公开(公告)号：US11368658B2

公开(公告)日：2022-06-21

申请号：US16901481

申请日：2020-06-15

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael Edward Samples ,  Mikhail Smirnov ,  Jozef Barnabas Houben ,  Damon Marlow Domjan ,  Joshua Owen Miller

IPC: H04N9/31 ,  G01K13/08 ,  G02B26/08 ,  G02B26/10 ,  G06K9/62

Abstract: A MEMS scanning device (“Device”) includes at least (1) laser projector(s) controlled by a laser drive to project a laser beam, (2) MEMS scanning mirror(s) controlled by a MEMS drive to scan the laser beam to generate a raster scan, (3) a display configured to receive the raster scan, (4) a thermometer configured to detect a current temperature, (5) a display observing camera configured to capture an image of a predetermined area of the display, and (6) a computer-readable media that stores temperature model(s), each of which is custom-built using machine learning. The device uses the display observing camera to capture image(s) of predetermined pattern(s), which are then used to extract feature(s). The extracted feature(s) are compared with ideal feature(s) to identify a discrepancy. When the identified discrepancy is greater than a threshold, the temperature model(s) are updated accordingly.

公开(公告)号：US11743434B2

公开(公告)日：2023-08-29

申请号：US17832180

申请日：2022-06-03

Applicant: Microsoft Technology Licensing, LLC

Inventor： Michael Edward Samples ,  Mikhail Smirnov ,  Jozef Barnabas Houben ,  Damon Marlow Domjan ,  Joshua Owen Miller

IPC: H04N9/31 ,  G01K13/08 ,  G02B26/08 ,  G02B26/10 ,  G06F18/25

CPC classification number: H04N9/3135 ,  G01K13/08 ,  G02B26/0858 ,  G02B26/101 ,  G06F18/253 ,  H04N9/3194

Abstract: A MEMS scanning device (“Device”) includes at least (1) laser projector(s) controlled by a laser drive to project a laser beam, (2) MEMS scanning mirror(s) controlled by a MEMS drive to scan the laser beam to generate a raster scan, (3) a display configured to receive the raster scan, (4) a thermometer configured to detect a current temperature, (5) a display observing camera configured to capture an image of a predetermined area of the display, and (6) a computer-readable media that stores temperature model(s), each of which is custom-built using machine learning. The device uses the display observing camera to capture image(s) of predetermined pattern(s), which are then used to extract feature(s). The extracted feature(s) are compared with ideal feature(s) to identify a discrepancy. When the identified discrepancy is greater than a threshold, the temperature model(s) are updated accordingly.

公开(公告)号：US20180278910A1

公开(公告)日：2018-09-27

申请号：US15466361

申请日：2017-03-22

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

Inventor： Michael John Schoenberg ,  Kamal Ramachandran Kuzhinjedathu ,  Mikhail Smirnov ,  Christopher Stephen Messer ,  Michael Jason Gourlay

IPC: H04N13/02

CPC classification number: H04N13/25 ,  G01S11/00 ,  G01S17/107 ,  G01S17/42 ,  G01S17/89 ,  H04N13/207

Abstract: A system for determining distances to features in a scene is disclosed. The system includes, among other features, a target portion identifier module, a target surface generator, a reflector selection module, a light transport simulation module, a depth measurement correction generation module, and a distance calculation module. The target portion identifier module is configured to identify a plurality of target portions of the scene. The target surface generator is configured to simulate a plurality of target surfaces. The reflector selection module is configured to select a first plurality of reflector surfaces from the plurality of target surfaces and a second plurality of reflector surfaces from the first plurality of reflector surfaces. The light transport simulation module is configured to, for each target surface included in the target surfaces, simulate a multipath reflection of light emitted by the camera, reflected by the reflector surface to the target surface, and reflected by the target surface to the camera, to generate a simulated multipath response for the target surface. The depth measurement correction generation module is configured to generate a depth measurement correction for each target surface based on the simulated multipath response. The distance calculation module is configured to determine distances for the pixels based on the depth measurement corrections.