-
公开(公告)号：US10817977B2
公开(公告)日：2020-10-27
申请号：US16884962
申请日：2020-05-27
Applicant: GoPro, Inc.
Inventor： David A. Newman , Joshua Edward Bodinet , Otto Kenneth Sievert , Timothy MacMillan
Abstract: In a video capture system, a virtual lens is simulated when applying a crop or zoom effect to an input video. An input video frame is received from the input video that has a first field of view and an input lens distortion caused by a lens used to capture the input video frame. A selection of a sub-frame representing a portion of the input video frame is obtained that has a second field of view smaller than the first field of view. The sub-frame is processed to remap the input lens distortion to a desired lens distortion in the sub-frame. The processed sub-frame is the outputted.
-
公开(公告)号：US20200286204A1
公开(公告)日：2020-09-10
申请号：US16884962
申请日：2020-05-27
Applicant: GoPro, Inc.
Inventor： David A. Newman , Joshua Edward Bodinet , Otto Kenneth Sievert , Timothy MacMillan
Abstract: In a video capture system, a virtual lens is simulated when applying a crop or zoom effect to an input video. An input video frame is received from the input video that has a first field of view and an input lens distortion caused by a lens used to capture the input video frame. A selection of a sub-frame representing a portion of the input video frame is obtained that has a second field of view smaller than the first field of view. The sub-frame is processed to remap the input lens distortion to a desired lens distortion in the sub-frame. The processed sub-frame is the outputted.
-
公开(公告)号：US10529052B2
公开(公告)日：2020-01-07
申请号：US16535940
申请日：2019-08-08
Applicant: GoPro, Inc.
Inventor： David A. Newman , Joshua Edward Bodinet , Otto Kenneth Sievert , Timothy MacMillan
Abstract: In a video capture system, a virtual lens is simulated when applying a crop or zoom effect to an input video. An input video frame is received from the input video that has a first field of view and an input lens distortion caused by a lens used to capture the input video frame. A selection of a sub-frame representing a portion of the input video frame is obtained that has a second field of view smaller than the first field of view. The sub-frame is processed to remap the input lens distortion to a desired lens distortion in the sub-frame. The processed sub-frame is the outputted.
-
公开(公告)号：US20190362462A1
公开(公告)日：2019-11-28
申请号：US16535886
申请日：2019-08-08
Applicant: GoPro, Inc.
Inventor： David A. Newman , Joshua Edward Bodinet , Otto Kenneth Sievert , Timothy MacMillan
Abstract: In a video capture system, a virtual lens is simulated when applying a crop or zoom effect to an input video. An input video frame is received from the input video that has a first field of view and an input lens distortion caused by a lens used to capture the input video frame. A selection of a sub-frame representing a portion of the input video frame is obtained that has a second field of view smaller than the first field of view. The sub-frame is processed to remap the input lens distortion to a desired lens distortion in the sub-frame. The processed sub-frame is the outputted.
-
公开(公告)号：US09965883B2
公开(公告)日：2018-05-08
申请号：US15724532
申请日：2017-10-04
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Timothy MacMillan
CPC classification number: G06T11/60 , G06T3/4038 , G06T7/50 , G06T7/73 , G06T2207/20021 , G06T2207/20221 , G06T2207/30244
Abstract: A unified image processing algorithm results in better post-processing quality for combined images that are made up of multiple single-capture images. To ensure that each single-capture image is processed in the context of the entire combined image, the combined image is analyzed to determine portions of the image (referred to as “zones”) that should be processed with the same parameters for various image processing algorithms. These zones may be determined based on the content of the combined image. Alternatively, these zones may be determined based on the position of each single-capture image with respect to the entire combined image or the other single-capture images. Once zones and their corresponding image processing parameters are determined for the combined image, they are translated to corresponding zones each of the single-capture images. Finally, the image processing algorithms are applied to each of the single-capture images using the zone-specified parameters.
-
Patent Agency Ranking
公开(公告)号：US09786077B2
公开(公告)日：2017-10-10
申请号：US14872063
申请日：2015-09-30
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Timothy MacMillan
CPC classification number: G06T11/60 , G06T3/4038 , G06T7/50 , G06T7/73 , G06T2207/20021 , G06T2207/20221 , G06T2207/30244
Abstract: A unified image processing algorithm results in better post-processing quality for combined images that are made up of multiple single-capture images. To ensure that each single-capture image is processed in the context of the entire combined image, the combined image is analyzed to determine portions of the image (referred to as “zones”) that should be processed with the same parameters for various image processing algorithms. These zones may be determined based on the content of the combined image. Alternatively, these zones may be determined based on the position of each single-capture image with respect to the entire combined image or the other single-capture images. Once zones and their corresponding image processing parameters are determined for the combined image, they are translated to corresponding zones each of the single-capture images. Finally, the image processing algorithms are applied to each of the single-capture images using the zone-specified parameters.
-
公开(公告)号：US09652667B2
公开(公告)日：2017-05-16
申请号：US14637193
申请日：2015-03-03
Applicant: GoPro, Inc.
Inventor： Timothy MacMillan , David A. Newman , Balineedu Chowdary Adsumilli
IPC: H04N5/93 , G06K9/00 , G06T3/00 , H04N21/233 , H04N21/234 , G06F17/30 , H04L29/06 , H04N13/00 , G03B37/04 , H04N5/232
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.
-
公开(公告)号：US09571759B1
公开(公告)日：2017-02-14
申请号：US14872017
申请日：2015-09-30
Applicant: GoPro, Inc.
Inventor： Balineedu Chowdary Adsumilli , Timothy MacMillan
CPC classification number: H04N5/3415 , G01B2210/52 , G03G15/36 , G06T5/008 , G06T2207/20208 , H04N5/23238 , H04N5/247 , H04N5/265 , H04N5/355 , H04N9/646 , H04N9/77
Abstract: Use of separate range tone mapping for combined images can help minimize loss of image information in scenes that have drastically different luminance values, i.e., scenes that have both bright and shadowed regions. Separate range tone mapping is particularly useful for combined images, such as those from spherical camera systems, which may have a higher probability of including luminance variability. The resulting increased bit depth of separate range tone mapping can make the transition between different images that make up a combined image more subtle. Each of a plurality of images that make up a combined image can use a different tone map that is optimized for the particular image data of the image. Multiple tone maps that are applied to overlapping regions of the plurality of images can subsequently be combined to expand the bit depth of the overlapping regions.
Abstract translation: 对于组合图像使用单独的范围色调映射可以帮助最小化具有极大不同的亮度值的场景中的图像信息的损失，即，具有明亮区域和阴影区域的场景。 单独的范围色调映射对于诸如来自球面照相机系统的组合图像特别有用，其可以具有更高的包括亮度变化的概率。 分离范围色调映射的结果增加的位深度可以使构成组合图像的不同图像之间的转换更微妙。 构成组合图像的多个图像中的每一个可以使用针对图像的特定图像数据而优化的不同色调图。 随后可以组合应用于多个图像的重叠区域的多个色调图以扩大重叠区域的位深度。
-
公开(公告)号：US20160142655A1
公开(公告)日：2016-05-19
申请号：US14921399
申请日：2015-10-23
Applicant: GoPro, Inc.
Inventor： Timothy MacMillan , Scott Patrick Campbell
CPC classification number: H04N5/3415 , G06T3/0068 , G06T3/0093 , G06T3/4038 , G06T5/006 , G06T5/50 , G06T7/344 , G06T2207/10004 , G06T2207/20128 , G06T2207/20221 , G06T2210/22 , H04N5/2252 , H04N5/2253 , H04N5/2257 , H04N5/2258 , H04N5/23216 , H04N5/23229 , H04N5/23232 , H04N5/23238 , H04N5/247 , H04N5/2624 , H04N5/2628
Abstract: Multiple cameras are arranged in an array at a pitch, roll, and yaw that allow the cameras to have adjacent fields of view such that each camera is pointed inward relative to the array. The read window of an image sensor of each camera in a multi-camera array can be adjusted to minimize the overlap between adjacent fields of view, to maximize the correlation within the overlapping portions of the fields of view, and to correct for manufacturing and assembly tolerances. Images from cameras in a multi-camera array with adjacent fields of view can be manipulated using low-power warping and cropping techniques, and can be taped together to form a final image.
Abstract translation: 多个相机以阵列，俯仰和偏转方式布置，允许相机具有相邻的视野，使得每个相机相对于阵列向内指向。 可以调整多相机阵列中每个相机的图像传感器的读取窗口，以使相邻视场之间的重叠最小化，以使视场的重叠部分之间的相关性最大化，并纠正制造和组装 公差。 可以使用低功率翘曲和裁剪技术来操纵具有相邻视场的多相机阵列中的相机的图像，并且可以将其粘贴在一起以形成最终图像。
-
公开(公告)号：US09330436B2
公开(公告)日：2016-05-03
申请号：US14308495
申请日：2014-06-18
Applicant: GoPro, Inc.
Inventor： Timothy MacMillan , Scott Patrick Campbell
IPC: G06T3/00 , G06T7/00 , G06T3/40 , H04N5/232 , H04N5/225 , H04N5/247 , G06T5/00 , H04N5/262 , G06T5/50 , H04N5/341
CPC classification number: H04N5/3415 , G06T3/0068 , G06T3/0093 , G06T3/4038 , G06T5/006 , G06T5/50 , G06T7/344 , G06T2207/10004 , G06T2207/20128 , G06T2207/20221 , G06T2210/22 , H04N5/2252 , H04N5/2253 , H04N5/2257 , H04N5/2258 , H04N5/23216 , H04N5/23229 , H04N5/23232 , H04N5/23238 , H04N5/247 , H04N5/2624 , H04N5/2628
Abstract: Multiple cameras are arranged in an array at a pitch, roll, and yaw that allow the cameras to have adjacent fields of view such that each camera is pointed inward relative to the array. The read window of an image sensor of each camera in a multi-camera array can be adjusted to minimize the overlap between adjacent fields of view, to maximize the correlation within the overlapping portions of the fields of view, and to correct for manufacturing and assembly tolerances. Images from cameras in a multi-camera array with adjacent fields of view can be manipulated using low-power warping and cropping techniques, and can be taped together to form a final image.
Abstract translation: 多个相机以阵列，俯仰和偏转方式布置，允许相机具有相邻的视野，使得每个相机相对于阵列向内指向。 可以调整多相机阵列中每个相机的图像传感器的读取窗口，以使相邻视场之间的重叠最小化，以使视场的重叠部分之间的相关性最大化，并纠正制造和组装 公差。 可以使用低功率翘曲和裁剪技术来操纵具有相邻视场的多相机阵列中的相机的图像，并且可以将其粘贴在一起以形成最终图像。
-
-
-
-
-
-
-
-
-
Search Results
63
records
(took 0.033 seconds)
