-
公开(公告)号:US20220284554A1
公开(公告)日:2022-09-08
申请号:US17751981
申请日:2022-05-24
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Bruno Faure , Vincent Vacquerie , Bruno César Douady
Abstract: Image analysis and processing may include a first sensor readout unit receiving first Bayer format image data corresponding to a first input image, a second sensor readout unit receiving second Bayer format image data corresponding to a second input image, a first Bayer-to-RGB unit obtaining first RGB format image data based on the first Bayer format image data, a second Bayer-to-RGB unit obtaining second RGB format image data based on the second Bayer format image data, a high dynamic range unit configured obtaining high dynamic range image data based on a combination of the first RGB format image data and the second RGB format image data, an RGB-to-YUV unit obtaining YUV format image data based on the high dynamic range image data, and a three-dimensional noise reduction unit obtaining processed image data based on the YUV format image data.
-
公开(公告)号:US20210073956A1
公开(公告)日:2021-03-11
申请号:US16968707
申请日:2019-02-11
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Bruno Faure , Vincent Vacquerie , Bruno César Douady
Abstract: Image analysis and processing may include a first sensor readout unit configured to receive first Bayer format image data, a second sensor readout unit configured to receive second Bayer format image data, a first Bayer-to-RGB unit configured to obtain first RGB format image data based on the first Bayer format image data, a second Bayer-to-RGB unit configured to obtain second RGB format image data based on the second Bayer format image data, a high dynamic range unit configured to obtain high dynamic range image data based on a combination of the first RGB format image data and the second RGB format image data, an RGB-to-YUV unit configured to obtain YUV format image data based on the high dynamic range image data, and a three-dimensional noise reduction unit configured to obtain noise reduced image data based on the YUV format image data.
-
公开(公告)号:US11908111B2
公开(公告)日:2024-02-20
申请号:US17751981
申请日:2022-05-24
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Bruno Faure , Vincent Vacquerie , Bruno César Douady
CPC classification number: G06T5/009 , G06T3/40 , G06T5/002 , G06T5/003 , G06T5/50 , G06T9/00 , H04N9/646 , H04N23/10 , G06T2207/10016 , G06T2207/10024 , G06T2207/20208
Abstract: Image analysis and processing may include a first sensor readout unit receiving first Bayer format image data corresponding to a first input image, a second sensor readout unit receiving second Bayer format image data corresponding to a second input image, a first Bayer-to-RGB unit obtaining first RGB format image data based on the first Bayer format image data, a second Bayer-to-RGB unit obtaining second RGB format image data based on the second Bayer format image data, a high dynamic range unit configured obtaining high dynamic range image data based on a combination of the first RGB format image data and the second RGB format image data, an RGB-to-YUV unit obtaining YUV format image data based on the high dynamic range image data, and a three-dimensional noise reduction unit obtaining processed image data based on the YUV format image data.
-
公开(公告)号:US20190230274A1
公开(公告)日:2019-07-25
申请号:US16368974
申请日:2019-03-29
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Antoine Regimbeau , Thomas Nicolas Emmanuel Veit , Bruno César Douady-Pleven , Violaine Marie Mong-lan Sudret
CPC classification number: H04N5/2355 , G06T5/008 , G06T5/009 , G06T5/50 , G06T2207/20028 , H04N5/23229
Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.
-
公开(公告)号:US20160366309A1
公开(公告)日:2016-12-15
申请号:US15081688
申请日:2016-03-25
Applicant: GoPro, Inc.
Inventor: Bruno Cesar Douady-Pleven , Michael Serge André Kraak , Guillaume Matthieu Guerin , Thomas Nicolas Emmanuel Veit
CPC classification number: G06T3/4015 , G06T5/002 , G06T5/004 , G06T5/008 , G06T5/009 , G06T5/40 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20182 , H04N5/213 , H04N5/217 , H04N5/2355 , H04N5/357 , H04N9/646 , H04N9/735 , H04N9/77 , H04N2209/046
Abstract: A system access a reference frame and temporally adjacent frames. For each portion of the reference image frame, the system calculates a pixel distance value between the portion of the reference image frame and a corresponding portion of each temporally adjacent image frame. If the pixel distance value indicates a potential ghosting artifact, the system computes a set of spatial noise reduction values for the image portion. Otherwise, the system computes a set of temporal noise reduction values for the image portion. The system blends the sets of computed spatial noise reduction values and the sets of computed temporal noise reduction values, and generates a modified reference image frame based on the blended set of noise reduction values.
Abstract translation: 系统访问参考帧和时间上相邻的帧。 对于参考图像帧的每个部分,系统计算参考图像帧的部分和每个时间上相邻的图像帧的相应部分之间的像素距离值。 如果像素距离值表示潜在的重影伪像,则系统计算图像部分的一组空间降噪值。 否则,系统计算图像部分的一组时间噪声降低值。 该系统将计算出的空间噪声降低值的集合和所计算的时间噪声降低值的集合进行混合,并且基于混合的降噪值集合生成修改的参考图像帧。
-
公开(公告)号:US11800238B2
公开(公告)日:2023-10-24
申请号:US17526740
申请日:2021-11-15
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Antoine Regimbeau , Thomas Nicolas Emmanuel Veit , Bruno Cesar Douady-Pleven , Violaine Marie Mong-Ian Sudret
IPC: H04N23/741 , H04N23/80 , G06T5/00 , G06T5/50
CPC classification number: H04N23/741 , G06T5/008 , H04N23/80 , G06T5/009 , G06T5/50 , G06T2207/20028
Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.
-
公开(公告)号:US10554903B2
公开(公告)日:2020-02-04
申请号:US16368974
申请日:2019-03-29
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Antoine Regimbeau , Thomas Nicolas Emmanuel Veit , Bruno César Douady-Pleven , Violaine Marie Mong-lan Sudret
Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.
-
公开(公告)号:US10284785B2
公开(公告)日:2019-05-07
申请号:US15690772
申请日:2017-08-30
Applicant: GoPro, Inc.
Inventor: Guillaume Matthieu Guerin , Antoine Regimbeau , Thomas Nicolas Emmanuel Veit , Bruno Cesar Douady-Pleven , Violaine Marie Mong-lan Sudret
Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include receiving an image from an image sensor; applying a filter to the image to obtain a low-frequency component image and a high-frequency component image; determining a first enhanced image based on a weighted sum of the low-frequency component image and the high-frequency component image, where the high-frequency component image is weighted more than the low-frequency component image; determining a second enhanced image based on the first enhanced image and a tone mapping; and storing, displaying, or transmitting an output image based on the second enhanced image.
-
公开(公告)号:US20160366386A1
公开(公告)日:2016-12-15
申请号:US15081680
申请日:2016-03-25
Applicant: GoPro, Inc.
Inventor: Bruno Cesar Douady-Pleven , Michael Serge André Kraak , Guillaume Matthieu Guerin , Thomas Nicolas Emmanuel Veit
CPC classification number: G06T3/4015 , G06T5/002 , G06T5/004 , G06T5/008 , G06T5/009 , G06T5/40 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20182 , H04N5/213 , H04N5/217 , H04N5/2355 , H04N5/357 , H04N9/646 , H04N9/735 , H04N9/77 , H04N2209/046
Abstract: A system determines for each color channel of each portion of the image, a corresponding adjustment value to apply to the color channel to correct for a color irregularity. The system determines a corrected adjustment value based on a difference between twice the pixel value and the maximum saturation value. If the adjustment value as applied is larger than the corrected adjustment value, the system applies the adjustment value to the corresponding color channel of the image portion to produce the adjusted color channel. Otherwise, the system applies the corrected adjustment to the corresponding color channel of the image portion to produce an adjusted color channel. The system generates a modified image based on the adjusted color channel.
Abstract translation: 系统为图像的每个部分的每个颜色通道确定应用于颜色通道以校正颜色不规则性的相应调整值。 系统基于像素值和最大饱和度值之间的差异来确定校正的调整值。 如果所应用的调整值大于校正的调整值,则系统将调整值应用于图像部分的相应颜色通道,以产生经调整的色彩通道。 否则,系统将校正的调整应用于图像部分的相应颜色通道,以产生调整的色彩通道。 系统根据调整后的颜色通道生成修改后的图像。
-
公开(公告)号:US20160364841A1
公开(公告)日:2016-12-15
申请号:US15081677
申请日:2016-03-25
Applicant: GoPro, Inc.
Inventor: Bruno Cesar Douady-Pleven , Michael Serge André Kraak , Guillaume Matthieu Guerin , Thomas Nicolas Emmanuel Veit
CPC classification number: G06T3/4015 , G06T5/002 , G06T5/004 , G06T5/008 , G06T5/009 , G06T5/40 , G06T5/50 , G06T2207/10016 , G06T2207/10024 , G06T2207/20182 , H04N5/213 , H04N5/217 , H04N5/2355 , H04N5/357 , H04N9/646 , H04N9/735 , H04N9/77 , H04N2209/046
Abstract: A system identifies a scaling position in a captured image, and identifies red subpixels adjacent to the scaling position. The system computes a scaled red subpixel for the scaling position based on the identified red subpixels according to constraints. The system further computes a scaled blue subpixel based on identified adjacent blue subpixels, according to constraints, and computes a scaled green subpixel position based on Gr and Gb subpixels adjacent to the scaling position according to certain constraints. The system then generates a scaled image representative of the captured image, the scaled image including at least the scaled red subpixel value, the scaled blue subpixel value, and the scaled green subpixel value.
Abstract translation: 系统识别拍摄图像中的缩放位置,并识别与缩放位置相邻的红色子像素。 根据约束,系统基于识别的红色子像素计算缩放位置的缩放红色子像素。 根据约束,该系统还基于识别的相邻的蓝色子像素进一步计算缩放的蓝色子像素,并且根据某些约束,基于与缩放位置相邻的Gr和Gb子像素来计算缩放的绿色子像素位置。 然后,系统生成表示拍摄图像的缩放图像,缩放图像至少包括缩放的红色子像素值,缩放的蓝色子像素值和缩放的绿色子像素值。
-
-
-
-
-
-
-
-
-