-
公开(公告)号：US09392194B2
公开(公告)日：2016-07-12
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
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。
-
公开(公告)号：US20160196852A1
公开(公告)日：2016-07-07
申请号：US14883943
申请日：2015-10-15
Applicant: GoPro, Inc.
Inventor： Otto K. Sievert , Gurprit Cheema , David A. Newman
CPC classification number: G11B27/036 , G06K9/00718 , G06K9/00744 , G11B27/102 , G11B27/3027 , G11B27/3081
Abstract: A video identifier uniquely identifying a video captured by a camera is generated. The video includes video frames and optionally concurrently captured audio as well as video metadata describing the video. Video data is extracted from at least two of the video's frames. By combining the extracted video data in an order specified by an identifier generation protocol, an extracted data object is generated. The extracted data object is hashed to generate the unique media identifier, which is stored in association with the video. The identifier generation protocol may indicate the portions of the video data to extract, such as video data corresponding to particular video frames and audio data corresponding to particular audio samples. The extracted data object may include a size of particular video frames, a number of audio samples in the video, or the duration of the video, for example.
Abstract translation: 生成唯一地识别由相机拍摄的视频的视频标识符。 视频包括视频帧和可选地同时捕获的音频以及描述视频的视频元数据。 从视频的至少两个帧中提取视频数据。 通过以由标识符生成协议指定的顺序组合提取的视频数据，生成提取的数据对象。 所提取的数据对象被散列以生成与视频相关联地存储的唯一媒体标识符。 标识符生成协议可以指示要提取的视频数据的部分，例如对应于特定视频帧的视频数据和对应于特定音频样本的音频数据。 所提取的数据对象可以包括例如特定视频帧的大小，视频中的多个音频样本，或视频的持续时间。
-
83.发明申请Scene and Activity Identification in Video Summary Generation Based on Motion Detected in a Video 有权基于视频中检测到的运动的视频摘要生成中的场景和活动识别公开(公告)号：US20160055381A1
公开(公告)日：2016-02-25
申请号：US14705864
申请日：2015-05-06
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Ryan Lustig , David A. Newman
IPC: G06K9/00 , G11B27/031 , G11B27/30
CPC classification number: G11B27/10 , G06K9/00718 , G06K9/00751 , G06K2009/00738 , G10L15/063 , G10L15/22 , G10L25/54 , G10L25/57 , G10L2015/0631 , G10L2015/223 , G11B27/031 , G11B27/13 , G11B27/28 , G11B27/3081 , G11B27/34 , H04N5/77 , H04N5/772 , H04N5/91 , H04N9/8205
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. In one example, best scenes are identified based on the motion values associated with frames or portions of a frame of a video. Motion values are determined for each frame and portions of the video including frames with the most motion are identified as best scenes. Best scenes may also be identified based on the motion profile of a video. The motion profile of a video is a measure of global or local motion within frames throughout the video. For example, best scenes are identified from portion of the video including steady global motion. A video summary can be generated including one or more of the identified best scenes.
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。 在一个示例中，基于与帧或帧的视频的一部分相关联的运动值来识别最佳场景。 为每个帧确定运动值，并且包括具有最大运动的帧的视频的部分被识别为最佳场景。 还可以基于视频的运动配置文件来识别最佳场景。 视频的运动曲线是整个视频帧内全局或局部运动的度量。 例如，从包括稳定的全局运动的视频的部分中识别最佳场景。 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。
-
公开(公告)号：US20150281305A1
公开(公告)日：2015-10-01
申请号：US14675442
申请日：2015-03-31
Applicant: GoPro, Inc.
Inventor： Otto K. Sievert , Todd C. Mason , David A. Newman , Paul D. Osborne , Nicholas D. Woodman , Eric Wiggins , Jeffrey S. Youel , David Dudas
CPC classification number: H04L65/602 , G11B27/031 , G11B27/30 , H04L65/607 , H04L65/80 , H04N5/23254 , H04N19/162 , H04N19/164 , H04N19/17 , H04N19/40 , H04N19/46 , H04N19/59 , H04N21/2743 , H04N21/4223 , H04N21/440263 , H04N21/4424 , H04N21/47205 , H04N21/6543 , H04N21/6547
Abstract: A cloud video system selectively uploads a high-resolution video and instructs one or more client devices to perform distributed processing on the high-resolution video. A client device registers high-resolution videos accessed by the client device from a camera communicatively coupled to the client device. A portion of interest within a low-resolution video transcoded from the high-resolution video is selected. A task list is generated specifying the selected portion of the high-resolution video and at least one task to perform on the portion of the high-resolution video. Commands are transmitted to prompt the client device to perform the at least one task on the specified portion of the high-resolution video according to the task list. The specified portion of the high-resolution video is modified according to the task list and uploaded to the cloud. Example tasks include transcoding, applying edits, extracting metadata, and generating highlight tags.
Abstract translation: 云视频系统选择性地上传高分辨率视频并指示一个或多个客户端设备对高分辨率视频执行分布式处理。 客户端设备将客户端设备访问的高分辨率视频从通信耦合到客户端设备的相机注册。 选择从高分辨率视频转码的低分辨率视频中的感兴趣部分。 生成任务列表，指定高分辨率视频的所选部分和要在高分辨率视频的一部分上执行的至少一个任务。 发送命令以提示客户端设备根据任务列表在高分辨率视频的指定部分上执行至少一个任务。 高分辨率视频的指定部分根据任务列表进行修改并上传到云端。 示例任务包括转码，应用编辑，提取元数据和生成高亮标记。
-
公开(公告)号：US20150271421A1
公开(公告)日：2015-09-24
申请号：US14606019
申请日：2015-01-27
Applicant: GoPro, Inc.
Inventor： Timothy MacMillan , Scott Patrick Campbell , David A. Newman , Yajie Sun
CPC classification number: H04N13/246 , H04N5/23203 , H04N5/23238 , H04N5/247 , H04N5/265 , H04N5/3532 , H04N13/00 , H04N13/239 , H04N13/296 , H04N17/002
Abstract: A pair of cameras having an overlapping field of view is aligned based on images captured by image sensors of the pair of cameras. A pixel shift is identified between the images. Based on the identified pixel shift, a calibration is applied to one or both of the pair of cameras. To determine the pixel shift, the camera applies correlation methods including edge matching. Calibrating the pair of cameras may include adjusting a read window on an image sensor. The pixel shift can also be used to determine a time lag, which can be used to synchronize subsequent image captures.
Abstract translation: 具有重叠视野的一对相机基于由该对相机的图像传感器捕获的图像来对准。 在图像之间识别像素漂移。 基于所识别的像素偏移，校准被应用于该对照相机中的一个或两个。 为了确定像素偏移，相机应用包括边缘匹配的相关方法。 校准一对相机可能包括调整图像传感器上的读取窗口。 像素偏移也可用于确定时间滞后，可用于同步后续图像捕获。
-
Patent Agency Ranking
公开(公告)号：US20150256808A1
公开(公告)日：2015-09-10
申请号：US14637180
申请日：2015-03-03
Applicant: GoPro, Inc.
Inventor： Timothy MacMillan , David A. Newman , Balineedu Chowdary Adsumilli , Scott Patrick Campbell
CPC classification number: H04N5/23238 , G03B37/04 , G06F17/30858 , G06K9/00281 , G06K9/00355 , G06K9/00711 , G06T3/0062 , G06T7/246 , G06T2207/10016 , G06T2207/30201 , H04L65/00 , H04L65/4084 , H04L65/602 , H04L67/42 , H04N13/106 , H04N21/233 , H04N21/23418
Abstract: A spherical content capture system captures spherical video content. A spherical video sharing platform enables users to share the captured spherical content and enables users to access spherical content shared by other users. 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.
Abstract translation: 球面内容捕获系统捕获球面视频内容。 一个球面视频共享平台使用户能够共享所捕获的球面内容，并使用户能够访问其他用户共享的球面内容。 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。
-
公开(公告)号：US09025896B2
公开(公告)日：2015-05-05
申请号：US14504326
申请日：2014-10-01
Applicant: GoPro, Inc.
Inventor： David A. Newman
IPC: G06K9/36 , G06K9/46 , H04N5/232 , H04N1/64 , H04N9/04 , G06T9/00 , H04N19/117 , H04N19/136 , H04N19/186 , H04N19/44 , G06F3/0484
CPC classification number: H04N5/23293 , G06F3/0484 , G06K9/36 , G06T9/00 , H04N1/648 , H04N5/23245 , H04N5/265 , H04N9/045 , H04N19/117 , H04N19/136 , H04N19/186 , H04N19/44 , H04N19/85
Abstract: A method is described to greatly improve the efficiency of and reduce the complexity of image compression when using single-sensor color imagers for video acquisition. The method in addition allows for this new image compression type to be compatible with existing video processing tools, improving the workflow for film and television production.
Abstract translation: 描述了一种方法，以便在使用单传感器彩色成像器进行视频采集时，大大提高图像压缩效率并降低图像压缩的复杂度。 该方法另外允许这种新的图像压缩类型与现有的视频处理工具兼容，从而改善电影和电视制作的工作流程。
-
公开(公告)号：US08988509B1
公开(公告)日：2015-03-24
申请号：US14221254
申请日：2014-03-20
Applicant: GoPro, Inc.
Inventor： Timothy Macmillan , Scott Patrick Campbell , David A. Newman , Yajie Sun
CPC classification number: H04N13/246 , H04N5/23203 , H04N5/23238 , H04N5/247 , H04N5/265 , H04N5/3532 , H04N13/00 , H04N13/239 , H04N13/296 , H04N17/002
Abstract: A pair of cameras having an overlapping field of view is aligned based on images captured by image sensors of the pair of cameras. A pixel shift is identified between the images. Based on the identified pixel shift, a calibration is applied to one or both of the pair of cameras. To determine the pixel shift, the camera applies correlation methods including edge matching. Calibrating the pair of cameras may include adjusting a read window on an image sensor. The pixel shift can also be used to determine a time lag, which can be used to synchronize subsequent image captures.
Abstract translation: 具有重叠视野的一对相机基于由该对相机的图像传感器捕获的图像来对准。 在图像之间识别像素漂移。 基于所识别的像素偏移，校准被应用于该对照相机中的一个或两个。 为了确定像素偏移，相机应用包括边缘匹配的相关方法。 校准一对相机可能包括调整图像传感器上的读取窗口。 像素偏移也可用于确定时间滞后，可用于同步后续图像捕获。
-
公开(公告)号：US20150010286A1
公开(公告)日：2015-01-08
申请号：US14340873
申请日：2014-07-25
Applicant: GoPro, Inc.
Inventor： David A. Newman , Brian G. Schunck
IPC: G11B27/028 , G11B27/00 , G11B20/00
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.
-
公开(公告)号：US12267616B2
公开(公告)日：2025-04-01
申请号：US18415279
申请日：2024-01-17
Applicant: GoPro, Inc.
Inventor： David A. Newman
IPC: H04N5/262 , G11B27/034 , H04N23/68
Abstract: Methods and apparatus for metadata-based cinematography, production effects, shot selection, and/or other content augmentation. Effective cinematography conveys storyline, emotion, excitement, etc. Unfortunately, most amateur filmmakers lack the knowledge and ability to create cinema quality media. Various aspects of the present disclosure are directed to, among other things, rendering media based on instantaneous metadata. Unlike traditional post-processing techniques that rely on human subjectivity, some of the various techniques described herein leverage the camera's actual experiential data to enable cinema-quality post-processing for the general consuming public. Instantaneous metadata-based cinematography and shot selection advisories and architectures are also described.
-
-
-
-
-
-
-
-
-
Search Results
164
records
(took 0.025 seconds)
