-
公开(公告)号：US10701282B2
公开(公告)日：2020-06-30
申请号：US14749483
申请日：2015-06-24
Applicant: Intel Corporation
Inventor： Maha El Choubassi , Yan Xu , Alexey M. Supikov , Oscar Nestares
IPC: H04N5/262 , H04N5/222 , G06T15/20 , H04N13/111 , H04N13/271 , H04N13/207 , G06T7/50
Abstract: A plurality of frames of a video recorded by a video camera and depth maps of the plurality of frames are stored in a data storage. One or more target video camera positions are determined. Each frame of the plurality of frames is associated with one or more of the target video camera positions. For each frame, one or more synthesized frames from the viewpoint of the one or more target camera positions associated with that frame are generated by applying a view interpolation algorithm to that frame using the color pixels of that frame and the depth map of that frame. Users can provide their input about the new camera positions and other camera parameters through multiple input modalities. The synthesized frames are concatenated to create a modified video. Other embodiments are also described and claimed.
-
Patent Agency Ranking
公开(公告)号：US20190095670A1
公开(公告)日：2019-03-28
申请号：US16127929
申请日：2018-09-11
Applicant: Intel Corporation
Inventor： Yan Xu , Maha El Choubassi , Joshua Ratcliff
Abstract: This application is directed to dynamic control for data capture. A device may comprise a capture logic module to receive at least one of biometric data from a biometric sensing module, context data from a context sensing module or content data from a content sensing module. The capture logic module may determine if a capture scenario exists based on at least one of the biometric data and context data. The determination may be weighted based on an operational mode. If a capture scenario is determined to exist, the capture logic module may then determine whether to capture data based on at least the content data. Captured data may be stored in a capture database in the device (e.g., along with enhanced metadata based on at least one of the biometric data, the context data or the content data). The device may also comprise a feedback database including feedback data.
-
公开(公告)号：US09262696B2
公开(公告)日：2016-02-16
申请号：US14127952
申请日：2013-10-30
Applicant: INTEL CORPORATION
Inventor： Joshua J. Ratcliff , Ronald T. Azuma , Yan Xu , Gheric Speiginer
CPC classification number: G06K9/627 , G06K9/4671 , G06T7/00 , G06T7/66 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/30168 , H04N5/232 , H04N5/23222 , H04N5/23293
Abstract: Embodiments for image capture feedback are disclosed. In some embodiments, a computing system may receive a first image from an image capture device and generate a score for the first image. The computing system may generate a recommendation for an action, such that if the image capture device captures a second image after the action is performed, the score for the second image will be better than the score for the first image. The computing system may indicate the recommended action to the user on an output device. Other embodiments may be disclosed and/or claimed.
Abstract translation: 公开了用于图像捕获反馈的实施例。 在一些实施例中，计算系统可以从图像捕获设备接收第一图像并生成第一图像的得分。 计算系统可以产生针对动作的建议，使得如果在执行动作之后图像捕获设备捕获第二图像，则第二图像的得分将优于第一图像的得分。 计算系统可以在输出设备上向用户指示推荐的动作。 可以公开和/或要求保护其他实施例。
-
公开(公告)号：US20150178592A1
公开(公告)日：2015-06-25
申请号：US14127952
申请日：2013-10-30
Applicant: INTEL CORPORATION
Inventor： Joshua J. Ratcliff , Ronald T. Azuma , Yan Xu , Gheric Speiginer
CPC classification number: G06K9/627 , G06K9/4671 , G06T7/00 , G06T7/66 , G06T2207/10016 , G06T2207/10024 , G06T2207/10028 , G06T2207/30168 , H04N5/232 , H04N5/23222 , H04N5/23293
Abstract: Embodiments for image capture feedback are disclosed. In some embodiments, a computing system may receive a first image from an image capture device and generate a score for the first image. The computing system may generate a recommendation for an action, such that if the image capture device captures a second image after the action is performed, the score for the second image will be better than the score for the first image. The computing system may indicate the recommended action to the user on an output device. Other embodiments may be disclosed and/or claimed.
Abstract translation: 公开了用于图像捕获反馈的实施例。 在一些实施例中，计算系统可以从图像捕获设备接收第一图像并生成第一图像的得分。 计算系统可以产生针对动作的建议，使得如果在执行动作之后图像捕获设备捕获第二图像，则第二图像的得分将优于第一图像的得分。 计算系统可以在输出设备上向用户指示推荐的动作。 可以公开和/或要求保护其他实施例。
-
公开(公告)号：US10074003B2
公开(公告)日：2018-09-11
申请号：US14329711
申请日：2014-07-11
Applicant: Intel Corporation
Inventor： Yan Xu , Maha El Choubassi , Joshua Ratcliff
CPC classification number: G06K9/0002 , G06F1/3206 , G06F1/325 , G06F16/51 , G06F21/32 , G06F2203/011 , G06F2216/01 , G06F2216/03 , G06K9/00885 , G06K9/2054 , H04N5/225 , H04N5/23219 , H04N5/23222 , H04N5/23241 , H04N2101/00
Abstract: This application is directed to dynamic control for data capture. A device may comprise a capture logic module to receive at least one of biometric data from a biometric sensing module, context data from a context sensing module or content data from a content sensing module. The capture logic module may determine if a capture scenario exists based on at least one of the biometric data and context data. The determination may be weighted based on an operational mode. If a capture scenario is determined to exist, the capture logic module may then determine whether to capture data based on at least the content data. Captured data may be stored in a capture database in the device (e.g., along with enhanced metadata based on at least one of the biometric data, the context data or the content data). The device may also comprise a feedback database including feedback data.
-
公开(公告)号：US20160381341A1
公开(公告)日：2016-12-29
申请号：US14749483
申请日：2015-06-24
Applicant: Intel Corporation
Inventor： Maha El Choubassi , Yan Xu , Alexey M. Supikov , Oscar Nestares
Abstract: A plurality of frames of a video recorded by a video camera and depth maps of the plurality of frames are stored in a data storage. One or more target video camera positions are determined. Each frame of the plurality of frames is associated with one or more of the target video camera positions. For each frame, one or more synthesized frames from the viewpoint of the one or more target camera positions associated with that frame are generated by applying a view interpolation algorithm to that frame using the color pixels of that frame and the depth map of that frame. Users can provide their input about the new camera positions and other camera parameters through multiple input modalities. The synthesized frames are concatenated to create a modified video. Other embodiments are also described and claimed.
Abstract translation: 由摄像机记录的视频的多个帧和多个帧的深度图被存储在数据存储器中。 确定一个或多个目标摄像机位置。 多个帧中的每个帧与目标摄像机位置中的一个或多个相关联。 对于每个帧，通过使用该帧的颜色像素和该帧的深度图对该帧应用视图插值算法来生成与该帧相关联的一个或多个目标摄像机位置的视点的一个或多个合成帧。 用户可以通过多种输入模式提供有关新相机位置和其他相机参数的输入。 合成的帧被级联以创建修改的视频。 还描述和要求保护其他实施例。
-
-
-
-
-
Search Results
6
records
(took 0.03 seconds)
