CN115243035A - Video compression quality assessment method, apparatus, electronic device and medium - Google Patents
Video compression quality assessment method, apparatus, electronic device and mediumDownload PDFInfo
- Publication number
- CN115243035A CN115243035ACN202210827391.9ACN202210827391ACN115243035ACN 115243035 ACN115243035 ACN 115243035ACN 202210827391 ACN202210827391 ACN 202210827391ACN 115243035 ACN115243035 ACN 115243035A
- Authority
- CN
- China
- Prior art keywords
- video
- image frame
- assisted driving
- model
- driving model
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Images
Classifications
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/154—Measured or subjectively estimated visual quality after decoding, e.g. measurement of distortion
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
Translated fromChinese
Description
Translated fromChinese技术领域technical field
本公开涉及计算机技术领域，尤其涉及视频处理技术领域，可应用于自动驾驶、辅助驾驶等场景，具体涉及一种视频压缩质量评估方法、装置、电子设备、计算机可读存储介质和计算机程序产品。The present disclosure relates to the field of computer technology, in particular to the field of video processing technology, and can be applied to scenarios such as automatic driving and assisted driving, and in particular to a video compression quality assessment method, apparatus, electronic device, computer-readable storage medium and computer program product.
背景技术Background technique
自动驾驶汽车或辅助驾驶汽车可以依靠人工智能、视觉计算和全球定位系统的协同合作，自主或辅助地操作车辆行驶。其中，视觉计算单元可以基于车辆的图像采集设备在车辆行驶过程中所采集的图像分析路况，从而为规划行驶策略提供支持。此外，所采集的图像或视频还可以备份在存储设备中，这些备份的图像或视频可以用于对自动驾驶或辅助驾驶的算法进行优化分析。Self-driving or assisted driving vehicles can rely on the collaboration of artificial intelligence, visual computing and global positioning systems to operate the vehicle autonomously or assisted. Wherein, the visual computing unit can analyze the road conditions based on the images collected by the image collection device of the vehicle during the driving of the vehicle, so as to provide support for planning the driving strategy. In addition, the collected images or videos can also be backed up in the storage device, and these backed-up images or videos can be used to optimize and analyze the algorithms for automatic driving or assisted driving.
在此部分中描述的方法不一定是之前已经设想到或采用的方法。除非另有指明，否则不应假定此部分中描述的任何方法仅因其包括在此部分中就被认为是现有技术。类似地，除非另有指明，否则此部分中提及的问题不应认为在任何现有技术中已被公认。The approaches described in this section are not necessarily approaches that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any of the approaches described in this section qualify as prior art merely by virtue of their inclusion in this section. Similarly, unless otherwise indicated, the issues raised in this section should not be considered to be recognized in any prior art.
发明内容SUMMARY OF THE INVENTION
本公开提供了一种视频压缩质量评估方法、装置、电子设备、计算机可读存储介质和计算机程序产品。The present disclosure provides a video compression quality assessment method, apparatus, electronic device, computer-readable storage medium and computer program product.
根据本公开的一方面，提供了一种视频压缩质量评估方法。该方法包括：获取第一视频中的至少一个第一图像帧，第一视频是由车辆上的图像采集设备在车辆的行驶过程中采集的；获取第二视频，第二视频是对第一视频进行视频压缩生成的；将第二视频解压缩，以获取第三视频；从第三视频中提取至少一个第二图像帧，至少一个第二图像帧各自与至少一个第一图像帧中的相应一个第一图像帧对应；将至少一个第一图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第一预测结果；将至少一个第二图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第二预测结果；以及基于第一预测结果和第二预测结果，对经压缩的第二视频进行质量评估。According to an aspect of the present disclosure, a video compression quality assessment method is provided. The method includes: acquiring at least one first image frame in a first video, where the first video is acquired by an image acquisition device on the vehicle during the driving of the vehicle; acquiring a second video, the second video is a comparison of the first video Generated by performing video compression; decompressing the second video to obtain a third video; extracting at least one second image frame from the third video, each of the at least one second image frame and the corresponding one of the at least one first image frame Corresponding to the first image frame; input at least one first image frame into the assisted driving model to obtain the first prediction result output by the assisted driving model; input at least one second image frame into the assisted driving model to obtain the first prediction result output by the assisted driving model; two prediction results; and performing a quality assessment on the compressed second video based on the first prediction result and the second prediction result.
根据本公开的另一方面，提供了一种视频压缩质量评估装置。该装置包括：第一图像帧获取单元，被配置为获取第一视频中的至少一个第一图像帧，第一视频是由车辆上的图像采集设备在车辆的行驶过程中采集的；第二视频获取单元，被配置为获取第二视频，第二视频是对第一视频进行视频压缩生成的；解压缩单元，被配置为将第二视频解压缩，以获取第三视频；提取单元，被配置为从第三视频中提取至少一个第二图像帧，至少一个第二图像帧各自与至少一个第一图像帧中的相应一个第一图像帧对应；第一预测单元，被配置为将至少一个第一图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第一预测结果；第二预测单元，被配置为将至少一个第二图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第二预测结果；以及评估单元，被配置为基于第一预测结果和第二预测结果，对经压缩的第二视频进行质量评估。According to another aspect of the present disclosure, a video compression quality evaluation apparatus is provided. The device includes: a first image frame acquisition unit configured to acquire at least one first image frame in a first video, where the first video is acquired by an image acquisition device on the vehicle during the driving process of the vehicle; the second video an acquisition unit, configured to acquire a second video, which is generated by performing video compression on the first video; a decompression unit, configured to decompress the second video to acquire a third video; an extraction unit, configured In order to extract at least one second image frame from the third video, each of the at least one second image frame corresponds to a corresponding one of the at least one first image frame; the first prediction unit is configured to convert the at least one first image frame; An image frame is input into the assisted driving model to obtain a first prediction result output by the assisted driving model; a second prediction unit is configured to input at least one second image frame into the assisted driving model to obtain a second prediction output by the assisted driving model the result; and an evaluation unit configured to perform quality evaluation on the compressed second video based on the first prediction result and the second prediction result.
根据本公开的另一方面，提供了一种电子设备，包括：至少一个处理器；以及与至少一个处理器通信连接的存储器；其中存储器存储有可被至少一个处理器执行的指令，指令被至少一个处理器执行，以使至少一个处理器能够执行上述的视频压缩质量评估方法。According to another aspect of the present disclosure, there is provided an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by at least one processor A processor executes to enable at least one processor to execute the above-described video compression quality assessment method.
根据本公开的再一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，计算机指令用于使计算机执行上述的视频压缩质量评估方法。According to yet another aspect of the present disclosure, there is provided a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause a computer to execute the above-described video compression quality assessment method.
根据本公开的再一方面，提供了一种计算机程序产品，包括计算机程序，其中，计算机程序在被处理器执行时实现上述的视频压缩质量评估方法。According to yet another aspect of the present disclosure, there is provided a computer program product, including a computer program, wherein the computer program, when executed by a processor, implements the above-described video compression quality assessment method.
根据本公开的一个或多个实施例，可以评估压缩视频对辅助驾驶模型预测结果的影响。According to one or more embodiments of the present disclosure, the impact of the compressed video on the prediction results of the assisted driving model can be evaluated.
应当理解，本部分所描述的内容并非旨在标识本公开的实施例的关键或重要特征，也不用于限制本公开的范围。本公开的其它特征将通过以下的说明书而变得容易理解。It should be understood that what is described in this section is not intended to identify key or critical features of embodiments of the disclosure, nor is it intended to limit the scope of the disclosure. Other features of the present disclosure will become readily understood from the following description.
附图说明Description of drawings
附图示例性地示出了实施例并且构成说明书的一部分，与说明书的文字描述一起用于讲解实施例的示例性实施方式。所示出的实施例仅出于例示的目的，并不限制权利要求的范围。在所有附图中，相同的附图标记指代类似但不一定相同的要素。The accompanying drawings illustrate the embodiments by way of example and constitute a part of the specification, and together with the written description of the specification serve to explain exemplary implementations of the embodiments. The shown embodiments are for illustrative purposes only and do not limit the scope of the claims. Throughout the drawings, the same reference numbers refer to similar but not necessarily identical elements.
图1示出了根据本公开的实施例的可以在其中实施本文描述的各种方法的示例性系统的示意图；1 shows a schematic diagram of an exemplary system in which various methods described herein may be implemented, according to embodiments of the present disclosure;
图2示出了根据本公开的实施例的视频压缩质量评估方法的流程图；2 shows a flowchart of a video compression quality assessment method according to an embodiment of the present disclosure;
图3示出了根据本公开的实施例的视频压缩质量评估方法的部分过程的流程图；3 shows a flowchart of a part of a process of a video compression quality assessment method according to an embodiment of the present disclosure;
图4示出了根据本公开的实施例的视频压缩质量评估装置的结构框图；以及FIG. 4 shows a structural block diagram of an apparatus for evaluating video compression quality according to an embodiment of the present disclosure; and
图5示出了能够用于实现本公开的实施例的示例性电子设备的结构框图。5 shows a block diagram of an exemplary electronic device that can be used to implement embodiments of the present disclosure.
具体实施方式Detailed ways
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的各种细节以助于理解，应当将它们认为仅仅是示范性的。因此，本领域普通技术人员应当认识到，可以对这里描述的实施例做出各种改变和修改，而不会背离本公开的范围。同样，为了清楚和简明，以下的描述中省略了对公知功能和结构的描述。Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding and should be considered as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope of the present disclosure. Also, descriptions of well-known functions and constructions are omitted from the following description for clarity and conciseness.
在本公开中，除非另有说明，否则使用术语“第一”、“第二”等来描述各种要素不意图限定这些要素的位置关系、时序关系或重要性关系，这种术语只是用于将一个要素与另一要素区分开。在一些示例中，第一要素和第二要素可以指向该要素的同一实例，而在某些情况下，基于上下文的描述，它们也可以指代不同实例。In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, timing relationship or importance relationship of these elements, and such terms are only used for Distinguish one element from another. In some examples, the first element and the second element may refer to the same instance of the element, while in some cases they may refer to different instances based on the context of the description.
在本公开中对各种所述示例的描述中所使用的术语只是为了描述特定示例的目的，而并非旨在进行限制。除非上下文另外明确地表明，如果不特意限定要素的数量，则该要素可以是一个也可以是多个。此外，本公开中所使用的术语“和/或”涵盖所列出的项目中的任何一个以及全部可能的组合方式。The terminology used in the description of the various described examples in this disclosure is for the purpose of describing particular examples only and is not intended to be limiting. Unless the context clearly dictates otherwise, if the number of an element is not expressly limited, the element may be one or more. Furthermore, as used in this disclosure, the term "and/or" covers any and all possible combinations of the listed items.
本公开的技术方案中，所涉及的用户个人信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。In the technical solution of the present disclosure, the acquisition, storage and application of the user's personal information involved are all in compliance with the provisions of relevant laws and regulations, and do not violate public order and good customs.
车辆的图像采集设备在车辆行驶过程中可以采集视频，以用于为自动驾驶或辅助驾驶提供策略支持。并且所采集的视频还可以被备份到存储设备(例如硬盘)中，这些备份的视频可以用于对自动驾驶或辅助驾驶的算法进行优化分析。例如，工程师可以调取备份的视频，利用该备份的视频对自动驾驶或辅助驾驶模型的预测结果进行分析，从而分析或优化模型算法。然而，行驶过程中所采集的视频通常会占据较大的存储空间。而且，为了实现更好的辅助驾驶或自动驾驶性能，一些车辆采用性能更高的视频采集设备，这使得采集到的视频清晰度更高、占据的存储空间更大。如此巨大的存储量和数据传输速度对存储器件提出了巨大挑战。The image acquisition device of the vehicle can collect video during the driving process of the vehicle to provide policy support for automatic driving or assisted driving. And the collected videos can also be backed up to a storage device (such as a hard disk), and these backed up videos can be used to optimize and analyze algorithms for automatic driving or assisted driving. For example, engineers can retrieve the backup video and use the backup video to analyze the prediction results of the autonomous driving or assisted driving model, so as to analyze or optimize the model algorithm. However, videos captured during driving usually occupy a large storage space. Moreover, in order to achieve better assisted driving or automatic driving performance, some vehicles use video capture equipment with higher performance, which makes the captured video higher in definition and occupies a larger storage space. Such a huge amount of storage and data transfer speed pose great challenges to storage devices.
在相关技术中，可以在备份视频前将视频进行压缩，再将压缩的视频备份到存储器件中，这能够缓解存储器件面临的压力。然而，视频经压缩后，清晰度等性质会发生变化，当压缩的视频与未经压缩的原始视频之间的性质差异过大时，便无法用于对自动驾驶或辅助驾驶的算法进行优化分析。因此，需要对压缩视频的质量进行评估。在相关技术中，工程师可以通过人眼评估压缩视频的质量(例如观察清晰度)，也可以通过计算视频的信噪比来评估压缩视频的质量。然而，上述的评估方式不仅效率较低，而且无法评估压缩视频对辅助驾驶模型预测结果的影响。In the related art, the video can be compressed before backing up the video, and then the compressed video can be backed up to the storage device, which can relieve the pressure on the storage device. However, after the video is compressed, the properties such as definition will change. When the quality difference between the compressed video and the uncompressed original video is too large, it cannot be used for the optimization analysis of the algorithm for automatic driving or assisted driving. . Therefore, the quality of the compressed video needs to be evaluated. In the related art, engineers can evaluate the quality of compressed video through human eyes (such as observation clarity), and can also evaluate the quality of compressed video by calculating the signal-to-noise ratio of the video. However, the above evaluation methods are not only inefficient, but also unable to evaluate the impact of compressed video on the prediction results of the assisted driving model.
基于此，本公开提出一种视频压缩质量评估方法。通过利用辅助驾驶模型分别对输入其中的第一视频的图像帧和第三视频的图像帧进行预测，并基于二者的预测结果来评估经压缩的第二视频的质量，使得在保证了评估压缩视频的效率的同时，能够评估压缩视频对辅助驾驶模型预测结果的影响。Based on this, the present disclosure proposes a video compression quality assessment method. By using the assisted driving model to predict the image frames of the first video and the image frames of the third video, respectively, and to evaluate the quality of the compressed second video based on the prediction results of the two, it is possible to ensure the evaluation of compression While improving the efficiency of video, it is possible to evaluate the impact of compressed video on the prediction results of the assisted driving model.
下面将结合附图详细描述本公开的实施例。Embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.
图1示出了根据本公开的实施例可以将本文描述的各种方法和装置在其中实施的示例性系统100的示意图。参考图1，该系统100包括机动车辆110、服务器120以及将机动车辆110耦接到服务器120的一个或多个通信网络130。1 shows a schematic diagram of an
在本公开的实施例中，机动车辆110可以包括根据本公开实施例的计算设备和/或被配置以用于执行根据本公开实施例的方法。In an embodiment of the present disclosure, the
服务器120可以运行能够执行上述视频压缩质量评估方法的一个或多个服务或软件应用。在某些实施例中，服务器120还可以提供其他服务或软件应用，这些服务或软件应用可以包括非虚拟环境和虚拟环境。在图1所示的配置中，服务器120可以包括实现由服务器120执行的功能的一个或多个组件。这些组件可以包括可由一个或多个处理器执行的软件组件、硬件组件或其组合。机动车辆110的用户可以依次利用一个或多个客户端应用程序来与服务器120进行交互以利用这些组件提供的服务。应当理解，各种不同的系统配置是可能的，其可以与系统100不同。因此，图1是用于实施本文所描述的各种方法的系统的一个示例，并且不旨在进行限制。The
服务器120可以包括一个或多个通用计算机、专用服务器计算机(例如PC(个人计算机)服务器、UNIX服务器、中端服务器)、刀片式服务器、大型计算机、服务器群集或任何其他适当的布置和/或组合。服务器120可以包括运行虚拟操作系统的一个或多个虚拟机，或者涉及虚拟化的其他计算架构(例如可以被虚拟化以维护服务器的虚拟存储设备的逻辑存储设备的一个或多个灵活池)。在各种实施例中，服务器120可以运行提供下文所描述的功能的一个或多个服务或软件应用。
服务器120中的计算单元可以运行包括上述任何操作系统以及任何商业上可用的服务器操作系统的一个或多个操作系统。服务器120还可以运行各种附加服务器应用程序和/或中间层应用程序中的任何一个，包括HTTP服务器、FTP服务器、CGI服务器、JAVA服务器、数据库服务器等。The computing units in
在一些实施方式中，服务器120可以包括一个或多个应用程序，以分析和合并从机动车辆110接收的数据馈送和/或事件更新。服务器120还可以包括一个或多个应用程序，以经由机动车辆110的一个或多个显示设备来显示数据馈送和/或实时事件。In some implementations,
网络130可以是本领域技术人员熟知的任何类型的网络，其可以使用多种可用协议中的任何一种(包括但不限于TCP/IP、SNA、IPX等)来支持数据通信。仅作为示例，一个或多个网络130可以是卫星通信网络、局域网(LAN)、基于以太网的网络、令牌环、广域网(WAN)、因特网、虚拟网络、虚拟专用网络(VPN)、内部网、外部网、区块链网络、公共交换电话网(PSTN)、红外网络、无线网络(包括例如蓝牙、WiFi)和/或这些与其他网络的任意组合。Network 130 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP/IP, SNA, IPX, and the like. By way of example only, the one or more networks 130 may be a satellite communications network, a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet , extranet, blockchain network, public switched telephone network (PSTN), infrared network, wireless network (including, for example, Bluetooth, WiFi) and/or any combination of these and other networks.
系统100还可以包括一个或多个数据库150。在某些实施例中，这些数据库可以用于存储数据和其他信息。例如，数据库150中的一个或多个可用于存储诸如音频文件和视频文件的信息。数据存储库150可以驻留在各种位置。例如，由服务器120使用的数据存储库可以在服务器120本地，或者可以远离服务器120且可以经由基于网络或专用的连接与服务器120通信。数据存储库150可以是不同的类型。在某些实施例中，由服务器120使用的数据存储库可以是数据库，例如关系数据库。这些数据库中的一个或多个可以响应于命令而存储、更新和检索到数据库以及来自数据库的数据。
在某些实施例中，数据库150中的一个或多个还可以由应用程序使用来存储应用程序数据。由应用程序使用的数据库可以是不同类型的数据库，例如键值存储库，对象存储库或由文件系统支持的常规存储库。In some embodiments, one or more of the
机动车辆110可以包括传感器111用于感知周围环境。传感器111可以包括下列传感器中的一个或多个：视觉摄像头、红外摄像头、超声波传感器、毫米波雷达以及激光雷达(LiDAR)。不同的传感器可以提供不同的检测精度和范围。摄像头可以安装在车辆的前方、后方或其他位置。视觉摄像头可以实时捕获车辆内外的情况并呈现给驾驶员和/或乘客。此外，通过对视觉摄像头捕获的画面进行分析，可以获取诸如交通信号灯指示、交叉路口情况、其他车辆运行状态等信息。红外摄像头可以在夜视情况下捕捉物体。超声波传感器可以安装在车辆的四周，用于利用超声波方向性强等特点来测量车外物体距车辆的距离。毫米波雷达可以安装在车辆的前方、后方或其他位置，用于利用电磁波的特性测量车外物体距车辆的距离。激光雷达可以安装在车辆的前方、后方或其他位置，用于检测物体边缘、形状信息，从而进行物体识别和追踪。由于多普勒效应，雷达装置还可以测量车辆与移动物体的速度变化。
机动车辆110还可以包括通信装置112。通信装置112可以包括能够从卫星141接收卫星定位信号(例如，北斗、GPS、GLONASS以及GALILEO)并且基于这些信号产生坐标的卫星定位模块。通信装置112还可以包括与移动通信基站142进行通信的模块，移动通信网络可以实施任何适合的通信技术，例如GSM/GPRS、CDMA、LTE等当前或正在不断发展的无线通信技术(例如5G技术)。通信装置112还可以具有车联网或车联万物(Vehicle-to-Everything，V2X)模块，被配置用于实现例如与其它车辆143进行车对车(Vehicle-to-Vehicle，V2V)通信和与基础设施144进行车辆到基础设施(Vehicle-to-Infrastructure，V2I)通信的车与外界的通信。此外，通信装置112还可以具有被配置为例如通过使用IEEE802.11标准的无线局域网或蓝牙与用户终端145(包括但不限于智能手机、平板电脑或诸如手表等可佩戴装置)进行通信的模块。利用通信装置112，机动车辆110还可以经由网络130接入服务器120。The
机动车辆110还可以包括控制装置113。控制装置113可以包括与各种类型的计算机可读存储装置或介质通信的处理器，例如中央处理单元(CPU)或图形处理单元(GPU)，或者其他的专用处理器等。控制装置113可以包括用于自动控制车辆中的各种致动器的自动驾驶系统。自动驾驶系统被配置为经由多个致动器响应来自多个传感器111或者其他输入设备的输入而控制机动车辆110(未示出的)动力总成、转向系统以及制动系统等以分别控制加速、转向和制动，而无需人为干预或者有限的人为干预。控制装置113的部分处理功能可以通过云计算实现。例如，可以使用车载处理器执行某一些处理，而同时可以利用云端的计算资源执行其他一些处理。控制装置113可以被配置以执行根据本公开的方法。此外，控制装置113可以被实现为根据本公开的机动车辆侧(客户端)的计算设备的一个示例。The
图1的系统100可以以各种方式配置和操作，以使得能够应用根据本公开所描述的各种方法和装置。The
图2示出了根据本公开的实施例的视频压缩质量评估方法200的流程图。FIG. 2 shows a flowchart of a video compression
如图2所示，方法200包括：As shown in FIG. 2,
步骤S210、获取第一视频中的至少一个第一图像帧，第一视频是由车辆上的图像采集设备在车辆的行驶过程中采集的；Step S210, acquiring at least one first image frame in the first video, where the first video is collected by an image collection device on the vehicle during the driving process of the vehicle;
步骤S220、获取第二视频，第二视频是对第一视频进行视频压缩生成的；Step S220, acquiring a second video, the second video is generated by performing video compression on the first video;
步骤S230、将第二视频解压缩，以获取第三视频；Step S230, decompress the second video to obtain the third video;
步骤S240、从第三视频中提取至少一个第二图像帧，至少一个第二图像帧各自与至少一个第一图像帧中的相应一个第一图像帧对应；Step S240, extracting at least one second image frame from the third video, where each of the at least one second image frame corresponds to a corresponding one of the at least one first image frame;
步骤S250、将至少一个第一图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第一预测结果；Step S250, inputting at least one first image frame into the assisted driving model to obtain a first prediction result output by the assisted driving model;
步骤S260、将至少一个第二图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第二预测结果；以及Step S260, inputting at least one second image frame into the assisted driving model to obtain a second prediction result output by the assisted driving model; and
步骤S270、基于第一预测结果和第二预测结果，对经压缩的第二视频进行质量评估。Step S270: Based on the first prediction result and the second prediction result, perform quality assessment on the compressed second video.
通过利用辅助驾驶模型分别对输入其中的第一视频的图像帧和第三视频的图像帧进行预测，并基于二者的预测结果来评估经压缩的第二视频的质量，使得在保证了评估压缩视频的效率的同时，能够评估压缩视频对辅助驾驶模型预测结果的影响。By using the assisted driving model to predict the image frames of the first video and the image frames of the third video, respectively, and to evaluate the quality of the compressed second video based on the prediction results of the two, it is possible to ensure the evaluation of compression While improving the efficiency of video, it is possible to evaluate the impact of compressed video on the prediction results of the assisted driving model.
根据一些实施例，上述步骤S210、获取第一视频中的至少一个第一图像帧可以包括：According to some embodiments, the above step S210, acquiring at least one first image frame in the first video may include:
从第一视频中提取至少一个第一图像帧；以及extracting at least one first image frame from the first video; and
记录至少一个第一图像帧中的每个第一图像帧在第一视频中的标识。The identification of each of the at least one first image frame in the first video is recorded.
并且上述步骤S240、从第三视频中提取至少一个第二图像帧可以包括：从第三视频中提取与该标识对应的第二图像帧。And in the above step S240, extracting at least one second image frame from the third video may include: extracting a second image frame corresponding to the identifier from the third video.
在一个示例中，可以从第一视频中间隔地提取多个第一图像帧(例如第1、11、21帧)，并记录所提取的每个帧的帧号(1、11、21)或文件名，接着，可以从第三视频中提取与帧号1、11、21相对应的三个第二图像帧。由此，可以确保从第三视频中提取出的至少一个第二图像帧各自与从第一视频中提取出的相应一个第一图像帧对应。In one example, a plurality of first image frames (eg, 1st, 11th, and 21st frames) may be extracted from the first video at intervals, and the frame number (1, 11, 21) of each extracted frame is recorded or filename, then three second image frames corresponding to frame numbers 1, 11, 21 can be extracted from the third video. Thereby, it can be ensured that each of the at least one second image frame extracted from the third video corresponds to a corresponding one of the first image frames extracted from the first video.
在上述步骤S220中，第二视频可以是利用各种视频压缩平台或视频压缩软件、基于各种视频压缩标准(例如H.264/AVC标准或H.265/HEVC标准)对第一视频进行视频压缩生成的。并且第二视频可以具有各种压缩格式或各种压缩比(例如1:10、1:30)。经压缩的第二视频可以占据比未经压缩的第一视频更小的存储空间。In the above step S220, the second video may be video compression of the first video based on various video compression standards (eg H.264/AVC standard or H.265/HEVC standard) using various video compression platforms or video compression software. Compressed. And the second video may have various compression formats or various compression ratios (eg 1:10, 1:30). The compressed second video may occupy less storage space than the uncompressed first video.
由此可见，利用方法200可以跨平台地评估各种压缩格式的压缩视频，而无需针对不同压缩平台、不同压缩格式进行复杂的适应性设计。It can be seen that the
在上述步骤S230中，将第二视频解压缩所获取到的第三视频可以是YUV格式的视频。YUV中的“Y”表示明亮度(Luminance或Luma)，“U”和“V”表示的则是色度(Chrominance或Chroma)。In the above step S230, the third video obtained by decompressing the second video may be a video in YUV format. "Y" in YUV stands for Luminance (Luminance or Luma), while "U" and "V" stand for Chrominance or Chroma.
根据一些实施例，辅助驾驶模型可以包括障碍物识别子模型和交通灯识别子模型。并且第一预测结果可以包括由障碍物识别子模型输出的第一障碍物识别结果和由交通灯识别子模型输出的第一交通灯信号识别结果；第二预测结果可以包括由障碍物识别子模型输出的第二障碍物识别结果和由交通灯识别子模型输出的第二交通灯信号识别结果。According to some embodiments, the assisted driving model may include an obstacle recognition sub-model and a traffic light recognition sub-model. And the first prediction result may include the first obstacle identification result output by the obstacle identification sub-model and the first traffic light signal identification result output by the traffic light identification sub-model; the second prediction result may include the obstacle identification sub-model. The outputted second obstacle recognition result and the second traffic light signal recognition result output by the traffic light recognition sub-model.
由于自动驾驶车辆或辅助驾驶车辆通常可以利用上述两种子模型来进行视觉分析，从而基于此规划行驶策略。通过分别利用障碍物识别子模型和交通灯识别子模型对输入的图像帧进行预测，使得预测结果更加符合自动驾驶车辆或辅助驾驶车辆的实际应用场景，从而更加准确地评估压缩视频对辅助驾驶模型是否能识别障碍物以及是否能识别信号灯信号的影响。Since autonomous vehicles or assisted driving vehicles can usually use the above two sub-models for visual analysis, driving strategies can be planned based on them. By using the obstacle recognition sub-model and the traffic light recognition sub-model to predict the input image frames, the prediction results are more in line with the actual application scenarios of autonomous vehicles or assisted driving vehicles, so as to more accurately evaluate the impact of compressed video on the assisted driving model. Whether obstacles can be identified and whether the influence of signal lights can be identified.
障碍物识别子模型可以识别或感知到图像中的各种预设类别的障碍物(例如图像中的其它车辆、行人、建筑物等)。示例性地，障碍物识别子模型还可以根据图像中的障碍物的属性(例如遮挡属性、截断属性、方向属性、位置属性等)将图像中的车辆预测为多个子类别(例如、卡车、轿车、自行车等)。The obstacle identification sub-model can identify or perceive obstacles of various preset categories in the image (eg, other vehicles, pedestrians, buildings, etc. in the image). Exemplarily, the obstacle recognition sub-model can also predict vehicles in the image into multiple sub-categories (eg, trucks, cars, etc.) , bicycles, etc.).
在一个示例中，第一障碍物识别结果和第二障碍物识别结果可以是针对障碍物识别得到的标注框的种类、数量和位置。In one example, the first obstacle identification result and the second obstacle identification result may be the types, numbers and positions of the callout boxes obtained for the obstacle identification.
另一方面，交通灯识别子模型可以识别或感知到图像中的交通灯以及该交通灯的信号类型。示例性地，交通灯识别子模型可以根据障碍物的形状，识别出图像中的哪些障碍物属于交通灯，并识别交通灯是绿灯、红灯或黄灯。On the other hand, the traffic light recognition sub-model can identify or perceive a traffic light in an image and the signal type of that traffic light. Exemplarily, the traffic light recognition sub-model can identify which obstacles in the image belong to the traffic lights according to the shapes of the obstacles, and identify whether the traffic lights are green, red or yellow.
类似地，在一个示例中，第一交通灯信号识别结果和第二交通灯信号识别结果可以是针对交通灯识别得到的标注框的种类、数量和位置。Similarly, in one example, the first traffic light signal recognition result and the second traffic light signal recognition result may be the types, numbers and positions of the callout boxes obtained for the traffic light recognition.
图3示出了根据本公开的实施例的视频压缩质量评估方法200的部分过程的流程图。如图3所示，根据一些实施例，步骤S270、基于第一预测结果和第二预测结果，对经压缩的第二视频进行质量评估可以包括：FIG. 3 shows a flowchart of part of a process of a video compression
步骤S371、将第二障碍物识别结果的识别率与第一障碍物识别结果的识别率进行比较；Step S371, comparing the recognition rate of the second obstacle recognition result with the recognition rate of the first obstacle recognition result;
步骤S372、将第二交通灯信号识别结果的识别率与第一交通灯信号识别结果的识别率进行比较；以及Step S372, comparing the recognition rate of the second traffic light signal recognition result with the recognition rate of the first traffic light signal recognition result; and
步骤S373、响应于确定第二障碍物识别结果的识别率大于或等于第一障碍物识别结果的识别率并且第二交通灯信号识别结果的识别率大于或等于第一交通灯信号识别结果的识别率，确定经压缩的第二视频质量符合要求。Step S373, in response to determining that the recognition rate of the second obstacle recognition result is greater than or equal to the recognition rate of the first obstacle recognition result and the recognition rate of the second traffic light signal recognition result is greater than or equal to the recognition of the first traffic light signal recognition result rate, it is determined that the quality of the compressed second video meets the requirements.
由此，当辅助驾驶模型输出的第二障碍物识别结果和第二交通灯信号识别结果均分别优于其输出的第一障碍物识别结果和第一交通灯信号识别结果时，才确定经压缩的第二视频质量符合要求。Therefore, when the second obstacle recognition result and the second traffic light signal recognition result output by the assisted driving model are both better than the first obstacle recognition result and the first traffic light signal recognition result output by the assisted driving model, it is determined that the compressed The quality of the second video meets the requirements.
在一些场景中，自动驾驶车辆或辅助驾驶车辆上安装的用于采集图像的相机(例如鱼眼相机)会使所采集的图像产生畸变，为了更加准确地评估压缩视频的压缩质量，可以对输入辅助驾驶模型的图像帧进行去除畸变处理。In some scenarios, the camera (such as a fisheye camera) installed on the autonomous vehicle or assisted driving vehicle for capturing images will distort the captured images. In order to more accurately evaluate the compression quality of the compressed video, the input The image frame of the assisted driving model is de-distorted.
根据一些实施例，方法200还可以包括：According to some embodiments,
去除至少一个第一图像帧以及至少一个第二图像帧中的图像畸变。Image distortion is removed in at least one first image frame and at least one second image frame.
并且，上述步骤S250可以包括：将经去除图像畸变的至少一个第一图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第一预测结果；Moreover, the above step S250 may include: inputting at least one first image frame from which image distortion has been removed into the assisted driving model to obtain a first prediction result output by the assisted driving model;
并且，上述步骤S260可以包括：将经去除图像畸变的至少一个第二图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第二预测结果。Furthermore, the above step S260 may include: inputting at least one second image frame from which the image distortion has been removed into the assisted driving model to obtain a second prediction result output by the assisted driving model.
根据一些实施例，方法200可以由分布式系统执行。分布式系统可以包括第一服务器和与第一服务器通信连接的第二服务器。辅助驾驶模型可以部署在第一服务器中，并且第二服务器用于将第二视频解压缩并从第三视频中提取至少一个第二图像帧。According to some embodiments,
由此，将视频的解压缩和辅助驾驶模型的运行分别部署在不同的服务器中，不仅可以减少每个服务器的运行压力，还能够进一步提高压缩视频质量的评估效率。Therefore, deploying video decompression and assisted driving model operation in different servers can not only reduce the operating pressure of each server, but also further improve the evaluation efficiency of compressed video quality.
在一些示例中，自动驾驶车辆可以包括多个图像采集设备，每个图像采集设备均可以独立地捕获(不同角度的)视频。相应地，分布式系统可以包括多台第二服务器，分别用于将多个第二视频中的相应一个或多个解压缩、并从多个第三视频中的相应一个或多个中提取至少一个第二图像帧。In some examples, an autonomous vehicle may include multiple image capture devices, each of which may capture video (at different angles) independently. Correspondingly, the distributed system may include a plurality of second servers for decompressing corresponding one or more of the plurality of second videos, and extracting at least one corresponding one or more of the plurality of third videos, respectively. a second image frame.
相应地，每个第二服务器可以将图像帧发送至部署有辅助驾驶模型的第一服务器。Accordingly, each second server may send the image frame to the first server on which the assisted driving model is deployed.
根据本公开的另一方面，提供了一种视频压缩质量评估装置。图4示出了根据本公开的实施例的视频压缩质量评估装置400的结构框图。如图4所示，装置400包括：According to another aspect of the present disclosure, a video compression quality evaluation apparatus is provided. FIG. 4 shows a structural block diagram of an
第一图像帧获取单元410，被配置为获取第一视频中的至少一个第一图像帧，第一视频是由车辆上的图像采集设备在车辆的行驶过程中采集的；The first image
第二视频获取单元420，被配置为获取第二视频，第二视频是对第一视频进行视频压缩生成的；The second
解压缩单元430，被配置为将第二视频解压缩，以获取第三视频；a
提取单元440，被配置为从第三视频中提取至少一个第二图像帧，至少一个第二图像帧各自与至少一个第一图像帧中的相应一个第一图像帧对应；an
第一预测单元450，被配置为将至少一个第一图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第一预测结果；The
第二预测单元460，被配置为将至少一个第二图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第二预测结果；以及The
评估单元470，被配置为基于第一预测结果和第二预测结果，对经压缩的第二视频进行质量评估。The
应当理解，图4中所示装置400的各个单元可以与参考图2描述的方法200中的各个步骤相对应。由此，上面针对方法200描述的操作、特征和优点同样适用于装置400及其包括的单元。为了简洁起见，某些操作、特征和优点在此不再赘述。It should be understood that various units of the
根据一些实施例，其中，辅助驾驶模型可以包括障碍物识别子模型和交通灯识别子模型。第一预测结果可以包括由障碍物识别子模型输出的第一障碍物识别结果和由交通灯识别子模型输出的第一交通灯信号识别结果。并且第二预测结果可以包括由障碍物识别子模型输出的第二障碍物识别结果和由交通灯识别子模型输出的第二交通灯信号识别结果。According to some embodiments, the assisted driving model may include an obstacle identification sub-model and a traffic light identification sub-model. The first prediction result may include a first obstacle recognition result output by the obstacle recognition sub-model and a first traffic light signal recognition result output by the traffic light recognition sub-model. And the second prediction result may include a second obstacle recognition result output by the obstacle recognition sub-model and a second traffic light signal recognition result output by the traffic light recognition sub-model.
根据一些实施例，评估单元470可以被进一步配置为：According to some embodiments, the
将第二障碍物识别结果的识别率与第一障碍物识别结果的识别率进行比较；comparing the recognition rate of the second obstacle recognition result with the recognition rate of the first obstacle recognition result;
将第二交通灯信号识别结果的识别率与第一交通灯信号识别结果的识别率进行比较；以及comparing the recognition rate of the second traffic light signal recognition result with the recognition rate of the first traffic light signal recognition result; and
响应于确定第二障碍物识别结果的识别率大于或等于第一障碍物识别结果的识别率并且第二交通灯信号识别结果的识别率大于或等于第一交通灯信号识别结果的识别率，确定经压缩的第二视频质量符合要求。In response to determining that the recognition rate of the second obstacle recognition result is greater than or equal to the recognition rate of the first obstacle recognition result and the recognition rate of the second traffic light signal recognition result is greater than or equal to the recognition rate of the first traffic light signal recognition result, determining The compressed second video quality meets the requirements.
根据一些实施例，装置400还可以包括畸变去除单元(图中未示出)，畸变去除单元被配置为去除至少一个第一图像帧以及至少一个第二图像帧中的图像畸变。并且第一预测单元450被进一步配置为：将经去除图像畸变的至少一个第一图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第一预测结果；并且第二预测单元460被进一步配置为：将经去除图像畸变的至少一个第二图像帧输入辅助驾驶模型，以获取辅助驾驶模型输出的第二预测结果。According to some embodiments, the
根据一些实施例，第一图像帧获取单元410可以被进一步配置为从第一视频中提取至少一个第一图像帧；以及记录至少一个第一图像帧中的每个第一图像帧在第一视频中的标识。According to some embodiments, the first image
并且提取单元440可以被进一步配置为从第三视频中提取与标识对应的第二图像帧。And the
根据本公开的实施例，还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。According to embodiments of the present disclosure, an electronic device, a readable storage medium, and a computer program product are also provided.
参考图5，现将描述可以作为本公开的服务器或客户端的电子设备500的结构框图，其是可以应用于本公开的各方面的硬件设备的示例。电子设备旨在表示各种形式的数字电子的计算机设备，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示各种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。Referring to FIG. 5 , a structural block diagram of an
如图5所示，电子设备500包括计算单元501，其可以根据存储在只读存储器(ROM)502中的计算机程序或者从存储单元508加载到随机访问存储器(RAM)503中的计算机程序，来执行各种适当的动作和处理。在RAM503中，还可存储电子设备500操作所需的各种程序和数据。计算单元501、ROM 502以及RAM 503通过总线504彼此相连。输入/输出(I/O)接口505也连接至总线504。As shown in FIG. 5 , the
电子设备500中的多个部件连接至I/O接口505，包括：输入单元506、输出单元507、存储单元508以及通信单元509。输入单元506可以是能向电子设备500输入信息的任何类型的设备，输入单元506可以接收输入的数字或字符信息，以及产生与电子设备的用户设置和/或功能控制有关的键信号输入，并且可以包括但不限于鼠标、键盘、触摸屏、轨迹板、轨迹球、操作杆、麦克风和/或遥控器。输出单元507可以是能呈现信息的任何类型的设备，并且可以包括但不限于显示器、扬声器、视频/音频输出终端、振动器和/或打印机。存储单元508可以包括但不限于磁盘、光盘。通信单元509允许电子设备500通过诸如因特网的计算机网络和/或各种电信网络与其他设备交换信息/数据，并且可以包括但不限于调制解调器、网卡、红外通信设备、无线通信收发机和/或芯片组，例如蓝牙TM设备、802.11设备、WiFi设备、WiMax设备、蜂窝通信设备和/或类似物。Various components in the
计算单元501可以是各种具有处理和计算能力的通用和/或专用处理组件。计算单元501的一些示例包括但不限于中央处理单元(CPU)、图形处理单元(GPU)、各种专用的人工智能(AI)计算芯片、各种运行机器学习模型算法的计算单元、数字信号处理器(DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元501执行上文所描述的各个方法和处理，例如方法200。例如，在一些实施例中，方法200可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元508。在一些实施例中，计算机程序的部分或者全部可以经由ROM 502和/或通信单元509而被载入和/或安装到电子设备500上。当计算机程序加载到RAM 503并由计算单元501执行时，可以执行上文描述的方法200的一个或多个步骤。备选地，在其他实施例中，计算单元501可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行方法200。
本文中以上描述的系统和技术的各种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、芯片上系统的系统(SOC)、负载可编程逻辑设备(CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些各种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。Various implementations of the systems and techniques described herein above may be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips system (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpretable on a programmable system including at least one programmable processor that The processor, which may be a special purpose or general-purpose programmable processor, may receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device an output device.
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer or other programmable data processing apparatus, such that the program code, when executed by the processor or controller, performs the functions/functions specified in the flowcharts and/or block diagrams. Action is implemented. The program code may execute entirely on the machine, partly on the machine, partly on the machine and partly on a remote machine as a stand-alone software package or entirely on the remote machine or server.
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with the instruction execution system, apparatus or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), fiber optics, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，CRT(阴极射线管)或者LCD(液晶显示器)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。To provide interaction with a user, the systems and techniques described herein may be implemented on a computer having a display device (eg, a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user ); and a keyboard and pointing device (eg, a mouse or trackball) through which a user can provide input to the computer. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (eg, visual feedback, auditory feedback, or tactile feedback); and can be in any form (including acoustic input, voice input, or tactile input) to receive input from the user.
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(LAN)、广域网(WAN)、互联网和区块链网络。The systems and techniques described herein may be implemented on a computing system that includes back-end components (eg, as a data server), or a computing system that includes middleware components (eg, an application server), or a computing system that includes front-end components (eg, a user's computer having a graphical user interface or web browser through which a user may interact with implementations of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system may be interconnected by any form or medium of digital data communication (eg, a communication network). Examples of communication networks include: Local Area Networks (LANs), Wide Area Networks (WANs), the Internet, and blockchain networks.
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上运行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，也可以为分布式系统的服务器，或者是结合了区块链的服务器。A computer system can include clients and servers. Clients and servers are generally remote from each other and usually interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a distributed system server, or a server combined with blockchain.
应该理解，可以使用上面所示的各种形式的流程，重新排序、增加或删除步骤。例如，本公开中记载的各步骤可以并行地执行、也可以顺序地或以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, the steps described in the present disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, which are not limited herein.
虽然已经参照附图描述了本公开的实施例或示例，但应理解，上述的方法、系统和设备仅仅是示例性的实施例或示例，本发明的范围并不由这些实施例或示例限制，而是仅由授权后的权利要求书及其等同范围来限定。实施例或示例中的各种要素可以被省略或者可由其等同要素替代。此外，可以通过不同于本公开中描述的次序来执行各步骤。进一步地，可以以各种方式组合实施例或示例中的各种要素。重要的是随着技术的演进，在此描述的很多要素可以由本公开之后出现的等同要素进行替换。Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-described methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but is limited only by the appended claims and their equivalents. Various elements of the embodiments or examples may be omitted or replaced by equivalents thereof. Furthermore, the steps may be performed in an order different from that described in this disclosure. Further, various elements of the embodiments or examples may be combined in various ways. Importantly, as technology evolves, many of the elements described herein may be replaced by equivalent elements that appear later in this disclosure.
Claims (14)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210827391.9ACN115243035A (en) | 2022-07-13 | 2022-07-13 | Video compression quality assessment method, apparatus, electronic device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210827391.9ACN115243035A (en) | 2022-07-13 | 2022-07-13 | Video compression quality assessment method, apparatus, electronic device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115243035Atrue CN115243035A (en) | 2022-10-25 |
Family
ID=83673061
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210827391.9APendingCN115243035A (en) | 2022-07-13 | 2022-07-13 | Video compression quality assessment method, apparatus, electronic device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115243035A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040028139A1 (en)* | 2002-08-06 | 2004-02-12 | Andre Zaccarin | Video encoding |
| CN102932649A (en)* | 2011-08-08 | 2013-02-13 | 华为软件技术有限公司 | Video decoding quality detection method and device of set top box |
| US20140002735A1 (en)* | 2011-12-28 | 2014-01-02 | Barry A. O'Mahony | Method of and apparatus for performing an objective video quality assessment using non-intrusive video frame tracking |
| CN113748683A (en)* | 2019-05-12 | 2021-12-03 | 脸谱公司 | System and method for preserving in-band metadata in compressed video files |
| WO2022071695A1 (en)* | 2020-09-29 | 2022-04-07 | 삼성전자 주식회사 | Device for processing image and method for operating same |
| CN114721692A (en)* | 2022-05-06 | 2022-07-08 | 阿波罗智能技术(北京)有限公司 | System, method and device for upgrading automatic driving model |
- 2022
- 2022-07-13CNCN202210827391.9Apatent/CN115243035A/enactivePending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040028139A1 (en)* | 2002-08-06 | 2004-02-12 | Andre Zaccarin | Video encoding |
| CN102932649A (en)* | 2011-08-08 | 2013-02-13 | 华为软件技术有限公司 | Video decoding quality detection method and device of set top box |
| US20140002735A1 (en)* | 2011-12-28 | 2014-01-02 | Barry A. O'Mahony | Method of and apparatus for performing an objective video quality assessment using non-intrusive video frame tracking |
| CN113748683A (en)* | 2019-05-12 | 2021-12-03 | 脸谱公司 | System and method for preserving in-band metadata in compressed video files |
| WO2022071695A1 (en)* | 2020-09-29 | 2022-04-07 | 삼성전자 주식회사 | Device for processing image and method for operating same |
| CN114721692A (en)* | 2022-05-06 | 2022-07-08 | 阿波罗智能技术(北京)有限公司 | System, method and device for upgrading automatic driving model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113887400B (en) | Obstacle detection method, model training method, device and autonomous vehicle | |
| CN111291650A (en) | Method and device for automatic parking assistance | |
| CN115366920B (en) | Decision-making method, device, equipment and medium for automatic driving vehicle | |
| CN112037142B (en) | Image denoising method, device, computer and readable storage medium | |
| CN113920174B (en) | Point cloud registration method, device, equipment, medium and automatic driving vehicle | |
| CN114689036B (en) | Map updating method, automatic driving method, electronic device and storage medium | |
| CN115019060A (en) | Target recognition method, and training method and device of target recognition model | |
| CN114970112B (en) | Method, device, electronic equipment and storage medium for automatic driving simulation | |
| CN114758502B (en) | Two-vehicle joint trajectory prediction method and device, electronic equipment and automatic driving vehicle | |
| CN114429610A (en) | Method, device, electronic device and storage medium for obtaining license plate information | |
| CN113074955B (en) | Method, apparatus, electronic device and medium for controlling data collection | |
| CN117035032A (en) | Method for model training by fusing text data and automatic driving data and vehicle | |
| CN113792016A (en) | Method, device, equipment and medium for extracting driving data | |
| CN113408325A (en) | Method and device for identifying surrounding environment of vehicle and related equipment | |
| US10366286B2 (en) | Detection of traffic light signal changes | |
| CN115082690A (en) | Target recognition method, target recognition model training method and device | |
| CN117542042B (en) | Three-dimensional object detection method and device, electronic equipment and storage medium | |
| WO2023273467A1 (en) | True value data determination method and apparatus, neural network training method and apparatus, and travel control method and apparatus | |
| CN117710939A (en) | Signal lamp detection method, device and system and automatic driving vehicle | |
| CN117707172A (en) | Decision-making method and device for automatic driving vehicle, equipment and medium | |
| CN113850909B (en) | Point cloud data processing method and device, electronic equipment and automatic driving equipment | |
| CN115243035A (en) | Video compression quality assessment method, apparatus, electronic device and medium | |
| CN116469069B (en) | Scene coding model training method, device and medium for automatic driving | |
| CN117831000A (en) | Traffic light detection method and device, electronic equipment and storage medium | |
| CN116580367A (en) | Data processing method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |