WO2020248890A1 - Video quality evaluation method and apparatus, and electronic device - Google Patents

Abstract

Provided in the present disclosure are a video quality evaluation method and apparatus, an electronic device, and a computer readable storage medium, the method comprising: setting a first video as a test video and setting a second video as a reference video, and using a predetermined video quality evaluation method to obtain a first evaluation value; setting the second video as a test video and setting the first video as a reference video, and using the predetermined video quality estimation method to obtain a second evaluation value; and, on the basis of the first evaluation value and the second evaluation value, evaluating the quality of the first video and the second video according to a predetermined rule; according to the predetermined video quality evaluation method, when the quality of the first video is different to the quality of the second video, the first evaluation value is different to the second evaluation value.

Description

一种视频质量评估方法、装置和电子设备Video quality evaluation method, device and electronic equipment

相关申请的交叉引用Cross references to related applications

本申请基于申请号为201910517059.0、申请日为2019年06月14日，名称为“一种视频质量评估方法、装置和电子设备”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。This application is filed based on the Chinese patent application with the application number 201910517059.0, the filing date of June 14, 2019, and the title "A method, device and electronic equipment for video quality evaluation", and the priority of the Chinese patent application is claimed. The entire content of the Chinese patent application is hereby incorporated into this application as a reference.

技术领域Technical field

本公开涉及视频质量评估，更具体地，涉及一种视频质量评估方法、装置、电子设备和计算机可读存储介质。The present disclosure relates to video quality evaluation, and more specifically, to a video quality evaluation method, device, electronic equipment, and computer-readable storage medium.

背景技术Background technique

图像/视频质量评估在图像/视频处理中起着至关重要的作用，它可以用于预测图像/视频质量并评估各种视频处理/压缩算法的性能。通常有两类评估视频质量的方法：主观方法和客观方法。主观方法依赖于人类主体观看视频并提供质量评级，客观方法使用算法来预测人类观看者如何评价视频。Image/video quality evaluation plays a vital role in image/video processing. It can be used to predict image/video quality and evaluate the performance of various video processing/compression algorithms. There are generally two types of methods for evaluating video quality: subjective methods and objective methods. Subjective methods rely on human subjects watching videos and provide quality ratings, and objective methods use algorithms to predict how human viewers rate videos.

由于客观方法不需要强烈的人类参与，因而对于大规模的实时评估更加实用。取决于是否需要参考视频(或参考视频的特征)用于图像/视频质量评估，客观方法可以进一步分为三类：全参考(Full Reference)视频质量评估方法，部分参考(Reduced Reference，RR)视频质量评估方法和无参考(no reference，NR)制品质量评估方法，其中全参考视频质量评估方法使用完整的原始视频信号作为对比数据来评估视频质量，部分参考视频质量评估方法使用经过提取的部分视频特征作为对比数据来评估视频质量，无参考视频质量评估方法仅使用用户得到的实际数据来评估视频质量。Since the objective method does not require strong human participation, it is more practical for large-scale real-time evaluation. Depending on whether the reference video (or the characteristics of the reference video) is required for image/video quality evaluation, objective methods can be further divided into three categories: Full Reference (Full Reference) video quality evaluation methods, and Partial Reference (Reduced Reference, RR) video Quality evaluation methods and no reference (NR) product quality evaluation methods, in which the full reference video quality evaluation method uses the complete original video signal as comparison data to evaluate the video quality, and some reference video quality evaluation methods use the extracted part of the video Features are used as comparative data to evaluate video quality, and the non-reference video quality evaluation method only uses actual data obtained by users to evaluate video quality.

发明内容Summary of the invention

本公开提供了一种视频质量评估方法、装置、电子设备和计算机可读存储介质。The present disclosure provides a video quality evaluation method, device, electronic equipment, and computer-readable storage medium.

根据本公开的一方面，提供了一种视频质量评估方法，该方法包括：将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值；以及基于第一评估值和第二评估值，根据预定准则来评估第一视频和第二视频的质量，其中，根据预定视频质量评估方法，在第一视频的质量不同于第二视频的质量的情况下，第一评估值不同于第二评估值。According to an aspect of the present disclosure, there is provided a video quality evaluation method, which includes: using a first video as a test video, using a second video as a reference video, and obtaining a first evaluation value using a predetermined video quality evaluation method; The second video is used as a test video, the first video is used as a reference video, and a predetermined video quality evaluation method is used to obtain the second evaluation value; and based on the first evaluation value and the second evaluation value, the first video and the second video are evaluated according to predetermined criteria Wherein, according to a predetermined video quality evaluation method, in a case where the quality of the first video is different from the quality of the second video, the first evaluation value is different from the second evaluation value.

根据本公开的另一方面，提供了一种视频质量评估装置，该装置包括：评估值计算模块，用于执行以下操作：将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值；和质量评估模块，用于基于第一评估值和第二评估值，根据预定准则来评估第一视频和第二视频的质量，其中，根据预定视频质量评估方法，在第一视频的质量不同于第二视频的质量的情况下，第一评估值不同于第二评估值。According to another aspect of the present disclosure, there is provided a video quality evaluation device. The device includes: an evaluation value calculation module for performing the following operations: using a first video as a test video, using a second video as a reference video, and using a predetermined The video quality evaluation method obtains the first evaluation value; the second video is used as the test video, the first video is used as the reference video, and the predetermined video quality evaluation method is used to obtain the second evaluation value; and the quality evaluation module is configured to be based on the first evaluation value And the second evaluation value to evaluate the quality of the first video and the second video according to predetermined criteria, wherein, according to a predetermined video quality evaluation method, in the case where the quality of the first video is different from the quality of the second video, the first evaluation The value is different from the second evaluation value.

根据本公开的又一方面，提供了一种包括存储器和处理器的电子设备，存储器上存储有计算机程序指令，该计算机程序指令在由该处理器加载并运行时，使该处理器执行以下操作：将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值；以及基于第一评估值和第二评估值，根据预定准则来评估第一视频和第二视频的质量，其中，根据预定视频质量评估方法，在第一视频的质量不同于第二视频的质量的情况下，第一评估值不同于第二评估值。According to another aspect of the present disclosure, there is provided an electronic device including a memory and a processor, and computer program instructions are stored on the memory, and the computer program instructions, when loaded and run by the processor, cause the processor to perform the following operations : Use the first video as the test video, use the second video as the reference video, and use the predetermined video quality evaluation method to obtain the first evaluation value; use the second video as the test video, use the first video as the reference video, and use the predetermined video quality evaluation Method to obtain a second evaluation value; and based on the first evaluation value and the second evaluation value, the quality of the first video and the second video are evaluated according to a predetermined criterion, wherein, according to the predetermined video quality evaluation method, the quality of the first video is different In the case of the quality of the second video, the first evaluation value is different from the second evaluation value.

根据本公开的再一方面，提供了一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序指令，该计算机程序指令在由处理器加载并运行时，使该处理器执行以下操作：将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值；以及基于第一评估值和第二评估值，根据预定准则来评估第一视频和第二视频的质量，其中，根据预定视频质量评估方法，在第一视频的质量不同于第二视频的质量的情况下，第一评估值不同于第二评估值。According to another aspect of the present disclosure, there is provided a computer-readable storage medium having computer program instructions stored thereon, and the computer program instructions, when loaded and run by a processor, cause the processor to execute the following Operation: use the first video as the test video, use the second video as the reference video, and use the predetermined video quality evaluation method to obtain the first evaluation value; use the second video as the test video, use the first video as the reference video, and use the predetermined video quality The evaluation method obtains the second evaluation value; and based on the first evaluation value and the second evaluation value, the quality of the first video and the second video are evaluated according to predetermined criteria, wherein, according to the predetermined video quality evaluation method, the quality of the first video When the quality of the second video is different, the first evaluation value is different from the second evaluation value.

如以下将详细描述的，本公开提出了一种在不存在参考视频的情况下，使用诸如全参考视频质量评估方法和部分参考视频质量评估方法的视频质量评估方法来评估两个视频的质量的方法。换言之，即使在参考视频不可用时，根据本公开的实施例的视频质量评估方法也可以使用全参考视频质量评估方法或部分参考视频质量评估方法来评估视频的质量，例如，对视频的质量进行排序。As will be described in detail below, the present disclosure proposes a method for evaluating the quality of two videos using a video quality evaluation method such as a full reference video quality evaluation method and a partial reference video quality evaluation method in the absence of a reference video. method. In other words, even when the reference video is not available, the video quality evaluation method according to the embodiment of the present disclosure may use the full reference video quality evaluation method or the partial reference video quality evaluation method to evaluate the quality of the video, for example, to rank the quality of the video .

应该理解，前面的一般描述和下面的详细描述两者都是示例性的，并且旨在提供要求保护的技术的进一步说明，而不旨在限制本公开的技术构思。It should be understood that the foregoing general description and the following detailed description are both exemplary, and are intended to provide a further description of the claimed technology, and are not intended to limit the technical idea of the present disclosure.

附图说明Description of the drawings

结合附图并参考以下具体实施方式，本公开各实施例的上述和其他特征、优点及方面将变得更加明显。贯穿附图中，相同或相似的附图标记表示相同或相似的元素。应当理解附图是示意性的，原件和元素不一定按照比例绘制。The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent in conjunction with the drawings and with reference to the following specific embodiments. Throughout the drawings, the same or similar reference signs indicate the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

图1是根据本公开的一些实施例的视频质量评估方法的一个示意流程图；Fig. 1 is a schematic flowchart of a video quality evaluation method according to some embodiments of the present disclosure;

图2是根据本公开的一些实施例的视频质量评估方法的另一个示意流程图；Fig. 2 is another schematic flowchart of a video quality evaluation method according to some embodiments of the present disclosure;

图3是根据本公开的一些实施例的用于视频质量评估的电子装置的一个示意图；FIG. 3 is a schematic diagram of an electronic device for video quality evaluation according to some embodiments of the present disclosure;

图4是根据本公开的一些实施例的用于视频质量评估的电子装置的另一个示意图；Fig. 4 is another schematic diagram of an electronic device for video quality evaluation according to some embodiments of the present disclosure;

图5是根据本公开的一些实施例的用于视频质量评估的电子设备的示意图；Figure 5 is a schematic diagram of an electronic device for video quality evaluation according to some embodiments of the present disclosure;

图6是根据本公开的一些实施例的用于视频质量评估的另一电子设备的示意图；以及FIG. 6 is a schematic diagram of another electronic device for video quality evaluation according to some embodiments of the present disclosure; and

图7是根据本公开的一些实施例的用于视频质量评估的计算机可读存储介质的示意图。FIG. 7 is a schematic diagram of a computer-readable storage medium used for video quality evaluation according to some embodiments of the present disclosure.

具体实施方式如上所述，由于全参考视频质量评估方法和部分参考视频质量评估方法在评估视频质量时利用原始视频，因而全参考视频质量评估方法和部分参考视频质量评估方法对于某些应用更准确；而无参考视频质量评估方法可能具有更广泛的应用，因为无参考视频质量评估方法不需要参考视 频。DETAILED DESCRIPTION As described above, since the full reference video quality evaluation method and the partial reference video quality evaluation method use the original video when evaluating the video quality, the full reference video quality evaluation method and the partial reference video quality evaluation method are more accurate for certain applications. ; The non-reference video quality evaluation method may have a wider application, because the non-reference video quality evaluation method does not require a reference video.

基于上述问题而提出了本公开，本公开的发明人通过研究分析发现全参考视频质量评估方法和部分参考视频质量评估方法中的一些评估方法，例如，视频质量多方法评估融合(Video Multimethod Assessment Fusion，VMAF)方法，在一些情况下具有如下特性：对于两个质量不同的视频，第一视频和第二视频，将第一视频作为测试视频，将第二视频作为参考视频，使用这些视频质量评估方法得到的评估值，不同于将第二视频作为测试视频，将第一视频作为参考视频而得到的评估值。基于此而提出了本公开，本公开提出了一种视频质量评估方法、装置、电子设备和计算机可读存储介质。根据本公开的实施例的视频质量评估方法在不存在参考视频的情况下，使用具有以上特性的诸如VMAF的视频质量评估方法来评估两个视频的质量。换言之，即使在参考视频不可用时，根据本公开的实施例的视频质量评估方法也可以使用具有以上特性的全参考视频质量评估方法或部分参考视频质量评估方法来评估视频的质量，例如，对视频的质量进行排名。The present disclosure is proposed based on the above-mentioned problems. The inventors of the present disclosure have discovered through research and analysis that some of the full-reference video quality assessment methods and partial reference video quality assessment methods, for example, Video Multimethod Assessment Fusion (Video Multimethod Assessment Fusion) , VMAF) method, in some cases has the following characteristics: for two different quality videos, the first video and the second video, the first video is used as the test video, the second video is used as the reference video, and these video quality evaluations are used The evaluation value obtained by the method is different from the evaluation value obtained by using the second video as the test video and the first video as the reference video. Based on this, the present disclosure is proposed, and the present disclosure proposes a video quality evaluation method, device, electronic equipment, and computer-readable storage medium. The video quality evaluation method according to an embodiment of the present disclosure uses a video quality evaluation method such as VMAF having the above characteristics to evaluate the quality of two videos in the absence of a reference video. In other words, even when the reference video is not available, the video quality evaluation method according to the embodiment of the present disclosure may use the full reference video quality evaluation method or the partial reference video quality evaluation method having the above characteristics to evaluate the quality of the video, for example, The quality of the ranking.

为了使得本公开的目的、技术方案和优点更为明显，下面将参照附图更详细地描述本公开的实施例。虽然附图中显示了本公开的某些实施例，然而应当理解的是，本公开可以通过各种形式来实现，而且不应该被解释为限于这里阐述的实施例，相反提供这些实施例是为了更加透彻和完整地理解本公开。应当理解的是，本公开的附图及实施例仅用于示例性作用，并非用于限制本公开的保护范围。In order to make the objectives, technical solutions and advantages of the present disclosure more obvious, the embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided for Have a more thorough and complete understanding of this disclosure. It should be understood that the drawings and embodiments of the present disclosure are only used for exemplary purposes and are not used to limit the protection scope of the present disclosure.

应当理解，本公开的方法实施方式中记载的各个步骤可以按照不同的顺序执行，和/或并行执行。此外，方法实施方式可以包括附加的步骤和/或省略执行示出的步骤。本公开的范围在此方面不受限制。It should be understood that the steps recorded in the method embodiments of the present disclosure may be executed in a different order, and/or executed in parallel. Furthermore, method implementations may include additional steps and/or omit to perform the illustrated steps. The scope of the present disclosure is not limited in this respect.

本文使用的术语“包括”及其变形是开放性包括，即“包括但不限于”。术语“基于”是“至少部分地基于”。术语“一个实施例”表示“至少一个实施例”；术语“另一实施例”表示“至少一个另外的实施例”；术语“一些实施例”表示“至少一些实施例”。其他术语的相关定义将在下文描述中给出。The term "including" and its variations as used herein are open-ended includes, that is, "including but not limited to". The term "based on" is "based at least in part on." The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments." Related definitions of other terms will be given in the following description.

需要注意，本公开中提及的“第一”、“第二”等概念仅用于对不同的装置、模块或单元进行区分，并非用于限定这些装置、模块或单元所执行的功能的顺序或者相互依存关系。It should be noted that the concepts of “first” and “second” mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units. Or interdependence.

需要注意，本公开中提及的“一个”、“多个”的修饰是示意性而非限制 性的，本领域技术人员应当理解，除非在上下文另有明确指出，否则应该理解为“一个或多个”。It should be noted that the modifications of “a” and “a plurality of” mentioned in this disclosure are illustrative and not restrictive. Those skilled in the art should understand that unless the context clearly indicates otherwise, they should be understood as “one or Multiple".

本公开实施方式中的多个装置之间所交互的消息或者信息的名称仅用于说明性的目的，而并不是用于对这些消息或信息的范围进行限制。The names of messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes, and are not used to limit the scope of these messages or information.

首先，参考图1，图1是根据本公开的一些实施例的视频质量评估方法的一个示意流程图。如图1所示，根据本公开的一些实施例的视频质量评估方法可以从步骤S100处开始。First, referring to FIG. 1, FIG. 1 is a schematic flowchart of a video quality evaluation method according to some embodiments of the present disclosure. As shown in FIG. 1, the video quality evaluation method according to some embodiments of the present disclosure may start at step S100.

在步骤S100处，根据本公开的一些实施例的视频质量评估方法将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值。之后，根据本公开的一些实施例的视频质量评估方法前进到步骤S102。在步骤S102处，根据本公开的一些实施例的视频质量评估方法将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值。其中，第一视频和第二视频是需要评估的两个视频。并且其中预定视频质量评估方法可以是如上所述的具有以下特性的视频质量评估方法：对于两个质量不同的视频，第一视频和第二视频，将第一视频作为测试视频，将第二视频作为参考视频，使用该视频质量评估方法得到的评估值，不同于将第二视频作为测试视频，将第一视频作为参考视频而得到的评估值。具体地，在一些实施例中，预定视频质量评估方法可以是视频质量多方法评估融合。关于该特性，本公开的发明人通过研究分析具备该特性的视频质量评估方法发现，可以提取视频中表征图像的特征向量(例如，自然场景统计(Natural Scene Statistics，NSS))以及视频中的图像与无失真自然图像的接近度的视频质量评估方法(例如，VMAF)可以具备该特性。换言之，根据本公开的一些实施例的预定视频质量评估方法可以用于提取视频(第一视频和第二视频)中表征图像的特征向量以及视频中的图像与无失真自然图像的接近度。At step S100, the video quality evaluation method according to some embodiments of the present disclosure uses the first video as the test video and the second video as the reference video, and uses a predetermined video quality evaluation method to obtain the first evaluation value. After that, the video quality evaluation method according to some embodiments of the present disclosure proceeds to step S102. At step S102, the video quality evaluation method according to some embodiments of the present disclosure uses the second video as a test video, the first video as a reference video, and a predetermined video quality evaluation method is used to obtain the second evaluation value. Among them, the first video and the second video are two videos that need to be evaluated. And the predetermined video quality evaluation method may be the above-mentioned video quality evaluation method with the following characteristics: for two videos with different qualities, the first video and the second video, the first video is used as the test video, and the second video As the reference video, the evaluation value obtained by using the video quality evaluation method is different from the evaluation value obtained by using the second video as the test video and the first video as the reference video. Specifically, in some embodiments, the predetermined video quality evaluation method may be a video quality multi-method evaluation fusion. Regarding this feature, the inventor of the present disclosure has discovered through research and analysis of video quality evaluation methods with this feature that it is possible to extract feature vectors representing images in videos (for example, Natural Scene Statistics (NSS)) and images in videos A video quality evaluation method (for example, VMAF) that is close to an undistorted natural image may have this characteristic. In other words, the predetermined video quality evaluation method according to some embodiments of the present disclosure may be used to extract feature vectors representing images in videos (first video and second video) and the closeness of the images in the video to the undistorted natural image.

之后，根据本公开的一些实施例的视频质量评估方法可以前进到步骤S104。在步骤S104处，根据本公开的一些实施例的视频质量评估方法基于在步骤S100处得到的第一评估值和在步骤S102处得到的第二评估值，根据预定准则来评估第一视频和第二视频的质量。具体地，在一些实施例中，根据本公开的一些实施例的视频质量评估方法可以根据如下准则来评估第一视频和第二视频的质量：响应于在步骤S100处得到的第一评估值大于在步骤S102 处得到的第二评估值，确定第一视频的质量好于第二视频的质量。并且其中，评估第一视频和第二视频的质量可以包括但不限于：(i)对第一视频的质量和第二视频的质量进行排序，例如，按照视频质量的高低，从高到底排序或者从低到高排序；(ii)确定进行评估的两个视频中的哪个视频质量较高或较好；(iii)确定进行评估的两个视频中的哪个视频质量较低或较差。After that, the video quality evaluation method according to some embodiments of the present disclosure may proceed to step S104. At step S104, the video quality evaluation method according to some embodiments of the present disclosure is based on the first evaluation value obtained at step S100 and the second evaluation value obtained at step S102, and evaluates the first video and the first video according to predetermined criteria. 2. The quality of the video. Specifically, in some embodiments, the video quality evaluation method according to some embodiments of the present disclosure may evaluate the quality of the first video and the second video according to the following criteria: in response to the first evaluation value obtained at step S100 being greater than The second evaluation value obtained in step S102 determines that the quality of the first video is better than the quality of the second video. In addition, evaluating the quality of the first video and the second video may include but is not limited to: (i) sorting the quality of the first video and the quality of the second video, for example, sorting the quality of the video from high to low, or Sort from low to high; (ii) determine which of the two videos to be evaluated is of higher or better quality; (iii) determine which of the two videos to be evaluated is of lower or worse quality.

为了使本领域技术人员更好的理解上面结合图1描述的根据本公开的一些实施例的视频质量评估方法，在下文中，本公开将给出一个具体示例。在该示例中，预定视频质量评估方法是VMAF，要评估的两个视频为test–video1(第一视频)和test-video2(第二视频)。如上所述，首先将test-video1作为测试视频，将test-video2作为参考视频，使用VMAF，得到第一评估值VMAF-value1。然后将test-video2作为测试视频，将test-video1作为参考视频，使用VMAF，得到第二评估值VMAF-value2。之后，比较VMAF-value1和VMAF-value2，如果VMAF-value1>VMAF-value2，则视频test-video1的质量好于视频test-video2的质量；反之，视频test-video2的质量好于视频test-video1的质量。In order to enable those skilled in the art to better understand the video quality evaluation method according to some embodiments of the present disclosure described above in conjunction with FIG. 1, in the following, the present disclosure will give a specific example. In this example, the predetermined video quality evaluation method is VMAF, and the two videos to be evaluated are test-video1 (first video) and test-video2 (second video). As mentioned above, first use test-video1 as the test video, test-video2 as the reference video, and use VMAF to obtain the first evaluation value VMAF-value1. Then use test-video2 as the test video, test-video1 as the reference video, and use VMAF to obtain the second evaluation value VMAF-value2. After that, compare VMAF-value1 and VMAF-value2. If VMAF-value1>VMAF-value2, the quality of video test-video1 is better than that of video test-video2; conversely, the quality of video test-video2 is better than video test-video1 the quality of.

应该理解，虽然在上面的示例中，预定视频质量评估方法使用的是VMAF，但是本公开对此没有限制。如上所述，任何具有以下特性的视频质量评估方法：对于两个质量不同的视频，第一视频和第二视频，将第一视频作为测试视频，将第二视频作为参考视频，使用该视频质量评估方法得到的评估值，不同于将第二视频作为测试视频，将第一视频作为参考视频而得到的评估值，都可以作为根据本公开的一些实施例的视频质量评估方法中的预定视频质量评估方法。It should be understood that although in the above example, the predetermined video quality evaluation method uses VMAF, the present disclosure has no limitation on this. As mentioned above, any video quality evaluation method with the following characteristics: For two videos with different qualities, the first video and the second video, the first video is used as the test video, and the second video is used as the reference video, and the video quality is used The evaluation value obtained by the evaluation method is different from the evaluation value obtained by using the second video as the test video and the first video as the reference video, and can be used as the predetermined video quality in the video quality evaluation method according to some embodiments of the present disclosure. evaluation method.

还应该理解，虽然在上面的示例中，预定准则为：响应于在步骤S100处得到的第一评估值大于在步骤S102处得到的第二评估值，评估第一视频的质量好于第二视频的质量，但是根据本公开对此没有限制。即，根据本公开的一些实施例的视频质量评估方法中的预定准则可以是适用于前述预定视频质量评估方法的任何准则。换言之，预定准则是取决于所使用的预定视频质量评估方法的准则。It should also be understood that although in the above example, the predetermined criterion is: in response to the first evaluation value obtained in step S100 being greater than the second evaluation value obtained in step S102, it is estimated that the quality of the first video is better than the second video. Quality, but there is no limit to this according to the present disclosure. That is, the predetermined criterion in the video quality evaluation method according to some embodiments of the present disclosure may be any criterion applicable to the aforementioned predetermined video quality evaluation method. In other words, the predetermined criterion is a criterion that depends on the predetermined video quality evaluation method used.

还应该理解，虽然在前述描述和示例中，第一视频和第二视频是质量不同的两个视频，但是本公开对此没有限制。即，根据本公开的一些实施例的视频质量评估方法也可以用于评估质量相同的两个视频。在这种情况下，将 第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值可以等于将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值，并且可以确定两个视频的质量相同。It should also be understood that, although in the foregoing description and examples, the first video and the second video are two videos with different qualities, the present disclosure has no limitation on this. That is, the video quality evaluation method according to some embodiments of the present disclosure can also be used to evaluate two videos with the same quality. In this case, using the first video as the test video and the second video as the reference video, and using the predetermined video quality evaluation method to obtain the first evaluation value may be equivalent to using the second video as the test video and the first video as the reference video , Use the predetermined video quality evaluation method to obtain the second evaluation value, and it can be determined that the quality of the two videos is the same.

还应该理解，虽然在前述描述和示例中，根据本公开的一些实施例的视频质量评估方法用于评估两个视频的质量，但是本公开对此没有限制。即，通过适当的使用根据本公开的一些实施例的视频质量评估方法可以评估多个视频的质量，例如，对多个视频的质量进行排序。It should also be understood that although in the foregoing description and examples, the video quality evaluation method according to some embodiments of the present disclosure is used to evaluate the quality of two videos, the present disclosure is not limited thereto. That is, by appropriately using the video quality evaluation method according to some embodiments of the present disclosure, the quality of multiple videos can be evaluated, for example, the quality of multiple videos can be ranked.

还应该理解，虽然在前述描述和示例中，根据本公开的一些实施例的视频质量评估方法用于评估两个视频的质量，但是本公开对此没有限制。即，根据本公开的一些实施例的视频质量评估方法除了用于评估两个视频的质量之外，还可以用于评估两个图像的质量。因此，在本公开中，视频可以包括图像或者可以是图像。It should also be understood that although in the foregoing description and examples, the video quality evaluation method according to some embodiments of the present disclosure is used to evaluate the quality of two videos, the present disclosure is not limited thereto. That is, in addition to evaluating the quality of two videos, the video quality evaluation method according to some embodiments of the present disclosure can also be used to evaluate the quality of two images. Therefore, in the present disclosure, the video may include an image or may be an image.

上面结合图1描述的根据本公开的一些实施例的视频质量评估方法在不存在参考视频的情况下，利用诸如全参考视频质量评估方法和部分参考视频质量评估方法的视频质量评估方法的以下特性：对于两个质量不同的视频，第一视频和第二视频，将第一视频作为测试视频，将第二视频作为参考视频，使用该视频质量评估方法得到的评估值，不同于将第二视频作为测试视频，将第一视频作为参考视频而得到的评估值，来评估两个视频的质量。换言之，即使在参考视频不可用时，根据本公开的一些实施例的视频质量评估方法也可以使用具有前述特性的视频质量评估方法来评估视频的质量，例如，对视频的质量进行排名。从而增加了具有前述特性的视频质量评估方法的应用范围。The video quality evaluation method according to some embodiments of the present disclosure described above in conjunction with FIG. 1 utilizes the following characteristics of the video quality evaluation method such as the full reference video quality evaluation method and the partial reference video quality evaluation method in the absence of a reference video : For two videos with different quality, the first video and the second video, the first video is used as the test video, and the second video is used as the reference video. The evaluation value obtained using this video quality evaluation method is different from the second video As the test video, use the first video as the evaluation value obtained from the reference video to evaluate the quality of the two videos. In other words, even when the reference video is not available, the video quality evaluation method according to some embodiments of the present disclosure may use the video quality evaluation method having the aforementioned characteristics to evaluate the quality of the video, for example, to rank the quality of the video. Therefore, the application range of the video quality evaluation method with the aforementioned characteristics is increased.

上面结合图1描述了根据本公开的一些实施例的视频质量评估方法，在下文中，本公开将结合表1来给出根据本公开的一些实施例的视频质量评估方法的评估结果。在该示例中，本公开测试两种不同压缩级别(CRF 24和CRF 28)的500个视频。本领域技术人员理解，这些视频的质量等级应为SOURCE>CRF24>CRF28。测试结果如表1所示。The video quality evaluation method according to some embodiments of the present disclosure is described above with reference to FIG. 1. In the following, the present disclosure will combine Table 1 to give the evaluation result of the video quality evaluation method according to some embodiments of the present disclosure. In this example, the present disclosure tests 500 videos with two different compression levels (CRF 24 and CRF 28). Those skilled in the art understand that the quality level of these videos should be SOURCE>CRF24>CRF28. The test results are shown in Table 1.

表1Table 1

从表1可以看出，根据本公开的一些实施例的视频质量评估方法可以以正确的顺序确定视频集的质量的等级。即，正确地确定视频的质量的高低顺序。It can be seen from Table 1 that the video quality evaluation method according to some embodiments of the present disclosure can determine the quality level of the video set in the correct order. That is, the order of the quality of the video is correctly determined.

图2是根据本公开的一些实施例的视频质量评估方法的另一个示意流程图。和图1所示的根据本公开的一些实施例的视频质量评估方法的示意流程相比，图2所示的根据本公开的一些实施例的视频质量评估方法的示例流程除了包括步骤S100、步骤S102和步骤S104之外，还包括步骤S200。即，根据本公开的一些实施例的视频质量评估方法在对两个视频的质量进行评估之前，还可以对预定视频质量评估方法进行训练，使得根据本公开的一些实施例的视频质量评估方法具有更好的性能和更广的应用范围。Fig. 2 is another schematic flowchart of a video quality evaluation method according to some embodiments of the present disclosure. Compared with the schematic flow of the video quality evaluation method according to some embodiments of the present disclosure shown in FIG. 1, the example flow of the video quality evaluation method according to some embodiments of the present disclosure shown in FIG. 2 includes step S100, In addition to step S102 and step S104, step S200 is also included. That is, the video quality evaluation method according to some embodiments of the present disclosure may further train a predetermined video quality evaluation method before evaluating the quality of two videos, so that the video quality evaluation method according to some embodiments of the present disclosure has Better performance and wider application range.

具体地，在步骤S200处，以主观视频质量评估方法对第一视频和第二视频进行评估得到的视频质量分数为训练目标，基于第一训练视频和第二训练视频来执行训练，其中第一训练视频和第二训练视频是不同失真程度的视频。例如，在一些示例实施例中，训练目标可以是通过主观测试得到的差分平均意见分数(Difference Mean Opinion Score，DMOS)，第一训练视频可以是高清视频，第二训练视频可以是高清视频以某种编码模式(例如，CRF 23，CRF 26和2-pass-ABR)编码之后的视频、和高清视频同内容的模糊失真视频等。在训练过程中，可以使用支持向量机(Support Vector Machine，SVM)回归器，以主观视频质量评估方法得到的视频质量分数DMOS为训练目标，基于第一训练视频和第二训练视频来训练所使用的预定视频质量评估方法。由于训练过程S200与常规的参考视频训练方法(例如，VMAF的训练方法)类似，因此为了简洁，此处省略其详细描述。Specifically, at step S200, the video quality score obtained by evaluating the first video and the second video by the subjective video quality evaluation method is used as the training target, and the training is performed based on the first training video and the second training video. The training video and the second training video are videos with different degrees of distortion. For example, in some example embodiments, the training target may be a Difference Mean Opinion Score (DMOS) obtained through a subjective test, the first training video may be a high-definition video, and the second training video may be a high-definition video with a certain value. Two encoding modes (for example, CRF 23, CRF 26, and 2-pass-ABR) encoded video, blurry and distorted video with the same content as HD video, etc. In the training process, a support vector machine (SVM) regressor can be used, the video quality score DMOS obtained by subjective video quality evaluation method is used as the training target, and the training used is based on the first training video and the second training video. The predetermined video quality assessment method. Since the training process S200 is similar to the conventional reference video training method (for example, the training method of VMAF), for the sake of brevity, its detailed description is omitted here.

应该理解，在上面的描述中，虽然训练目标的示例是通过主观测试得到的DMOS，但是本公开对此没有限制。另外，虽然在上述公开中第一训练视频的示例是高清视频，但是本公开对此没有限制，也就是说，在本公开中，高清视频可以是指同一内容的训练视频中的清晰度最高(即，失真程度最低) 的视频，例如高清视频、超高清视频等。另外，虽然在上述公开中是使用SVM回归器来训练预定视频质量评估方法，但是本公开对此没有限制，也就是说可以使用现有的或在未来研发的任何适于训练视频质量评估方法的训练算法来训练预定视频质量方法，例如K-means算法等。It should be understood that in the above description, although an example of the training target is a DMOS obtained through a subjective test, the present disclosure is not limited thereto. In addition, although the example of the first training video in the above disclosure is a high-definition video, the present disclosure has no limitation on this, that is, in the present disclosure, high-definition video may refer to the highest definition among training videos of the same content ( That is, the video with the lowest degree of distortion, such as high-definition video, ultra-high-definition video, etc. In addition, although the SVM regressor is used to train the predetermined video quality evaluation method in the above disclosure, this disclosure has no limitation on this, that is to say, any existing or future development suitable for training video quality evaluation method can be used. Training algorithms to train predetermined video quality methods, such as K-means algorithm.

结合图2描述的根据本公开的一些实施例的视频质量评估方法通过训练目标视频质量评估方法，使得根据本公开的一些实施例的视频质量评估方法可以在不存在参考视频的情况下，利用目标视频质量评估方法(例如VMAF)来评估多种不同失真程度的视频的质量，从而使得根据本公开的一些实施例的视频质量评估方法具有更好的性能和更广的应用范围。The video quality assessment method according to some embodiments of the present disclosure described in conjunction with FIG. 2 trains the target video quality assessment method, so that the video quality assessment method according to some embodiments of the present disclosure can utilize the target in the absence of a reference video. A video quality evaluation method (for example, VMAF) evaluates the quality of a variety of videos with different degrees of distortion, so that the video quality evaluation method according to some embodiments of the present disclosure has better performance and a wider application range.

在上文中，结合图1和图2描述了根据本公开的一些实施例的视频质量评估方法，并结合表1描述了根据本公开的一些实施例的视频质量评估方法的评估结果。从结合表1的描述中可以看出，根据本公开的一些实施例的视频质量评估方法可以正确地评估视频的质量，例如正确地确定视频的质量的高低顺序。In the above, the video quality evaluation method according to some embodiments of the present disclosure is described in conjunction with FIG. 1 and FIG. 2, and the evaluation result of the video quality evaluation method according to some embodiments of the present disclosure is described in conjunction with Table 1. As can be seen from the description in conjunction with Table 1, the video quality evaluation method according to some embodiments of the present disclosure can correctly evaluate the quality of the video, for example, correctly determine the order of the video quality.

下面，本公开将结合图3至图7来描述根据本公开的一些实施例的用于视频质量评估的装置、电子设备和计算机可读存储介质。Hereinafter, the present disclosure will describe the apparatus, electronic equipment, and computer-readable storage medium for video quality evaluation according to some embodiments of the present disclosure in conjunction with FIGS. 3 to 7.

图3是根据本公开的一些实施例的用于视频质量评估的电子装置300的示意图。如图3所示，根据本公开的一些实施例的用于视频质量评估的电子装置300可以包括评估值计算模块310和质量评估模块320。其中，评估值计算模块310用于执行以下操作：将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值；质量评估模块320，用于基于第一评估值和第二评估值，根据预定准则来评估第一视频和第二视频的质量，其中，根据预定视频质量评估方法，在第一视频的质量不同于第二视频的质量的情况下，第一评估值不同于第二评估值。可替代地或另外地，图3所示的评估值计算模块310和质量评估模块320还可以执行上面结合图1和图2描述的根据本公开的一些实施例的视频质量评估方法。FIG. 3 is a schematic diagram of an electronic device 300 for video quality evaluation according to some embodiments of the present disclosure. As shown in FIG. 3, the electronic device 300 for video quality evaluation according to some embodiments of the present disclosure may include an evaluation value calculation module 310 and a quality evaluation module 320. The evaluation value calculation module 310 is configured to perform the following operations: use the first video as a test video, use the second video as a reference video, and use a predetermined video quality evaluation method to obtain the first evaluation value; use the second video as a test video, and The first video is used as a reference video, and a predetermined video quality evaluation method is used to obtain the second evaluation value; the quality evaluation module 320 is configured to evaluate the first video and the second video according to predetermined criteria based on the first evaluation value and the second evaluation value. Quality, wherein, according to a predetermined video quality evaluation method, in a case where the quality of the first video is different from the quality of the second video, the first evaluation value is different from the second evaluation value. Alternatively or additionally, the evaluation value calculation module 310 and the quality evaluation module 320 shown in FIG. 3 may also execute the video quality evaluation method according to some embodiments of the present disclosure described above in conjunction with FIG. 1 and FIG. 2.

图4是根据本公开的一些实施例的用于视频质量评估的电子装置400的示意图。如图4所示，根据本公开的一些实施例的用于视频质量评估的电子装置400除了包括与图3所示的电子装置300中包括的评估值计算模块310 和质量评估模块320类似的评估值计算模块410和质量评估模块420之外，图4所示的电子装置400还可以包括训练模块430。其中，图4所示的电子装置400中的评估值计算模块410和质量评估模块420和图3所示的评估值计算模块310和质量评估模块320所执行的操作类似，为了简便，此处省略其详细描述。图4所示的电子装置400中的训练模块430用于执行以下操作：以主观视频质量评估方法对第一视频和第二视频进行评估得到的视频质量分数为训练目标，基于第一训练视频和第二训练视频来执行训练，其中第一训练视频和第二训练视频是不同失真程度的视频。可替代地或另外地，图4所示的训练模块430还可以执行上面结合图2描述的根据本公开的一些实施例的视频质量评估方法中包括的训练过程。FIG. 4 is a schematic diagram of an electronic device 400 for video quality evaluation according to some embodiments of the present disclosure. As shown in FIG. 4, the electronic device 400 for video quality evaluation according to some embodiments of the present disclosure includes evaluation similar to the evaluation value calculation module 310 and the quality evaluation module 320 included in the electronic device 300 shown in FIG. In addition to the value calculation module 410 and the quality evaluation module 420, the electronic device 400 shown in FIG. 4 may further include a training module 430. The operations performed by the evaluation value calculation module 410 and the quality evaluation module 420 in the electronic device 400 shown in FIG. 4 are similar to those performed by the evaluation value calculation module 310 and the quality evaluation module 320 shown in FIG. 3, which are omitted here for simplicity. Its detailed description. The training module 430 in the electronic device 400 shown in FIG. 4 is configured to perform the following operations: the video quality score obtained by evaluating the first video and the second video by the subjective video quality evaluation method is used as the training target, based on the first training video and The second training video is used to perform the training, where the first training video and the second training video are videos with different degrees of distortion. Alternatively or additionally, the training module 430 shown in FIG. 4 may also perform the training process included in the video quality evaluation method according to some embodiments of the present disclosure described above in conjunction with FIG. 2.

图5是根据本公开的一些实施例的用于视频质量评估的电子设备500的示意图。如图5所示，根据本公开的一些实施例的用于视频质量评估的电子设备500可以包括处理器510和存储器520，该存储器520上存储有计算机程序指令，该计算机程序指令在由该处理器510运行时，使该处理器510执行上面结合图1和图2描述的根据本公开的一些实施例的视频质量评估方法。FIG. 5 is a schematic diagram of an electronic device 500 for video quality evaluation according to some embodiments of the present disclosure. As shown in FIG. 5, an electronic device 500 for video quality evaluation according to some embodiments of the present disclosure may include a processor 510 and a memory 520. The memory 520 stores computer program instructions, and the computer program instructions are executed by the processor. When the processor 510 is running, the processor 510 is caused to execute the video quality evaluation method according to some embodiments of the present disclosure described above in conjunction with FIG. 1 and FIG. 2.

图6是根据本公开的一些实施例的用于视频质量评估的电子设备600的示意图。图6示出了适于用来实现本公开实施例的电子设备600的结构示意图。电子设备600可以是云平台、服务器和终端设备等等。本公开实施例中的终端设备可以包括但不限于诸如移动电话、笔记本电脑、数字广播接收器、PDA(个人数字助理)、PAD(平板电脑)、PMP(便携式多媒体播放器)、车载终端(例如车载导航终端)等等的移动终端以及诸如数字TV、台式计算机等等的固定终端。图6示出的电子设备仅仅是一个示例，不应对本公开实施例的功能和使用范围带来任何限制。FIG. 6 is a schematic diagram of an electronic device 600 for video quality evaluation according to some embodiments of the present disclosure. FIG. 6 shows a schematic structural diagram of an electronic device 600 suitable for implementing embodiments of the present disclosure. The electronic device 600 may be a cloud platform, a server, a terminal device, and so on. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablets), PMPs (portable multimedia players), vehicle-mounted terminals (e.g. Mobile terminals such as car navigation terminals) and fixed terminals such as digital TVs, desktop computers, etc. The electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the function and scope of use of the embodiments of the present disclosure.

如图6所示，电子设备600可以包括处理装置(例如中央处理器、图形处理器等)610，其可以根据存储在只读存储器(ROM)620中的程序或者从存储装置680加载到随机访问存储器(RAM)630中的程序而执行各种适当的动作和处理。在RAM 630中，还存储有电子设备600操作所需的各种程序和数据。处理装置610、ROM 620以及RAM 630通过总线640彼此相连。输入/输出(I/O)接口650也连接至总线640。As shown in FIG. 6, the electronic device 600 may include a processing device (such as a central processing unit, a graphics processor, etc.) 610, which may be loaded into a random access device according to a program stored in a read-only memory (ROM) 620 or from a storage device 680 The programs in the memory (RAM) 630 execute various appropriate actions and processes. In the RAM 630, various programs and data required for the operation of the electronic device 600 are also stored. The processing device 610, the ROM 620, and the RAM 630 are connected to each other through a bus 640. An input/output (I/O) interface 650 is also connected to the bus 640.

通常，以下装置可以连接至I/O接口650：包括例如触摸屏、触摸板、键盘、鼠标、摄像头、麦克风、加速度计、陀螺仪等的输入装置660；包括 例如液晶显示器(LCD)、扬声器、振动器等的输出装置670；包括例如磁带、硬盘等的存储装置680；以及通信装置690。通信装置690可以允许电子设备600与其他设备进行无线或有线通信以交换数据。虽然图6示出了具有各种装置的电子设备600，但是应理解的是，并不要求实施或具备所有示出的装置。可以替代地实施或具备更多或更少的装置。特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实施为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在非暂态计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信装置690从网络上被下载和安装，或者从存储装置680被安装，或者从ROM 620被安装。在该计算机程序被处理装置610运行时，执行本公开实施例的方法中限定的上述功能。Generally, the following devices can be connected to the I/O interface 650: including input devices 660 such as touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; including, for example, liquid crystal display (LCD), speakers, vibration An output device 670 such as a device; a storage device 680 such as a magnetic tape, a hard disk, etc.; and a communication device 690. The communication device 690 may allow the electronic device 600 to perform wireless or wired communication with other devices to exchange data. Although FIG. 6 shows an electronic device 600 having various devices, it should be understood that it is not required to implement or have all the illustrated devices. It may alternatively be implemented or provided with more or fewer devices. In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication device 690, or installed from the storage device 680, or installed from the ROM 620. When the computer program is executed by the processing device 610, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

图7是根据本公开的一些实施例的用于视频质量评估的计算机可读存储介质700的示意图。如图7所示，根据本公开的一些实施例的用于视频质量评估的计算机可读存储介质700上存储有计算机程序指令710，该计算机程序指令710在由处理器运行时，使该处理器执行上面结合图1和图2描述的根据本公开的一些实施例的视频质量评估方法。FIG. 7 is a schematic diagram of a computer-readable storage medium 700 for video quality evaluation according to some embodiments of the present disclosure. As shown in FIG. 7, the computer-readable storage medium 700 for video quality evaluation according to some embodiments of the present disclosure stores computer program instructions 710, and the computer program instructions 710 cause the processor to The video quality evaluation method according to some embodiments of the present disclosure described above in conjunction with FIG. 1 and FIG. 2 is executed.

在上文中，结合图1至图7描述了根据本公开的一些实施例的视频质量评估方法、装置、电子设备和计算机可读存储介质，并且结合表1描述了根据本公开的一些实施例的视频质量评估方法的评估结果。从上面的描述可以看出，根据本公开的一些实施例的视频质量评估方法、装置、电子设备和计算机可读存储介质可以在不存在参考视频的情况下，利用目标视频质量评估方法(例如VMAF)来评估多种类型的视频的质量，从而增加了该目标视频质量评估方法的应用范围。In the foregoing, the video quality evaluation method, apparatus, electronic device, and computer-readable storage medium according to some embodiments of the present disclosure are described in conjunction with FIG. 1 to FIG. 7, and in conjunction with Table 1, the video quality assessment methods according to some embodiments of the present disclosure are described. The evaluation result of the video quality evaluation method. It can be seen from the above description that the video quality evaluation method, device, electronic device, and computer-readable storage medium according to some embodiments of the present disclosure can utilize a target video quality evaluation method (such as VMAF) in the absence of a reference video. ) To evaluate the quality of multiple types of videos, thereby increasing the scope of application of the target video quality evaluation method.

需要说明的是，本公开上述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的***、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本公开中，计算机 可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行***、装置或者器件使用或者与其结合使用。而在本公开中，计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读信号介质可以发送、传播或者传输用于由指令执行***、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：电线、光缆、RF(射频)等等，或者上述的任意合适的组合。It should be noted that the aforementioned computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electric, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as a part of a carrier wave, and a computer-readable program code is carried therein. This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than the computer-readable storage medium. The computer-readable signal medium may send, propagate, or transmit the program for use by or in combination with the instruction execution system, apparatus, or device . The program code contained on the computer-readable medium can be transmitted by any suitable medium, including but not limited to: wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

在一些实施方式中，客户端、服务器可以利用诸如HTTP(HyperText Transfer Protocol，超文本传输协议)之类的任何当前已知或未来研发的网络协议进行通信，并且可以与任意形式或介质的数字数据通信(例如，通信网络)互连。通信网络的示例包括局域网(“LAN”)，广域网(“WAN”)，网际网(例如，互联网)以及端对端网络(例如，ad hoc端对端网络)，以及任何当前已知或未来研发的网络。In some embodiments, the client and server can communicate with any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can communicate with digital data in any form or medium. Communication (e.g., communication network) interconnects. Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as any currently known or future research and development network of.

上述计算机可读介质可以是上述电子设备中所包含的；也可以是单独存在，而未装配入该电子设备中。The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist alone without being assembled into the electronic device.

上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备执行时，使得该电子设备：获取至少两个网际协议地址；向节点评价设备发送包括所述至少两个网际协议地址的节点评价请求，其中，所述节点评价设备从所述至少两个网际协议地址中，选取网际协议地址并返回；接收所述节点评价设备返回的网际协议地址；其中，所获取的网际协议地址指示内容分发网络中的边缘节点。The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains at least two Internet protocol addresses; and sends to the node evaluation device including the at least two A node evaluation request for an Internet Protocol address, wherein the node evaluation device selects an Internet Protocol address from the at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; wherein, the obtained The Internet Protocol address indicates the edge node in the content distribution network.

或者，上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该电子设备运行时，使得该电子设备：接收包括至少两个网际协议地址的节点评价请求；从所述至少两个网际协议地址中，选取网际协议地址；返回选取出的网际协议地址；其中，接收到的网际协议地址指示内容分发网络中的边缘节点。Alternatively, the aforementioned computer-readable medium carries one or more programs, and when the aforementioned one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; Among the at least two Internet Protocol addresses, select an Internet Protocol address; return the selected Internet Protocol address; wherein, the received Internet Protocol address indicates an edge node in the content distribution network.

可以以一种或多种程序设计语言或其组合来编写用于执行本公开的操作的计算机程序代码，上述程序设计语言包括但不限于面向对象的程序设计语 言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。The computer program code used to perform the operations of the present disclosure can be written in one or more programming languages or a combination thereof. The above-mentioned programming languages include but are not limited to object-oriented programming languages such as Java, Smalltalk, C++, and Including conventional procedural programming languages-such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partly on the user's computer, executed as an independent software package, partly on the user's computer and partly executed on a remote computer, or entirely executed on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user’s computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to pass Internet connection).

附图中的流程图和框图，图示了按照本公开各种实施例的***、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的***来实现，或者可以用专用硬件与计算机指令的组合来实现。The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions, and operations of the system, method, and computer program product according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, program segment, or part of code, and the module, program segment, or part of code contains one or more for realizing the specified logical function Executable instructions. It should also be noted that, in some alternative implementations, the functions marked in the block may also occur in a different order from the order marked in the drawings. For example, two blocks shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and/or flowchart, and the combination of the blocks in the block diagram and/or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or operations Or it can be realized by a combination of dedicated hardware and computer instructions.

描述于本公开实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。其中，单元的名称在某种情况下并不构成对该单元本身的限定，例如，第一获取单元还可以被描述为“获取至少两个网际协议地址的单元”。The units involved in the embodiments described in the present disclosure may be implemented in a software manner, or may be implemented in a hardware manner. Wherein, the name of the unit does not constitute a limitation on the unit itself under certain circumstances. For example, the first obtaining unit can also be described as "a unit for obtaining at least two Internet Protocol addresses."

本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如，非限制性地，可以使用的示范类型的硬件逻辑部件包括：现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上***(SOC)、复杂可编程逻辑设备(CPLD)等等。The functions described hereinabove may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that can be used include: Field Programmable Gate Array (FPGA), Application Specific Integrated Circuit (ASIC), Application Specific Standard Product (ASSP), System on Chip (SOC), Complex Programmable Logical device (CPLD) and so on.

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***、装置或设备使用或与指令执行***、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***、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, which may contain or store a program for use by or in combination 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. The machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media would include electrical connections based on one or more wires, portable computer disks, hard drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.

根据本公开的一个或多个实施例，提供了一种视频质量评估方法，以及实施该方法的装置、电子设备和计算可读存储介质。该方法包括，将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；将第二视频作为测试视频，将第一视频作为参考视频，使用预定视频质量评估方法得到第二评估值；以及基于第一评估值和第二评估值，根据预定准则来评估第一视频和第二视频的质量，其中，根据预定视频质量评估方法，在第一视频的质量不同于第二视频的质量的情况下，第一评估值不同于第二评估值。According to one or more embodiments of the present disclosure, there are provided a video quality evaluation method, as well as an apparatus, electronic equipment, and computer-readable storage medium for implementing the method. The method includes using the first video as the test video, using the second video as the reference video, and using a predetermined video quality evaluation method to obtain the first evaluation value; using the second video as the test video, using the first video as the reference video, and using the predetermined The video quality evaluation method obtains the second evaluation value; and based on the first evaluation value and the second evaluation value, the quality of the first video and the second video are evaluated according to predetermined criteria, wherein, according to the predetermined video quality evaluation method, the first video In the case where the quality of is different from the quality of the second video, the first evaluation value is different from the second evaluation value.

根据本公开的一个或多个实施例，在该方法中，根据预定准则来评估第一视频和第二视频的质量包括：响应于第一评估值大于第二评估值，确定第一视频的质量好于第二视频的质量。According to one or more embodiments of the present disclosure, in the method, evaluating the quality of the first video and the second video according to a predetermined criterion includes: in response to the first evaluation value being greater than the second evaluation value, determining the quality of the first video Better than the quality of the second video.

根据本公开的一个或多个实施例，在该方法中，预定视频质量评估方法用于提取第一视频和第二视频中表征图像的特征向量以及第一视频和第二视频中的图像与无失真自然图像的接近度。According to one or more embodiments of the present disclosure, in the method, the predetermined video quality evaluation method is used to extract feature vectors representing images in the first video and the second video, and the difference between the images in the first video and the second video. The proximity of the distorted natural image.

根据本公开的一个或多个实施例，在该方法中，预定视频质量评估方法包括：视频质量多方法评估融合。According to one or more embodiments of the present disclosure, in the method, the predetermined video quality evaluation method includes: video quality multi-method evaluation fusion.

根据本公开的一个或多个实施例，该方法还包括：以主观视频质量评估方法对第一视频和第二视频进行评估得到的视频质量分数为训练目标，基于第一训练视频和第二训练视频来执行训练，其中，第一训练视频和第二训练视频是不同失真程度的视频。According to one or more embodiments of the present disclosure, the method further includes: using the subjective video quality evaluation method to evaluate the video quality scores of the first video and the second video as the training target, based on the first training video and the second training Video is used to perform training, where the first training video and the second training video are videos with different degrees of distortion.

根据本公开的一个或多个实施例，在该方法中，以主观视频质量评估方法对第一视频和第二视频进行评估得到的视频质量分数为训练目标，基于第一训练视频和第二训练视频来执行训练包括：以主观视频质量评估方法得到的视频质量分数为训练目标，使用支持向量机(SVM)回归器，基于第一训练视频和第二训练视频来执行训练。以上描述仅为本公开的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本公开中所涉及的公开范围，并不限于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述公开构思的情况下，由上述技术特征或其等同特征进行任意组 合而形成的其它技术方案。例如上述特征与本公开中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。According to one or more embodiments of the present disclosure, in the method, the video quality score obtained by evaluating the first video and the second video by the subjective video quality evaluation method is used as the training target, based on the first training video and the second training video. Performing training with video includes: taking the video quality score obtained by the subjective video quality evaluation method as the training target, using a support vector machine (SVM) regression, and performing training based on the first training video and the second training video. The above description is only a preferred embodiment of the present disclosure and an explanation of the applied technical principles. Those skilled in the art should understand that the scope of disclosure involved in this disclosure is not limited to the technical solutions formed by the specific combination of the above technical features, and should also cover the above technical features or technical solutions without departing from the above disclosed concept. Other technical solutions formed by any combination of its equivalent features. For example, the above-mentioned features and the technical features disclosed in the present disclosure (but not limited to) with similar functions are mutually replaced to form a technical solution.

此外，虽然采用特定次序描绘了各操作，但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下，多任务和并行处理可能是有利的。同样地，虽然在上面论述中包含了若干具体实现细节，但是这些不应当被解释为对本公开的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地，在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。In addition, although the operations are depicted in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or performed in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Likewise, although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Certain features that are described in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable subcombination.

尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题，但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反，上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。Although the subject matter has been described in language specific to structural features and/or logical actions of the method, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely exemplary forms of implementing the claims.

Claims (10)

1. 一种视频质量评估方法，所述方法包括：A video quality evaluation method, the method includes:

   将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；Use the first video as a test video, use the second video as a reference video, and use a predetermined video quality evaluation method to obtain the first evaluation value;

   将所述第二视频作为测试视频，将所述第一视频作为参考视频，使用所述预定视频质量评估方法得到第二评估值；以及Using the second video as a test video, using the first video as a reference video, and obtaining a second evaluation value using the predetermined video quality evaluation method; and

   基于所述第一评估值和所述第二评估值，根据预定准则来评估所述第一视频和所述第二视频的质量，Based on the first evaluation value and the second evaluation value, evaluating the quality of the first video and the second video according to a predetermined criterion,

   其中，根据所述预定视频质量评估方法，在所述第一视频的质量不同于所述第二视频的质量的情况下，所述第一评估值不同于所述第二评估值。Wherein, according to the predetermined video quality evaluation method, when the quality of the first video is different from the quality of the second video, the first evaluation value is different from the second evaluation value.
2. 根据权利要求1所述的方法，其中，所述根据预定准则来评估所述第一视频和所述第二视频的质量包括：The method according to claim 1, wherein said evaluating the quality of said first video and said second video according to predetermined criteria comprises:

   响应于所述第一评估值大于所述第二评估值，确定所述第一视频的质量好于所述第二视频的质量。In response to the first evaluation value being greater than the second evaluation value, it is determined that the quality of the first video is better than the quality of the second video.
3. 根据权利要求1或2所述的方法，其中，所述预定视频质量评估方法用于提取所述第一视频和所述第二视频中表征图像的特征向量以及所述第一视频和所述第二视频中的图像与无失真自然图像的接近度。The method according to claim 1 or 2, wherein the predetermined video quality evaluation method is used to extract feature vectors representing images in the first video and the second video, and the first video and the second video 2. The closeness of the image in the video to the undistorted natural image.
4. 根据权利要求1至3中任一项所述的方法，其中，所述预定视频质量评估方法包括：视频质量多方法评估融合。The method according to any one of claims 1 to 3, wherein the predetermined video quality evaluation method comprises: video quality multi-method evaluation fusion.
5. 根据权利要求1至4中的任一项所述的方法，还包括：The method according to any one of claims 1 to 4, further comprising:

   以主观视频质量评估方法对所述第一视频和所述第二视频进行评估得到的视频质量分数为训练目标，基于第一训练视频和第二训练视频来执行训练，其中，所述第一训练视频和所述第二训练视频是不同失真程度的视频。The subjective video quality evaluation method evaluates the video quality scores of the first video and the second video as the training target, and performs training based on the first training video and the second training video, wherein the first training The video and the second training video are videos with different degrees of distortion.
6. 根据权利要求5所述的方法，其中以主观视频质量评估方法对所述第一视频和所述第二视频进行评估得到的视频质量分数为训练目标，基于第一 训练视频和第二训练视频来执行训练包括：The method according to claim 5, wherein the subjective video quality evaluation method is used to evaluate the video quality scores of the first video and the second video as the training target, and the training target is based on the first training video and the second training video. Execution training includes:

   以主观视频质量评估方法得到的视频质量分数为训练目标，使用支持向量机(SVM)回归器，基于所述第一训练视频和所述第二训练视频来执行训练。Taking the video quality score obtained by the subjective video quality evaluation method as the training target, a support vector machine (SVM) regressor is used to perform training based on the first training video and the second training video.
7. 一种视频质量评估装置，所述装置包括：A video quality evaluation device, the device includes:

   评估值计算模块，用于执行以下操作：The evaluation value calculation module is used to perform the following operations:

   将第一视频作为测试视频，将第二视频作为参考视频，使用预定视频质量评估方法得到第一评估值；Use the first video as a test video, use the second video as a reference video, and use a predetermined video quality evaluation method to obtain the first evaluation value;

   将所述第二视频作为测试视频，将所述第一视频作为参考视频，使用所述预定视频质量评估方法得到第二评估值；和Using the second video as a test video, using the first video as a reference video, and using the predetermined video quality evaluation method to obtain a second evaluation value; and

   质量评估模块，用于基于所述第一评估值和所述第二评估值，根据预定准则来评估所述第一视频和所述第二视频的质量，The quality evaluation module is configured to evaluate the quality of the first video and the second video according to a predetermined criterion based on the first evaluation value and the second evaluation value,

   其中，根据所述预定视频质量评估方法，在所述第一视频的质量不同于所述第二视频的质量的情况下，所述第一评估值不同于所述第二评估值。Wherein, according to the predetermined video quality evaluation method, when the quality of the first video is different from the quality of the second video, the first evaluation value is different from the second evaluation value.
8. 根据权利要求7所述的装置，还包括：The device according to claim 7, further comprising:

   训练模块，用于执行以下操作：The training module is used to perform the following operations:

   以主观视频质量评估方法对所述第一视频和所述第二视频进行评估得到的视频质量分数为训练目标，基于第一训练视频和第二训练视频来执行训练，其中，所述第一训练视频和第二训练视频是不同失真程度的视频。The subjective video quality evaluation method evaluates the video quality scores of the first video and the second video as the training target, and performs training based on the first training video and the second training video, wherein the first training The video and the second training video are videos with different degrees of distortion.
9. 一种电子设备，包括：An electronic device including:

   处理器；以及Processor; and

   存储器，用于存储计算机程序指令；Memory, used to store computer program instructions;

   其中，当所述计算机程序指令由所述处理器加载并运行时，所述处理器执行如权利要求1至6中任一项所述的方法。Wherein, when the computer program instructions are loaded and run by the processor, the processor executes the method according to any one of claims 1 to 6.
10. 一种计算机可读存储介质，其上存储有计算机程序指令，所述指令在由处理器加载并运行时，使所述处理器执行如权利要求1至6中任一项所述的方法。A computer-readable storage medium has computer program instructions stored thereon, and when the instructions are loaded and run by a processor, the processor executes the method according to any one of claims 1 to 6.

Images