公开(公告)号：US11635671B2

公开(公告)日：2023-04-25

申请号：US17240602

申请日：2021-04-26

Applicant: Ringo AI, Inc.

Inventor： Matthew D. Weaver ,  James Kingman ,  Jay Hurley ,  Jeffrey Saake ,  Sanjoy Ghose

IPC: G06T7/90 ,  G03B15/05 ,  H04N5/341 ,  H04N5/225 ,  G03B43/00 ,  H04N5/232 ,  G06K9/00 ,  H04N9/04 ,  H05B45/20 ,  H05B47/125 ,  G06V10/56 ,  G06V10/141 ,  G06V30/194 ,  G06V40/13 ,  G06V40/12

Abstract: Introduced here are computer programs and associated computer-implemented techniques for determining reflectance of an image on a per-pixel basis. More specifically, a characterization module can initially acquire a first data set generated by a multi-channel light source and a second data set generated by a multi-channel image sensor. The first data set may specify the illuminance of each color channel of the multi-channel light source (which is configured to produce a flash), while the second data set may specify the response of each sensor channel of the multi-channel image sensor (which is configured to capture an image in conjunction with the flash). Thus, the characterization module may determine reflectance based on illuminance and sensor response. The characterization module may also be configured to determine illuminance based on reflectance and sensor response, or determine sensor response based on illuminance and reflectance.

公开(公告)号：US10990793B2

公开(公告)日：2021-04-27

申请号：US16421178

申请日：2019-05-23

Applicant: Ringo AI, Inc.

Inventor： Matthew D. Weaver ,  James Kingman ,  Jay Hurley ,  Jeffrey Saake ,  Sanjoy Ghose

IPC: G06K9/00 ,  H04N5/341 ,  H04N5/225 ,  G06K9/66 ,  G03B43/00 ,  G06K9/20 ,  H04N5/232 ,  H04N9/04 ,  G06K9/46 ,  G06T7/90 ,  H05B45/20 ,  G03B15/05

Abstract: Introduced here are computer programs and associated computer-implemented techniques for determining reflectance of an image on a per-pixel basis. More specifically, a characterization module can initially acquire a first data set generated by a multi-channel light source and a second data set generated by a multi-channel image sensor. The first data set may specify the illuminance of each color channel of the multi-channel light source (which is configured to produce a flash), while the second data set may specify the response of each sensor channel of the multi-channel image sensor (which is configured to capture an image in conjunction with the flash). Thus, the characterization module may determine reflectance based on illuminance and sensor response. The characterization module may also be configured to determine illuminance based on reflectance and sensor response, or determine sensor response based on illuminance and reflectance.

公开(公告)号：US20190340407A1

公开(公告)日：2019-11-07

申请号：US16421178

申请日：2019-05-23

Applicant: Ringo AI, Inc.

Inventor： Matthew D. Weaver ,  James Kingman ,  Jay Hurley ,  Jeffrey Saake ,  Sanjoy Ghose

IPC: G06K9/00 ,  G06K9/66 ,  G03B15/05 ,  H04N5/225 ,  H05B33/08 ,  H04N5/341 ,  H04N9/04 ,  G03B43/00 ,  H04N5/232 ,  G06T7/90 ,  G06K9/46 ,  G06K9/20

Abstract: Introduced here are computer programs and associated computer-implemented techniques for determining reflectance of an image on a per-pixel basis. More specifically, a characterization module can initially acquire a first data set generated by a multi-channel light source and a second data set generated by a multi-channel image sensor. The first data set may specify the illuminance of each color channel of the multi-channel light source (which is configured to produce a flash), while the second data set may specify the response of each sensor channel of the multi-channel image sensor (which is configured to capture an image in conjunction with the flash). Thus, the characterization module may determine reflectance based on illuminance and sensor response. The characterization module may also be configured to determine illuminance based on reflectance and sensor response, or determine sensor response based on illuminance and reflectance.

公开(公告)号：US10706253B2

公开(公告)日：2020-07-07

申请号：US16459038

申请日：2019-07-01

Applicant: Ringo AI, Inc.

Inventor： Matthew D. Weaver ,  James Kingman ,  Jay Hurley ,  Jeffrey Saake ,  Sanjoy Ghose

IPC: H05B37/02 ,  H05B39/04 ,  H05B41/36 ,  G06K9/00 ,  H04N5/341 ,  H04N5/225 ,  G06K9/66 ,  G03B43/00 ,  G06K9/20 ,  H04N5/232 ,  H04N9/04 ,  G06K9/46 ,  G06T7/90 ,  H05B45/20 ,  G03B15/05

Abstract: Introduced here are light sources for flash photography configured to produce high-fidelity white light that is tunable over a broader range of correlated color temperatures (CCTs) than conventional flash technologies. The light source can include multiple independently controllable color channels representing illuminants (e.g., light-emitting diodes) of different colors with varying degrees of saturation. Operating collectively, the multiple color channels can produce a high spectral quality white light corresponding to different CCTs (e.g., “warm” white light having a red hue, “cool” white light having a blue hue). Operating independently, these same color channels can be pre-flashed in a variety of prescribed sequences to probe the spectral characteristics of a scene, thereby allowing for an enhanced, spectrally matched white flash as well as collecting per-pixel reflectivity data that can be later used in during post processing of the captured image.

公开(公告)号：US20190325191A1

公开(公告)日：2019-10-24

申请号：US16459038

申请日：2019-07-01

Applicant: Ringo AI, Inc.

Inventor： Matthew D. Weaver ,  James Kingman ,  Jay Hurley ,  Jeffrey Saake ,  Sanjoy Ghose

IPC: G06K9/00 ,  G06K9/66 ,  G03B15/05 ,  H04N5/225 ,  H05B33/08 ,  H04N5/341 ,  H04N9/04 ,  G03B43/00 ,  H04N5/232 ,  G06T7/90 ,  G06K9/46 ,  G06K9/20

Abstract: Introduced here are light sources for flash photography configured to produce high-fidelity white light that is tunable over a broader range of correlated color temperatures (CCTs) than conventional flash technologies. The light source can include multiple independently controllable color channels representing illuminants (e.g., light-emitting diodes) of different colors with varying degrees of saturation. Operating collectively, the multiple color channels can produce a high spectral quality white light corresponding to different CCTs (e.g., “warm” white light having a red hue, “cool” white light having a blue hue). Operating independently, these same color channels can be pre-flashed in a variety of prescribed sequences to probe the spectral characteristics of a scene, thereby allowing for an enhanced, spectrally matched white flash as well as collecting per-pixel reflectivity data that can be later used in during post processing of the captured image.