IP Library › Granted Patent US 12,738,140
Granted Patent B2
US 12,738,140 · App. 18/902,651 · Granted Sep 15, 2026

Ultra-wideband-based fall detection

Inventors: Han Wang (Allen, TX); Wei Sun (Allen, TX); Hao Chen (Allen, TX); Aditya Dave (Plano, TX); Russell Douglas Ford (Campbell, CA); Satvir S. Bhatia (Sunnyvale, CA); Andrea M. Small (San Francisco, CA)
Assignee: Samsung Electronics Co., Ltd.
G08B21/043G01S13/0209G01S13/5246G01S13/582G08B21/0415G08B21/0438
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 12,738,140
App. No.
18/902,651
Granted
Sep 15, 2026
Kind
B2
Abstract

An electronic device includes a transceiver configured to transmit and receive ultrawide band (UWB) radar signals. The electronic device also includes a processor operatively coupled to the transceiver. The processor is configured to, based on the received UWB radar signals, detect a human within a detection area of the transceiver. The processor is further configured to perform, based on the detection of the human within the detection area of the transceiver, a motion detection operation, and perform, based on a result of the motion detection operation, a fall detection operation.

Claims (99)

1 . An electronic device comprising:

a transceiver configured to transmit and receive ultrawide band (UWB) radar signals; and

a processor operatively coupled to the transceiver, the processor configured to:

generate a plurality of UWB channel impulse response (CIR) frames based on the transmitted and received UWB radar signals;

store the plurality of UWB CIR frames within a buffer;

preprocess the plurality of UWB CIR frames stored within the buffer;

perform range doppler calculations on the preprocessed plurality of UWB CIR frames;

perform, based on a result of the range doppler calculations, a range bin selection operation;

detect a human within a detection area of the transceiver based on a result of the range bin selection operation and based on removing one or more non-human artifacts;

perform, based on the detection of the human within the detection area of the transceiver, a motion detection operation; and

perform, based on a result of the motion detection operation, a fall detection operation.

2 . The electronic device of claim 1 , wherein the processor is further configured to:

determine, based on a result of the fall detection operation, that a fall has a occurred; and

process an alert in response to the determination that a fall has occurred.

3 . The electronic device of claim 1 , wherein:

the transceiver comprises at least two receive (RX) antennas configured to receive the UWB radar signals; and

to perform the motion detection operation, the processor is further configured to:

determine an azimuth difference in the UWB radar signals received by the at least two RX antennas;

determine an angle of arrival based on the determined azimuth difference; and

estimate a location of the human based on the angle of arrival and a range bin.

4 . The electronic device of claim 1 , wherein:

the fall detection operation is performed based on the result of the motion detection operation being a detection of a motion; and

to perform the fall detection operation, the processor is further configured to:

determine whether the motion meets a fall threshold; and

when the motion meets the fall threshold, determine that a fall has occurred.

5 . The electronic device of claim 4 , wherein to determine whether the motion meets the fall threshold, the processor is further configured to determine whether at least one of:

a change in an elevation angle of the human has exceeded an elevation change threshold; or

a velocity of the human has exceeded a velocity threshold.

6 . The electronic device of claim 1 , wherein:

the fall detection operation is performed based on the result of the motion detection operation being no detection of a motion; and

to perform the fall detection operation, the processor is further configured to perform an inactivity tracking operation.

7 . The electronic device of claim 6 , wherein to perform the inactivity tracking operation, the processor is further configured to:

determine whether the human has been inactive for a time threshold; and

when the human has been inactive for at least the time threshold, determine that a fall has occurred.

8 . A method of operating an electronic device, the method comprising:

transmitting and receiving ultrawide band (UWB) radar signals;

generating a plurality of UWB channel impulse response (CIR) frames based on the transmitted and received UWB radar signals;

storing the plurality of UWB CIR frames within a buffer;

preprocessing the plurality of UWB CIR frames stored within the buffer;

performing range doppler calculations on the preprocessed plurality of UWB CIR frames;

performing, based on a result of the range doppler calculations, a range bin selection operation;

detecting a human within a detection area of the electronic device based on a result of the range bin selection operation and based on removing one or more non-human artifacts;

performing, based on the detection of the human within the detection area of the electronic device, a motion detection operation; and

performing, based on a result of the motion detection operation, a fall detection operation.

9 . The method of claim 8 , further comprising:

determining, based on a result of the fall detection operation, that a fall has a occurred; and

processing an alert in response to the determination that a fall has occurred.

10 . The method of claim 8 , wherein:

the electronic device comprises at least two receive (RX) antennas configured to receive the UWB radar signals; and

to perform the motion detection operation, the method further comprises:

determining an azimuth difference in the UWB radar signals received by the at least two RX antennas;

determining an angle of arrival based on the determined azimuth difference; and

estimating a location of the human based on the angle of arrival and a range bin.

11 . The method of claim 8 , wherein:

the fall detection operation is performed based on the result of the motion detection operation being a detection of a motion; and

to perform the fall detection operation, the method further comprises:

determining whether the motion meets a fall threshold; and

when the motion meets the fall threshold, determining that a fall has occurred.

12 . The method of claim 11 , wherein to determine whether the motion meets the fall threshold, the method further comprises determining whether at least one of:

a change in an elevation angle of the human has exceeded an elevation change threshold; or

a velocity of the human has exceeded a velocity threshold.

13 . The method of claim 8 , wherein:

the fall detection operation is performed based on the result of the motion detection operation being no detection of a motion; and

to perform the fall detection operation, the method further comprises performing an inactivity tracking operation.

14 . The method of claim 13 , wherein to perform the inactivity tracking operation, the method further comprises:

determining whether the human has been inactive for a time threshold; and

when the human has been inactive for at least the time threshold, determining that a fall has occurred.

15 . A non-transitory computer readable medium embodying a computer program, the computer program comprising program code that, when executed by a processor of a device, causes the device to:

transmit and receive ultrawide band (UWB) radar signals;

generate a plurality of UWB channel impulse response (CIR) frames based on the transmitted and received UWB radar signals;

store the plurality of UWB CIR frames within a buffer;

preprocess the plurality of UWB CIR frames stored within the buffer;

perform range doppler calculations on the preprocessed plurality of UWB CIR frames;

perform, based on a result of the range doppler calculations, a range bin selection operation;

detect a human within a detection area of the device based on a result of the range bin selection operation and based on removing one or more non-human artifacts;

perform, based on the detection of the human within the detection area of the device, a motion detection operation; and

perform, based on a result of the motion detection operation, a fall detection operation.

16 . The non-transitory computer readable medium of claim 15 , wherein the program code, when executed by the processor of the device, further causes the device to:

determine, based on a result of the fall detection operation, that a fall has a occurred; and

process an alert in response to the determination that a fall has occurred.

17 . The non-transitory computer readable medium of claim 15 , wherein:

the device comprises at least two receive (RX) antennas configured to receive the UWB radar signals; and

to perform the motion detection operation, the program code, when executed by the processor of the device, further causes the device to:

determine an azimuth difference in the UWB radar signals received by the at least two RX antennas;

determine an angle of arrival based on the determined azimuth difference; and

estimate a location of the human based on the angle of arrival and a range bin.

18 . The non-transitory computer readable medium of claim 15 , wherein:

the fall detection operation is performed based on the result of the motion detection operation being a detection of a motion; and

to perform the fall detection operation, the program code, when executed by the processor of the device, further causes the device to:

determine whether the motion meets a fall threshold; and

when the motion meets the fall threshold, determine that a fall has occurred.

19 . The non-transitory computer readable medium of claim 18 , wherein to determine whether the motion meets the fall threshold, the program code, when executed by the processor of the device, further causes the device to determine whether at least one of:

a change in an elevation angle of the human has exceeded an elevation change threshold; or

a velocity of the human has exceeded a velocity threshold.

20 . The non-transitory computer readable medium of claim 15 , wherein:

the fall detection operation is performed based on the result of the motion detection operation being no detection of a motion; and

to perform the fall detection operation, the program code, when executed by the processor of the device, further causes the device to perform an inactivity tracking operation comprising:

determining whether the human has been inactive for a time threshold; and

when the human has been inactive for at least the time threshold, determining that a fall has occurred.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 30, 2024
From: WANG, HAN; SUN, WEI; CHEN, HAO; DAVE, ADITYA; FORD, RUSSELL DOUGLAS; BHATIA, SATVIR S.; SMALL, ANDREA M.
To: SAMSUNG ELECTRONICS CO., LTD.
Reel/Frame 068746/0101 →
Continuity (2)
Provisional Application 63542712 · Oct 5, 2023
Related Publication 20250118186A1 · Apr 10, 2025
References Cited (21)
US 7567200B1 · Osterweil · 2009 [cited by applicant]
US 11163052B2 · Eckert et al. · 2021 [cited by applicant]
US 20180330593A1 · Zack · 2018 [cited by examiner]
US 20200342735A1 · Tan · 2020 [cited by examiner]
US 20220026531A1 · Wu · 2022 [cited by examiner]
US 20220283292A1 · Dvash · 2022 [cited by examiner]
US 20230000396A1 · Coffey et al. · 2023 [cited by applicant]
US 20230073570A1 · Adimoolam et al. · 2023 [cited by applicant]
US 20240004054A1 · Rigazio et al. · 2024 [cited by applicant]
US 20240077603A1 · Sundholm et al. · 2024 [cited by applicant]
US 20240112559A1 · Shin et al. · 2024 [cited by applicant]
US 20240168128A1 · Sethuraman · 2024 [cited by examiner]
CN 116863646A · 2023 [cited by applicant]
CN 114005246B · 2024 [cited by applicant]
CN 117471451A · 2024 [cited by applicant]
WO 2023131422A1 · 2023 [cited by applicant]
International Search Report and Written Opinion issued Jan. 8, 2025 regarding International Application No. PCT/KR2024/015231, 8 pages. [cited by applicant]
Han et al. “IR-UWB Sensor Based Fall Detection Method Using CNN Algorithm” Sensors, vol. 20, No. 20, Oct. 2020, 23 pages. [cited by applicant]
Maitre, J., et al., “Fall Detection With UWB Radars and CNN-LSTM Architecture”, IEEE Journal of Biomedical and Health Informatics, vol. 25, No. 4, Apr. 2021, 11 pages. [cited by applicant]
Mokhtari, G., et al., “Non-wearable UWB Sensor to Detect Falls in Smart Home Environment”, IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Mar. 13-17, 2017, 5 pages. [cited by applicant]
Chen, M., et al., “A Three-Stage Low-Complexity Human Fall Detection Method Using IR-UWB Radar”, IEEE Sensors Journal, vol. 22, No. 15, Aug. 1, 2022, 15 pages. [cited by applicant]