-
公开(公告)号：US20160173778A1
公开(公告)日：2016-06-16
申请号：US15049015
申请日：2016-02-20
Applicant: GoPro, Inc.
Inventor： Scott Patrick Campbell , Paul Mobbs , Balineedu Chowdary Adsumilli , Sumit Chawla
CPC classification number: G06T1/20 , G06T3/4015 , H04N1/6019 , H04N1/6027 , H04N5/232 , H04N5/23212 , H04N5/23216 , H04N5/23222 , H04N5/23229 , H04N5/23241 , H04N5/23245 , H04N5/23254 , H04N5/23267 , H04N5/23296 , H04N5/2353 , H04N5/247 , H04N5/374 , H04N5/378 , H04N9/045 , H04N9/09 , H04N9/735 , H04N9/8042 , H04N19/102 , H04N19/12 , H04N19/132 , H04N19/156 , H04N19/164 , H04N19/172 , H04N19/186 , H04N19/1883 , H04N19/33 , H04N19/42 , H04N19/423 , H04N19/44 , H04N19/517 , H04N19/63 , H04N19/91
Abstract: An image capture accelerator performs accelerated processing of image data. In one embodiment, the image capture accelerator includes accelerator circuitry including a pre-processing engine and a compression engine. The pre-processing engine is configured to perform accelerated processing on received image data, and the compression engine is configured to compress processed image data received from the pre-processing engine. In one embodiment, the image capture accelerator further includes a demultiplexer configured to receive image data captured by an image sensor array implemented within, for example, an image sensor chip. The demultiplexer may output the received image data to an image signal processor when the image data is captured by the image sensor array in a standard capture mode, and may output the received image data to the accelerator circuitry when the image data is captured by the image sensor array in an accelerated capture mode.
Abstract translation: 图像捕获加速器执行图像数据的加速处理。 在一个实施例中，图像捕获加速器包括包括预处理引擎和压缩引擎的加速器电路。 预处理引擎被配置为对接收的图像数据执行加速处理，并且压缩引擎被配置为压缩从预处理引擎接收的经处理的图像数据。 在一个实施例中，图像捕获加速器还包括解复用器，其被配置为接收由例如图像传感器芯片内实现的图像传感器阵列捕获的图像数据。 当图像数据以标准捕捉模式被图像传感器阵列捕获时，解复用器可以将接收到的图像数据输出到图像信号处理器，并且当图像数据被图像捕获时，可以将接收到的图像数据输出到加速器电路 传感器阵列处于加速捕获模式。
-
公开(公告)号：US09355433B1
公开(公告)日：2016-05-31
申请号：US14754695
申请日：2015-06-30
Applicant: GoPro, Inc.
CPC classification number: G06T3/4038 , G06T3/0093 , G06T2207/20221
Abstract: Images captured by multi-camera arrays with overlap regions can be stitched together using image stitching operations. An image stitching operation can be selected for use in stitching images based on a number of factors. An image stitching operation can be selected based on a view window location of a user viewing the images to be stitched together. An image stitching operation can also be selected based on a type, priority, or depth of image features located within an overlap region. Finally, an image stitching operation can be selected based on a likelihood that a particular image stitching operation will produce visible artifacts. Once a stitching operation is selected, the images corresponding to the overlap region can be stitched using the stitching operation, and the stitched image can be stored for subsequent access.
Abstract translation: 使用重叠区域的多相机阵列拍摄的图像可以使用图像拼接操作拼接在一起。 可以基于多个因素来选择图像拼接操作以用于拼接图像。 可以基于观看要缝合的图像的用户的视窗位置来选择图像拼接操作。 还可以基于位于重叠区域内的图像特征的类型，优先级或深度来选择图像拼接操作。 最后，可以基于特定图像拼接操作将产生可见伪影的可能性来选择图像拼接操作。 一旦选择了缝合操作，就可以使用缝合操作来缝合与重叠区域相对应的图像，并且可以存储缝合图像以供后续访问。
-
123.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：US20160029004A1
公开(公告)日：2016-01-28
申请号：US14875690
申请日：2015-10-05
Applicant: GoPro, Inc.
Inventor： Scott Patrick Campbell , Balineedu Chowdary Adsumilli
CPC classification number: H04N13/204 , G06T5/002 , G06T7/571 , G06T7/593 , G06T2200/04 , G06T2207/10028 , G06T2207/10148 , H04N5/262 , H04N5/2621 , H04N13/122 , H04N13/271 , H04N2013/0081 , H04N2013/0088 , H04N2013/0096
Abstract: Blurring is simulated in post-processing for captured images. A 3D image is received from a 3D camera, and depth information in the 3D image is used to determine the relative distances of objects in the image. One object is chosen as the subject of the image, and an additional object in the image is identified. Image blur is applied to the identified additional object based on the distance between the 3D camera and the subject object, the distance between the subject object and the additional object, and a virtual focal length and virtual f-number.
Abstract translation: 在捕获图像的后处理中模拟模糊。 从3D摄像机接收3D图像，并且使用3D图像中的深度信息来确定图像中物体的相对距离。 选择一个对象作为图像的主题，并且识别图像中的附加对象。 基于3D摄像机与被摄对象之间的距离，被摄对象与附加对象之间的距离以及虚拟焦距和虚拟f数，将图像模糊应用于所识别的附加对象。
-
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。
-
Patent Agency Ranking
公开(公告)号：US11611699B2
公开(公告)日：2023-03-21
申请号：US17371371
申请日：2021-07-09
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Scott Patrick Campbell
Abstract: Images captured by multi-camera arrays with overlap regions can be stitched together using image stitching operations. An image stitching operation can be selected for use in stitching images based on a number of factors. An image stitching operation can be selected based on a view window location of a user viewing the images to be stitched together. An image stitching operation can also be selected based on a type, priority, or depth of image features located within an overlap region. Finally, an image stitching operation can be selected based on a likelihood that a particular image stitching operation will produce visible artifacts. Once a stitching operation is selected, the images corresponding to the overlap region can be stitched using the stitching operation, and the stitched image can be stored for subsequent access.
-
公开(公告)号：US20220103800A1
公开(公告)日：2022-03-31
申请号：US17545156
申请日：2021-12-08
Applicant: GoPro, Inc.
Inventor： Adeel Abbas , Balineedu Chowdary Adsumilli , David Newman
IPC: H04N13/161 , H04N13/111 , H04N13/194 , H04N13/243 , H04N13/282 , H04N5/232 , H04N19/597 , H04N13/344 , H04N5/225
Abstract: A device includes a processor that is configured to obtain first facets of a first wide field-of-view image. An object is identified in a facet of the first facets. A second wide field-of-view image is obtained. A location of the object is identified in the second wide field-of-view image. Using the location of the object, the second wide field-of-view image is partitioned into second facets such that no boundary of any of the second facets overlaps the object. The second facets are then encoded in a compressed bitstream.
-
公开(公告)号：US20210337118A1
公开(公告)日：2021-10-28
申请号：US17371371
申请日：2021-07-09
Applicant: GOPRO, INC.
Inventor： Balineedu Chowdary Adsumilli , Scott Patrick Campbell
Abstract: Images captured by multi-camera arrays with overlap regions can be stitched together using image stitching operations. An image stitching operation can be selected for use in stitching images based on a number of factors. An image stitching operation can be selected based on a view window location of a user viewing the images to be stitched together. An image stitching operation can also be selected based on a type, priority, or depth of image features located within an overlap region. Finally, an image stitching operation can be selected based on a likelihood that a particular image stitching operation will produce visible artifacts. Once a stitching operation is selected, the images corresponding to the overlap region can be stitched using the stitching operation, and the stitched image can be stored for subsequent access.
-
129.发明申请公开(公告)号：US20210218891A1
公开(公告)日：2021-07-15
申请号：US17215362
申请日：2021-03-29
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Adeel Abbas , Sumit Chawla
IPC: H04N5/232 , H04N19/597 , H04N19/122 , H04N19/115 , H04N19/117 , H04N19/126 , H04N19/167 , H04N19/57 , H04N13/243 , H04N13/296 , H04N13/178 , H04N13/344
Abstract: A method includes obtaining visual content comprising spatial portions; determining respective spatial qualities of the spatial portions, wherein the respective spatial qualities are based on locations of the spatial portions within the visual content; and encoding the spatial portions of the visual content based on the respective spatial qualities. An apparatus includes a camera, a display, and a processor. The processor is configured to identify, using facial recognition, a face of a user of the apparatus; identify a distance of the face of the user to the display; and render visual content on the display using a quality that is based on the distance.
-
130.发明授权公开(公告)号：US10965868B2
公开(公告)日：2021-03-30
申请号：US16363668
申请日：2019-03-25
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Adeel Abbas , Sumit Chawla
IPC: G06K9/00 , H04N5/232 , H04N19/597 , H04N19/122 , H04N19/115 , H04N19/117 , H04N19/126 , H04N19/167 , H04N19/57 , H04N13/243 , H04N13/296 , H04N13/178 , H04N13/344
Abstract: Methods and apparatus for encoding and decoding image data based on one or more parameters. In one embodiment, various spatial portions or regions of image data (e.g., a still or moving image) are weighted according to the perceived or measured quality. Processing for these weighted regions can be selectively altered or adjusted so as to optimize one or more operational parameters including for example processing and/or memory requirements, or speed.
-
-
-
-
-
-
-
-
-
Search Results
163
records
(took 0.019 seconds)
