TECHNOLOGIES FOR LOCALIZED AUDIO ENHANCEMENT OF A THREE-DIMENSIONAL VIDEO
    1.
    发明申请
    TECHNOLOGIES FOR LOCALIZED AUDIO ENHANCEMENT OF A THREE-DIMENSIONAL VIDEO 审中-公开
    用于三维视频本地化音频增强的技术

    公开(公告)号:US20160381459A1

    公开(公告)日:2016-12-29

    申请号:US14752895

    申请日:2015-06-27

    摘要: Technologies for localized audio enhancement of a three-dimensional video include capturing a three-dimensional video including depth data using a three-dimensional camera of a mobile computing device and receiving a three-dimensional audio associated with the three-dimensional video using a microphone array. A user may enhance localized audio by selecting a region of the three-dimensional image from the three-dimensional video. In response, the mobile computing device generates an audio component of the three-dimensional audio corresponding to the selected region based on depth data associated with the selected region. A user may subsequently enhance the audio component by, for example, increasing the volume of the audio component or increasing the clarity of the audio component. In this way, a user may focus the audio playback on a selected portion of the three-dimensional video, which improves the user's ability to listen and understand an individual, group of individuals, or region captured in the three-dimensional video.

    摘要翻译: 用于三维视频的本地化音频增强的技术包括使用移动计算设备的三维相机捕获包括深度数据的三维视频,并使用麦克风阵列接收与三维视频相关联的三维音频 。 用户可以通过从三维视频中选择三维图像的区域来增强本地化音频。 作为响应,移动计算设备基于与所选择的区域相关联的深度数据来生成与所选区域相对应的三维音频的音频分量。 用户可以随后通过例如增加音频分量的音量或增加音频分量的清晰度来增强音频分量。 以这种方式,用户可以将音频回放聚焦在三维视频的所选部分上,这提高了用户听取和理解在三维视频中捕获的个人,一组个体或区域的能力。