使用 Azure 门户分析媒体Analyze your media using the Azure portal

Note

若要完成本教程,需要一个 Azure 帐户。To complete this tutorial, you need an Azure account. 有关详细信息,请参阅 Azure 试用版For details, see Azure Trial.

概述Overview

Azure 媒体服务分析是一系列语音和影像组件(具企业规模、合规性、安全性和全球性覆盖),让组织和企业可以从其视频文件中更轻松地获得可操作的见解。Azure Media Services Analytics is a collection of speech and vision components (at enterprise scale, compliance, security and global reach) that make it easier for organizations and enterprises to derive actionable insights from their video files. 有关 Azure 媒体服务分析的详细概述,请参阅主题。For more detailed overview of Azure Media Services Analytics see this topic.

本主题讨论如何使用 Azure 门户通过媒体分析媒体处理器 (MP) 处理媒体。This topic discusses how to process your media with Media Analytics media processors (MPs) using the Azure portal. 媒体分析 MP 会生成 MP4 文件或 JSON 文件。Media Analytics MPs produce MP4 files or JSON files. 如果媒体处理器生成了 MP4 文件,可以采用渐进方式下载该文件。If a media processor produced an MP4 file, you progressively download the file. 如果媒体处理器生成了 JSON 文件,可以从 Azure Blob 存储下载该文件。If a media processor produced a JSON file, you download the file from the Azure blob storage.

选择想要分析的资产Choose an asset that you want to analyze

  1. Azure 门户中,选择 Azure 媒体服务帐户。In the Azure portal, select your Azure Media Services account.

  2. 在“设置” 窗口中,选择“资产” 。In the Settings window, select Assets.

    分析视频

  3. 选择想要分析的资产,并按“分析” 按钮。Select the asset that you would like to analyze and press the Analyze button.

    分析视频

  4. 在“使用媒体分析处理媒体资产” 窗口中,选择处理器。In the Process media asset with Media Analytics window, select the processor.

    本文的其余部分介绍每种处理器的功能和使用方式。The rest of the article explains why and how to use each processor.

  5. 按“创建” 启动作业。Press Create to the start a job.

Azure Media IndexerAzure Media Indexer

Azure Media Indexer 媒体处理器 (MP) 让用户能够使媒体文件和内容可供搜索,以及生成隐藏式字幕轨道。The Azure Media Indexer media processor enables you to make media files and content searchable, as well as generate closed captioning tracks. 本部分提供有关可为此 MP 指定的选项的一些详细信息。This section gives some details about options that you specify for this MP.

分析视频

语言Language

要在多媒体文件中识别的自然语言。The natural language to be recognized in the multimedia file. 例如,英语或西班牙语。For example, English or Spanish.

字幕Captions

可以选择要根据内容生成的字幕格式。You can choose a caption format that will be generated from your content. 索引作业可以生成以下格式的隐藏字幕文件:An indexing job can generate closed caption files in the following formats:

  • SAMISAMI
  • TTMLTTML
  • WebVTTWebVTT

采用这些格式的隐藏式字幕 (CC) 文件可用于使有听力障碍的用户能够访问音频和视频文件。Closed Caption (CC) files in these formats can be used to make audio and video files accessible to people with hearing disability.

AIB 文件AIB file

如果想要生成与自定义 SQL Server IFilter 搭配使用的音频索引 Blob 文件,请选择此选项。Select this option if you would like to generate the Audio Index Blob file for use with the custom SQL Server IFilter. 有关详细信息,请参阅 博客。For more information, see this blog.

关键字Keywords

如果想要生成关键字 XML 文件,请选择此选项。Select this option if you would like to generate a keywords XML file. 此文件包含从语音内容中提取的关键字,以及频率和偏移量信息。This file contains keywords extracted from the speech content, with frequency and offset information.

作业名称Job name

可以识别该作业的友好名称。A friendly name that lets you identify the job. 文章介绍了如何监视作业的进度。This article describes how you can monitor the progress of a job.

输出文件Output file

可以识别输出内容的友好名称。A friendly name that lets you identify the output content.

SpeedSpeed

指定输入视频的加速倍数。Specify the speed with which to speed up the input video. 输出是输入视频经过稳定和缩时转译的结果。The output is a stabilized and time-lapsed rendition of the input video.

作业名称Job name

可以识别该作业的友好名称。A friendly name that lets you identify the job. 文章介绍了如何监视作业的进度。This article describes how you can monitor the progress of a job.

输出文件Output file

可以识别输出内容的友好名称。A friendly name that lets you identify the output content.

Azure 媒体面部检测器Azure Media Face Detector

借助 Azure Media Face Detector 媒体处理器 (MP),可通过面部表情来统计、跟踪动作,甚至计量受众的参与和反应。The Azure Media Face Detector media processor (MP) enables you to count, track movements, and even gauge audience participation and reaction via facial expressions. 此服务包含两项功能:This service contains two features:

  • 面部检测Face detection

    面部检测能够找出并跟踪视频中的人脸。Face detection finds and tracks human faces within a video. 可以检测多个面部,随后随着对象移动进行跟踪,并将时间和位置的元数据以 JSON 文件的形式返回。Multiple faces can be detected and subsequently be tracked as they move around, with the time and location metadata returned in a JSON file. 跟踪期间,该服务会在人员于屏幕上四处移动时,尝试为他们的面部赋予相同的 ID,即使他们被挡住或暂时离帧。During tracking, it will attempt to give a consistent ID to the same face while the person is moving around on screen, even if they are obstructed or briefly leave the frame.

    Note

    此服务并不执行面部识别。This services does not perform facial recognition. 面部离帧或被挡住太久的人员,会在回来时赋予新的 ID。An individual who leaves the frame or becomes obstructed for too long will be given a new ID when they return.

  • 情绪检测Emotion detection

    情绪检测是面部检测媒体处理器的可选组件,它根据检测到的面部返回多个情绪属性的分析,包括快乐、悲伤、恐惧、愤怒等等。Emotion Detection is an optional component of the Face Detection Media Processor that returns analysis on multiple emotional attributes from the faces detected, including happiness, sadness, fear, anger, and more.

分析视频

检测模式Detection mode

处理器可以使用以下模式之一:One of the following modes can be used by the processor:

  • 面部检测face detection
  • 根据人脸表情检测per face emotion detection
  • 聚合情感检测aggregate emotion detection

作业名称Job name

可以识别该作业的友好名称。A friendly name that lets you identify the job. 文章介绍了如何监视作业的进度。This article describes how you can monitor the progress of a job.

输出文件Output file

可以识别输出内容的友好名称。A friendly name that lets you identify the output content.

Azure Media Motion DetectorAzure Media Motion Detector

借助 Azure Media Motion Detector 媒体处理器 (MP),用户可在冗长且平淡的视频中有效识别出感兴趣的部分。The Azure Media Motion Detector media processor (MP) enables you to efficiently identify sections of interest within an otherwise long and uneventful video. 可以对静态相机数据片段使用动作检测,以识别视频中有动作的部分。Motion detection can be used on static camera footage to identify sections of the video where motion occurs. 它会生成 JSON 文件,其中包含带时间戳的元数据,以及发生事件的边界区域。It generates a JSON file containing a metadata with timestamps and the bounding region where the event occurred.

此技术面向安全视频提要,它可以将动作分类为相关事件和误报(例如阴影或光源变化)。Targeted towards security video feeds, this technology is able to categorize motion into relevant events and false positives such as shadows and lighting changes. 这样,便可以在无需查看无止境的不相关事件的情况下,从相机输出生成安全警报,并从长时间的监控视频中提取感兴趣的片段。This allows you to generate security alerts from camera feeds without being spammed with endless irrelevant events, while being able to extract moments of interest from extremely long surveillance videos.

分析视频

Azure 媒体视频缩略图Azure Media Video Thumbnails

此处理器可通过自动选择来自源视频的有趣片段来帮助创建长视频的摘要。This processor can help you create summaries of long videos by automatically selecting interesting snippets from the source video. 要提供有关长视频内容的快速概述时,这很有用。This is useful when you want to provide a quick overview of what to expect in a long video. 有关详细信息和示例,请参阅 使用 Azure 媒体视频缩略图创建视频摘要For detailed information and examples, see Use Azure Media Video Thumbnails to Create a Video Summarization

分析视频

作业名称Job name

可以识别该作业的友好名称。A friendly name that lets you identify the job. 文章介绍了如何监视作业的进度。This article describes how you can monitor the progress of a job.

输出文件Output file

可以识别输出内容的友好名称。A friendly name that lets you identify the output content.

Azure 媒体内容审查器Azure Media Content Moderator

此处理器可以帮助检测视频中可能存在的成人和猥亵内容。This processor helps you detect potential adult and racy content in videos. 此处理器自动检测视频中的快照和关键帧。The processor automatically detects shots and keyframes in the video. 它为可能存在成人或猥亵内容的关键帧评分,并根据默认阈值建议评审。It scores the keyframes for possible adult or racy content, and suggests reviews based on default thresholds. 有关详细信息和示例,请参阅使用 Azure 媒体内容审查器审查视频For detailed information and examples, see Use Azure Media Content Moderator to moderate videos

审查视频

版本Version

使用“2.0”。Use "2.0".

ModeMode

2.0 版忽略 Mode 设置。The 2.0 version ignore the Mode setting.

后续步骤Next steps

查看媒体服务学习路径。View Media Services learning paths.

媒体服务 v3(最新版本)Media Services v3 (latest)

查看最新版本的 Azure 媒体服务!Check out the latest version of Azure Media Services!

媒体服务 v2(旧版)Media Services v2 (legacy)