CN111583251A

Movatterモバイル変換

Info

Publication number: CN111583251A
Application number: CN202010411368.2A
Authority: CN
Inventors: 吴建伟; 王云烨; 杨鸿珍; 赖晓翰; 刘秀; 卢文达; 方晴程; 吴慧; 史俊潇; 段玉帅; 翁晨帆; 詹佳雯; 沈桂竹
Original assignee: Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd
Current assignee: Information and Telecommunication Branch of State Grid Zhejiang Electric Power Co Ltd
Priority date: 2020-05-15
Filing date: 2020-05-15
Publication date: 2020-08-25

Abstract

The invention provides a video image analysis method, a video image analysis device and electronic equipment. In the process of determining the image quality, the invention firstly determines that the video image meets the preset environmental parameters and then analyzes the video image, thereby avoiding the influence of environmental factors on the video image quality, improving the accuracy of video image quality analysis and ensuring that the judgment result of determining whether to continue the video conference according to the video image quality analysis result is more accurate.

Description

Translated fromChinese

一种视频图像分析方法、装置及电子设备A video image analysis method, device and electronic device

技术领域technical field

本发明涉及图像处理领域，更具体的说，涉及一种视频图像分析方法、装置及电子设备。The present invention relates to the field of image processing, and more particularly, to a video image analysis method, device and electronic equipment.

背景技术Background technique

视频会议系统作为一种方便、快捷的简短会议方式，已经在各企业中普遍应用。在使用视频会议系统进行视频会议时，由于网速不稳定等因素会影响视频图像质量，从而影响视频会议的效果，降低用户体验。为了提高用户体验，可以对视频图像质量进行分析，若满足相应的质量要求，则可以进行视频会议。As a convenient and fast short meeting method, the video conference system has been widely used in various enterprises. When a video conference system is used for video conference, the unstable network speed and other factors will affect the video image quality, thereby affecting the effect of the video conference and reducing the user experience. In order to improve the user experience, the video image quality can be analyzed, and if the corresponding quality requirements are met, a video conference can be performed.

现有技术中，在分析视频会议的视频图像质量时，需要检测该视频会议的视频图像的清晰度、亮度等数据，与相应的预设阈值作比较，从而确定出视频图像质量的高低。这种视频图像质量的分析方法，准确度较低，从而使得依据该视频图像质量分析结果确定是否继续视频会议的判断结果不准确。In the prior art, when analyzing the video image quality of a video conference, it is necessary to detect data such as the definition and brightness of the video image of the video conference, and compare it with a corresponding preset threshold to determine the quality of the video image. This method for analyzing video image quality has low accuracy, so that the result of determining whether to continue the video conference according to the video image quality analysis result is inaccurate.

发明内容SUMMARY OF THE INVENTION

有鉴于此，本发明提供一种视频图像分析方法、装置及电子设备，以解决现有技术中视频图像质量分析的准确度较低的问题。In view of this, the present invention provides a video image analysis method, device and electronic device to solve the problem of low accuracy of video image quality analysis in the prior art.

为实现上述目的，本发明提供如下技术方案：To achieve the above object, the present invention provides the following technical solutions:

一种视频图像分析方法，包括：A video image analysis method, comprising:

获取采集终端实时采集的视频图像；Obtain the video images collected in real time by the collection terminal;

计算所述视频图像与参考视频图像的图像相似度，所述参考视频图像为符合预设环境条件、且与所述采集终端对应的图像；calculating the image similarity between the video image and a reference video image, where the reference video image is an image that meets preset environmental conditions and corresponds to the collection terminal;

在所述图像相似度大于预设相似度阈值的情况下，对所述视频图像进行图像检测，得到预设质量分析维度对应的维度值；In the case that the image similarity is greater than the preset similarity threshold, image detection is performed on the video image to obtain the dimension value corresponding to the preset quality analysis dimension;

依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果。The quality analysis result of the video image is determined according to the dimension value corresponding to the preset quality analysis dimension.

可选地，在所述图像相似度不大于预设相似度阈值的情况下，还包括：Optionally, in the case that the similarity of the images is not greater than a preset similarity threshold, it also includes:

输出预设信息；所述预设信息表征所述视频图像的图像环境不符合所述预设环境条件。Output preset information; the preset information indicates that the image environment of the video image does not conform to the preset environment condition.

判断所述采集终端的采集角度是否为预设角度；Judging whether the collection angle of the collection terminal is a preset angle;

若不是，在预设时间之后调整所述采集终端的采集角度为所述预设角度。If not, adjust the collection angle of the collection terminal to the preset angle after the preset time.

可选地，依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果，包括：Optionally, determining the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension, including:

将所述预设质量分析维度对应的维度值与所述预设质量分析维度对应的维度阈值作比较，得到比较结果；所述预设质量分析维度包括清晰度、亮度和/或对比度；Comparing the dimension value corresponding to the preset quality analysis dimension with the dimension threshold corresponding to the preset quality analysis dimension to obtain a comparison result; the preset quality analysis dimension includes clarity, brightness and/or contrast;

将所述比较结果确定为所述视频图像的质量分析结果。The comparison result is determined as the quality analysis result of the video image.

可选地，所述预设质量分析维度还包括：黑屏分析维度和/或雪花分析维度；Optionally, the preset quality analysis dimension further includes: a black screen analysis dimension and/or a snowflake analysis dimension;

相应的，依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果，还包括：Correspondingly, determining the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension, further comprising:

将所述比较结果、所述黑屏分析维度对应的维度值和/或所述雪花分析维度对应的维度值确定为所述视频图像的质量分析结果。The comparison result, the dimension value corresponding to the black screen analysis dimension, and/or the dimension value corresponding to the snowflake analysis dimension are determined as the quality analysis result of the video image.

可选地，所述预设环境条件包括预设区域。Optionally, the preset environmental conditions include a preset area.

一种视频图像分析装置，包括：A video image analysis device, comprising:

图像获取模块，用于获取采集终端实时采集的视频图像；The image acquisition module is used to acquire the video images collected in real time by the acquisition terminal;

相似度计算模块，用于计算所述视频图像与参考视频图像的图像相似度，所述参考视频图像为符合预设环境条件、且与所述采集终端对应的图像；a similarity calculation module, configured to calculate the image similarity between the video image and a reference video image, where the reference video image is an image that meets preset environmental conditions and corresponds to the collection terminal;

图像检测模块，用于在所述图像相似度大于预设相似度阈值的情况下，对所述视频图像进行图像检测，得到预设质量分析维度对应的维度值；an image detection module, configured to perform image detection on the video image when the similarity of the images is greater than a preset similarity threshold to obtain a dimension value corresponding to a preset quality analysis dimension;

结果确定模块，用于依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果。The result determination module is configured to determine the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension.

可选地，还包括：Optionally, also include:

信息输出模块，用于在所述图像相似度不大于预设相似度阈值的情况下，还包括：An information output module, configured to further include: when the similarity of the images is not greater than a preset similarity threshold:

可选地，还包括：Optionally, also include:

判断模块，用于在所述图像相似度不大于预设相似度阈值的情况下，判断所述采集终端的采集角度是否为预设角度；a judgment module, configured to judge whether the collection angle of the collection terminal is a preset angle when the similarity of the images is not greater than a preset similarity threshold;

调整模块，用于在若判断模块判断出采集终端的采集角度不是预设角度，在预设时间之后调整所述采集终端的采集角度为所述预设角度。The adjustment module is configured to adjust the collection angle of the collection terminal to the preset angle after a preset time if the judgment module determines that the collection angle of the collection terminal is not the preset angle.

一种电子设备，包括：存储器和处理器；An electronic device, comprising: a memory and a processor;

其中，所述存储器用于存储程序；Wherein, the memory is used to store programs;

处理器调用程序并用于：The processor invokes the program and is used to:

经由上述的技术方案可知，本发明提供了一种视频图像分析方法、装置及电子设备，在进行视频图像质量分析时，首先获取采集终端实时采集的视频图像以及符合预设环境参数的预设视频图像，然后计算所述视频图像与预设视频图像的图像相似度，若所述图像相似度大于预设相似度阈值，则说明当前的视频环境满足环境要求，此时才执行后续处理。由于本发明在对图像质量确定的过程中，先确定视频图像满足预设环境参数的情况下，再对其进行分析从而避免了环境因素对视频图像质量的影响，从而提高了视频图像质量分析的准确性，使得依据该视频图像质量分析结果确定是否继续视频会议的判断结果更准确。As can be seen from the above technical solutions, the present invention provides a video image analysis method, device and electronic equipment. When performing video image quality analysis, first obtain the video image collected in real time by the collection terminal and the preset video that conforms to the preset environmental parameters. image, and then calculate the image similarity between the video image and the preset video image. If the image similarity is greater than the preset similarity threshold, it means that the current video environment meets the environmental requirements, and the subsequent processing is performed only at this time. In the process of determining the image quality, the present invention first determines that the video image meets the preset environmental parameters, and then analyzes it, thereby avoiding the influence of environmental factors on the video image quality, thereby improving the accuracy of video image quality analysis. The accuracy makes it more accurate to determine whether to continue the video conference according to the video image quality analysis result.

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据提供的附图获得其他的附图。In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without creative work.

图1为本发明实施例提供的一种视频图像分析方法的方法流程图；1 is a method flowchart of a video image analysis method provided by an embodiment of the present invention;

图2为本发明实施例提供的另一种视频图像分析方法的方法流程图；2 is a method flowchart of another video image analysis method provided by an embodiment of the present invention;

图3为本发明实施例提供的一种视频图像分析装置的结构示意图。FIG. 3 is a schematic structural diagram of a video image analysis apparatus according to an embodiment of the present invention.

具体实施方式Detailed ways

下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

现有技术中，在分析视频会议的视频图像质量时，需要检测该视频会议的视频图像的清晰度、亮度等数据，与相应的预设阈值作比较，从而确定出视频图像质量的高低。这种视频图像质量的分析方法仅考虑了图像的清晰度、亮度等图像本身存在的特定信息，忽略了图像的内容对视频图像质量的影响，会使得图像质量确定准确度较低，从而使得依据该视频图像质量分析结果确定是否继续视频会议的判断结果不准确。In the prior art, when analyzing the video image quality of a video conference, it is necessary to detect data such as the definition and brightness of the video image of the video conference, and compare it with a corresponding preset threshold to determine the quality of the video image. This analysis method of video image quality only considers the specific information of the image itself, such as the clarity and brightness of the image, and ignores the influence of the content of the image on the quality of the video image, which will make the image quality determination less accurate, thus making the basis for The result of the video image quality analysis to determine whether to continue the video conference is inaccurate.

举例来说，两个清晰度、亮度等维度对应的维度值均相同的两个图像，一个图像中会议现场整齐，如桌椅整齐，人员均就座，另一张图像中，会议现场混乱，人员走动，桌椅不整齐，明显第二张图像的视频图像质量更差。也就是说，图像的环境也是影响视频图像质量的一个因素，只有消除了环境因素对图像质量的影响，才可以使用上述的检测该视频会议的视频图像的清晰度、亮度等数据，与相应的预设阈值作比较，从而确定出视频图像质量的高低的方法。For example, two images with the same dimension values corresponding to the dimensions such as definition and brightness. In one image, the conference site is neat, such as neat tables and chairs, and all people are seated. In the other image, the conference site is chaotic. People move around, tables and chairs are not neat, and the video image quality of the second image is obviously worse. That is to say, the environment of the image is also a factor that affects the quality of the video image. Only after eliminating the influence of the environmental factor on the image quality, can the above-mentioned data such as the definition and brightness of the video image of the video conference be used, and the corresponding data can be used. Preset thresholds are compared to determine the quality of the video image.

具体的，参照图1，视频图像分析方法可以包括：Specifically, referring to FIG. 1, the video image analysis method may include:

S11、获取采集终端实时采集的视频图像。S11. Acquire a video image collected in real time by a collection terminal.

在实际应用时，主要是采集的视频会议现场的视频图像，会议现场的数量可以是一个，可以是多个，每个会议现场会设置有采集终端(数量可以为一个，也可以为多个，为了节省开支，可以将采集终端的数量设置为一个)，如摄像头，在会议现场的会议召开时，采集终端正常工作时，会实时采集到会议现场的图像，如采集终端设置在会议现场的墙壁上，以向下45°的方式实时采集图像。每一会议现场的采集终端采集的视频图像单独处理，最终每一采集终端采集的视频图像对应一视频图像的质量分析结果。In practical application, it mainly collects video images of the video conference site. The number of conference sites can be one or more, and each conference site will be provided with a collection terminal (the number can be one or multiple, In order to save costs, the number of acquisition terminals can be set to one), such as cameras, when the meeting at the conference site is held, the acquisition terminal will collect the images of the conference site in real time when the acquisition terminal is working normally, such as the acquisition terminal is set on the wall of the conference site. , the image is acquired in real time with a downward 45° angle. The video images collected by the collection terminal at each conference site are processed separately, and finally the video image collected by each collection terminal corresponds to the quality analysis result of a video image.

本实施例中的视频图像分析方法的执行者可以是与采集终端连接的后台服务器，后台服务器具有主控单元，主控单元执行方法步骤S11-S14。The executor of the video image analysis method in this embodiment may be a background server connected to the collection terminal, the background server has a main control unit, and the main control unit executes steps S11-S14 of the method.

S12、计算所述视频图像与参考视频图像的图像相似度，所述参考视频图像为符合预设环境条件、且与所述采集终端对应的图像。S12. Calculate the image similarity between the video image and a reference video image, where the reference video image is an image that conforms to a preset environmental condition and corresponds to the collection terminal.

本实施例中，为每一采集终端设置一对应的参考视频图像，若采集终端的数量为一个，也即每一会议现场设置一参考视频图像，如可以在会议现场布置完成之后，使用该采集终端对会议现场进行拍照，就可以得到该参考视频图像，本实施例中，参考视频图像符合预设环境条件，如上述的可以对布置好的会议现场进行拍照，此时预设环境条件即为预设区域(布置好的会议现场)。In this embodiment, a corresponding reference video image is set for each collection terminal. If the number of collection terminals is one, that is, a reference video image is set for each conference site. For example, after the conference site is arranged, the collection terminal can be used. The terminal can obtain the reference video image by taking a picture of the conference site. In this embodiment, the reference video image conforms to the preset environmental conditions. As mentioned above, the arranged conference site can be photographed. In this case, the preset environmental conditions are Preset area (arranged meeting site).

本实施例中，在计算视频图像与参考视频图像的图像相似度时，可以采用人工比对的方式，如人工比对两张图像的图像内容是否相似，若相似，则确定一个较高的图像相似度，若不相似，则确定一个较低的图像相似度。In this embodiment, when calculating the image similarity between the video image and the reference video image, a manual comparison method can be used, such as manually comparing whether the image contents of the two images are similar, and if they are similar, determine a higher image Similarity, if not similar, determine a lower image similarity.

举例来说，若参考视频图像与视频图像的桌椅摆放、人员座椅位置均相差不多，则认为图像相似，则图像相似度较高，若参考视频图像与视频图像的桌椅摆放、人员座椅位置均相差较多，则认为图像不相似，则图像相似度较低。For example, if the table and chair placement and personnel seat positions of the reference video image and the video image are similar, the images are considered to be similar, and the image similarity is high. If the seat positions of the personnel are quite different, it is considered that the images are not similar, and the similarity of the images is low.

此外，为了减少人工确定视频图像与参考视频图像的图像相似度带来的浪费人力的问题，还可以使用服务器或电子设备自动计算图像相似度。In addition, in order to reduce the problem of wasting manpower caused by manually determining the image similarity between the video image and the reference video image, a server or an electronic device can also be used to automatically calculate the image similarity.

S13、在所述图像相似度大于预设相似度阈值的情况下，对所述视频图像进行图像检测，得到预设质量分析维度对应的维度值。S13. When the image similarity is greater than a preset similarity threshold, perform image detection on the video image to obtain a dimension value corresponding to a preset quality analysis dimension.

若图像相似度大于预设相似度阈值，也就是说，当前的视频会议现场与布置好的会议现场差不多，也即当前的视频会议现场较符合人工对会议现场的要求，也就是说，当前的会议现场符合视频环境要求，进而在这种情况下，分析得到的视频图像质量就可以忽略视频环境对视频图像质量的影响，此时，就可以通过检测视频图像的亮度、清晰度等参数，其中，亮度、清晰度可以称为预设质量分析维度，检测得到的亮度值、清晰度值即为预设质量分析维度对应的维度值。If the image similarity is greater than the preset similarity threshold, that is to say, the current video conference site is similar to the arranged conference site, that is, the current video conference site is more in line with the manual requirements for the conference site, that is, the current video conference site The conference site meets the requirements of the video environment. In this case, the video image quality obtained by the analysis can ignore the influence of the video environment on the video image quality. In this case, parameters such as brightness and clarity of the video image can be detected. , the brightness and sharpness can be called preset quality analysis dimensions, and the detected brightness value and sharpness value are the dimension values corresponding to the preset quality analysis dimension.

需要说明的是，本实施例中的预设相似度阈值是人工根据具体使用场景进行设定的，如0.95。It should be noted that the preset similarity threshold in this embodiment is manually set according to a specific usage scenario, such as 0.95.

若图像相似度不大于预设相似度阈值，则说明当前的视频会议现场与布置好的会议现场相差较多，也即当前的视频会议现场较不符合人工对会议现场的要求，也就是说，当前的会议现场不符合视频环境要求，在此种情况下，无法忽略视频会议所在环境对视频图像质量的影响，则不能仅从亮度、清晰度等维度对视频图像质量进行分析，此时可以输出预设信息，所述预设信息表征所述视频图像的图像环境不符合所述预设环境条件，本实施例中，输出的预设信息可以输出至主控单元的显示界面，此外，还可以输出至管理视频图像的管理人员的终端，如手机、电脑等。If the image similarity is not greater than the preset similarity threshold, it means that the current video conference site is quite different from the arranged conference site, that is, the current video conference site does not meet the manual requirements for the conference site, that is, The current conference site does not meet the requirements of the video environment. In this case, the influence of the environment where the video conference is located on the video image quality cannot be ignored, and the video image quality cannot be analyzed only from the dimensions of brightness and clarity. Preset information, the preset information indicates that the image environment of the video image does not meet the preset environmental conditions. In this embodiment, the output preset information can be output to the display interface of the main control unit. Output to terminals of managers who manage video images, such as mobile phones, computers, etc.

若接收到预设信息之后，视频会议管理人员会通知会议现场人员对会议现场进行调整，如恢复桌椅原有的位置、禁止人员走动等操作。After receiving the preset information, the video conference management personnel will notify the meeting site personnel to make adjustments to the meeting site, such as restoring the original positions of tables and chairs, and prohibiting people from moving around.

此外，还有一种情况就是，会议现场的采集终端的采集角度被人调整了，本实施例中，设定采集终端具有自复位功能。In addition, there is also a situation that the collection angle of the collection terminal at the conference site is adjusted by someone. In this embodiment, the collection terminal is set to have a self-reset function.

在所述图像相似度不大于预设相似度阈值的情况下，还可以包括：In the case that the image similarity is not greater than the preset similarity threshold, it may also include:

判断所述采集终端的采集角度是否为预设角度，若不是，在预设时间之后调整所述采集终端的采集角度为所述预设角度。It is judged whether the collection angle of the collection terminal is the preset angle, and if not, the collection angle of the collection terminal is adjusted to the preset angle after a preset time.

在实际应用中，检测采集终端的采集角度是否发生变化是通过判断所述采集终端的采集角度是否为预设角度来实现的，本实施例中的预设角度可以是斜向下45°，若判断出采集终端的采集角度不是预设角度，即说明采集终端的采集角度被人调整过，则在预设时间之后，控制采集终端的采集角度恢复至预设角度，在实际应用中，主控单元可以发送复位指令至采集终端，采集终端就可以自复位至预设角度。In practical applications, detecting whether the collection angle of the collection terminal changes is realized by judging whether the collection angle of the collection terminal is a preset angle. The preset angle in this embodiment may be 45° diagonally downward. It is determined that the collection angle of the collection terminal is not the preset angle, which means that the collection angle of the collection terminal has been adjusted by someone, and after the preset time, the collection angle of the collection terminal is controlled to return to the preset angle. In practical applications, the main control The unit can send a reset command to the acquisition terminal, and the acquisition terminal can reset itself to the preset angle.

经过上述的调整后，实时监测视频图像，若新的视频图像与参考视频图像的图像相似度大于预设相似度阈值，则说明会议现场环境合格，此时人工可以观察采集终端采集的视频图像，观察是否经常性存在黑屏、雪花、对比度较差、亮度不适合等问题，若存在上述任一问题，可以通过更换采集终端、更换传输线等方式进行问题修复。After the above adjustment, the video images are monitored in real time. If the image similarity between the new video image and the reference video image is greater than the preset similarity threshold, it means that the meeting site environment is qualified. At this time, the video images collected by the collection terminal can be observed manually. Observe whether there are frequent problems such as black screen, snowflakes, poor contrast, and unsuitable brightness. If any of the above problems exist, you can repair the problem by replacing the acquisition terminal or replacing the transmission line.

举例来说，若是经常性出现黑屏现象，则人工可以推断出采集终端出现故障，如摄像头故障，此时可以通过更换摄像头解决。若是出现雪花现象，则人工可以推断出是传输线出现故障，则可以通过更换传输线解决。For example, if the black screen phenomenon occurs frequently, it can be manually inferred that the acquisition terminal is faulty, such as a camera fault, which can be solved by replacing the camera at this time. If a snowflake phenomenon occurs, it can be inferred manually that the transmission line is faulty, which can be solved by replacing the transmission line.

在上述出现的任一问题都解决之后，若人工认为当前采集的视频图像正常，即经常性出现黑屏、雪花、对比度较差、亮度不适合等问题解决了，此时就可以使用主控单元中的图像检测软件来检测预设质量分析维度对应的维度值，预设质量分析维度可以是上述的黑屏分析维度、雪花分析维度、亮度、和/或对比度等维度。After any of the above problems are solved, if the currently collected video image is considered to be normal, that is, the frequent occurrence of black screen, snowflakes, poor contrast, unsuitable brightness and other problems are solved, then you can use the main control unit. The image detection software is used to detect the dimension value corresponding to the preset quality analysis dimension, and the preset quality analysis dimension may be the above-mentioned black screen analysis dimension, snowflake analysis dimension, brightness, and/or contrast and other dimensions.

本实施例中，若预设质量分析维度为亮度、对比度时，得到的维度值为数值，如对比度为0.5。In this embodiment, if the preset quality analysis dimensions are brightness and contrast, the obtained dimension value is a numerical value, for example, the contrast is 0.5.

若预设质量分析维度为黑屏分析维度、雪花分析维度时，得到的维度值为是否出现黑屏、雪花的判断结果。If the preset quality analysis dimension is the black screen analysis dimension and the snowflake analysis dimension, the obtained dimension value is the judgment result of whether there is a black screen or snowflake.

S14、依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果。S14. Determine the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension.

在实际应用中，参照图2，步骤S14可以通过下述步骤实现；In practical application, referring to Fig. 2, step S14 can be realized by the following steps;

S21、将所述预设质量分析维度对应的维度值与所述预设质量分析维度对应的维度阈值作比较，得到比较结果。S21. Compare the dimension value corresponding to the preset quality analysis dimension with the dimension threshold corresponding to the preset quality analysis dimension to obtain a comparison result.

S22、将所述比较结果确定为所述视频图像的质量分析结果。S22. Determine the comparison result as the quality analysis result of the video image.

在当所述预设质量分析维度为清晰度、亮度和/或对比度时，人工会预先设定该清晰度、亮度和/或对比度对应的维度阈值，维度阈值可以根据不同的会议现场环境进行设定，如会议现场环境为会议室与草坪对应的亮度不同。When the preset quality analysis dimension is clarity, brightness and/or contrast, the dimension threshold corresponding to the clarity, brightness and/or contrast will be manually preset, and the dimension threshold may be set according to different conference site environments. For example, the brightness corresponding to the conference room and the lawn is different in the meeting scene environment.

在得到预设质量分析维度对应的维度值与维度阈值后，二者进行比对，得到比较结果，举例来说，以亮度为例，亮度对应的维度阈值为0.3-0.6，也就是说，若检测的视频图像的亮度值在0.3-0.6范围内，则认为亮度正常，否则认为亮度不正常。After obtaining the dimension value corresponding to the preset quality analysis dimension and the dimension threshold, the two are compared to obtain the comparison result. For example, taking brightness as an example, the dimension threshold corresponding to brightness is 0.3-0.6, that is, if If the brightness value of the detected video image is in the range of 0.3-0.6, the brightness is considered to be normal; otherwise, the brightness is considered to be abnormal.

此外，比较结果还可以是：In addition, the comparison result can also be:

计算预设质量分析维度对应的维度值与维度阈值的差值，然后判断差值是否在预设范围内，若是，则比较结果为正常，若否，则比较结果为异常。Calculate the difference between the dimension value corresponding to the preset quality analysis dimension and the dimension threshold, and then determine whether the difference is within the preset range. If so, the comparison result is normal, and if not, the comparison result is abnormal.

需要说明的是，在执行步骤S21之前，还可以先判断主控单元中是否存储有预设质量分析维度对应的维度阈值，若没有，则需要获取预设质量分析维度对应的维度阈值，若有，则执行步骤S21。It should be noted that, before step S21 is performed, it is also possible to determine whether the main control unit stores a dimension threshold corresponding to the preset quality analysis dimension. If not, the dimension threshold corresponding to the preset quality analysis dimension needs to be obtained. , then step S21 is executed.

进一步，述预设质量分析维度还包括黑屏分析维度和/或雪花分析维度时，步骤S14还可以包括：Further, when the preset quality analysis dimension also includes the black screen analysis dimension and/or the snowflake analysis dimension, step S14 may further include:

上述已经介绍了黑屏分析维度对应的维度值和/或所述雪花分析维度对应的维度值为是否出现黑屏、雪花的判断结果，也就是说，质量分析结果不仅包括对比度、亮度与相应阈值的比较结果，还包括是否出现黑屏、雪花的判断结果。在视频会议结束之后，可以将本次实时检测的每一帧视频图像的质量分析结果进行汇总，得到亮度正常或不正常的次数、对比度正常或不正常的次数、黑屏的次数、雪花的次数。The above has introduced the dimension value corresponding to the black screen analysis dimension and/or the dimension value corresponding to the snowflake analysis dimension. The judgment result of whether a black screen or snowflake occurs, that is to say, the quality analysis result not only includes the comparison of contrast, brightness and corresponding thresholds The result also includes the judgment result of whether there is a black screen or snowflakes. After the video conference is over, the quality analysis results of each frame of video image detected in real time can be summarized to obtain the number of normal or abnormal brightness, normal or abnormal contrast, the number of black screens, and the number of snowflakes.

本实施例中，在进行视频图像质量分析时，首先获取采集终端实时采集的视频图像以及符合预设环境参数的预设视频图像，然后计算所述视频图像与预设视频图像的图像相似度，若所述图像相似度大于预设相似度阈值，则说明当前的视频环境满足环境要求，此时才执行后续处理。由于本发明在对图像质量确定的过程中，先确定视频图像满足预设环境参数的情况下，再对其进行分析从而避免了环境因素对视频图像质量的影响，从而提高了视频图像质量分析的准确性，使得依据该视频图像质量分析结果确定是否继续视频会议的判断结果更准确。In this embodiment, when analyzing the video image quality, first acquire the video image collected in real time by the collection terminal and the preset video image conforming to the preset environmental parameters, and then calculate the image similarity between the video image and the preset video image, If the image similarity is greater than the preset similarity threshold, it means that the current video environment meets the environmental requirements, and the subsequent processing is performed only at this time. In the process of determining the image quality, the present invention first determines that the video image meets the preset environmental parameters, and then analyzes it, thereby avoiding the influence of environmental factors on the video image quality, thereby improving the accuracy of video image quality analysis. The accuracy makes it more accurate to determine whether to continue the video conference according to the video image quality analysis result.

可选地，在上述视频图像分析方法的实施例的基础上，本发明的另一实施例提供了一种视频图像分析装置，参照图3，可以包括：Optionally, based on the above embodiments of the video image analysis method, another embodiment of the present invention provides a video image analysis apparatus, referring to FIG. 3 , which may include:

图像获取模块11，用于获取采集终端实时采集的视频图像；The image acquisition module 11 is used to acquire the video images collected in real time by the collection terminal;

相似度计算模块12，用于计算所述视频图像与参考视频图像的图像相似度，所述参考视频图像为符合预设环境条件、且与所述采集终端对应的图像；asimilarity calculation module 12, configured to calculate the image similarity between the video image and a reference video image, where the reference video image is an image that meets preset environmental conditions and corresponds to the collection terminal;

图像检测模块13，用于在所述图像相似度大于预设相似度阈值的情况下，对所述视频图像进行图像检测，得到预设质量分析维度对应的维度值；Animage detection module 13, configured to perform image detection on the video image when the similarity of the images is greater than a preset similarity threshold to obtain a dimension value corresponding to a preset quality analysis dimension;

结果确定模块14，用于依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果。Theresult determination module 14 is configured to determine the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension.

进一步，还包括：Further, it also includes:

进一步，结果确定模块14用于依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果时，具体用于：Further, when theresult determination module 14 is configured to determine the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension, it is specifically used for:

进一步，所述预设质量分析维度还包括：黑屏分析维度和/或雪花分析维度；Further, the preset quality analysis dimension further includes: a black screen analysis dimension and/or a snowflake analysis dimension;

结果确定模块14用于依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果时，还用于：Theresult determination module 14 is used for determining the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension, and is also used for:

进一步，所述预设环境条件包括预设区域。Further, the preset environmental condition includes a preset area.

需要说明的是，本实施例中的各个模块的工作过程，请参照上述实施例中的相应说明，在此不再赘述。It should be noted that, for the working process of each module in this embodiment, please refer to the corresponding description in the foregoing embodiment, which will not be repeated here.

可选地，在上述视频图像分析方法及装置的实施例的基础上，本发明的另一实施例提供了一种电子设备，包括：存储器和处理器；Optionally, based on the foregoing embodiments of the video image analysis method and apparatus, another embodiment of the present invention provides an electronic device, including: a memory and a processor;

进一步，在所述图像相似度不大于预设相似度阈值的情况下，还包括：Further, in the case that the similarity of the images is not greater than the preset similarity threshold, it also includes:

进一步，依据所述预设质量分析维度对应的维度值，确定所述视频图像的质量分析结果，包括：Further, determining the quality analysis result of the video image according to the dimension value corresponding to the preset quality analysis dimension, including:

本申请是参照根据本申请实施例的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It will be understood that each flow and/or block in the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer, embedded processor or other programmable data processing device to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing device produce Means for implementing the functions specified in a flow or flow of a flowchart and/or a block or blocks of a block diagram.

在一个典型的配置中，设备包括一个或多个处理器(CPU)、存储器和总线。设备还可以包括输入/输出接口、网络接口等。In a typical configuration, a device includes one or more processors (CPUs), memory, and a bus. Devices may also include input/output interfaces, network interfaces, and the like.

存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。存储器是计算机可读介质的示例。Memory may include non-persistent memory in computer readable media, random access memory (RAM) and/or non-volatile memory, such as read only memory (ROM) or flash memory (flash RAM), the memory including at least one memory chip. Memory is an example of a computer-readable medium.

计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。Computer-readable media includes both persistent and non-permanent, removable and non-removable media, and storage of information may be implemented by any method or technology. Information may be computer readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), Flash Memory or other memory technology, Compact Disc Read Only Memory (CD-ROM), Digital Versatile Disc (DVD) or other optical storage, Magnetic tape cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media, such as modulated data signals and carrier waves.

还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。It should also be noted that the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device comprising a series of elements includes not only those elements, but also Other elements not expressly listed, or which are inherent to such a process, method, article of manufacture, or apparatus are also included. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in the process, method, article of manufacture or apparatus that includes the element.

本领域技术人员应明白，本申请的实施例可提供为方法、系统或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。It will be appreciated by those skilled in the art that the embodiments of the present application may be provided as a method, a system or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

需要说明的是，本说明书中的各个实施例均采用递进的方式描述，每个实施例重点说明的都是与其他实施例的不同之处，各个实施例之间相同相似的部分互相参见即可。It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. For the same and similar parts among the various embodiments, refer to each other Can.

还需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括上述要素的物品或者设备中还存在另外的相同要素。It should also be noted that in this document, relational terms such as first and second are used only to distinguish one entity or operation from another, and do not necessarily require or imply those entities or operations There is no such actual relationship or order between them. Furthermore, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that an article or device comprising a list of elements includes not only those elements, but also other elements not expressly listed, Or also include elements inherent to the article or equipment. Without further limitation, an element defined by the phrase "comprising a..." does not preclude the presence of additional identical elements in an article or device that includes the above-mentioned element.

对所公开的实施例的上述说明，使本领域专业技术人员能够实现或使用本发明。对这些实施例的多种修改对本领域的专业技术人员来说将是显而易见的，本文中所定义的一般原理可以在不脱离本发明的精神或范围的情况下，在其它实施例中实现。因此，本发明将不会被限制于本文所示的这些实施例，而是要符合与本文所公开的原理和新颖特点相一致的最宽的范围。The above description of the disclosed embodiments enables any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.