中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

164 records (took 0.027 seconds)

    SCENE AND ACTIVITY IDENTIFICATION IN VIDEO SUMMARY GENERATION
    46.
    发明申请
    SCENE AND ACTIVITY IDENTIFICATION IN VIDEO SUMMARY GENERATION 审中-公开
    视频摘要生成中的场景和活动识别

    公开(公告)号：US20160027470A1

    公开(公告)日：2016-01-28

    申请号：US14513149

    申请日：2014-10-13

    Applicant: GoPro, Inc.

    Inventor： David A. Newman ,  Adam Silver

    IPC: G11B27/00 ,  G11B27/22 ,  G06K9/00 ,  G11B27/031

    CPC classification number: G06K9/00751 ,  G06K2009/00328 ,  G06K2009/00738 ,  G06K2009/00939 ,  G06K2209/27 ,  G11B27/002 ,  G11B27/031 ,  G11B27/22 ,  G11B27/34 ,  H04N5/232 ,  H04N5/23216 ,  H04N5/23293 ,  H04N5/77 ,  H04N5/772 ,  H04N5/91 ,  H04N9/8205 ,  H04N13/172 ,  H04N13/178 ,  H04N21/2353 ,  H04N21/8549 ,  H04N2201/3228 ,  H04N2201/3229 ,  H04N2201/3256

    Abstract: Video and corresponding metadata is accessed. Events of interest within the video are identified based on the corresponding metadata, and best scenes are identified based on the identified events of interest. A video summary can be generated including one or more of the identified best scenes. The video summary can be generated using a video summary template with slots corresponding to video clips selected from among sets of candidate video clips. Best scenes can also be identified by receiving an indication of an event of interest within video from a user during the capture of the video. Metadata patterns representing activities identified within video clips can be identified within other videos, which can subsequently be associated with the identified activities.

    Abstract translation: 访问视频和相应的元数据。 基于相应的元数据来识别视频内感兴趣的事件，并且基于所识别的感兴趣的事件来识别最佳场景。 可以生成包括所识别的最佳场景中的一个或多个的视频摘要。 视频摘要可以使用具有与从候选视频剪辑的集合中选择的视频片段相对应的时隙的视频摘要模板生成。 也可以通过在捕获视频期间从用户接收来自用户的视频内感兴趣的事件的指示来识别最佳场景。 可以在其他视频中识别表示视频剪辑中识别的活动的元数据模式，随后可以与所识别的活动相关联。

    AUTOMATIC GENERATION OF VIDEO AND DIRECTIONAL AUDIO FROM SPHERICAL CONTENT
    47.
    发明申请
    AUTOMATIC GENERATION OF VIDEO AND DIRECTIONAL AUDIO FROM SPHERICAL CONTENT 有权
    视频和方向音频的自动生成从球面内容

    公开(公告)号：US20160005435A1

    公开(公告)日：2016-01-07

    申请号：US14789706

    申请日：2015-07-01

    Applicant: GoPro, Inc.

    Inventor： Scott Patrick Campbell ,  Zhinian Jing ,  Timothy MacMillan ,  David A. Newman ,  Balineedu Chowdary Adsumilli

    IPC: G11B27/031 ,  G11B27/30 ,  H04N5/232 ,  H04N9/802 ,  H04N5/77

    CPC classification number: G11B27/3081 ,  H04N5/23238 ,  H04N5/77 ,  H04N9/806 ,  H04N9/8205 ,  H04N9/8211

    Abstract: A spherical content capture system captures spherical video and audio content. In one embodiment, captured metadata or video/audio processing is used to identify content relevant to a particular user based on time and location information. The platform can then generate an output video from one or more shared spherical content files relevant to the user. The output video may include a non-spherical reduced field of view such as those commonly associated with conventional camera systems. Particularly, relevant sub-frames having a reduced field of view may be extracted from each frame of spherical video to generate an output video that tracks a particular individual or object of interest. For each sub-frame, a corresponding portion of an audio track is generated that includes a directional audio signal having a directionality based on the selected sub-frame.

    Abstract translation: 球面内容捕获系统捕获球面视频和音频内容。 在一个实施例中，捕获的元数据或视频/音频处理被用于基于时间和位置信息来识别与特定用户相关的内容。 然后，平台可以从与用户相关的一个或多个共享球面内容文件生成输出视频。 输出视频可以包括诸如通常与常规相机系统相关联的非球面缩小视场。 特别地，可以从球面视频的每个帧中提取具有减小的视场的相关子帧，以生成跟踪特定个人或感兴趣对象的输出视频。 对于每个子帧，生成音频轨道的对应部分，其包括具有基于所选择的子帧的方向性的定向音频信号。

    ENCODING AND DECODING SELECTIVELY RETRIEVABLE REPRESENTATIONS OF VIDEO CONTENT
    48.
    发明申请
    ENCODING AND DECODING SELECTIVELY RETRIEVABLE REPRESENTATIONS OF VIDEO CONTENT 有权
    编辑和解码视频内容的可选择的可替代的表示

    公开(公告)号：US20150382001A1

    公开(公告)日：2015-12-31

    申请号：US14852868

    申请日：2015-09-14

    Applicant: GoPro, Inc.

    Inventor： David A. Newman ,  Brian G. Schunck

    IPC: H04N19/44

    CPC classification number: H04N19/44 ,  G11B20/00007 ,  G11B27/031 ,  G11B2020/00072 ,  H04N19/423 ,  H04N19/63

    Abstract: A system and method disposed to enable encoding, decoding and manipulation of digital video with substantially less processing load than would otherwise be required. In particular, one disclosed method is directed to generating a compressed video data structure that is selectively decodable to a plurality of resolutions including the full resolution of the uncompressed stream. The desired number of data components and the content of the data components that make up the compressed video data, which determine the available video resolutions, are variable based upon the processing carried out and the resources available to decode and process the data components. During decoding, efficiency is substantially improved because only the data components necessary to generate a desired resolution are decoded. In variations, both temporal and spatial decoding are utilized to reduce frame rates, and hence, further reduce processor load. The system and method are particularly useful for real-time video editing applications.

    Abstract translation: 一种被设置为能够以比其它方式要求的处理负载小得多的数字视频进行编码，解码和操纵的系统和方法。 特别地，一种公开的方法涉及生成可选择性地解码为包括未压缩流的全分辨率的多种分辨率的压缩视频数据结构。 基于执行的处理和可用于解码和处理数据组件的资源，确定可用视频分辨率的组成压缩视频数据的数据组件的期望数量和数据组件的内容是可变的。 在解码期间，由于仅产生所需分辨率所需的数据分量被解码，所以效率显着提高。 在变型中，利用时间和空间解码来降低帧速率，并因此进一步减少处理器负载。 该系统和方法对于实时视频编辑应用特别有用。

    Frame Manipulation to Reduce Rolling Shutter Artifacts
    49.
    发明申请
    Frame Manipulation to Reduce Rolling Shutter Artifacts 有权
    框架操作减少滚动快门人工制品

    公开(公告)号：US20150109488A1

    公开(公告)日：2015-04-23

    申请号：US14451437

    申请日：2014-08-05

    Applicant: GoPro, Inc.

    Inventor： Paul Mobbs ,  Scott Patrick Campbell ,  David A. Newman ,  Kasturi Rangam ,  Sumit Chawla

    IPC: H04N5/353 ,  H04N5/232 ,  H04N5/355

    CPC classification number: H04N5/2329 ,  H04N1/2137 ,  H04N1/215 ,  H04N5/23229 ,  H04N5/23232 ,  H04N5/23277 ,  H04N5/3532 ,  H04N5/35572 ,  H04N2101/00

    Abstract: An image sensor of a camera system captures an image over an image capture interval of time, and waits a blanking interval of time before capturing an additional image. The captured image is provided to a frame controller, and is buffered until an image signal processor accesses the captured image. The image signal processor processes the accessed image over an image processing interval of time, producing a processed image. The image processing interval of time is selected to be greater than the image capture interval of time, but less than the sum of the image capture interval of time and the blanking interval of time. By reducing the image capture interval of time but maintaining an image processing interval of time, rolling shutter artifacts are beneficially reduced without increasing the processing resources or power required by the image signal processor to process the image.

    Abstract translation: 相机系统的图像传感器通过图像捕获时间间隔拍摄图像，并且在捕获附加图像之前等待消隐间隔时间。 将捕获的图像提供给帧控制器，并且被缓冲直到图像信号处理器访问所捕获的图像。 图像信号处理器在图像处理间隔处理所访问的图像，产生经处理的图像。 图像处理时间间隔选择为大于图像捕获时间间隔，但小于图像捕获间隔时间和消隐间隔时间之和。 通过减小图像捕获时间间隔，但是保持图像处理时间间隔，有利地减少滚动快门伪影，而不增加图像信号处理器处理图像所需的处理资源或功率。

    Image sensor data compression and DSP decompression
    50.
    发明授权
    Image sensor data compression and DSP decompression 有权
    图像传感器数据压缩和DSP解压缩

    公开(公告)号：US08970726B2

    公开(公告)日：2015-03-03

    申请号：US14174812

    申请日：2014-02-06

    Applicant: GoPro, Inc.

    Inventor： Scott Patrick Campbell ,  David A. Newman ,  Brian G. Schunck

    IPC: H04N5/228

    CPC classification number: H04N1/2137 ,  H04N1/00209 ,  H04N5/23206 ,  H04N5/335 ,  H04N5/341 ,  H04N5/374 ,  H04N9/045 ,  H04N19/0049 ,  H04N19/137 ,  H04N19/156 ,  H04N19/172 ,  H04N19/423 ,  H04N19/426 ,  H04N19/625 ,  H04N19/63 ,  H04N19/91

    Abstract: An image sensor compresses image data prior to transmitting the image data to a DSP. The image sensor captures light representing an image, for instance via a camera's aperture. A focal plane array converts the captured light into pixel data. The pixel data is sorted into categories, and is compressed in parallel by a compression engine. The compressed pixel data is then sent to a DSP, which may be located off-chip. The DSP then decompresses the compressed pixel data, performs image signal processing operations on the compressed pixel data, and then compresses the processed pixel data into a digital image format. The image sensor may buffer the pixel data for one or more images to accommodate for slowdown by the compression engine. The pixel data may be sorted by row and column of a pixel array. Alternatively, the pixel data may be sorted by color from a Bayer color filter.

    Abstract translation: 图像传感器在将图像数据发送到DSP之前压缩图像数据。 图像传感器例如通过相机的光圈捕获表示图像的光。 焦平面阵列将捕获的光转换成像素数据。 像素数据被分类并被压缩引擎并行压缩。 压缩的像素数据然后被发送到可以位于芯片外的DSP。 然后，DSP解压缩压缩像素数据，对压缩像素数据执行图像信号处理操作，然后将经处理的像素数据压缩为数字图像格式。 图像传感器可以缓冲一个或多个图像的像素数据，以适应压缩引擎的减速。 像素数据可以按像素阵列的行和列排序。 或者，像素数据可以由拜耳滤色器的颜色分类。

Patent Agency Ranking