Controller to detect non-swim activity of a swimmer and method thereof

Patent metadata

Field	Value
Publication number	US-12573281-B2
Application number	US-202318305353-A
Country	US
Kind code	B2
Filing date	Apr 23, 2023
Priority date	Apr 29, 2022
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

A controller is configured to receive raw signals from at least one gyroscope for at least two axes. The controller processes the raw signals through a BPF and output a filtered signal. The controller processes the filtered signal through an energy envelope estimator and determines an energy envelope signal for at least one axis. The controller then determines a nonswim activity in a segment based on the energy envelope signal through a detector. The energy envelope estimator is configured to generate the energy envelope signal using sliding window average of a preset window size over the filtered signal. The detector is configured to compare values of the energy envelope signal for at least one axis against respective threshold value, and classify the segment of the raw signals as non-swim activity upon satisfactory comparison.

First claim

What is claimed is:

1 . A system for determining non-swim activity of a swimmer, comprising:
a processor configured to:
receive raw signals from at least one gyroscope for at least two axes of the at least one gyroscope;
process the raw signals through a band pass filter and receive a filtered signal from the band pass filter, the band pass filter stored in a non-transitory memory operably connected to the processor;
process the filtered signal using an energy envelope estimator, the energy envelope estimator stored in the non-transitory memory, and determine an energy envelope signal for at least one axis of the at least two axes; and
determine a non-swim activity segment of the raw signals based on the energy envelope signal using a detector, the detector stored in the non-transitory memory,
wherein the energy envelope estimator is configured to generate the energy envelope signal using a sliding window average of a preset window size over the filtered signal.

2 . The system as claimed in claim 1 , wherein the detector is configured to (i) compare values of the energy envelope signal for the at least one axis against a respective threshold value, and (ii) classify the non-swim activity segment of the raw signals as the non-swim activity upon satisfactory comparison.

3 . The system as claimed in claim 1 , wherein the at least one axis is selected from a group comprising: Y-axis, and X-axis and Y-axis.

4 . The system as claimed in claim 1 , wherein the processor is further configured to discard false positives of a stroke counter module, a length count module, and a swim type classifier module when the non-swim activity segment is detected.

5 . The system as claimed in claim 1 , wherein:
the at least one gyroscope is part of (i) a wearable device configured to be worn by the swimmer, or (ii) an external device connected to the wearable device, and the wearable device is selected from a group comprising: a smart watch, a smart ring, and a smart band.

6 . A method for determining non-swim activity of a swimmer, comprising:
receiving raw signals from at least one gyroscope for at least two axes of the at least one gyroscope; processing the raw signals through a band pass filter and receiving a filtered signal; processing the filtered signal by an energy envelope estimator, and determining an energy envelope signal for at least one axis of the at least two axes, and determining, by a detector, a non-swim activity segment of the raw signals based on the energy envelope signal, wherein the energy envelope estimator is configured to generate the energy envelope signal using a sliding window average of a preset window size over the filtered signal.

7 . The method as claimed in claim 6 , wherein the detector is configured to (i) compare values of the energy envelope signal for the at least one axis against a respective threshold value, and (ii) classify the non-swim activity segment of the raw signals as non-swim activity based upon satisfactory comparison.

8 . The method as claimed in claim 7 , wherein the at least one axis is selected from a group comprising: Y-axis, and X-axis and Y-axis.

9 . The method as claimed in claim 6 , further comprising:
discarding false positives of a stroke counter module, a length count module, and a swim type classifier module when the non-swim activity segment is detected.

10 . The method as claimed in claim 6 , wherein:
the at least one gyroscope is located in (i) a wearable device worn by the swimmer, or (ii) an external device connected to the wearable device, and the wearable device is selected from a group comprising: a smart watch, a smart ring, a smart band, and a sensor module.

Assignees

• Bosch Gmbh Robert
• Robert Bosch Engineering And Business Solutions Private Ltd
• Robert Bosch Eng And Business Solutions

Inventors

• Pooja Mohan

Classifications

• G06F2218/12

  Classification; Matching · CPC title

• G08B21/0446 Primary

  worn on the body to detect changes of posture, e.g. a fall, inclination, acceleration, gait · CPC title

• G06F18/24 Primary

  Classification techniques · CPC title