IP Library Granted Patent US 12,602,949
Granted Patent B2
US 12,602,949 · App. 18/335,046 · Granted Apr 14, 2026

System and method for detecting human presence based on depth sensing and inertial measurement

Inventors: Xiaoyong Yang (San Jose, CA); Kalyan-Kumar Vadlamudi-Reddy (San Jose, CA)
Assignee: STMICROELECTRONICS, INC.
G06V40/166G01B7/30G01B11/22G01C19/00G01P15/18G01S17/08G01S17/894G06F18/214G06F18/25G06V40/171
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,602,949
App. No.
18/335,046
Granted
Apr 14, 2026
Kind
B2
Abstract

An electronic device includes a depth sensor and an inertial measurement unit. The electronic device detects a presence of the user of the electronic device by analyzing a combination of inertial sensor signals from the inertial measurement unit and depth sensor signals from the depth sensor.

Claims (52)

1 . An electronic device, comprising:

a top lid;

a bottom lid;

a hinge coupled to the top lid and the bottom lid;

a display in the top lid;

a depth sensor in the top lid and including a reflectance sensor and configured to sense a distance between the display and objects in view of the depth sensor and to generate a depth map including a plurality of zones;

a first inertial measurement unit in the top lid and configured to generate first inertial sensor data;

a second inertial measurement unit in the bottom lid and configured to generate second inertial sensor data; and

a sensor processing unit configured to:

receive the first inertial sensor data, the second inertial sensor data, and the depth map;

to determine a heading of the electronic device based on one or both of the first inertial sensor data and the second inertial sensor data;

to determine a rotational angle of the top lid and the bottom lid;

to identify an expected zone from the plurality of zones of the depth map in which a user of the electronic device is expected to be located based on the heading and the rotational angle, wherein identifying an expected zone includes identifying the expected zone based on rotation motion indicated by first and second inertial sensor data;

to detect a presence of the user within the expected zone by analyzing the expected zone; and

tracking a face of the user based on the first and second inertial sensor data indicating rotational motion.

2 . The electronic device of claim 1 , wherein the depth sensor includes a time of flight sensor.

3 . The electronic device of claim 1 , wherein at least one of the first and second inertial measurement units includes an accelerometer.

4 . The electronic device of claim 1 , wherein at least one of the first and second inertial measurement units includes a gyroscope.

5 . The electronic device of claim 1 , wherein the sensor processing unit is configured to detect the presence of the user based on whether or not reflectance sensor signals of the reflectance sensor indicate a reflectance less than a threshold reflectance.

6 . A method, comprising:

generating depth sensor data with a depth sensor in a top lid of an electronic device and including a reflectance sensor;

generating first inertial sensor data with a first inertial sensor in the top lid of the electronic device;

generating second inertial sensor signals with a second inertial sensor in a bottom lid of the electronic device, the bottom lid being rotatably coupled to the top lid by a hinge;

generating a depth map based on the depth sensor signals;

receiving, with a sensor processing unit of the electronic device, the first inertial sensor data, the second inertial sensor data, and the depth map;

determining, with the sensor processing unit, a heading of the electronic device based on one or both of the first inertial sensor data and the second inertial sensor data;

determining, with the sensor processing unit, a rotational angle of the top lid and the bottom lid;

identifying, with the sensor processing unit, an expected zone from a plurality of zones of the depth map in which a user of the electronic device is expected to be located based on the heading and the rotational angle, wherein identifying an expected zone includes identifying the expected zone based on rotation motion indicated by first and second inertial sensor data;

detecting, with the sensor processing unit, a presence of the user within the expected zone by analyzing the expected zone; and

tracking a face of the user based on the first and second inertial sensor data indicating rotational motion.

7 . The method of claim 6 , wherein the electronic device is a laptop computer.

8 . The method of claim 6 , wherein the sensor processing unit includes a first neural network.

9 . The method of claim 8 , wherein the sensor processing unit includes a second neural network.

10 . The method of claim 8 , further comprising generating combined sensor data with the first neural network.

11 . A device, comprising:

an upper lid;

a lower lid coupled to the upper lid;

a depth sensor positioned in the upper lid, the depth sensor configured to generate a depth map including a plurality of zones;

a first inertial measurement unit positioned in the upper lid, the first inertial measurement unit configured to generate a first inertial measurement of the device;

a second inertial measurement unit positioned in the lower lid, the second inertial measurement unit configured to generate a second inertial measurement of the device; and

a sensor processing unit configured to:

receive the first inertial sensor data, the second inertial sensor data, and the depth map;

to determine a heading of the device based on one or both of the first inertial sensor data and the second inertial sensor data;

to determine a rotational angle of the upper lid and the lower lid;

to identify an expected zone from the plurality of zones of the depth map in which a user of the electronic device is expected to be located based on the heading and the rotational angle, wherein identifying an expected zone includes identifying the expected zone based on rotation motion indicated by first and second inertial sensor data;

to detect a presence of the user within the expected zone by analyzing the expected zone; and

track a face of the user based on the first and second inertial sensor data indicating rotational motion.

12 . The device of claim 11 , wherein the sensor processing unit is configured to detect the presence of the user based on whether or not reflectance measurement of the depth sensor is less than a threshold reflectance.

13 . The device of claim 11 , wherein the sensor processing unit includes a first neural network.

14 . The device of claim 13 , wherein the sensor processing unit includes a second neural network.

15 . The device of claim 11 , wherein the first inertial measurement unit includes an accelerometer.

16 . The device of claim 11 , wherein the first inertial measurement unit includes a gyroscope.

Continuity (2)
Continuation 17006594 · Aug 28, 2020
Related Publication 20230326239A1 · Oct 12, 2023
References Cited (40)
US 9442564B1 · Dillon · 2016 [cited by applicant]
US 9760837B1 · Nowozin et al. · 2017 [cited by applicant]
US 10055013B2 · Ramaswamy et al. · 2018 [cited by applicant]
US 10627917B2 · Hou et al. · 2020 [cited by applicant]
US 11367306B1 · Kuo et al. · 2022 [cited by applicant]
US 20130116049A1 · Pellman · 2013 [cited by examiner]
US 20140226855A1 · Savvides · 2014 [cited by examiner]
US 20140240469A1 · Lee · 2014 [cited by applicant]
US 20150019163A1 · Needham · 2015 [cited by applicant]
US 20150066494A1 · Salvador et al. · 2015 [cited by applicant]
US 20150161434A1 · Ross et al. · 2015 [cited by applicant]
US 20150363035A1 · Hinckley · 2015 [cited by examiner]
US 20160364612A1 · Dixon · 2016 [cited by examiner]
US 20180053056A1 · Rabinovich et al. · 2018 [cited by applicant]
US 20180288303A1 · Wang et al. · 2018 [cited by applicant]
US 20190050729A1 · Lakshmanan et al. · 2019 [cited by applicant]
US 20190079536A1 · Zhu et al. · 2019 [cited by applicant]
US 20190101917A1 · Yao · 2019 [cited by examiner]
US 20190213309A1 · Morestin et al. · 2019 [cited by applicant]
US 20200086861A1 · McGill, Jr. et al. · 2020 [cited by applicant]
US 20200110451A1 · He et al. · 2020 [cited by applicant]
US 20200125179A1 · Okuley · 2020 [cited by applicant]
US 20200175401A1 · Shen · 2020 [cited by examiner]
US 20200301013A1 · Banerjee · 2020 [cited by examiner]
US 20200377108A1 · Balazs · 2020 [cited by applicant]
US 20210110615A1 · Zhao · 2021 [cited by examiner]
US 20210304514A1 · Croxford et al. · 2021 [cited by applicant]
US 20210332555A1 · Metzger · 2021 [cited by examiner]
US 20220036577A1 · Lopez Mendez et al. · 2022 [cited by applicant]
US 20220060622A1 · Brändli · 2022 [cited by examiner]
US 20220067525A1 · Sequeira et al. · 2022 [cited by applicant]
US 20230251078A1 · Rizzardini · 2023 [cited by examiner]
EP 3477616A1 · 2019 [cited by examiner]
Bartels, “Applications for Time-of-Flight Cameras in Robotics, Logistics and Medicine,” White Paper, <<https://www.baslerweb.com/en/sales-support/downloads/document-downloads/tof-cameras-in-logistics-robotics-and-medici… [cited by applicant]
Haselton, “Samsung Galaxy S8's facial recognation can be tricked with a photo,” Mar. 31, 2017, <<https://www.cnbc.com/2017/03/31/galaxy-s8-facial-recognition-can-be-tricked-with-a-photo.html>> downloaded Jan. 5, 2018, 3… [cited by applicant]
Microsoft, “Windows Hello face authentication,” Nov. 16, 2018 <<https://docs.microsoft.com/en-us/windows-hardware/design/device-experiences/windows-hello-face-authentication>> downloaded Dec. 28, 2018, 4 pages. [cited by applicant]
Yoshida, “iPhones X's TrueDepth Module Dissected,” EE Times, Nov. 17, 2017 <<https://www.eetimes.com/iphone-xs-truedepth-module-dissected/?page_number=1>> downloaded Dec. 28, 2018, 3 pages. [cited by applicant]
Chen et al., “A Real Time Human Action Recognition System Using Depth and Inertial Sensor Fusion”, [cited by applicant]
Ahmad et al., “Towards improved human action recognition using convolutional neural networks and multi modal fusion of depth and inertial sensor data,” 2018 IEEE International Symposium on Multimedia (ISM), pp. 223-230. [cited by applicant]
U.S. Pat. No. 10,922,395, Feb. 16, 2021. [cited by applicant]