公开(公告)号：US20170053392A1

公开(公告)日：2017-02-23

申请号：US15345002

申请日：2016-11-07

Applicant: GoPro, Inc.

Inventor： Yajie Sun ,  Timothy Macmillan ,  Elizabeth Torres Edwards ,  Sumit Chawla

IPC: G06T7/00 ,  G06T3/40 ,  G06T5/00

CPC classification number: G06T3/4038 ,  G06K9/4604 ,  G06K9/52 ,  G06K9/6201 ,  G06T5/002 ,  G06T7/13 ,  G06T7/337 ,  G06T7/80 ,  G06T7/85 ,  H04N5/23229 ,  H04N5/2329 ,  H04N5/349 ,  H04N5/374 ,  H04N13/239 ,  H04N13/246 ,  H04N13/271 ,  H04N13/296 ,  H04N17/002 ,  H04N2013/0081

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：US20170019606A1

公开(公告)日：2017-01-19

申请号：US15282306

申请日：2016-09-30

Applicant: GoPro, Inc.

Inventor： Scott Patrick Campbell ,  Paul Mobbs ,  Balineedu Chowdary Adsumilli ,  Sumit Chawla

IPC: H04N5/232 ,  H04N19/91 ,  H04N5/247 ,  G06T3/40 ,  H04N19/169 ,  H04N19/172

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：US09485417B2

公开(公告)日：2016-11-01

申请号：US15049011

申请日：2016-02-20

Applicant: GoPro, Inc.

Inventor： Scott Patrick Campbell ,  Paul Mobbs ,  Balineedu Chowdary Adsumilli ,  Sumit Chawla

IPC: H04N5/232 ,  H04N19/102 ,  H04N19/91 ,  H04N19/63 ,  H04N19/169 ,  G06T3/40 ,  H04N5/378 ,  H04N9/04 ,  H04N5/235 ,  H04N9/73 ,  H04N19/164 ,  H04N19/172 ,  H04N5/247

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：US20160173785A1

公开(公告)日：2016-06-16

申请号：US15049011

申请日：2016-02-20

Applicant: GoPro, Inc.

Inventor： Scott Patrick Campbell ,  Paul Mobbs ,  Balineedu Chowdary Adsumilli ,  Sumit Chawla

IPC: H04N5/232 ,  H04N19/169 ,  H04N5/247

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：US09294671B2

公开(公告)日：2016-03-22

申请号：US14536315

申请日：2014-11-07

Applicant: GoPro, Inc.

Inventor： Nicholas D. Woodman ,  Sumit Chawla ,  Loic Segapelli ,  Scott Patrick Campbell

IPC: H04N5/228 ,  H04N5/232 ,  H04N21/2343 ,  H04N21/4402 ,  H04N5/262

CPC classification number: H04N5/2628 ,  G06T3/0093 ,  G06T3/20 ,  G06T3/40 ,  G06T3/4069 ,  G06T3/4084 ,  G09G5/005 ,  G09G2340/0442 ,  H04N5/23229 ,  H04N7/0122 ,  H04N21/234372 ,  H04N21/440272

Abstract: A camera system captures an image in a source aspect ratio and applies a transformation to the input image to scale and warp the image to generate an output image having a target aspect ratio different than the source aspect ratio. The output image has the same field of view as the input image, maintains image resolution, and limits distortion to levels that do not substantially affect the viewing experience. In one embodiment, the output image is non-linearly warped relative to the input image such that a distortion in the output image relative to the input image is greater in a corner region of the output image than a center region of the output image.

Abstract translation: 相机系统以源宽高比捕获图像，并且对输入图像应用变换以缩放和扭曲图像以生成具有不同于源宽高比的目标纵横比的输出图像。 输出图像与输入图像具有相同的视野，保持图像分辨率，并将失真限制到不会对观看体验产生实质影响的水平。 在一个实施例中，输出图像相对于输入图像非线性翘曲，使得输出图像中相对于输入图像的失真在输出图像的拐角区域中大于输出图像的中心区域。

公开(公告)号：US20150271398A1

公开(公告)日：2015-09-24

申请号：US14521460

申请日：2014-10-22

Applicant: GoPro, Inc.

Inventor： Sumit Chawla ,  Elizabeth Torres Edwards ,  Ying Chen

IPC: H04N5/232 ,  H04N9/69 ,  H04N9/64 ,  H04N9/04

CPC classification number: H04N9/643 ,  H04N1/6033 ,  H04N9/68

Abstract: The conversion of RAW data captured by a camera can have artifacts in smoothness of various hues for varying chroma. To optimize smoothness and color accuracy, transform coefficients defining conversion of a standard color model to a target color model are determined. The RAW data is converted to data in a standard color model and the data in the standard color model is converted to data in the target color model using the transform coefficients. The process is repeated for various lightness levels and combined into a look up table to efficiently convert RAW data to data in the target color model for various lightness levels.

Abstract translation: 由相机拍摄的RAW数据的转换可以具有用于变化色度的各种色调的平滑度的伪影。 为了优化平滑度和颜色精度，确定将标准颜色模型的转换定义为目标颜色模型的变换系数。 将RAW数据转换为标准颜色模型中的数据，并使用变换系数将标准颜色模型中的数据转换为目标颜色模型中的数据。 对于各种亮度级别重复该过程并组合成查找表，以有效地将RAW数据转换为目标颜色模型中的数据，以获得各种亮度级别。

公开(公告)号：US11722631B2

公开(公告)日：2023-08-08

申请号：US17536699

申请日：2021-11-29

Applicant: GoPro, Inc.

Inventor： Nicholas D. Woodman ,  Sumit Chawla ,  Loic Segapelli ,  Scott Patrick Campbell

IPC: H04N5/262 ,  H04N21/2343 ,  G09G5/00 ,  H04N7/01 ,  H04N23/80 ,  G06T3/00 ,  G06T3/40 ,  H04N21/4402 ,  G06T3/20

CPC classification number: H04N5/2628 ,  G06T3/0093 ,  G06T3/4069 ,  G09G5/005 ,  H04N7/0122 ,  H04N21/234372 ,  H04N23/80 ,  G06T3/20 ,  G06T3/40 ,  G06T3/4084 ,  G09G2340/0442 ,  H04N21/440272

Abstract: A camera system captures an image in a source aspect ratio and applies a transformation to the input image to scale and warp the input image to generate an output image having a target aspect ratio different than the source aspect ratio. The output image has the same field of view as the input image, maintains image resolution, and limits distortion to levels that do not substantially affect the viewing experience. In one embodiment, the output image is non-linearly warped relative to the input image such that a distortion in the output image relative to the input image is greater in a corner region of the output image than a center region of the output image.

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.

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.

公开(公告)号：US20190327426A1

公开(公告)日：2019-10-24

申请号：US16456613

申请日：2019-06-28

Applicant: GoPro, Inc.

Inventor： Nicholas D. Woodman ,  Sumit Chawla ,  Loic Segapelli ,  Scott Patrick Campbell

IPC: H04N5/262 ,  H04N21/2343 ,  G09G5/00 ,  G06T3/40 ,  G06T3/00 ,  H04N7/01 ,  H04N5/232

Abstract: A camera system captures an image in a source aspect ratio and applies a transformation to the input image to scale and warp the input image to generate an output image having a target aspect ratio different than the source aspect ratio. The output image has the same field of view as the input image, maintains image resolution, and limits distortion to levels that do not substantially affect the viewing experience. In one embodiment, the output image is non-linearly warped relative to the input image such that a distortion in the output image relative to the input image is greater in a corner region of the output image than a center region of the output image.