WO2022115999A1

WO2022115999A1 - Data processing method and data processing device

Info

Publication number: WO2022115999A1
Application number: PCT/CN2020/133127
Authority: WO
Inventors: 王悦名; 郑萧桢
Original assignee: SZ DJI Technology Co Ltd
Current assignee: SZ DJI Technology Co Ltd
Priority date: 2020-12-01
Filing date: 2020-12-01
Publication date: 2022-06-09
Anticipated expiration: 2023-06-01
Also published as: CN114731412A

Abstract

A data processing method and a data processing device. The data processing method comprises: according to a global motion vector between a current frame and a reference frame, obtaining first image data of the reference frame from a data storage apparatus and caching the first image data; according to a motion vector of an image block to be encoded or to be decoded in the current frame, searching the cache for reference image data corresponding to the image block, and encoding or decoding the image block according to the reference image data. In this way, the efficiency of encoding or decoding can be effectively improved.

Description

A data processing method and data processing device

technical field

本申请涉及计算机技术领域，尤其涉及一种数据处理方法及数据处理设备。The present application relates to the field of computer technology, and in particular, to a data processing method and data processing device.

Background technique

随着计算机技术、数字多媒体技术以及编码解码技术的不断发展，视频及图像在各个领域以及人们的日常生活中也变得越来越普及。其中，编码器对视频或图像的编码可以包括帧间编码和帧内编码，而在编码器进行帧间编码时，往往需要从参考帧中获取参考数据来对当前帧进行预测。编码器中缓存参考数据的方法通常是基于Cache架构缓存参考数据，Cache是一种高速缓冲存储器，该方法将参考数据缓存到Cache内，进行帧间编码时，编码器可以从Cache中来获取参考数据以进行编码。With the continuous development of computer technology, digital multimedia technology and coding and decoding technology, video and images have become more and more popular in various fields and people's daily life. The encoding of the video or image by the encoder may include inter-frame encoding and intra-frame encoding. When the encoder performs inter-frame encoding, it is often necessary to obtain reference data from a reference frame to predict the current frame. The method of caching reference data in the encoder is usually based on the Cache architecture to cache the reference data. Cache is a kind of cache memory. This method caches the reference data in the Cache. When performing inter-frame encoding, the encoder can obtain the reference data from the Cache. data to encode.

目前，在一帧图像开始编码时，通常会根据零运动矢量来获取参考数据并缓存到Cache中。该方法在静止或小幅运动的视频编码时，通常能获取到帧间预测所需的参考数据，但是在有较大运动的视频编码时，往往获取不到帧间预测所需的参考数据，从而导致图像刚开始编码的部分的编码效率较低。而且，编码器需要的最优的参考数据可能不在Cache中，在这种情况下，编码器只能使用Cache内已有的数据来进行帧间预测，这样也会影响硬件编码器帧间预测的编码效率。At present, when a frame of image starts to be encoded, reference data is usually obtained according to the zero motion vector and cached in the Cache. This method can usually obtain the reference data required for inter-frame prediction when encoding still or small-moving videos, but often cannot obtain the reference data required for inter-frame prediction when encoding videos with large motion. As a result, the coding efficiency of the part of the image at the beginning of coding is low. Moreover, the optimal reference data required by the encoder may not be in the Cache. In this case, the encoder can only use the existing data in the Cache for inter-frame prediction, which will also affect the hardware encoder's inter-frame prediction. coding efficiency.

发明内容SUMMARY OF THE INVENTION

本申请实施例公开了一种数据处理方法及数据处理设备，可以有效提升编码或解码的效率。The embodiments of the present application disclose a data processing method and a data processing device, which can effectively improve the efficiency of encoding or decoding.

本申请实施例第一方面公开了一种数据处理方法，所述方法包括：A first aspect of the embodiments of the present application discloses a data processing method, and the method includes:

根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取所述参考帧的第一图像数据进行缓存；According to the global motion vector between the current frame and the reference frame, the first image data of the reference frame is obtained from the data storage device for buffering;

根据所述当前帧中待编码或待解码的图像块的运动矢量从所述缓存中查找所述图像块对应的参考图像数据，并根据所述参考图像数据对所述图像块进行编码或者解码。The reference image data corresponding to the image block is searched from the cache according to the motion vector of the image block to be encoded or decoded in the current frame, and the image block is encoded or decoded according to the reference image data.

本申请实施例第二方面公开了一种数据处理设备，所述数据处理设备包括：处理器和存储器，其中：A second aspect of the embodiments of the present application discloses a data processing device, the data processing device includes: a processor and a memory, wherein:

所述存储器，用于存储有计算机程序，所述计算机程序包括程序指令；the memory for storing a computer program, the computer program including program instructions;

所述处理器调用所述程序指令时用于执行：When the processor invokes the program instructions, it is used to execute:

本申请实施例第三方面公开了一种数据处理装置，所述装置包括：A third aspect of the embodiments of the present application discloses a data processing apparatus, and the apparatus includes:

获取模块，用于根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取所述参考帧的第一图像数据进行缓存；an acquisition module, configured to acquire the first image data of the reference frame from the data storage device for buffering according to the global motion vector between the current frame and the reference frame;

查找模块，用于根据所述当前帧中待编码或待解码的图像块的运动矢量从所述缓存中查找所述图像块对应的参考图像数据，并根据所述参考图像数据对所述图像块进行编码或者解码。A search module, configured to search for the reference image data corresponding to the image block from the cache according to the motion vector of the image block to be encoded or decoded in the current frame, and to search for the image block according to the reference image data to encode or decode.

本申请实施例第四方面公开了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序，所述计算机程序被处理器执行时实现上述第一方面所述的数据处理方法。A fourth aspect of the embodiments of the present application discloses a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, implements the data processing method described in the first aspect.

本申请实施例可以根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的第一图像数据进行缓存，再根据当前帧中待编码或待解码的图像块的运动矢量从缓存中查找图像块对应的参考图像数据，并根据参考图像数据对图像块进行编码或者解码，特别是对于有较大运动的视频编码或者解码场景，可以有效提升编码或解码的效率。In this embodiment of the present application, the first image data of the reference frame may be acquired from the data storage device according to the global motion vector between the current frame and the reference frame, and then buffered according to the motion vector of the image block to be encoded or decoded in the current frame. Find the reference image data corresponding to the image block from the cache, and encode or decode the image block according to the reference image data, especially for video encoding or decoding scenes with large motion, which can effectively improve the efficiency of encoding or decoding.

Description of drawings

为了更清楚地说明本申请实施例中的技术方案，下面将对实施例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性的前提下，还可以根据这些附图获得其他的附图。In order to illustrate the technical solutions in the embodiments of the present application more clearly, the following briefly introduces the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can also be obtained from these drawings without any creative effort.

图1a是本现有技术公开的一种帧间编码的示意图；1a is a schematic diagram of an inter-frame coding disclosed in the prior art;

图1b是本申请实施例公开的一种数据处理系统的架构示意图；FIG. 1b is a schematic diagram of the architecture of a data processing system disclosed in an embodiment of the present application;

图2是本申请实施例公开的一种数据处理方法的流程示意图；2 is a schematic flowchart of a data processing method disclosed in an embodiment of the present application;

图3是本申请实施例公开的一种帧间编码的示意图；3 is a schematic diagram of an inter-frame coding disclosed in an embodiment of the present application;

图4是本申请实施例公开的另一种数据处理方法的流程示意图；4 is a schematic flowchart of another data processing method disclosed in an embodiment of the present application;

图5是本申请实施例公开的一种数据处理装置的结构示意图；5 is a schematic structural diagram of a data processing apparatus disclosed in an embodiment of the present application;

图6是本申请实施例公开的一种数据处理设备的结构示意图。FIG. 6 is a schematic structural diagram of a data processing device disclosed in an embodiment of the present application.

Detailed ways

下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

在编码或解码领域，进行帧间编码或解码时，需要从参考帧中获取参考图像数据来对当前帧进行预测。其中，基于Cache架构缓存帧间编码或解码所需要的参考帧的数据的方法是编码或解码领域中缓存参考帧的数据的方法之一。具体地，在对一帧图像开始编码或解码时，通常会根据零运动矢量来获取参考帧的数据并缓存到Cache中。该方法在静止或小幅运动的帧间编码或解码时，通常能获取到帧间预测所需要的参考帧的数据。但是在有较大运动的帧间编码或解码时，往往获取不到帧间预测所需要的参考帧的数据，从而导致图像刚开始编码或解码的部分的编码或解码效率较低，而只有通过Cache的更新才能逐渐获得帧间预测所需要的参考帧的数据。例如，如图1a所示为有较大运动的帧间编码或解码的情况，如图1a中由11标记的图像是参考帧图像，由12标记的图像是当前帧图像。可以看出，相对于参考帧图像，当前帧图像是整体向下运动的，图1a中由101标记的方框和102 标记的方框分别为参考帧和当前帧中相对应的区域。在编码或解码当前帧时，先编码或解码的是由103标记的方框，如果Cache初始时是根据零运动矢量来获取参考帧的数据并缓存到Cache中，则在进行编码或解码时，获取的是由104标记的方框，从图中可以看到，当前帧所要编码或解码的由103标记的方框所需要的参考帧的数据并不在Cache获取到的数据中，即不在由104标记的方框内。In the field of encoding or decoding, when performing inter-frame encoding or decoding, it is necessary to obtain reference image data from a reference frame to predict the current frame. Among them, the method of buffering the data of the reference frame required for inter-frame encoding or decoding based on the Cache architecture is one of the methods of buffering the data of the reference frame in the field of encoding or decoding. Specifically, when encoding or decoding a frame of image, the data of the reference frame is usually obtained according to the zero motion vector and cached in the Cache. In this method, the data of the reference frame required for the inter-frame prediction can usually be obtained during the inter-frame encoding or decoding of static or small motion. However, in the case of inter-frame encoding or decoding with large motion, the data of the reference frame required for inter-frame prediction is often not obtained, resulting in low encoding or decoding efficiency of the part of the image at the beginning of encoding or decoding. The update of the Cache can gradually obtain the data of the reference frame required for the inter-frame prediction. For example, in the case of inter-frame encoding or decoding with large motion as shown in FIG. 1a, the image marked by 11 in FIG. 1a is the reference frame image, and the image marked by 12 is the current frame image. It can be seen that, relative to the reference frame image, the current frame image moves downward as a whole, and the boxes marked by 101 and 102 in FIG. 1a are the corresponding regions in the reference frame and the current frame, respectively. When encoding or decoding the current frame, the box marked by 103 is first encoded or decoded. If the Cache initially obtains the data of the reference frame according to the zero motion vector and caches it in the Cache, then when encoding or decoding, The block marked by 104 is obtained. As can be seen from the figure, the data of the reference frame required by the block marked by 103 to be encoded or decoded by the current frame is not in the data obtained by the Cache, that is, it is not in the data obtained by 104. inside the marked box.

为解决上述问题，本申请实施例提出了一种数据处理方法，数据处理装置可以根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的第一图像数据进行缓存，根据当前帧中待编码或待解码的图像块的运动矢量从缓存中查找图像块对应的参考图像数据，并根据参考图像数据对图像块进行编码或者解码。通过实施上述方法，可以避免因较大的运动，而导致的不能获取到编码或解码所需参考数据的问题，从而可以有效提升编码或解码的效率。In order to solve the above problem, an embodiment of the present application proposes a data processing method. The data processing device can obtain the first image data of the reference frame from the data storage device according to the global motion vector between the current frame and the reference frame, and cache it, The reference image data corresponding to the image block is searched from the cache according to the motion vector of the image block to be encoded or decoded in the current frame, and the image block is encoded or decoded according to the reference image data. By implementing the above method, the problem that the reference data required for encoding or decoding cannot be obtained due to large motion can be avoided, thereby effectively improving the efficiency of encoding or decoding.

以下对本申请实施例的技术方案的实现细节进行详细阐述：The implementation details of the technical solutions of the embodiments of the present application are described in detail below:

请参阅图1b，图1b是本申请实施例提供的一种数据处理系统的架构示意图。该数据处理系统包括数据存储装置和数据处理装置，其中，数据处理装置包括数据缓存模块和数据处理模块。Please refer to FIG. 1b. FIG. 1b is a schematic structural diagram of a data processing system provided by an embodiment of the present application. The data processing system includes a data storage device and a data processing device, wherein the data processing device includes a data cache module and a data processing module.

其中，数据存储装置可以用来存储参考帧的图像数据，以使得在编码或解码时，可以根据接收到的数据处理装置发送的数据获取请求，向数据处理装置发送数据获取请求所对应的参考帧的图像数据。可选的，该数据存储装置可以是双倍速率同步动态随机存储器(Double Rate Synchronous Dynamic Random Access Memory，DDR SDRAM)，可简称为DDR。The data storage device can be used to store the image data of the reference frame, so that during encoding or decoding, the reference frame corresponding to the data acquisition request can be sent to the data processing device according to the received data acquisition request sent by the data processing device. image data. Optionally, the data storage device may be a double rate synchronous dynamic random access memory (Double Rate Synchronous Dynamic Random Access Memory, DDR SDRAM), which may be referred to as DDR for short.

其中，数据处理装置中的数据缓存模块可以缓存上述参考帧的图像数据中的部分数据，该数据缓存模块中所缓存的参考帧的图像数据可以根据不定时的更新，以使得在编码或解码时，可以根据数据处理模块发送的数据获取请求，向数据处理模块发送数据获取请求所对应的参考帧的图像数据。可选的，该数据缓存模块可以是Cache，Cache是一种高速缓冲存储器。该数据处理模块可以是编码器或解码器中帧间预测的模块。数据处理装置中的数据处理模块可以对图像或视频进行编码或解码，并在编码或解码的过程中向数据缓存模块发送数据获取请求，以获取进行编码或解码所需要的参考帧的图像数据。Wherein, the data buffer module in the data processing device can buffer part of the data in the image data of the reference frame, and the buffered image data of the reference frame in the data buffer module can be updated from time to time, so that when encoding or decoding , the image data of the reference frame corresponding to the data acquisition request may be sent to the data processing module according to the data acquisition request sent by the data processing module. Optionally, the data cache module may be a Cache, which is a type of cache memory. The data processing module may be an inter-frame prediction module in an encoder or a decoder. The data processing module in the data processing device can encode or decode the image or video, and send a data acquisition request to the data cache module during the process of encoding or decoding, so as to acquire the image data of the reference frame required for encoding or decoding.

请参阅图2，图2是本申请实施例提供的一种数据处理方法的流程示意图。本实施例中所描述的数据处理方法可以包括以下步骤：Please refer to FIG. 2, which is a schematic flowchart of a data processing method provided by an embodiment of the present application. The data processing method described in this embodiment may include the following steps:

201、根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的第一图像数据进行缓存。201. Acquire the first image data of the reference frame from a data storage device according to the global motion vector between the current frame and the reference frame and buffer the data.

其中，当前帧与参考帧之间的全局运动矢量可以根据历史编码或解码中的所利用的全局运动矢量确定，例如，当前帧为第10帧，即当前是在对第10帧图像进行编码，则可以获取第10帧图像之前的图像帧所利用的全局运动矢量，假设获取了第5帧到第9帧图像的全局运动矢量分别为D1、D2、D3、D4、D5，则当前帧与参考帧之间的全局运动矢量可以为(D1+D2+D3+D4+D5)/5。也可以利用其他方式确定全局运动矢量，在本申请不做限定。The global motion vector between the current frame and the reference frame can be determined according to the global motion vector used in historical encoding or decoding. For example, the current frame is the 10th frame, that is, the 10th frame image is currently being encoded. Then the global motion vector used by the image frame before the 10th frame image can be obtained. Assuming that the global motion vector of the 5th to 9th frame images obtained are D1, D2, D3, D4, and D5 respectively, the current frame and the reference The global motion vector between frames may be (D1+D2+D3+D4+D5)/5. The global motion vector may also be determined in other manners, which are not limited in this application.

在一种实现方式中，在一帧图像开始编码或解码时，数据处理装置可以根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的图像数据，并将参考帧的图像数据缓存到数据处理装置中的数据缓存模块。具体的，数据处理装置中的数据处理模块可以根据当前帧与参考帧之间的全局运动矢量和当前帧中待编码或待解码的图像块的第一位置信息，确定参考帧的图像数据中的第二位置信息。可选的，该第二位置信息可以是第一位置信息加上全局运动矢量的结果。其中，该第一位置信息可以表示待编码或待解码的图像块在当前帧中的位置，例如，可以是待编码或待解码的图像块的坐标信息，还可以是其他表征位置的方式，在本申请不做限定。那么，在数据处理模块确定第二位置信息之后，可以将该第二位置信息发送给数据缓存模块。在数据缓存模块接收到该第二位置信息之后，再从数据存储装置存储的参考帧的图像数据中，获取以第二位置信息对应的图像区域的第一图像数据，并缓存在数据缓存模块。In an implementation manner, when encoding or decoding a frame of image, the data processing apparatus may acquire the image data of the reference frame from the data storage apparatus according to the global motion vector between the current frame and the reference frame, and store the reference frame The image data is cached to the data cache module in the data processing device. Specifically, the data processing module in the data processing device can determine the image data of the reference frame according to the global motion vector between the current frame and the reference frame and the first position information of the image block to be encoded or decoded in the current frame. second location information. Optionally, the second position information may be the result of adding the first position information to the global motion vector. Wherein, the first position information may represent the position of the image block to be encoded or decoded in the current frame, for example, it may be the coordinate information of the image block to be encoded or decoded, and may also be other means of representing the position. This application is not limited. Then, after the data processing module determines the second position information, the second position information can be sent to the data cache module. After the data cache module receives the second position information, the first image data of the image area corresponding to the second position information is obtained from the image data of the reference frame stored in the data storage device, and cached in the data cache module.

可选的，上述第二位置信息可以是数据处理装置中的数据处理模块根据当前帧与参考帧之间的全局运动矢量和当前帧中待编码或待解码的图像块的第一位置信息，确定第二位置信息。还可以是数据处理装置中的数据处理模块将当前帧与参考帧之间的全局运动矢量和当前帧中待编码或待解码的图像块的第一位置信息，发送给数据处理装置中的数据缓存模块，那么数据缓存模块在接收到全局运动矢量和第一位置信息之后，即可根据全局运动矢量和第一位置信息确定第二位置信息。Optionally, the above-mentioned second position information may be determined by the data processing module in the data processing device according to the global motion vector between the current frame and the reference frame and the first position information of the image block to be encoded or decoded in the current frame. second location information. It can also be that the data processing module in the data processing device sends the global motion vector between the current frame and the reference frame and the first position information of the image block to be encoded or decoded in the current frame to the data buffer in the data processing device. module, after receiving the global motion vector and the first position information, the data cache module can determine the second position information according to the global motion vector and the first position information.

在一种实现方式中，在数据缓存模块确定第二位置信息之后，数据缓存模块可以从数据存储装置存储的参考帧的图像数据中，获取以第二位置信息对应的图像区域为中心的第一图像数据，且第一图像数据的大小可以为预设尺寸。具体地，该第二位置信息可以携带在数据缓存模块向数据存储装置发送的数据获取请求中，其中，数据获取请求中还可以携带所要请求数据的预设尺寸，该预设尺寸的大小可以为M×N。那么，在数据存储装置接收到该数据获取请求之后，可以在所存储的参考帧的图像数据中，确定以第二位置信息对应的图像区域为中心的预设尺寸的第一图像数据，并将该第一图像数据发送给数据缓存模块，数据缓存模块接受到该第一图像数据之后，即可缓存该第一图像数据，以便于后续数据处理装置中的数据处理模块在数据缓存模块中获取所需要的参考图像数据。In an implementation manner, after the data caching module determines the second position information, the data caching module may obtain the first image area centered on the image area corresponding to the second position information from the image data of the reference frame stored in the data storage device image data, and the size of the first image data may be a preset size. Specifically, the second location information may be carried in a data acquisition request sent by the data caching module to the data storage device, wherein the data acquisition request may also carry a preset size of the data to be requested, and the size of the preset size may be M×N. Then, after the data storage device receives the data acquisition request, it may determine, in the stored image data of the reference frame, the first image data of the preset size centered on the image area corresponding to the second position information, and store the image data of the preset size. The first image data is sent to the data cache module, and after the data cache module receives the first image data, the first image data can be cached, so that the data processing module in the subsequent data processing device can obtain all the data in the data cache module. Required reference image data.

举例来说，如图3所示由31标记的图像为当前帧的图像数据，图3中由301标记的位置为当前帧中待编码或待解码的图像块(例如当前帧中第一个进行编码或解码的图像块，不限于第一个，也可以是第一行第一个、第一行第二个、第二行第一个、第二行第二个等等最先进行编码或解码的图像块)的第一位置信息，数据处理模块根据该第一位置信息和全局运动矢量可以确定第二位置信息，该第二位置信息可以如图3中由302标记的位置。数据处理模块可以将该第二位置信息和预设尺寸发送给数据缓存模块，那么数据缓存模块可以将该第二位置信息和预设尺寸携带在发送给数据存储装置的数据获取请求中，而在数据存储装置接收到该数据获取请求之后，可以将参考帧的图像数据中，以第二位置信息对应的图像区域为中心的预设尺寸的第一图像数据发送给数据缓存模块，该第一图像数据可以是如图3中由303标记的区域。For example, as shown in FIG. 3, the image marked by 31 is the image data of the current frame, and the position marked by 301 in FIG. 3 is the image block to be encoded or decoded in the current frame (for example, the first image block in the current frame is The encoded or decoded image block is not limited to the first one, but can also be the first in the first row, the second in the first row, the first in the second row, the second in the second row, etc. to be encoded first or The first position information of the decoded image block), the data processing module can determine the second position information according to the first position information and the global motion vector, and the second position information can be the position marked by 302 in FIG. 3 . The data processing module can send the second position information and the preset size to the data cache module, then the data cache module can carry the second position information and the preset size in the data acquisition request sent to the data storage device, and After receiving the data acquisition request, the data storage device may send the first image data of the preset size centered on the image area corresponding to the second position information in the image data of the reference frame to the data cache module, and the first image The data may be the area marked by 303 in FIG. 3 .

需要注意的是，考虑到第二位置信息可能是在参考帧的边缘位置，那么以第二位置信息对应的图像区域为中心的预设尺寸的图像数据，可能会超出参考帧的图像区域，如图3中由303标记的区域，即超出了参考帧的图像范围。那么，为保证第一图像数据只包括参考帧中的图像数据，数据处理装置在从数据存储装置存储的参考帧的图像数据中，获取以第二位置信息对应的图像区域为中心的预设尺寸的第一图像数据进行缓存时，还可以判断以第二位置信息对应的图像区域为中心的预设尺寸的图像区域，是否超出了参考帧的图像区域，如果以第二位置信息对应的图像区域为中心的预设尺寸的图像区域，不超出参考帧的图像区域，则可以从数据存储装置存储的参考帧的图像数据中，获取以第二位置信息对应的图像区域为中心的预设尺寸的第一图像数据进行缓存。如果以第二位置信息对应的图像区域为中心的预设尺寸的图像区域，超出了参考帧的图像区域，则可以对以第二位置信息对应的图像区域为中心的预设尺寸的图像数据进行调整，以使得调整后的数据只包括参考帧中的图像数据。It should be noted that, considering that the second position information may be at the edge of the reference frame, the image data of the preset size centered on the image area corresponding to the second position information may exceed the image area of the reference frame, such as The area marked by 303 in Fig. 3 is beyond the image range of the reference frame. Then, in order to ensure that the first image data only includes the image data in the reference frame, the data processing device obtains, in the image data of the reference frame stored from the data storage device, a preset size centered on the image area corresponding to the second position information When the first image data of the frame is cached, it can also be judged whether the image area of the preset size centered on the image area corresponding to the second position information exceeds the image area of the reference frame, if the image area corresponding to the second position information is used as the center The image area of the preset size centered on the image area does not exceed the image area of the reference frame, and the image area of the preset size centered on the image area corresponding to the second position information can be obtained from the image data of the reference frame stored in the data storage device. The first image data is cached. If the image area of the preset size centered on the image area corresponding to the second position information exceeds the image area of the reference frame, the image data of the preset size centered on the image area corresponding to the second position information may be processed. Adjusted so that the adjusted data includes only image data in the reference frame.

可选的，数据处理装置可以从数据存储装置存储的参考帧的图像数据中，获取预设尺寸的图像区域与参考帧的图像区域之间重叠的图像区域，并可以将该重叠的图像区域作为第一图像数据进行缓存。具体地，数据处理装置的数据缓存模块将携带有第二位置信息和预设尺寸的数据请求消息发送给数据存储装置。数据存储装置在接受到该数据获取请求之后，可以在存储的参考帧的图像数据中确定以第二位置信息对应的图像区域为中心的预设尺寸的图像区域。然后，还可以检测到该图像区域超出参考帧的图像区域，则可以确定预设尺寸的图像区域与参考帧的图像区域之间重叠的图像区域，那么该重叠的图像区域即为第一图像区域，该重叠的图像区域可以如图3中由304标记的区域。接着，数据存储装置即可将该重叠的图像区域发送给数据缓存模块，而数据缓存模块在接收到该重叠的图像区域之后，即可缓存。Optionally, the data processing device may obtain, from the image data of the reference frame stored in the data storage device, the image area that overlaps between the image area of the preset size and the image area of the reference frame, and may use the overlapped image area as the image area. The first image data is cached. Specifically, the data cache module of the data processing device sends the data request message carrying the second location information and the preset size to the data storage device. After receiving the data acquisition request, the data storage device may determine, in the stored image data of the reference frame, an image area of a preset size centered on the image area corresponding to the second position information. Then, it can also be detected that the image area exceeds the image area of the reference frame, and the image area overlapping between the image area of the preset size and the image area of the reference frame can be determined, and the overlapping image area is the first image area. , the overlapping image area may be the area marked by 304 in FIG. 3 . Then, the data storage device can send the overlapped image region to the data cache module, and the data cache module can cache the overlapped image region after receiving the overlapped image region.

可选的，数据处理装置还可以根据参考帧的图像区域的边界调整预设尺寸的图像区域的位置，以使得调整后的预设尺寸的图像区域的边界与参考帧的图像区域的边界重合，调整后的预设尺寸的图像区域可以如图3中由305标记的区域。那么在确定调整后的预设尺寸的图像区域之后，可以从数据存储装置存储的参考帧的图像数据中，获取该调整后的预设尺寸的图像区域对应的第一图像数据进行缓存。Optionally, the data processing apparatus may also adjust the position of the image area of the preset size according to the border of the image area of the reference frame, so that the border of the adjusted image area of the preset size coincides with the border of the image area of the reference frame, The image area of the adjusted preset size may be the area marked by 305 in FIG. 3 . Then, after determining the adjusted image area of the preset size, the first image data corresponding to the adjusted image area of the preset size may be obtained from the image data of the reference frame stored in the data storage device for buffering.

202、根据当前帧中待编码或待解码的图像块的运动矢量从缓存中查找图像块对应的参考图像数据，并根据参考图像数据对图像块进行编码或者解码。202. Search for reference image data corresponding to the image block from the cache according to the motion vector of the image block to be encoded or decoded in the current frame, and encode or decode the image block according to the reference image data.

其中，当前帧中待编码或待解码的图像块的运动矢量可以根据当前待编码或待解码的图像块的，邻近的已编码或待解码的图像块的运动矢量确定，还可以根据利用其他方式确定运动矢量，在本申请不做限定。例如，当前待编码或待解码的图像块为第5块，则可以获取第5块图像块之前的图像块所利用的运动矢量，假设获取了第2块到第4块图像块的运动矢量分别为d1、d2、d3，则待编码或待解码的图像块的运动矢量可以为(d1+d2+d3)/3。也可以将d1、d2、d3作为候选运动矢量，根据预设条件从d1、d2、d3中选择一个最优的候选运动矢量作为待编码或待解码的图像块的运动矢量，例如，该预设条件可以将编码残差或解码残差最小的候选运动矢量作为待编码或待解码的图像块的运动矢量，还可以是其他预设条件，在本申请不做限定。其中，编码残差可以是在对图像块进行帧间编码时，帧间预测得到的图像数据与实际的图像数据的差，解码残差可作同样理解。The motion vector of the image block to be encoded or to be decoded in the current frame may be determined according to the motion vector of the image block to be encoded or to be decoded and the motion vector of the adjacent image block to be encoded or to be decoded, and may also be determined according to the use of other methods. Determining the motion vector is not limited in this application. For example, if the current image block to be encoded or decoded is the fifth block, the motion vectors used by the image blocks before the fifth image block can be obtained. It is assumed that the motion vectors of the second to fourth image blocks are obtained respectively. are d1, d2, and d3, then the motion vector of the image block to be encoded or decoded may be (d1+d2+d3)/3. It is also possible to use d1, d2, and d3 as candidate motion vectors, and select an optimal candidate motion vector from d1, d2, and d3 according to preset conditions as the motion vector of the image block to be encoded or decoded. For example, the preset The condition can be a candidate motion vector with the smallest coding residual or decoding residual as the motion vector of the image block to be coded or decoded, and can also be other preset conditions, which are not limited in this application. The coding residual may be the difference between the image data obtained by inter-frame prediction and the actual image data when the image block is inter-coded, and the decoding residual may be understood in the same way.

在一种实现方式中，数据处理装置可以根据当前帧中待编码或待解码的图像块的位置信息以及运动矢量确定图像块对应的参考图像数据的标识信息，然后根据标识信息判断缓存中是否包括参考图像数据。具体地，数据处理装置中的数据处理模块可以根据当前帧中待编码或待解码的图像块的位置信息以及运动矢量确定图像块对应的参考图像数据的标识信息。然后，数据处理模块可以向数据缓存模块发送数据获取请求，以向数据缓存模块请求参考图像数据进行后续的编码或解码处理，该数据获取请求中可以携带标识信息。那么在数据缓存模块接收到数据处理模块的数据获取请求之后，可以根据数据获取请求中的标识信息来从缓存的参考帧的图像数据中，即第一图像数据中查找图像块对应的参考图像数据，并将该参考图像数据发送给数据处理模块，那么，数据处理模块在接收到该数据处理模块之后，就可以根据该参考图像数据对图像块进行编码或者解码。其中，上述标识信息可以是位置信息、区域索引和尺寸中的一种或多种，该位置信息可以是坐标信息。In an implementation manner, the data processing apparatus may determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector of the image block to be encoded or decoded in the current frame, and then determine whether the cache contains the information according to the identification information. Reference image data. Specifically, the data processing module in the data processing device can determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector of the image block to be encoded or decoded in the current frame. Then, the data processing module may send a data acquisition request to the data cache module to request the data cache module for reference image data for subsequent encoding or decoding processing, and the data acquisition request may carry identification information. Then, after the data cache module receives the data acquisition request from the data processing module, it can search for the reference image data corresponding to the image block from the cached image data of the reference frame, that is, the first image data, according to the identification information in the data acquisition request. , and send the reference image data to the data processing module, then, after receiving the data processing module, the data processing module can encode or decode the image block according to the reference image data. The above identification information may be one or more of location information, area index and size, and the location information may be coordinate information.

在本申请实施例中，根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的第一图像数据进行缓存，根据当前帧中待编码或待解码的图像块的运动矢量从缓存中查找图像块对应的参考图像数据，并根据参考图像数据对图像块进行编码或者解码。通过实施上述方法，利用当前帧与参考帧之间的全局运动矢量来获取参考帧的数据并缓存，能避免因较大的运动，而导致的不能获取到编码或解码所需参考数据的问题，从而可以有效提升编码或解码的效率。In the embodiment of the present application, according to the global motion vector between the current frame and the reference frame, the first image data of the reference frame is obtained from the data storage device for buffering, and the motion of the image block to be encoded or decoded in the current frame is obtained according to the motion of the current frame. The vector finds the reference image data corresponding to the image block from the cache, and encodes or decodes the image block according to the reference image data. By implementing the above method, the global motion vector between the current frame and the reference frame is used to obtain and cache the data of the reference frame, which can avoid the problem that the reference data required for encoding or decoding cannot be obtained due to large motion. Thus, the efficiency of encoding or decoding can be effectively improved.

请参阅图4，图4是本申请实施例提供的另一种数据处理方法的流程示意图。本实施例中所描述的数据处理方法可以包括以下步骤：Please refer to FIG. 4 , which is a schematic flowchart of another data processing method provided by an embodiment of the present application. The data processing method described in this embodiment may include the following steps:

401、根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的第一图像数据进行缓存。401. According to the global motion vector between the current frame and the reference frame, acquire the first image data of the reference frame from the data storage device for buffering.

402、根据当前帧中待编码或待解码的图像块的位置信息以及运动矢量确定图像块对应的参考图像数据的标识信息。402. Determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector of the image block to be encoded or decoded in the current frame.

在一种实现方式中，数据处理装置中的数据处理模块可以根据当前帧中待编码或待解码的图像块的位置信息以及运动矢量，确定图像块对应的参考图像数据的标识信息。其中，标识信息可以包括位置信息、区域索引和尺寸中的一种或多种。例如，以标识信息为位置信息为例，该位置信息可以是待编码或待解码的图像块的坐标信息，则数据处理模块可以将待编码或待解码的图像块的坐标信息加上运动矢量，即可得图像块对应的参考图像数据的的坐标信息。又如，以标识信息为区域索引为例，数据处理模块可以将待编码或待解码的图像块的位置信息加上运动矢量，即可得图像块对应的参考图像数据的位置信息，而数据处理模块中存储有区域与区域索引的对应关系，那么，数据处理模块可确定位置信息所在的区域，然后再根据位置信息所在的区域以及区域与区域索引的对应关系，确定图像块对应的参考图像数据的区域索引。又如，以标识信息为区域索引和尺寸为例，数据处理模块在确定图像块对应的参考图像数据的区域索引之后，还可以根据尺寸进一步确定图像块对应的参考图像数据的大小。In an implementation manner, the data processing module in the data processing apparatus may determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector of the image block to be encoded or decoded in the current frame. Wherein, the identification information may include one or more of location information, area index and size. For example, taking the identification information as the position information as an example, the position information may be the coordinate information of the image block to be encoded or decoded, then the data processing module may add the motion vector to the coordinate information of the image block to be encoded or decoded, Then the coordinate information of the reference image data corresponding to the image block can be obtained. For another example, taking the identification information as the region index as an example, the data processing module can add the motion vector to the position information of the image block to be encoded or decoded, and then the position information of the reference image data corresponding to the image block can be obtained, and the data processing module can obtain the position information of the reference image data corresponding to the image block. The module stores the corresponding relationship between the region and the region index. Then, the data processing module can determine the region where the position information is located, and then determine the reference image data corresponding to the image block according to the region where the position information is located and the corresponding relationship between the region and the region index. area index. For another example, taking the identification information as the region index and size as an example, after determining the region index of the reference image data corresponding to the image block, the data processing module may further determine the size of the reference image data corresponding to the image block according to the size.

其中，运动矢量可以参考上述的描述，在此处不在赘述。For the motion vector, reference may be made to the above description, which will not be repeated here.

在一种实现方式中，数据处理装置中的数据处理模块可以将当前帧中待编码或待解码的图像块的位置信息以及运动矢量，发送给数据处理装置中的数据缓存模块，那么在数据缓存模块接收到当前帧中待编码或待解码的图像块的位置信息以及运动矢量之后，可以根据位置信息以及运动矢量确定图像块对应的参考图像数据的标识信息。In an implementation manner, the data processing module in the data processing device can send the position information and motion vector of the image block to be encoded or decoded in the current frame to the data buffer module in the data processing device, then in the data buffer After the module receives the position information and the motion vector of the image block to be encoded or decoded in the current frame, it can determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector.

403、根据标识信息判断缓存中是否包括参考图像数据。403. Determine whether reference image data is included in the cache according to the identification information.

在一种实现方式中，数据处理装置可以根据标识信息判断缓存中是否包括参考图像数据。具体的，数据处理装置中的数据处理模块可以向数据缓存模块发送数据获取请求，以向数据缓存模块请求参考图像数据进行后续的编码或解码处理，该数据获取请求中可以携带标识信息。那么在数据缓存模块接收到数据处理模块的数据获取请求之后，可以根据数据获取请求中的标识信息来从缓存的参考帧的图像数据中，即从第一图像数据中查找该标识信息对应的数据，即图像块对应的参考图像数据，并确定第一图像数据中是否包括该参考图像数据。In an implementation manner, the data processing apparatus may determine whether the reference image data is included in the cache according to the identification information. Specifically, the data processing module in the data processing apparatus may send a data acquisition request to the data cache module to request the data cache module to perform subsequent encoding or decoding processing on reference image data, and the data acquisition request may carry identification information. Then, after the data cache module receives the data acquisition request from the data processing module, it can search for the data corresponding to the identification information from the cached image data of the reference frame, that is, from the first image data, according to the identification information in the data acquisition request. , that is, the reference image data corresponding to the image block, and it is determined whether the reference image data is included in the first image data.

404、若是，则从缓存中获取参考图像数据，并根据参考图像数据对图像块进行编码或者解码。404. If yes, obtain the reference image data from the cache, and encode or decode the image block according to the reference image data.

在一种实现方式中，如果数据处理装置根据标识信息判断缓存中包括参考图像数据，则可以从缓存中获取参考图像数据，并根据参考图像数据对图像块进行编码或者解码。具体的，如果数据处理装置中的数据处理模块根据标识信息确定缓存的参考帧的图像数据，即第一图像数据中包括参考图像数据，则可以从第一图像数据中获取参考图像数据，并将该参考图像数据发送给数据处理模块，以使得数据处理模块根据该参考图像数据对图像块进行编码或者解码。In an implementation manner, if the data processing apparatus determines that the cache includes reference image data according to the identification information, the reference image data may be obtained from the cache, and the image block may be encoded or decoded according to the reference image data. Specifically, if the data processing module in the data processing device determines the cached image data of the reference frame according to the identification information, that is, the first image data includes the reference image data, the reference image data can be obtained from the first image data, and the The reference image data is sent to the data processing module, so that the data processing module encodes or decodes the image block according to the reference image data.

405、若否，则当缓存满足预设更新条件时，根据标识信息从数据存储装置中获取参考帧的第二图像数据进行缓存，并从缓存中获取参考图像数据，根据参考图像数据对图像块进行编码或者解码。405. If not, when the cache satisfies the preset update condition, obtain the second image data of the reference frame from the data storage device according to the identification information for caching, and obtain the reference image data from the cache, and perform the image block analysis according to the reference image data. to encode or decode.

在一种实现方式中，如果数据处理装置根据标识信息判断缓存中不包括参考图像数据，则可以在缓存满足预设更新条件的情况下，根据标识信息从数据存储装置中获取参考帧的第二图像数据进行缓存，以从缓存中的第二图像数据中获取参考图像数据，并根据参考图像数据对图像块进行编码或者解码。具体的，如果数据处理装置中的数据处理模块根据标识信息确定缓存的参考帧的图像数据，即第一图像数据中不包括参考图像数据，则还需要确定当前数据缓存模块是否预设更新条件，如果满足预设更新条件，则可以根据标识信息从数据存储装置中获取参考帧的第二图像数据进行缓存，并从第二图像数据中获取参考图像数据，根据参考图像数据对图像块进行编码或者解码。其中，根据标识信息从数据存储装置中获取参考帧的第二图像数据的具体实施过程可参考根据上述根据第二位置信息从数据存储装置中获取参考帧的第一图像数据的具体实施过程，在此处不在赘述。In an implementation manner, if the data processing device determines according to the identification information that the reference image data is not included in the cache, the second data of the reference frame may be acquired from the data storage device according to the identification information under the condition that the cache meets the preset update condition. The image data is cached, so as to obtain reference image data from the second image data in the cache, and encode or decode image blocks according to the reference image data. Specifically, if the data processing module in the data processing device determines the cached image data of the reference frame according to the identification information, that is, the reference image data is not included in the first image data, it is also necessary to determine whether the current data cache module has preset update conditions, If the preset update condition is satisfied, the second image data of the reference frame may be obtained from the data storage device according to the identification information for buffering, and the reference image data may be obtained from the second image data, and the image block may be encoded according to the reference image data or decoding. Wherein, for the specific implementation process of acquiring the second image data of the reference frame from the data storage device according to the identification information, reference may be made to the specific implementation process of acquiring the first image data of the reference frame from the data storage device according to the second position information. I won't go into details here.

在一种实现方式中，如果数据处理装置根据标识信息判断缓存中不包括参考图像数据，且缓存不满足预设更新条件，则当前数据处理模块可以获取数据缓存模块中已有的图像数据，并根据该图像数据对图像块进行编码或者解码。例如，对于编码来说，数据处理模块可以获取数据缓存模块中已有的图像数据来进行帧间预测，或者不进行帧间预测，但是此时会大幅影响编码效率。In an implementation manner, if the data processing device determines according to the identification information that the reference image data is not included in the cache, and the cache does not meet the preset update conditions, the current data processing module can obtain the existing image data in the data cache module, and Image blocks are encoded or decoded based on the image data. For example, for encoding, the data processing module may obtain the existing image data in the data buffer module to perform inter-frame prediction, or not perform inter-frame prediction, but at this time, the encoding efficiency will be greatly affected.

在一种实现方式中，上述预设更新条件可以根据缓存中的图像数据没有被访问的次数，或没有被访问的时间，或缓存的剩余缓存空间等来确定。可选的，该预设更新条件可以是缓存中的图像数据没有被访问的时间或次数超过了第一阈值、也可以是图像数据缓存的时间超过了第二阈值、也可以是缓存的剩余缓存空间小于或等于第三阈值中，也可以是上述的任意组合，例如，可以是图像数据缓存的时间超过第二阈值，且缓存的剩余缓存空间小于或等于第三阈值。其中，上述的第一阈值、第二阈值以及第三阈值可以预先设置。In an implementation manner, the above-mentioned preset update condition may be determined according to the number of times the image data in the cache is not accessed, or the time when the image data in the cache is not accessed, or the remaining cache space of the cache. Optionally, the preset update condition may be that the time or the number of times that the image data in the cache is not accessed exceeds the first threshold, or the time that the image data is cached exceeds the second threshold, or the remaining cache of the cache. The space less than or equal to the third threshold may also be any combination of the above. For example, the image data may be cached for more than the second threshold, and the remaining cache space of the cache is less than or equal to the third threshold. Wherein, the above-mentioned first threshold, second threshold and third threshold may be preset.

其中，步骤401的具体实施方式可以参见上述实施例步骤201的具体描述，此处不再赘述。For the specific implementation of step 401, reference may be made to the specific description of step 201 in the foregoing embodiment, which will not be repeated here.

在本申请实施例中，根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取参考帧的第一图像数据进行缓存，根据当前帧中待编码或待解码的图像块的位置信息以及运动矢量确定图像块对应的参考图像数据的标识信息。根据标识信息判断缓存中是否包括参考图像数据。若是，则从缓存中获取参考图像数据，并根据参考图像数据对图像块进行编码或者解码。若否，则当缓存满足预设更新条件时，根据标识信息从数据存储装置中获取参考帧的第二图像数据进行缓存，并从缓存中获取参考图像数据，根据参考图像数据对图像块进行编码或者解码。通过实施上述方法，能避免因较大的运动，而导致的不能获取到编码或解码所需参考数据的问题，从而可以有效提升编码或解码的效率。In the embodiment of the present application, according to the global motion vector between the current frame and the reference frame, the first image data of the reference frame is obtained from the data storage device for buffering, and according to the position of the image block to be encoded or decoded in the current frame The information and the motion vector determine the identification information of the reference image data corresponding to the image block. It is judged according to the identification information whether the reference image data is included in the cache. If so, obtain the reference image data from the cache, and encode or decode the image block according to the reference image data. If not, when the cache satisfies the preset update condition, the second image data of the reference frame is obtained from the data storage device according to the identification information for caching, and the reference image data is obtained from the cache, and the image block is encoded according to the reference image data or decode. By implementing the above method, the problem that the reference data required for encoding or decoding cannot be obtained due to large motion can be avoided, thereby effectively improving the efficiency of encoding or decoding.

在一种实现方式中，数据处理装置中的数据缓存模块中所缓存的参考帧的图像数据可以进行不断地更新，以使得数据处理模块在要获取进行编码或者解码的参考图像数据时，可以快速的从数据缓存模块中获取所需要的参考图像数据，从而提升编码或解码的效率。In an implementation manner, the image data of the reference frame cached in the data cache module in the data processing device can be continuously updated, so that the data processing module can quickly acquire the reference image data for encoding or decoding. The required reference image data is obtained from the data cache module, thereby improving the efficiency of encoding or decoding.

可选的，数据缓存模块可以在响应于数据处理模块的数据获取请求时，可以判断缓存的参考帧的图像数据是否满足上述的预设更新条件，如果满足预设更新条件，则根据数据获取请求中携带的标识信息从数据存储装置中获取参考帧的第三图像数据进行缓存，并从缓存中获取参考图像数据。其中，根据数据获取请求中携带的标识信息从数据存储装置中获取参考帧的第三图像数据进行缓存的具体实现过程可以参考上述获取第二图像数据的具体实现过程，在此处不在赘述。Optionally, the data cache module may, in response to the data acquisition request from the data processing module, determine whether the cached image data of the reference frame satisfies the above preset update conditions, and if the preset update conditions are met, then according to the data acquisition request. The identification information carried in the third image data of the reference frame is obtained from the data storage device to be cached, and the reference image data is obtained from the cache. The specific implementation process of acquiring and buffering the third image data of the reference frame from the data storage device according to the identification information carried in the data acquisition request may refer to the specific implementation process of acquiring the second image data above, which will not be repeated here.

可选的，数据缓存模块还可以判断缓存是否满足预设更新条件，例如，数据缓存模块以预设时间间隔检测所缓存的参考帧的图像数据是否满足预设更新条件。其中，该预设时间间隔可以预先设置，例如，可以是1秒，或者是3秒，在本申请不做限定。如果数据缓存模块检测到所缓存的参考帧的图像数据满足预设更新条件，则可以根据最近一次接收的数据获取请求包括的参考图像数据的标识信息，从数据存储装置中获取参考帧的第四图像数据进行缓存。其中，根据数据获取请求中携带的标识信息从数据存储装置中获取参考帧的第四图像数据进行缓存的具体实现过程可以参考上述获取第二图像数据的具体实现过程，在此处不在赘述。Optionally, the data cache module may also determine whether the cache meets the preset update condition. For example, the data cache module detects at preset time intervals whether the cached image data of the reference frame meets the preset update condition. The preset time interval may be preset, for example, may be 1 second or 3 seconds, which is not limited in this application. If the data caching module detects that the cached image data of the reference frame satisfies the preset update condition, it can acquire the fourth image data of the reference frame from the data storage device according to the identification information of the reference image data included in the most recently received data acquisition request. Image data is cached. The specific implementation process of acquiring and caching the fourth image data of the reference frame from the data storage device according to the identification information carried in the data acquisition request may refer to the specific implementation process of acquiring the second image data above, which will not be repeated here.

请参阅图5，图5是本申请实施例提供的一种数据处理装置的结构示意图。所述数据处理装置包括：Please refer to FIG. 5 , which is a schematic structural diagram of a data processing apparatus provided by an embodiment of the present application. The data processing device includes:

获取模块501，用于根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取所述参考帧的第一图像数据进行缓存；an obtaining module 501, configured to obtain the first image data of the reference frame from a data storage device for buffering according to the global motion vector between the current frame and the reference frame;

查找模块502，用于根据所述当前帧中待编码或待解码的图像块的运动矢量从所述缓存中查找所述图像块对应的参考图像数据，并根据所述参考图像数据对所述图像块进行编码或者解码。The search module 502 is configured to search for the reference image data corresponding to the image block from the cache according to the motion vector of the image block to be encoded or decoded in the current frame, and to search for the image block according to the reference image data. Blocks are encoded or decoded.

在一种实现方式中，所述获取模块501，具体用于：In an implementation manner, the obtaining module 501 is specifically used for:

根据当前帧与参考帧之间的全局运动矢量和所述当前帧中的第一位置信息确定所述参考帧的图像数据中的第二位置信息；Determine the second position information in the image data of the reference frame according to the global motion vector between the current frame and the reference frame and the first position information in the current frame;

从数据存储装置存储的所述参考帧的图像数据中，获取以所述第二位置信息对应的图像区域为中心的预设尺寸的第一图像数据进行缓存。From the image data of the reference frame stored in the data storage device, first image data of a preset size centered on the image area corresponding to the second position information is acquired and cached.

判断以所述第二位置信息对应的图像区域为中心的预设尺寸的图像区域是否超出所述参考帧的图像区域；Determine whether the image area of the preset size centered on the image area corresponding to the second position information exceeds the image area of the reference frame;

若不超出所述参考帧的图像区域，则从数据存储装置存储的所述参考帧的图像数据中，获取以所述第二位置信息对应的图像区域为中心的预设尺寸的第一图像数据进行缓存。If it does not exceed the image area of the reference frame, obtain first image data of a preset size centered on the image area corresponding to the second position information from the image data of the reference frame stored in the data storage device cache.

在一种实现方式中，所述获取模块501，还用于：In an implementation manner, the obtaining module 501 is further configured to:

若超出所述参考帧的图像区域，则从所述数据存储装置存储的所述参考帧的图像数据中，获取所述预设尺寸的图像区域与所述参考帧的图像区域之间重叠的图像区域，并将所述重叠的图像区域作为第一图像数据进行缓存。If it exceeds the image area of the reference frame, obtain an image overlapping between the image area of the preset size and the image area of the reference frame from the image data of the reference frame stored in the data storage device area, and cache the overlapping image area as the first image data.

若超出所述参考帧的图像区域，则根据所述参考帧的图像区域的边界调整所述预设尺寸的图像区域的位置，以使得调整后的预设尺寸的图像区域的边界与所述参考帧的图像区域的边界重合；If it exceeds the image area of the reference frame, adjust the position of the image area of the preset size according to the boundary of the image area of the reference frame, so that the boundary of the adjusted image area of the preset size is the same as the reference frame. The boundaries of the image regions of the frame coincide;

从所述数据存储装置存储的所述参考帧的图像数据中，获取所述调整后的预设尺寸的图像区域对应的第一图像数据进行缓存。From the image data of the reference frame stored by the data storage device, the first image data corresponding to the adjusted image area of the preset size is acquired and cached.

在一种实现方式中，所述查找模块502，具体用于：In an implementation manner, the search module 502 is specifically used for:

根据所述当前帧中待编码或待解码的图像块的位置信息以及运动矢量确定所述图像块对应的参考图像数据的标识信息；Determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector of the image block to be encoded or decoded in the current frame;

根据所述标识信息判断所述缓存中是否包括所述参考图像数据；Determine whether the reference image data is included in the cache according to the identification information;

若是，则从所述缓存中获取所述参考图像数据；If so, obtain the reference image data from the cache;

若否，则当所述缓存满足预设更新条件时，根据所述标识信息从所述数据存储装置中获取所述参考帧的第二图像数据进行缓存，并从所述缓存中获取所述参考图像数据。If not, when the cache satisfies the preset update condition, acquire the second image data of the reference frame from the data storage device according to the identification information for caching, and acquire the reference from the cache image data.

在一种实现方式中，所述装置还包括更新模块503，具体用于：In an implementation manner, the apparatus further includes an update module 503, which is specifically configured to:

响应于数据获取请求，判断所述缓存是否满足预设更新条件，所述数据获取请求包括参考图像数据的标识信息；In response to a data acquisition request, judging whether the cache satisfies a preset update condition, the data acquisition request including identification information of the reference image data;

若是，则根据所述标识信息从所述数据存储装置中获取所述参考帧的第三图像数据进行缓存，并从所述缓存中获取所述参考图像数据。If so, the third image data of the reference frame is acquired from the data storage device according to the identification information for buffering, and the reference image data is acquired from the buffering.

在一种实现方式中，所述更新模块503，还用于：In an implementation manner, the update module 503 is further used for:

判断所述缓存是否满足预设更新条件；Judging whether the cache satisfies a preset update condition;

若是，则根据最近一次接收的数据获取请求包括的参考图像数据的标识信息，从所述数据存储装置中获取所述参考帧的第四图像数据进行缓存。If so, the fourth image data of the reference frame is acquired from the data storage device according to the identification information of the reference image data included in the most recently received data acquisition request for buffering.

在一种实现方式中，所述预设更新条件包括所述缓存中的图像数据未被访问的时间或次数超过第一阈值、所述图像数据缓存的时间超过第二阈值、所述缓存的剩余缓存空间小于或等于第三阈值中的一种或多种。In an implementation manner, the preset update condition includes that the time or the number of times that the image data in the cache has not been accessed exceeds a first threshold, the time that the image data is cached exceeds a second threshold, and the remaining amount of the cache The cache space is less than or equal to one or more of the third thresholds.

在一种实现方式中，所述标识信息包括位置信息、区域索引和尺寸中的一种或多种。In one implementation, the identification information includes one or more of location information, area index, and size.

可以理解的是，本申请实施例所描述的数据处理装置的各功能模块的功能可根据图2或者图4所述的方法实施例中的方法具体实现，其具体实现过程可以参照图2或者图4的方法实施例的相关描述，此处不再赘述。It can be understood that the functions of each functional module of the data processing apparatus described in the embodiments of the present application can be specifically implemented according to the method in the method embodiment described in FIG. 2 or FIG. 4 , and the specific implementation process can refer to FIG. 2 or FIG. 4 . The relevant description of the method embodiment of 4 is not repeated here.

本申请实施例中，获取模块501根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取所述参考帧的第一图像数据进行缓存，查找模块502根据所述当前帧中待编码或待解码的图像块的运动矢量从所述缓存中查找所述图像块对应的参考图像数据，并根据所述参考图像数据对所述图像块进行编码或者解码，从而可以有效提升编码或解码的效率。In the embodiment of the present application, the obtaining module 501 obtains the first image data of the reference frame from the data storage device according to the global motion vector between the current frame and the reference frame, and caches it, and the searching module 502 obtains the first image data of the reference frame according to the current frame to be cached. The motion vector of the image block to be encoded or to be decoded searches the cache for the reference image data corresponding to the image block, and encodes or decodes the image block according to the reference image data, so that the encoding or decoding can be effectively improved s efficiency.

请参阅图6，图6是本申请实施例提供的一种数据处理设备的结构示意图。本实施例中所描述的数据处理设备，包括：处理器601和存储器602。上述处理器601和存储器602通过总线连接。Please refer to FIG. 6. FIG. 6 is a schematic structural diagram of a data processing device provided by an embodiment of the present application. The data processing device described in this embodiment includes: a processor 601 and a memory 602 . The above-mentioned processor 601 and memory 602 are connected by a bus.

上述处理器601可以是中央处理单元(Central Processing Unit，CPU)，该处理器还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。The above-mentioned processor 601 can be a central processing unit (Central Processing Unit, CPU), and the processor can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC) ), off-the-shelf programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

上述存储器602可以包括只读存储器和随机存取存储器，并向处理器601提供程序指令和数据。存储器602的一部分还可以包括非易失性随机存取存储器。其中，所述处理器601调用所述程序指令时用于执行：The above-mentioned memory 602 may include read-only memory and random access memory, and provides program instructions and data to the processor 601 . A portion of memory 602 may also include non-volatile random access memory. Wherein, when the processor 601 calls the program instructions, it is used to execute:

在一种实现方式中，所述处理器601，具体用于：In an implementation manner, the processor 601 is specifically configured to:

在一种实现方式中，所述处理器601，还用于：In an implementation manner, the processor 601 is further configured to:

若超出所述参考帧的图像区域，则从所述数据存储装置存储的所述参考帧的图像数据中，获取所述预设尺寸的图像区域与所述参考帧的图像区域之间重叠的图像区域，并将所述重叠的图像区域作为第一图像数据进行缓存。If it exceeds the image area of the reference frame, acquire an image overlapping between the image area of the preset size and the image area of the reference frame from the image data of the reference frame stored in the data storage device area, and cache the overlapping image area as the first image data.

从所述数据存储装置存储的所述参考帧的图像数据中，获取所述调整后的预设尺寸的图像区域对应的第一图像数据进行缓存。From the image data of the reference frame stored in the data storage device, the first image data corresponding to the adjusted image area of the preset size is acquired and cached.

具体实现中，本申请实施例中所描述的处理器601和存储器602可执行本申请实施例图2或者图4提供的数据处理方法中所描述的实现方式，也可执行本申请实施例图5所描述的数据处理装置的实现方式，在此不再赘述。In specific implementation, the processor 601 and the memory 602 described in the embodiment of the present application may execute the implementation manner described in the data processing method provided in FIG. 2 or FIG. 4 in the embodiment of the present application, and may also execute the embodiment in FIG. 5 of the present application. The implementation manner of the described data processing apparatus will not be repeated here.

本申请实施例中，处理器601根据当前帧与参考帧之间的全局运动矢量，从数据存储装置中获取所述参考帧的第一图像数据进行缓存，根据所述当前帧中待编码或待解码的图像块的运动矢量从所述缓存中查找所述图像块对应的参考图像数据，并根据所述参考图像数据对所述图像块进行编码或者解码，从而可以有效提升编码或解码的效率。In the embodiment of the present application, the processor 601 acquires the first image data of the reference frame from the data storage device according to the global motion vector between the current frame and the reference frame, and buffers the first image data according to the current frame to be encoded or to be encoded according to the current frame. The motion vector of the decoded image block searches the cache for the reference image data corresponding to the image block, and encodes or decodes the image block according to the reference image data, thereby effectively improving the efficiency of encoding or decoding.

本申请实施例还提供了一种计算机存储介质，该计算机存储介质中存储有程序指令，所述程序执行时可包括如图2或者图4对应实施例中的数据处理方法的部分或全部步骤。Embodiments of the present application further provide a computer storage medium, where program instructions are stored in the computer storage medium, and when the program is executed, the program may include some or all of the steps of the data processing method in the embodiment corresponding to FIG. 2 or FIG. 4 .

需要说明的是，对于前述的各个方法实施例，为了简单描述，故将其都表述为一系列的动作组合，但是本领域技术人员应该知悉，本申请并不受所描述的动作顺序的限制，因为依据本申请，某一些步骤可以采用其他顺序或者同时进行。其次，本领域技术人员也应该知悉，说明书中所描述的实施例均属于优选实施例，所涉及的动作和模块并不一定是本申请所必须的。It should be noted that, for the sake of simple description, the foregoing method embodiments are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described action sequence. Because in accordance with the present application, certain steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：闪存盘、只读存储器(Read-Only Memory，ROM)、随机存取器(Random Access Memory，RAM)、磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: Flash disk, read-only memory (Read-Only Memory, ROM), random access device (Random Access Memory, RAM), magnetic disk or optical disk, etc.

以上对本申请实施例所提供的一种数据处理方法及数据处理设备进行了详细介绍，本文中应用了具体个例对本申请的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本申请的方法及其核心思想；同时，对于本领域的一般技术人员，依据本申请的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本申请的限制。A data processing method and a data processing device provided by the embodiments of the present application have been described in detail above. The principles and implementations of the present application are described in this paper by using specific examples. The descriptions of the above embodiments are only used to help understanding The method of the present application and its core idea; at the same time, for those skilled in the art, according to the idea of the present application, there will be changes in the specific implementation and application scope. In summary, the content of this specification should not be It is construed as a limitation of this application.

Claims

A data processing method, comprising:

According to the global motion vector between the current frame and the reference frame, the first image data of the reference frame is obtained from the data storage device for buffering;

The reference image data corresponding to the image block is searched from the cache according to the motion vector of the image block to be encoded or decoded in the current frame, and the image block is encoded or decoded according to the reference image data.

The method according to claim 1, wherein, according to the global motion vector between the current frame and the reference frame, obtaining the first image data of the reference frame from a data storage device for buffering, comprising:

Determine the second position information in the image data of the reference frame according to the global motion vector between the current frame and the reference frame and the first position information in the current frame;

From the image data of the reference frame stored in the data storage device, first image data of a preset size centered on the image area corresponding to the second position information is acquired and cached.

The method according to claim 2, characterized in that, in the image data of the reference frame stored from the data storage device, a first image of a preset size centered on an image area corresponding to the second position information is obtained. An image data is cached, including:

Determine whether the image area of the preset size centered on the image area corresponding to the second position information exceeds the image area of the reference frame;

If it does not exceed the image area of the reference frame, obtain first image data of a preset size centered on the image area corresponding to the second position information from the image data of the reference frame stored in the data storage device cache.

The method of claim 3, further comprising:

If it exceeds the image area of the reference frame, obtain an image overlapping between the image area of the preset size and the image area of the reference frame from the image data of the reference frame stored in the data storage device area, and cache the overlapping image area as the first image data.

The method of claim 3, further comprising:

If it exceeds the image area of the reference frame, adjust the position of the image area of the preset size according to the boundary of the image area of the reference frame, so that the boundary of the adjusted image area of the preset size is the same as the reference frame. The boundaries of the image regions of the frame coincide;

From the image data of the reference frame stored by the data storage device, the first image data corresponding to the adjusted image area of the preset size is acquired and cached.

The method according to any one of claims 1 to 5, wherein the reference corresponding to the image block is searched from the cache according to the motion vector of the image block to be encoded or decoded in the current frame Image data, including:

Determine the identification information of the reference image data corresponding to the image block according to the position information and the motion vector of the image block to be encoded or decoded in the current frame;

Determine whether the reference image data is included in the cache according to the identification information;

If so, obtain the reference image data from the cache;

If not, when the cache satisfies the preset update condition, acquire the second image data of the reference frame from the data storage device according to the identification information for caching, and acquire the reference from the cache image data.

The method according to any one of claims 1 to 5, further comprising:

In response to a data acquisition request, judging whether the cache satisfies a preset update condition, the data acquisition request including identification information of the reference image data;

If so, the third image data of the reference frame is acquired from the data storage device according to the identification information for buffering, and the reference image data is acquired from the buffering.

The method according to any one of claims 1 to 5, further comprising:

Judging whether the cache satisfies a preset update condition;

If so, the fourth image data of the reference frame is acquired from the data storage device according to the identification information of the reference image data included in the most recently received data acquisition request for buffering.

The method according to any one of claims 6 to 8, wherein the preset update condition comprises that the image data in the cache is not accessed for a time or a number of times exceeding a first threshold, the image data cache The time exceeds the second threshold, and the remaining cache space of the cache is less than or equal to one or more of the third threshold.

The method according to any one of claims 6 to 8, wherein the identification information includes one or more of location information, area index and size.

A data processing device, comprising: a processor and a memory, wherein:

the memory for storing program instructions;

When the processor invokes the program instructions, it is used to execute:

The data processing device according to claim 11, wherein the processor is specifically configured to:

The data processing device according to claim 12, wherein the processor is specifically configured to:

Judging whether the image area of the preset size centered on the image area corresponding to the second position information exceeds the image area of the reference frame;

The data processing device according to claim 13, wherein the processor is further configured to:

The data processing device according to any one of claims 11 to 15, wherein the processor is specifically configured to:

If so, obtain the reference image data from the cache;

The data processing device according to any one of claims 11 to 15, wherein the processor is further configured to:

Judging whether the cache satisfies a preset update condition;

The data processing device according to any one of claims 16 to 18, wherein the preset update condition includes that the image data in the cache has not been accessed for a time or a number of times exceeding a first threshold, the image data One or more of the cache time exceeds the second threshold and the remaining cache space of the cache is less than or equal to the third threshold.

The data processing device according to any one of claims 16 to 18, wherein the identification information includes one or more of location information, area index and size.