US 12,070,324 B2
Contactless sleep detection and disturbance attribution for multiple users
Dongeek Shin, Mountain View, CA (US); Michael Dixon, Sunnyvale, CA (US); and Andrew William Goldenson, Belmont, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Aug. 11, 2020, as Appl. No. 16/990,714.
Prior Publication US 2022/0047209 A1, Feb. 17, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. A61B 5/00 (2006.01); A61B 5/0205 (2006.01); A61B 5/11 (2006.01); G01S 13/28 (2006.01); G01S 13/62 (2006.01); G01S 13/88 (2006.01); G06F 18/23 (2023.01); G01S 13/32 (2006.01)
CPC A61B 5/4809 (2013.01) [A61B 5/0004 (2013.01); A61B 5/0205 (2013.01); A61B 5/11 (2013.01); A61B 5/742 (2013.01); G01S 13/282 (2013.01); G01S 13/62 (2013.01); G01S 13/88 (2013.01); G06F 18/23 (2023.01); G01S 13/32 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A contactless sleep analysis device for monitoring multiple users, the contactless sleep analysis device comprising:
a housing;
a radar sensor, housed by the housing, that uses frequency-modulated continuous wave (FMCW) radar;
a processing system, comprising one or more processors, housed by the housing, in communication with the radar sensor, wherein the processing system is configured to:
receive data from the radar sensor;
process the data from the radar sensor, comprising applying a movement filter to remove data indicative of static objects, such that the processed data comprises a first dimension representative of distance, a second dimension representative of frequency, and a third dimension representative of magnitude;
perform clustering on the processed data, wherein the clustered data indicates a first cluster and a second cluster;
based on the clustering performed on the processed data received from the radar sensor, determine that two users are present;
in response to determining that two users are present, calculate a midpoint location between the first cluster and the second cluster;
map a first portion of the processed data from the radar sensor to a first user based on the calculated midpoint;
map a second portion of the processed data from the radar sensor to a second user based on the calculated midpoint;
perform separate sleep analyses over a period of time on the first portion of the processed data for the first user and the second portion of the processed data for the second user; and
output sleep information for the first user based on the first portion of the processed data for over the period of time and sleep information for the second user based on the second portion of the processed data for over the period of time.