in the DDR with the data of the reference pixel of the current row vector pixel. The previous data is used to adapt the data of the reference pixel in the DDR to the current row vector pixel.
  • a second aspect of the embodiment of the present application provides a device for storing video image data.
  • Figure 7 shows a schematic diagram of another embodiment of a video image data storage device provided by this application.
  • a device for storing video image data provided by this application includes: a first module 011 configured to obtain a pixel matrix of a video image and set reference pixels in row vector pixels; a second module 012, configured to perform logical operations in the row vector pixels starting from the pixels adjacent to the reference pixel and traverse in the order of the row vector of the pixel matrix to convert the corresponding pixels of each pixel in the pixel matrix The result is written into DDR; the third module 013 is configured to write the data of the reference pixel of the row vector pixel into the DDR, and update the reference pixel in the DDR with the data of the reference pixel of the current row vector pixel.
  • the previous data is used to adapt the data of the reference pixels in the DDR to the current row vector pixels; the fourth module 014 is configured to perform the opposite logical operation on the data of the pixels stored in the DDR in sequence according to the writing order of the DDR. operation to restore the pixel data stored in the DDR to the original data and read it out.
  • FIG. 8 shows a schematic diagram of an embodiment of the computer device provided by the present application.
  • an embodiment of a computer device provided by this application includes the following modules: at least one processor 021; and a memory 022.
  • the memory 022 stores computer instructions 023 that can be run on the processor 021.
  • FIG. 9 shows a schematic diagram of an embodiment of a non-volatile readable storage medium provided by this application.
  • the non-volatile readable storage medium 031 stores a computer program 032 that performs the above method when executed by the processor.
  • the steps executed by the computer program 032 include: obtaining the pixel matrix of the video image and setting reference pixels in the row vector pixels; performing logical operations in sequence starting from the pixels adjacent to the reference pixels in the row vector pixels. And traverse according to the row vector order of the pixel matrix to write the corresponding result of each pixel of the pixel matrix into DDR.
  • the method further includes: sequentially processing the pixel data stored in the DDR according to the writing order of the DDR. Perform the opposite operation of the logical operation to restore the pixel data stored in the DDR to the original data and read it out.
  • the method further includes: writing the data of the reference pixel of the row vector pixel into the DDR, and updating the previous data of the reference pixel in the DDR with the data of the reference pixel of the current row vector pixel. , so that the data of the reference pixel in the DDR is adapted to the current row vector pixel.
  • logical operations are performed on the row vector pixels starting from the pixels adjacent to the reference pixel and traversed in the order of the row vector of the pixel matrix to convert the pixels of each pixel in the pixel matrix into
  • Writing the corresponding results to DDR includes: sequentially performing XOR and then inversion operations on the row vector pixels starting from the pixels adjacent to the reference pixel, and traversing in the order of the row vector of the pixel matrix.
  • the method further includes: performing inversion and XOR operation on the pixel data stored in the DDR in sequence according to the writing order of the DDR, so as to restore the pixel data stored in the DDR to the original data and read out.
  • obtaining the pixel matrix of the video image and setting reference pixels in the row vector pixels includes: obtaining the row vector group and column vector group of the pixel matrix of the video image, and obtaining the row vector order of the pixel matrix and column vector order; set the first column pixel of the current row vector pixel as the reference pixel of the current row vector pixel, and set it in sequence according to the row vector order to adapt to the logical operation of the current row vector pixel.
  • the method further includes: performing a logical operation on the data of the reference pixel of the current row vector pixel and the previous data of the reference pixel in the DDR; The corresponding result is written into the DDR, and the data of the reference pixel in the DDR is updated to the data of the reference pixel of the current row vector pixel.
  • performing a logical operation on the data of the reference pixel point of the current row vector pixel point and the previous data of the reference pixel point in the DDR includes: comparing the data of the reference pixel point of the current row vector pixel point with the previous data of the reference pixel point in the DDR.
  • the previous data of the reference pixel is XORed and then inverted.
  • logical operations are performed on the row vector pixels starting from the pixels adjacent to the reference pixel and traversed in the order of the row vector of the pixel matrix to convert the pixels of each pixel in the pixel matrix into
  • Writing the corresponding results to DDR includes: performing logical operations with the data of the previous pixel in the current row vector pixel in column vector order and writing the corresponding results into DDR; traversing each pixel matrix in row vector order pixels and write their corresponding results into DDR.
  • performing a logical operation on the data of the previous pixel in the current row vector pixel in column vector order and writing the corresponding result into the DDR includes: performing a logical operation on the current row vector pixel in column vector order.
  • the data of the previous pixel is XORed and then inverted in sequence, and the corresponding result is written into the DDR.
  • the program of the method of setting system parameters can be stored in a computer-readable file.
  • the storage medium of the program can be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.
  • ROM read-only memory
  • RAM random access memory
  • the method disclosed according to the embodiment of the present application can also be implemented as a computer program executed by a processor, and the computer program can be stored in a non-volatile readable storage medium.
  • the computer program is executed by the processor, the above functions defined in the method disclosed in the embodiment of the present application are performed.
  • the above method steps and system units can also be implemented using a controller and a non-volatile readable storage medium for storing a computer program that enables the controller to implement the above steps or unit functions.
  • functionality may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functionality may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
  • Computer-readable media includes computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Storage media can be any available media that can be accessed by a general purpose or special purpose computer.
  • the computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, or may be used to carry or store instructions in the form of or any other medium containing the required program code for the data structures and capable of being accessed by a general-purpose or special-purpose computer or a general-purpose or special-purpose processor. Also, any connection is properly termed a computer-readable medium.
  • coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave are used to deliver software from a website, server, or other remote source
  • coaxial cable Cable, fiber optic cable, twisted pair, DOL or wireless technologies such as infrared, radio and microwave are included in the definition of media.
  • disks and optical disks include compact disks (CDs), laser disks, optical disks, digital versatile disks (DVDs), floppy disks, and Blu-ray disks, where disks typically reproduce data magnetically, while optical disks reproduce data optically using lasers. . of the above Combinations should also be included within the scope of computer-readable media.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Library & Information Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Image Processing (AREA)

Abstract

本申请涉及存储领域,公开了一种视频图像数据存储的方法、装置、设备及可读介质。所述方法包括:获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;在所述行向量像素点中从与所述参考像素点相邻的像素点开始依次进行逻辑运算并按照所述像素点矩阵的行向量顺序进行遍历,以将所述像素点矩阵的每个像素点的对应结果写入DDR。本发明公开的方法有效降低了DDR读写过程的能耗,并且对于大数据量应用场景降低功耗的效果尤为明显,对于产品功耗要求较高的场合具有实际意义。

Description

一种视频图像数据存储的方法、装置、设备及可读介质
相关申请的交叉引用
本申请要求于2022年09月16日提交中国专利局、申请号202211129967.0、申请名称为“一种视频图像数据存储的方法、装置、设备及可读介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及存储领域,尤其涉及一种视频图像数据存储的方法、装置、设备及可读介质。
背景技术
视频、图像是系统中常见的大数据量的应用场景,其经常使用DDR(Double Data Rate,全称DDR SDRAM,简称DDR,双倍速率同步动态随机存储器)作为缓存。其中DDR作为缓存时具有访问速度快、体积小、价格相比较SRAM(Static Random-Access Memory,SRAM静态随机存取存储器)低等优点,因此成为现代数字设备中的主要部件,主要负责数据的临时存取。
随着DDR的发展,其存储速率越来越高,但每次访问的功耗没有显著降低。现有技术中,降低DDR的功耗,大多采用硬件控制方法,比如采用门控时钟,通过控制部分逻辑的工作实现动态功耗管理;或者采用动态频率控制,根据工作负载率,实现在轻负载、对速率要求不高的情况下适当降低DDR工作频率,实现降低功耗的目的。然而,采用硬件控制方法降低DDR的功耗会存在诸多缺点,门控时钟只能降低DDR无访问需求时的功耗,且仅为DDR控制器或PHY(Physical,端口物理层)中的部分逻辑,不能有效减小DDR读写访问时的功耗,在DDR负载很高时效果不明显,动态频率控制同样在DDR负载很高时效果不明显。
发明内容
有鉴于此,本申请提出了一种视频图像数据存储的方法、装置、设备及可读介质。其中,本申请提出的一种视频图像数据存储的方法通过视频图像数据的相似性和DDR改变数据极性存储的电路特性,将视频图像数据在存储时转化为更多的“1”高电平进行存储,以减少存储时的功耗。
基于以上目的,本申请的实施例的一个方面提供了一种视频图像数据存储的方法,方法包括以下步骤:获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;在行向量 像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR。
在一些实施例中,方法还包括:将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点。
在一些实施例中,方法还包括:将DDR中存储的像素点的数据依次按照DDR的写入顺序进行与逻辑运算相反的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
在一些实施例中,在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR包括:在行向量像素点中从与参考像素点相邻的像素点开始依次进行异或后取反的运算并按照像素点矩阵的行向量顺序进行遍历。
在一些实施例中,方法还包括:将DDR中存储的像素点的数据依次按照DDR的写入顺序进行取反后异或的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
在一些实施例中,获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点包括:获取视频图像的像素点矩阵的行向量组和列向量组,得到像素点矩阵的行向量顺序和列向量顺序;设置当前行向量像素点的首列像素点为当前行向量像素点的参考像素点,并按照行向量顺序依次进行设置以适应当前行向量像素点的逻辑运算。
在一些实施例中,方法还包括:将当前行向量像素点的参考像素点的数据与DDR中的参考像素点的前一数据进行逻辑运算;将当前行向量像素点的参考像素点的对应结果写入DDR中,并更新DDR中参考像素点的数据为当前行向量像素点的参考像素点的数据。
在一些实施例中,将当前行向量像素点的参考像素点的数据与DDR中的参考像素点的前一数据进行逻辑运算包括:将当前行向量像素点的参考像素点的数据与DDR中的参考像素点的前一数据进行异或后取反的运算。
在一些实施例中,在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR包括:在当前行向量像素点中按照列向量顺序依次与前一像素点的数据进行逻辑运算并将对应的结果写入DDR中;按照行向量顺序遍历像素点矩阵的每个像素点并将其对应结果写入DDR中。
在一些实施例中,在当前行向量像素点中按照列向量顺序依次与前一像素点的数据进行 逻辑运算并将对应的结果写入DDR中包括:在当前行向量像素点中按照列向量顺序依次与前一像素点的数据进行异或后取反的运算并将对应的结果写入DDR中。
本申请实施例的另一个方面,还提供了一种视频图像数据存储的装置,装置包括以下模块:第一模块,配置用于获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;第二模块,配置用于在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR。
在一些实施例中,装置还包括:第三模块,配置用于将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点。
在一些实施例中,装置还包括:第四模块,配置用于将DDR中存储的像素点的数据依次按照DDR的写入顺序进行与逻辑运算相反的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
本申请实施例的另一方面,还提供一种计算机设备,包括至少一个处理器;以及存储器,存储器存储有可在处理器上运行的计算机指令,指令由处理器执行时实现上述任一方法的步骤。
本申请实施例的另一方面,还提供了一种非易失性可读存储介质,非易失性可读存储介质存储有被处理器执行时实现如上任一方法步骤的计算机程序。
本申请至少具有以下有益效果:本申请提出一种视频图像数据存储的方法、装置、设备及可读介质,其中本申请提出的一种视频图像数据存储的方法利用视频图像数据的相似性和DDR改变数据极性存储的电路特性,在保证数据读写正确的前提下,有效降低了DDR读写过程的能耗,并且对于大数据量应用场景降低功耗的效果尤为明显,对于产品功耗要求较高的场合具有实际意义。
附图说明
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其它的实施例。
图1示出的为本申请提供的一种视频图像数据存储的方法的实施例的示意图;
图2示出的为本申请提供的一种视频图像数据存储的方法的另一实施例的示意图;
图3示出的为本申请提供的一种视频图像数据存储的方法的另一实施例的示意图;
图4示出的为本申请提供的一种视频图像数据存储的方法的另一实施例的示意图;
图5示出的是本申请提供的一种视频图像数据存储的装置的实施例的示意图;
图6示出的是本申请提供的一种视频图像数据存储的装置的另一实施例的示意图;
图7示出的是本申请提供的一种视频图像数据存储的装置的另一实施例的示意图;
图8示出的是本申请提供的一种计算机设备的实施例的示意图;
图9示出的是本申请提供的一种非易失性可读存储介质的实施例的示意图。
具体实施方式
以下描述了本申请的实施例。然而,应该理解,所公开的实施例仅仅是示例,并且其它实施例可以采取各种替代形式。
此外,需要说明的是,本申请实施例中所有使用“第一”和“第二”的表述均是为了区分两个相同名称非相同的实体或者非相同的参量,可见“第一”“第二”仅为了表述的方便,不应理解为对本申请实施例的限定,后续实施例对此不再一一说明。术语“包括”、“包含”或其任何其它变形旨在涵盖非排他性的包括,以使包含一系列要素的过程、方法、物品或装置不仅包括那些要素,也可以包括未明确列出的或这些过程、方法、物品或装置所固有的要素。
视频图像数据由一帧帧的数据组成,每帧数据又由像素元素组成,像素数据包括RGB(Red、Green、Blue,一种颜色系统,通过R、G、B的变化和叠加表示各种颜色)。每帧数据的相邻像素数据(横向、纵向)一般具有连续性,即视频图像在DDR访问时,大量相邻数据会存在相似性。
DDR4作为DDR的一种,其相较于前代的DDR有一个新的特性,DDR4使用了一种新的驱动标准,即POD(Pseudo Open-Drain伪漏极开路)。在POD中,接收器将信号端接到VDD,而不是VDD/2。当DDR传输0时,SSTL(STUB SERIES TERMINATED LOGIC短截线串联端接逻辑)和POD均有电流消耗。DDR4采用比DDR3更低的电压,在一定程度上补偿了因DDR4接到VDD而造成的更多电流消耗。当DDR传输1时,POD在驱动高电平时不消耗能量。因此,当DDR访问时,字节中多于4个‘0’时,采用DBI(Data Bus Inversion,一种DDR中改变数据极性存储的方法,可用于减少功耗)功能,使其传输更多的‘1’,可以达到降低DDR访问功耗的目的。其中DBI功能的原理为:假设X xor Y=Z,则X xor Z=Y,基值X和基值Y异或后得到数据Z, 而基值X与数据Z异或后,可以恢复基值Y。
如果两个像素数据分别为A、B,A、B异或后得到C,两个相似的数据异或后的值C中‘0’较多。C值进行DBI得到‘1’值较多的D。DDR访问时传输D,较多的‘1’值传输,从而可降低功耗。完成传输后,再根据DBI状态,D变为C,将A与C异或后,恢复原像素数据B。
下面将结合附图说明本申请的一个或多个实施例。
基于以上目的,本申请实施例的第一个方面,提出了一种视频图像数据存储的方法的实施例。图1示出的为本申请提供的一种视频图像数据存储的方法的实施例的示意图。如图1所示,本申请实施例的一种视频图像数据存储的方法包括以下步骤:
S1、获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;
S2、在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR。
基于以上目的,本申请实施例的第一个方面,提出了一种视频图像数据存储的方法的实施例。图2示出的为本申请提供的一种视频图像数据存储的方法的另一实施例的示意图。如图2所示,本申请实施例的一种视频图像数据存储的方法包括以下步骤:
S1、获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;
S2、在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR;
S3、将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点。
基于以上目的,本申请实施例的第一个方面,提出了一种视频图像数据存储的方法的实施例。图3示出的为本申请提供的一种视频图像数据存储的方法的另一实施例的示意图。如图3所示,本申请实施例的一种视频图像数据存储的方法包括以下步骤:
S1、获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;
S2、在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR;
S3、将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点;
S4、将DDR中存储的像素点的数据依次按照DDR的写入顺序进行与逻辑运算相反的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
图4示出的为本申请提供的一种视频图像数据存储的方法的另一实施例的示意图,如图4所示,对于一张1080P(分辨率1920×1080)图像的像素排列,图像数据传输时按照像素点为单位,顺序为x0y0,x1y0,…,x1919y0,x0y1,x1y1,…,x1919y1,…,x0y1079,x1y1079,…,x1919y1079。
第一行像素点数据,记像素点x0y0的数据为D[x0y0],将其作为第一行数据的参考数据,将其写入DDR,并缓存在RAM(Random Access Memory,随机存取存储器)中,记为Reg0。像素点x1y0的数据D[x1y0]与像素点x0y0的数据D[x0y0]进行异或计算,将结果记为D`[x1y0],然后按位取反得到D``[x1y0],写入DDR中。像素点x2y0的数据D[x2y0]与像素点x1y0的数据D[x1y0]进行异或计算,将结果记为D`[x2y0],然后按位取反得到D``[x2y0]写入DDR中。以此类推,直至本行最后一个像素点计算完成,得到D`[x1919y0],然后按位取反得到D``[x1919y0]写入DDR中。
第二行像素点数据,记像素点x0y1的数据为D[x0y1],将其与Reg0的数据进行异或计算,并更新Reg0数据为D[x0y1],将异或计算结果记为D`[x0y1],然后按位取反得到D``[x0y1],写入DDR中。像素点x1y1的数据D[x1y1]与像素点x0y0的数据D[x1y1]进行异或计算,将结果记为D`[x1y1],然后按位取反得到D``[x1y1],写入DDR中。像素点x2y1的数据D[x2y1]与像素点x1y1的数据D[x1y1]进行异或计算,将结果记为D`[x2y1],然后按位取反得到D``[x2y1]写入DDR中。以此类推,直至本行最后一个像素点计算完成,得到D`[x1919y1],然后按位取反得到D``[x1919y1]写入DDR中。
第三行像素点数据,记像素点x0y3的数据为D[x0y2],将其与Reg0的数据进行异或计算,并更新Reg0数据为D[x0y2],将异或计算结果记为D`[x0y2],然后按位取反得到D``[x0y2],写入DDR中。像素点x1y2的数据D[x1y2]与像素点x0y0的数据D[x1y2]进行异或计算,将结果记为D`[x1y2],然后按位取反得到D``[x1y2],写入DDR中。像素点x2y2的数据D[x2y2]与像素点x1y2的数据D[x1y2]进行异或计算,将结果记为D`[x2y2],然后按位取反得到D``[x2y2]写入DDR中。以此类推,直至本行最后一个像素点计算完成,得到D`[x1919y2],然后按位取反得到D``[x1919y2]写入DDR中。以此类推,将全部的1080行数据依次进行计算后写入DDR中。
当从DDR中读出时,执行上述写入相反的操作,即可还原出原数据。首先读出像素点 x0y0的数据为D[x0y0],将其作为第一行数据的参考数据,并缓存在RAM中,记为Reg0。然后读出像素点x1y0的数据D``[x1y0],先按位取反,得到D`[x1y0],然后与像素点x0y0的数据D[x0y0]进行异或计算,则数据恢复为D[x1y0]。读出像素点x2y0的数据D``[x2y0],先按位取反,得到D`[x2y0],然后与像素点x1y0的数据D[x1y0]进行异或计算,则数据恢复为D[x2y0]。以此类推,直至本行最后一个像素点计算完成,得到D[x1919y0]。
读出第二行像素点x0y1的数据为D``[x0y1],先按位取反,得到D`[x0y1],将其与Reg0的数据进行异或计算,恢复出数据D[x0y1],并更新Reg0数据为D[x0y1],读出像素点x1y1的数据D``[x1y1],先按位取反,得到D`[x1y1],将其与D[x0y1]的数据进行异或计算,恢复出数据D[x1y1]。读出像素点x2y1的数据D``[x2y1],先按位取反,得到D`[x2y1],将其与D[x1y1]的数据进行异或计算,恢复出数据D[x2y1]。以此类推,直至本行最后一个像素点计算完成,得到D[x1919y1]。
读出第三行像素点x0y3的数据为D``[x0y2],先按位取反,得到D`[x0y2],将其与Reg0的数据进行异或计算,恢复出数据D[x0y2],并更新Reg0数据为D[x0y2],读出像素点x1y2的数据D``[x1y2],先按位取反,得到D`[x1y2],将其与D[x0y2]的数据进行异或计算,恢复出数据D[x1y2]。读出像素点x2y2的数据D``[x2y2],先按位取反,得到D`[x2y2],将其与D[x1y2]的数据进行异或计算,恢复出数据D[x2y2]。以此类推,直至本行最后一个像素点计算完成,得到D[x1919y2]。
以此类推,将全部1080行数据依次从DDR中读出,并通过按位取反和异或运算,恢复出图像原数据。
上述通过相邻数据相似性的特性,将相邻数据进行异或运算,可有效降低数据中1的个数,再利用DBI特性,进行按位取反后,则数据中1的个数比原数据明显增加,可有效降低DDR读写的能耗。并且这种方法不局限于的一种视频图像数据的DDR存储方法,可以扩展到类似的DDR使用领域,可有效提高降低DDR功耗,对产品功耗要求较高的场合具有实际意义。
本申请的实施例的第二个方面,提出了一种视频图像数据存储的装置。图5示出的是本申请提供的一种视频图像数据存储的装置的实施例的示意图。如图5所示,本申请提供的一种视频图像数据存储的装置包括:第一模块011,配置用于获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;第二模块012,配置用于在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR。
本申请实施例的第二个方面,提出了一种视频图像数据存储的装置。图6示出的是本申请提供的一种视频图像数据存储的装置的另一实施例的示意图。如图6所示,本申请提供的一种视频图像数据存储的装置包括:第一模块011,配置用于获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;第二模块012,配置用于在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR;第三模块013,配置用于将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点。
本申请实施例的第二个方面,提出了一种视频图像数据存储的装置。图7示出的是本申请提供的一种视频图像数据存储的装置的另一实施例的示意图。如图7所示,本申请提供的一种视频图像数据存储的装置包括:第一模块011,配置用于获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;第二模块012,配置用于在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR;第三模块013,配置用于将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点;第四模块014,配置用于将DDR中存储的像素点的数据依次按照DDR的写入顺序进行与逻辑运算相反的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
基于以上目的,本申请实施例的第三个方面,提出了一种计算机设备,图8示出的是本申请提供的一种计算机设备的实施例的示意图。如图8所示,本申请提供的一种计算机设备的实施例,包括以下模块:至少一个处理器021;以及存储器022,存储器022存储有可在处理器021上运行的计算机指令023。
本申请还提供了一种非易失性可读存储介质。图9示出的是本申请提供的一种非易失性可读存储介质的实施例的示意图。如图9所示,非易失性可读存储介质031存储有被处理器执行时执行如上方法的计算机程序032。其中,计算机程序032执行的步骤包括:获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR。
在一些实施例中,方法还包括:将DDR中存储的像素点的数据依次按照DDR的写入顺序进 行与逻辑运算相反的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
在一些实施例中,方法还包括:将行向量像素点的参考像素点的数据写入DDR中,并以当前行向量像素点的参考像素点的数据更新DDR中的参考像素点的前一数据,以使DDR中的参考像素点的数据适应当前行向量像素点。
在一些实施例中,在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR包括:在行向量像素点中从与参考像素点相邻的像素点开始依次进行异或后取反的运算并按照像素点矩阵的行向量顺序进行遍历。
在一些实施例中,方法还包括:将DDR中存储的像素点的数据依次按照DDR的写入顺序进行取反后异或的运算,以将DDR中存储的像素点的数据还原为原始数据并读出。
在一些实施例中,获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点包括:获取视频图像的像素点矩阵的行向量组和列向量组,得到像素点矩阵的行向量顺序和列向量顺序;设置当前行向量像素点的首列像素点为当前行向量像素点的参考像素点,并按照行向量顺序依次进行设置以适应当前行向量像素点的逻辑运算。
在一些实施例中,方法还包括:还包括:将当前行向量像素点的参考像素点的数据与DDR中的参考像素点的前一数据进行逻辑运算;将当前行向量像素点的参考像素点的对应结果写入DDR中,并更新DDR中参考像素点的数据为当前行向量像素点的参考像素点的数据。
在一些实施例中,将当前行向量像素点的参考像素点的数据与DDR中的参考像素点的前一数据进行逻辑运算包括:将当前行向量像素点的参考像素点的数据与DDR中的参考像素点的前一数据进行异或后取反的运算。
在一些实施例中,在行向量像素点中从与参考像素点相邻的像素点开始依次进行逻辑运算并按照像素点矩阵的行向量顺序进行遍历,以将像素点矩阵的每个像素点的对应结果写入DDR包括:在当前行向量像素点中按照列向量顺序依次与前一像素点的数据进行逻辑运算并将对应的结果写入DDR中;按照行向量顺序遍历像素点矩阵的每个像素点并将其对应结果写入DDR中。
在一些实施例中,在当前行向量像素点中按照列向量顺序依次与前一像素点的数据进行逻辑运算并将对应的结果写入DDR中包括:在当前行向量像素点中按照列向量顺序依次与前一像素点的数据进行异或后取反的运算并将对应的结果写入DDR中。
最后需要说明的是,本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程,可以通过计算机程序来指令相关硬件来完成,设置系统参数的方法的程序可存储于一计算机可读取存储介质中,该程序在执行时,可包括如上述各方法的实施例的流程。其中,程序的存储介质可为磁碟、光盘、只读存储记忆体(ROM)或随机存储记忆体(RAM)等。上述计算机程序的实施例,可以达到与之对应的前述任意方法实施例相同或者相类似的效果。
此外,根据本申请实施例公开的方法还可以被实现为由处理器执行的计算机程序,该计算机程序可以存储在非易失性可读存储介质中。在该计算机程序被处理器执行时,执行本申请实施例公开的方法中限定的上述功能。
此外,上述方法步骤以及系统单元也可以利用控制器以及用于存储使得控制器实现上述步骤或单元功能的计算机程序的非易失性可读存储介质实现。
本领域技术人员还将明白的是,结合这里的公开所描述的各种示例性逻辑块、模块、电路和算法步骤可以被实现为电子硬件、计算机软件或两者的组合。为了清楚地说明硬件和软件的这种可互换性,已经就各种示意性组件、方块、模块、电路和步骤的功能对其进行了一般性的描述。这种功能是被实现为软件还是被实现为硬件取决于具体应用以及施加给整个系统的设计约束。本领域技术人员可以针对每种具体应用以各种方式来实现的功能,但是这种实现决定不应被解释为导致脱离本申请实施例公开的范围。
在一个或多个示例性设计中,功能可以在硬件、软件、固件或其任意组合中实现。如果在软件中实现,则可以将功能作为一个或多个指令或代码存储在计算机可读介质上或通过计算机可读介质来传送。计算机可读介质包括计算机存储介质和通信介质,该通信介质包括有助于将计算机程序从一个位置传送到另一个位置的任何介质。存储介质可以是能够被通用或专用计算机访问的任何可用介质。作为例子而非限制性的,该计算机可读介质可以包括RAM、ROM、EEPROM、CD-ROM或其它光盘存储设备、磁盘存储设备或其它磁性存储设备,或者是可以用于携带或存储形式为指令或数据结构的所需程序代码并且能够被通用或专用计算机或者通用或专用处理器访问的任何其它介质。此外,任何连接都可以适当地称为计算机可读介质。例如,如果使用同轴线缆、光纤线缆、双绞线、数字用户线路(DSL)或诸如红外线、无线电和微波的无线技术来从网站、服务器或其它远程源发送软件,则上述同轴线缆、光纤线缆、双绞线、D0L或诸如红外线、无线电和微波的无线技术均包括在介质的定义。如这里所使用的,磁盘和光盘包括压缩盘(CD)、激光盘、光盘、数字多功能盘(DVD)、软盘、蓝光盘,其中磁盘通常磁性地再现数据,而光盘利用激光光学地再现数据。上述内容的 组合也应当包括在计算机可读介质的范围内。
以上是本申请公开的示例性实施例,但是应当注意,在不背离权利要求限定的本申请实施例公开的范围的前提下,可以进行多种改变和修改。根据这里描述的公开实施例的方法权利要求的功能、步骤和/或动作不需以任何特定顺序执行。此外,尽管本申请实施例公开的元素可以以个体形式描述或要求,但除非明确限制为单数,也可以理解为多个。
应当理解的是,在本文中使用的,除非上下文清楚地支持例外情况,单数形式“一个”旨在也包括复数形式。还应当理解的是,在本文中使用的“和/或”是指包括一个或者一个以上相关联地列出的项目的任意和所有可能组合。
上述本申请实施例公开实施例序号仅仅为了描述,不代表实施例的优劣。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成,也可以通过程序来指令相关的硬件完成,程序可以存储于一种非易失性可读存储介质中,上述提到的存储介质可以是只读存储器,磁盘或光盘等。
所属领域的普通技术人员应当理解:以上任何实施例的讨论仅为示例性的,并非旨在暗示本申请实施例公开的范围(包括权利要求)被限于这些例子;在本申请实施例的思路下,以上实施例或者不同实施例中的技术特征之间也可以进行组合,并存在如上的本申请实施例的不同方面的许多其它变化,为了简明它们没有在细节中提供。因此,凡在本申请实施例的精神和原则之内,所做的任何省略、修改、等同替换、改进等,均应包含在本申请实施例的保护范围之内。

Claims (20)

  1. 一种视频图像数据存储的方法,其特征在于,包括:
    获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;
    在所述行向量像素点中从与所述参考像素点相邻的像素点开始依次进行逻辑运算并按照所述像素点矩阵的行向量顺序进行遍历,以将所述像素点矩阵的每个像素点的对应结果写入DDR。
  2. 根据权利要求1所述的方法,其特征在于,还包括:
    将所述行向量像素点的参考像素点的数据写入所述DDR中,并以当前行向量像素点的参考像素点的数据更新所述DDR中的参考像素点的前一数据,以使所述DDR中的参考像素点的数据适应所述当前行向量像素点。
  3. 根据权利要求1所述的方法,其特征在于,所述行向量像素点包括第一行向量像素点,所述将所述行向量像素点的参考像素点的数据写入所述DDR中,包括:
    获取所述第一行向量像素点的第一行像素点数据,将所述第一行像素点数据作为所述参考像素点的数据,并写入所述DDR中。
  4. 根据权利要求3所述的方法,其特征在于,所述行向量像素点包括第二行向量像素点,所述将所述行向量像素点的参考像素点的数据写入所述DDR中,包括:
    获取所述第二行向量像素点的第二行像素点数据,将所述第二行像素点数据与所述第一行像素点数据进行异或计算,生成所述参考像素点的数据,并写入所述DDR中。
  5. 根据权利要求4所述的方法,其特征在于,所述行向量像素点包括第三行向量像素点,所述将所述行向量像素点的参考像素点的数据写入所述DDR中,包括:
    获取所述第三行向量像素点的第二行像素点数据,将所述第三行像素点数据与所述第二行像素点数据进行异或计算,生成所述参考像素点的数据,并写入所述DDR中。
  6. 根据权利要求1所述的方法,其特征在于,还包括:
    将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行与所述逻辑运算相反的运算,以将所述DDR中存储的像素点的数据还原为原始数据并读出。
  7. 根据权利要求6所述的方法,其特征在于,所述将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行与所述逻辑运算相反的运算,包括:
    获取所述视频图像的分辨率以及与所述分辨率对应的写入顺序;
    将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行与所述逻辑运算相反的运算。
  8. 根据权利要求1所述的方法,其特征在于,所述在所述行向量像素点中从与所述参考像素点相邻的像素点开始依次进行逻辑运算并按照所述像素点矩阵的行向量顺序进行遍历,以将所述像素点矩阵的每个像素点的对应结果写入DDR包括:
    在所述行向量像素点中从与所述参考像素点相邻的像素点开始依次进行异或后取反的运算并按照所述像素点矩阵的行向量顺序进行遍历。
  9. 根据权利要求8所述的方法,其特征在于,还包括:
    将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行取反后异或的运算,以将所述DDR中存储的像素点的数据还原为原始数据并读出。
  10. 根据权利要求9所述的方法,其特征在于,所述像素点的数据包括第一行像素点数据,所述将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行取反后异或的运算,以将所述DDR中存储的像素点的数据还原为原始数据并读出,包括:
    从所述DDR中读取与所述第一行像素点数据对应的参考像素点的数据,并存储至随机存取存储器中;
    依次按照所述DDR的写入顺序对所述第一行像素点数据进行按位取反处理,并将所述第一行像素点数据与所述参考像素点的数据进行异或计算,直至第一行向量像素点中最后一个像素点计算完成,将所述DDR中存储的像素点的数据还原为原始数据并读出。
  11. 根据权利要求10所述的方法,其特征在于,所述像素点的数据包括第二行像素点数据,所述将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行取反后异或的运算,以将所述DDR中存储的像素点的数据还原为原始数据并读出,包括:
    从所述DDR中读取与所述第二行像素点数据;
    依次按照所述DDR的写入顺序对所述第二行像素点数据进行按位取反处理,并将所述第二行像素点数据与所述参考像素点的数据进行异或计算,直至第二行向量像素点中最后一个像素点计算完成,将所述DDR中存储的像素点的数据还原为原始数据并读出。
  12. 根据权利要求11所述的方法,其特征在于,所述像素点的数据包括第三行像素点数据,所述将所述DDR中存储的像素点的数据依次按照所述DDR的写入顺序进行取反后异或的运算,以将所述DDR中存储的像素点的数据还原为原始数据并读出,包括:
    从所述DDR中读取所述第三行像素点数据;
    依次按照所述DDR的写入顺序对所述第三行像素点数据进行按位取反处理,并将所述第三行像素点数据与所述参考像素点的数据进行异或计算,直至第三行向量像素点中最后一个像素点计算完成,将所述DDR中存储的像素点的数据还原为原始数据并读出。
  13. 根据权利要求1所述的方法,其特征在于,所述获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点包括:
    获取视频图像的像素点矩阵的行向量组和列向量组,得到所述像素点矩阵的行向量顺序和列向量顺序;
    设置当前行向量像素点的首列像素点为所述当前行向量像素点的参考像素点,并按照所述行向量顺序依次进行设置以适应所述当前行向量像素点的逻辑运算。
  14. 根据权利要求13所述的方法,其特征在于,还包括:
    将所述当前行向量像素点的参考像素点的数据与所述DDR中的参考像素点的前一数据进行逻辑运算;
    将所述当前行向量像素点的参考像素点的对应结果写入DDR中,并更新所述DDR中参考像素点的数据为所述当前行向量像素点的参考像素点的数据。
  15. 根据权利要求14所述的方法,其特征在于,所述将所述当前行向量像素点的参考像素点的数据与所述DDR中的参考像素点的前一数据进行逻辑运算包括:
    将所述当前行向量像素点的参考像素点的数据与所述DDR中的参考像素点的前一数据进行异或后取反的运算。
  16. 根据权利要求14所述的方法,其特征在于,所述在所述行向量像素点中从与所述参考像素点相邻的像素点开始依次进行逻辑运算并按照所述像素点矩阵的行向量顺序进行遍历,以将所述像素点矩阵的每个像素点的对应结果写入DDR包括:
    在所述当前行向量像素点中按照所述列向量顺序依次与前一像素点的数据进行逻辑运算并将对应的结果写入所述DDR中;
    按照所述行向量顺序遍历所述像素点矩阵的每个像素点并将其对应结果写入DDR中。
  17. 根据权利要求16所述的方法,其特征在于,所述在所述当前行向量像素点中按照所述列向量顺序依次与前一像素点的数据进行逻辑运算并将对应的结果写入所述DDR中包括:
    在所述当前行向量像素点中按照所述列向量顺序依次与前一像素点的数据进行异或后取反的运算并将对应的结果写入所述DDR中。
  18. 一种视频图像数据存储的装置,其特征在于,包括:
    第一模块,配置用于获取视频图像的像素点矩阵并在行向量像素点中设置参考像素点;
    第二模块,配置用于在所述行向量像素点中从与所述参考像素点相邻的像素点开始依次进行逻辑运算并按照所述像素点矩阵的行向量顺序进行遍历,以将所述像素点矩阵的每个像素点的对应结果写入DDR。
  19. 一种计算机设备,其特征在于,包括:
    至少一个处理器;以及
    存储器,所述存储器存储有可在所述处理器上运行的计算机指令,所述指令由所述处理器执行时实现权利要求1-17任意一项所述方法的步骤。
  20. 一种非易失性可读存储介质,所述非易失性可读存储介质存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现权利要求1-17任意一项所述方法的步骤。
PCT/CN2023/077995 2022-09-16 2023-02-23 一种视频图像数据存储的方法、装置、设备及可读介质 WO2024055525A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211129967.0 2022-09-16
CN202211129967.0A CN115203470B (zh) 2022-09-16 2022-09-16 一种视频图像数据存储的方法、装置、设备及可读介质

Publications (1)

Publication Number Publication Date
WO2024055525A1 true WO2024055525A1 (zh) 2024-03-21

Family

ID=83573654

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/077995 WO2024055525A1 (zh) 2022-09-16 2023-02-23 一种视频图像数据存储的方法、装置、设备及可读介质

Country Status (2)

Country Link
CN (1) CN115203470B (zh)
WO (1) WO2024055525A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115203470B (zh) * 2022-09-16 2023-02-28 苏州浪潮智能科技有限公司 一种视频图像数据存储的方法、装置、设备及可读介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101039374A (zh) * 2006-03-14 2007-09-19 联想(北京)有限公司 一种图像无损压缩和图像解压缩方法
CN103124350A (zh) * 2012-12-24 2013-05-29 东软集团股份有限公司 基于rle的图像压缩方法及装置
WO2020181554A1 (zh) * 2019-03-14 2020-09-17 Oppo广东移动通信有限公司 预测值的确定方法、解码器以及计算机存储介质
CN113689407A (zh) * 2021-08-25 2021-11-23 青岛睿维申信息科技有限公司 图像校正方法及相关设备
CN115203470A (zh) * 2022-09-16 2022-10-18 苏州浪潮智能科技有限公司 一种视频图像数据存储的方法、装置、设备及可读介质

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112235568B (zh) * 2019-07-15 2024-03-26 华为技术有限公司 图像编码方法、解码方法、装置和存储介质
CN113706639B (zh) * 2021-07-21 2024-02-23 国网江苏省电力有限公司电力科学研究院 一种基于矩形nam的图像压缩方法、装置、存储介质及计算设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101039374A (zh) * 2006-03-14 2007-09-19 联想(北京)有限公司 一种图像无损压缩和图像解压缩方法
CN103124350A (zh) * 2012-12-24 2013-05-29 东软集团股份有限公司 基于rle的图像压缩方法及装置
WO2020181554A1 (zh) * 2019-03-14 2020-09-17 Oppo广东移动通信有限公司 预测值的确定方法、解码器以及计算机存储介质
CN113689407A (zh) * 2021-08-25 2021-11-23 青岛睿维申信息科技有限公司 图像校正方法及相关设备
CN115203470A (zh) * 2022-09-16 2022-10-18 苏州浪潮智能科技有限公司 一种视频图像数据存储的方法、装置、设备及可读介质

Also Published As

Publication number Publication date
CN115203470A (zh) 2022-10-18
CN115203470B (zh) 2023-02-28

Similar Documents

Publication Publication Date Title
WO2024055525A1 (zh) 一种视频图像数据存储的方法、装置、设备及可读介质
JP3177207B2 (ja) リフレッシュ間隔制御装置及び方法、並びにコンピュータ
JP2005327437A (ja) 半導体記憶装置
EP3382565A1 (en) Selective noise tolerance modes of operation in a memory
WO2014030941A1 (en) Apparatus and method for data movement
US20200134799A1 (en) Image processing method and device
WO2023185094A1 (zh) 一种视频压缩系统、方法、计算机可读存储介质及服务器
WO2021208558A1 (zh) 一种深度学习大模型训练的方法、系统、设备及介质
JP2016531378A (ja) スタティックランダムアクセスメモリ(sram)リセット動作中にsramビットセルをバイアスする電圧または電流のための回路ならびに関連するシステムおよび方法
WO2023221627A1 (zh) 写数据信号延迟控制方法、装置、设备和介质
JP2522258B2 (ja) 信号処理装置
TW200406784A (en) Reducing the effect of write disturbs in polymer memories
US11698730B2 (en) Data storage method, apparatus, and device, and readable storage medium
WO2023179136A1 (zh) 一种视频压缩系统及服务器
US20230281125A1 (en) Method and device for selecting cache line to be replaced, and storage medium
US20210004286A1 (en) Data processing
Gong et al. Design of high-speed real-time sensor image processing based on FPGA and DDR3
JP2638458B2 (ja) 半導体メモリ
JP2021157295A (ja) メモリ制御装置
TW201616478A (zh) 省電顯示系統及其方法
WO2022057054A1 (zh) 一种卷积运算优化方法、系统、终端以及存储介质
CN116862756B (zh) 行数据处理方法、行缓存器、电子设备及存储介质
CN112532894B (zh) 图像处理方法、装置及系统
KR102105644B1 (ko) Mlc stt-mram에 영상을 저장하는 메모리 제어 장치 및 방법
TWI700817B (zh) 靜態隨機存取記憶體系統及其資料讀寫方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23864268

Country of ref document: EP

Kind code of ref document: A1