Automated activity detection and tracking

Patent metadata

Field	Value
Publication number	US-11253747-B2
Application number	US-201916295511-A
Country	US
Kind code	B2
Filing date	Mar 7, 2019
Priority date	Mar 7, 2019
Publication date	Feb 22, 2022
Grant date	Feb 22, 2022

Abstract

A method is provided for detecting at least one fitness related activity is provided. Data is obtained from at least one sensor of a wearable device, wherein the at least one sensor detects the data based on at least one body movement of a user wearing the wearable device. Based on the obtained data, the at least one fitness related activity is detected from a set of fitness related activities, wherein the detection is performed without pre-training by the user for the detecting.

First claim

What is claimed is:

1. A method for detecting at least one fitness related activity, comprising:
obtaining data from at least one sensor of a wearable device, wherein the at least one sensor detects the data based on at least one body movement of a user wearing the wearable device; and
detecting, based on the data, the at least one fitness related activity from a set of fitness related activities and number of repetitions, wherein the detection is performed without pre-training by the user for the detecting, wherein the detecting comprises:
in a first stage, detecting the at least one fitness related activity based on a machine learning based activity detection algorithm; and
in a second stage, detecting the number of repetitions of the detected at least one fitness related activity based on a template specific to the detected fitness related activity using dynamic time warping.

2. The method of claim 1 , further comprising:
determining, based on the data, at least one characteristic related to the detected at least one fitness related activity.

3. The method of claim 2 , wherein the at least one characteristic comprises a number of repetitions of the detected at least one fitness related activity over a given time period.

4. The method of claim 2 , wherein the at least one characteristic comprises at least one of a duration of the at least one body movement related to the at least one fitness related activity, an extent of the at least one body movement related to the at least one fitness related activity, or intensity of performing the at least one fitness related activity.

5. The method of claim 1 , further comprising:
obtaining a selection by the user of the at least one fitness related activity from the set, wherein the detecting comprises attempting to detect, based on the data, the selected at least one fitness related activity.

6. The method of claim 5 , further comprising:
obtaining a desired number of repetitions of the selected at least one fitness related activity;
determining, upon detecting the selected at least one fitness related activity, a number of repetitions related to the selected at least one fitness related activity in a given time period; and
generating an indication when the number of repetitions is same as the desired number of repetitions.

7. The method of claim 1 , further comprising:
determining, based on the data, at least one pattern of the at least one body movement by the user associated with the detected at least one fitness related activity; and
adjusting sensitivity of the at least one sensor based on the determined pattern.

8. The method of claim 1 , wherein the detection of the at least one fitness related activity comprises:
obtaining a threshold value of at least one parameter included in the data; and
deciding that the at least one fitness related activity is detected when the at least one parameter equals or exceeds the threshold value.

9. The method of claim 1 , further comprising:
obtaining additional data from at least another sensor of at least another wearable device worn by the user, wherein the detecting is further based on the additional data.

10. The method of claim 1 , wherein the set of fitness related activities comprises at least one of squats, lunges, jumping jacks, jumping rope, push-ups, lateral jumps, squat jumps, step-ups, around the world plank, or skips.

11. The method of claim 1 , further comprising:
determining, based on the data, an accuracy of performing the detected at least one fitness related activity including at least one of a form, speed, intensity or consistency related to the performed at least one fitness related activity.

12. The method of claim 1 , wherein the at least one sensor comprises an inertial motion unit (IMU), and in the second stage, detecting the number of repetitions comprises:
comparing collected signals from the IMU to the template specific to the detected fitness related activity using dynamic time warping.

13. A non-transitory computer-readable medium for detecting at least one fitness related activity, the computer-readable medium storing instructions which when processed by at least one processor perform a method comprising:
obtaining data from at least one sensor of a wearable device, wherein the at least one sensor detects the data based on at least one body movement of a user wearing the wearable device; and
detecting, based on the data, the at least one fitness related activity from a set of fitness related activities and a number of repetitions, wherein the detection is performed without pre-training by the user for the detecting, wherein the detecting comprises:
in a first stage, detecting the at least one fitness related activity based on a machine learning based activity detection algorithm; and
in a second stage, detecting the number of repetitions of the detected at least one fitness related activity based on a template specific to the detected fitness related activity using dynamic time warping.

14. The computer-readable medium of claim 13 , further comprising instructions for:
determining, based on the data, at least one characteristic related to the detected at least one fitness related activity.

15. The computer-readable medium of claim 14 , wherein the at least one characteristic comprises a number of repetitions of the detected at least one fitness related activity over a given time period.

16. The computer-readable medium of claim 13 , further comprising instructions for:
obtaining a selection by the user of the at least one fitness related activity from the set, wherein the detecting comprises attempting to detect, based on the data, the selected at least one fitness related activity.

17. The computer-readable medium of claim 16 , further comprising instructions for:
obtaining a desired number of repetitions of the selected at least one fitness related activity;
determining, upon detecting the selected at least one fitness related activity, a number of repetitions related to the selected at least one fitness related activity in a given time period; and
generating an indication when the number of repetitions is same as the desired number of repetitions.

18. The computer-readable medium of claim 13 , further comprising instructions for:
determining, based on the data, at least one pattern of the at least one body movement by the user associated with the detected at least one fitness related activity; and
adjusting sensitivity of the at least one sensor based on the determined pattern.

19. The computer-readable medium of claim 13 , wherein the detecting the at least one fitness related activity comprises:
obtaining a threshold value of at least one parameter included in the data; and
deciding that the at least one fitness related activity is detected when the at least one parameter equals or exceeds the threshold value.

20. A system for detecting at least one fitness related activity, comprising:
at least one processor configured to:
obtain data from at least one sensor of a wearable device, wherein the at least one sensor detects the data based on body movements of a user wearing the wearable device; and
detect, based on the data, the at least one fitness related activity from a set of fitness related activities and a number of repetitions, wherein the detection is performed without pre-training by the user of a system configured for the detection, wherein the at least one processor is configured to detect by:
in a first stage, detect the at least one fitn

Assignees

• Bose Corp

Inventors

• Patil Naganagouda
• Sydorenko Mark
• Gordon John
• Levens Bruce C
• Burns Ryan K
• Kemmerer Jeremy
• Sales Juan Carlos Rodero
• Berardi William

Classifications

• G06F3/011 Primary

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• A63B2024/0071

  Distinction between different activities, movements, or kind of sports performed · CPC title

• G06F3/017

  Gesture based interaction, e.g. based on a set of recognized hand gestures (interaction based on gestures traced on a digitiser G06F3/04883) · CPC title

• A63B24/0062

  Monitoring athletic performances, e.g. for determining the work of a user on an exercise apparatus, the completed jogging or cycling distance · CPC title

• A63B24/0003 Primary

  Analysing the course of a movement or motion sequences during an exercise or trainings sequence, e.g. swing for golf or tennis · CPC title