IP Library Granted Patent US 12,247,849
Granted Patent B2
US 12,247,849 · App. 17/459,781 · Granted Mar 11, 2025

Enhanced human activity recognition

Inventors: Stefano Paolo Rivolta (Desio, IT); Roberto Mura (Milan, IT)
Assignee: STMICROELECTRONICS S.r.l.
G01D21/02A61B5/1118A61B5/2415G01P15/00G01R29/12A61B2562/0219
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 12,247,849
App. No.
17/459,781
Granted
Mar 11, 2025
Kind
B2
Abstract

The present disclosure is directed to a device with enhanced human activity recognition. The device detects a human activity using one more motion sensors, and enhances the detected human activity depending on whether the device is in an indoor environment or an outdoor environment. The device utilizes one or more electrostatic charge sensors to determine whether the device is in an indoor environment or an outdoor environment.

Claims (59)

1. A device, comprising:

a motion sensor configured to generate a motion measurement of the device;

an electrostatic charge sensor configured to generate an electrostatic charge measurement of the device; and

a processing unit configured to:

perform context detection to detect the device is indoors or outdoors based on the electrostatic charge measurement;

perform, subsequent to the device being determined to be indoors based on the electrostatic charge measurement, first human activity recognition to detect a first activity state of a user of the device selected from a plurality of indoor states based on the motion measurement, the first human activity recognition being performed without outdoor state detection;

perform, subsequent to the device being determined to be outdoors based on the electrostatic charge measurement, second human activity recognition to detect a second activity state of the user of the device selected from a plurality of outdoor states based on the motion measurement, the second human activity recognition being performed without indoor state detection; and

output the first activity state or the second activity state.

2. The device of claim 1 wherein the processing unit detects the device is indoors in a case where the electrostatic charge measurement includes a first peak at a frequency corresponding to an alternating current (AC) power line.

3. The device of claim 2 wherein the processing unit detects the device is outdoors in a case where the electrostatic charge measurement does not include a peak at the frequency corresponding to the AC power line, or the electrostatic charge measurement includes a second peak, which is smaller than the first peak, at the frequency corresponding to the AC power line.

4. The device of claim 1 wherein the processing unit is configured to determine at least one feature of the electrostatic charge measurement, and detect whether the device is indoors or outdoors based on the at least one feature.

5. The device of claim 4 wherein the at least one feature includes at least one of an energy calculation, a variance calculation, a zero crossing calculation, a peak-to-peak calculation, a peak count calculation, an absolute mean calculation, a maximum calculation, or a minimum calculation.

6. The device of claim 1 wherein the electrostatic charge sensor includes a single electrode.

7. The device of claim 1 wherein the electrostatic charge sensor includes a plurality of electrodes.

8. The device of claim 1 wherein the processing unit is configured to:

determine a first peak of the electrostatic charge measurement;

detect the device is indoors in a case where the first peak corresponds to an alternating current (AC) power line;

determine a second peak of the electrostatic charge measurement; and

detect the device is outdoors in a case where the second peak corresponds to the AC power line and is smaller than the first peak.

9. The device of claim 1 wherein

the plurality of indoor states includes a stationary state that indicates the user is remaining still, an indoor walking state that indicates the user is walking indoors, and a stationary bicycle state that indicates the user is cycling on a stationary bicycle, and

the plurality of outdoor states includes an outdoor walking state that indicates the user is walking outside, an outdoor cycling state that indicates the user is cycling outdoors, and a driving state that indicates the user is driving a vehicle.

10. The device of claim 1 wherein the processing unit is configured to:

count a first total number of times the first activity state has been determined;

output the first activity state in response to the first total number being equal to or greater than a first threshold count value;

count a second total number of times the second activity state has been determined;

output the second activity state in response to the second total number being equal to or greater than a second threshold count value.

11. The device of claim 1 wherein the processing unit is configured to:

filter the electrostatic charge measurement with a high pass filter, the device being determined to be indoors or outdoors based on the filtered electrostatic charge measurement.

12. A device, comprising:

a motion sensor configured to generate a motion measurement of the device;

an electrostatic charge sensor configured to generate an electrostatic charge measurement of the device; and

a processing unit configured to:

perform human activity recognition to detect a driving state of a user of the device based on the motion measurement, the driving state indicating the user is driving a vehicle;

perform context detection to detect the device is indoors or outdoors based on the electrostatic charge measurement;

detect a valid detection of the driving state determined based on the motion measurement in response to the device being determined to be outdoors based on the electrostatic charge measurement;

detect a false detection of the driving state determined based on the motion measurement in response to the device being determined to be indoors based on the electrostatic charge measurement;

output the driving state in response to the valid detection of the driving state determined based on the motion measurement being detected.

13. The device of claim 12 wherein the processing unit detects the device is indoors in a case where the electrostatic charge measurement includes a first peak at a frequency corresponding to an alternating current (AC) power line, and

detects the device is outdoors in a case where the electrostatic charge measurement does not include a peak at the frequency corresponding to the AC power line, or the electrostatic charge measurement includes a second peak, which is smaller than the first peak, at the frequency corresponding to the AC power line.

14. The device of claim 12 wherein the processing unit is configured to determine at least one feature of the electrostatic charge measurement, and detect whether the device is indoors or outdoors based on the at least one feature.

15. The device of claim 14 wherein the at least one feature includes at least one of an energy calculation, a variance calculation, a zero crossing calculation, a peak-to-peak calculation, a peak count calculation, an absolute mean calculation, a maximum calculation, or a minimum calculation.

16. The device of claim 12 wherein the processing unit is configured to, in response to the false detection of the driving state determined based on the motion measurement being detected, switch the driving state to another state different from the driving state, and output the another state.

17. A device, comprising:

a motion sensor configured to generate a motion measurement of the device;

an electrostatic charge sensor configured to generate an electrostatic charge measurement of the device; and

a processing unit configured to:

determine a walking state of a user of the device based on the motion measurement, the walking state indicating the user is walking;

determine a cycling state of the user of the device based on the motion measurement, the cycling state indicating the user is cycling;

determine the device is indoors or outdoors based on the electrostatic charge measurement;

in case the walking state is determined,

switch the walking state determined based on the motion measurement to an indoor walking state that indicates the user is walking indoors in response to the device being determined to be indoors based on the electrostatic charge measurement, and output the indoor walking state, and

switch the walking state to an outdoor walking state determined based on the motion measurement that indicates the user is walking outdoors in response to the device being determined to be outdoors, and output the outdoor walking state based on the electrostatic charge measurement; and

in case the cycling state is determined,

switch the cycling state determined based on the motion measurement to a stationary bicycle state that indicates the user is cycling on a stationary bicycle in response to the device being determined to be indoors based on the electrostatic charge measurement, and output the stationary bicycle state, and

switch the cycling state determined based on the motion measurement to an outdoor cycling state that indicates the user is cycling outdoors in response to the device being determined to be outdoors based on the electrostatic charge measurement, and output the outdoor cycling state.

18. The device of claim 17 wherein the processing unit

determines the device is indoors in a case where the electrostatic charge measurement incudes a first peak at a frequency corresponding to an alternating current (AC) power line, and

determines the device is outdoors in a case where the electrostatic charge measurement does not include a peak at the frequency corresponding to the AC power line, or the electrostatic charge measurement includes a second peak, which is smaller than the first peak, at the frequency corresponding to the AC power line.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 4, 2021
From: RIVOLTA, STEFANO PAOLO; MURA, ROBERTO
To: STMICROELECTRONICS S.R.L.
Reel/Frame 058024/0245 →
Continuity (1)
Related Publication 20230075382A1 · Mar 9, 2023
References Cited (38)
US 10141929B2 · Rakova · 2018 [cited by examiner]
US 10540597B1 · Tilton · 2020 [cited by examiner]
US 10605595B2 · Martensson et al. · 2020 [cited by applicant]
US 10943602B2 · Chowdhary et al. · 2021 [cited by applicant]
US 11257198B1 · Holub et al. · 2022 [cited by applicant]
US 20030001582A1 · Kraz · 2003 [cited by examiner]
US 20070100666A1 · Stivoric et al. · 2007 [cited by applicant]
US 20130159237A1 · Nath · 2013 [cited by examiner]
US 20140232516A1 · Stivoric et al. · 2014 [cited by applicant]
US 20140358473A1 · Goel · 2014 [cited by examiner]
US 20150097731A1 · Russell · 2015 [cited by examiner]
US 20160296144A1 · Gaddam · 2016 [cited by examiner]
US 20160305776A1 · Mårtensson · 2016 [cited by examiner]
US 20160342781A1 · Jeon · 2016 [cited by applicant]
US 20180096256A1 · Chowdhary · 2018 [cited by examiner]
US 20190038184A1 · Narasimhan et al. · 2019 [cited by applicant]
US 20200382613A1 · Sundstrom · 2020 [cited by examiner]
US 20210081032A1 · Passaniti et al. · 2021 [cited by applicant]
US 20210232227A1 · Passaniti et al. · 2021 [cited by applicant]
US 20210285773A1 · Alessi et al. · 2021 [cited by applicant]
US 20230035435A1 · Thamma · 2023 [cited by examiner]
US 20230050034A1 · Ben-Elazar · 2023 [cited by examiner]
US 20230065695A1 · Singleton · 2023 [cited by examiner]
CN 108236469A · 2018 [cited by applicant]
EP 2980609A1 · 2016 [cited by applicant]
KR 2001077112A · 2001 [cited by examiner]
KR 1020110061750A · 2011 [cited by applicant]
WO 2016166613A1 · 2016 [cited by applicant]
WO WO2019176762A1 · 2019 [cited by examiner]
WO WO2020196993A1 · 2020 [cited by applicant]
Wilmsdorff et al., “An experimental overview on electric field sensing,” [cited by applicant]
Cohn, G. et al., “An Ultra-Low-Power Human Body Motion Sensor Using Static Electric Field Sensing,” [cited by applicant]
Fu et al., “Sensing Technology for Human Activity Recognition: A Comprehensive Survey,” [cited by applicant]
Lima et al., “Human Activity Recognition Using Inertial Sensors in a Smartphone: An 2 Overview,” [cited by applicant]
Radivojevic et al., “Human Activity Recognition based on Machine Learning 3 Classification of Smartwatch Accelerometer Dataset,” [cited by applicant]
Khusainov, R.; Azzi, D.; Achumba, I.E.; Bersch, S.D. Real-Time Human Ambulation, Activity, and Physiological Monitoring: Taxonomy of Issues, Techniques, Applications, Challenges and Limitations. Sensors 2013, 13, 12852-… [cited by applicant]
Lutz, J.; Memmert, D.; Raabe, D.; Dornberger, R.; Donath, L. Wearables for Integrative Performance and Tactic Analyses: Opportunities, Challenges, and Future Directions. Int. J. Environ. Res. Public Health 2020, 17, 59.… [cited by applicant]
Del Rosario, M.B.; Redmond, S.J.; Lovell, N.H. Tracking the Evolution of Smartphone Sensing for Monitoring Human Movement. Sensors 2015, 15, 18901-18933. https://doi.org/10.3390/s150818901 (Year: 2015). [cited by applicant]