IP Library Granted Patent US 12,427,375
Granted Patent B2
US 12,427,375 · App. 17/416,236 · Granted Sep 30, 2025

Real-time, fully interactive, virtual sports and wellness trainer and physiotherapy system

Inventors: Kim Russell (Pinehurst, NC); David Horachek (Pinehurst, NC); Eduardo Guendelman (Pinehurst, NC); Jochem Hess (Pinehurst, NC)
Assignee: 4D Health Science LLC
A63B24/0062A63B24/0087A63B71/0622G06V10/25G06V40/103G06V40/23G16H20/30G16H40/67A63B2024/0096A63B2071/0677A63B2220/806
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 12,427,375
App. No.
17/416,236
Granted
Sep 30, 2025
Kind
B2
Abstract

A telehealth training system is provided which employs a three-dimensional camera programmed for capturing image data associated with an exercise program performed by a user. A computer-implemented body pose analysis and scoring module analyzes and scores body poses of the user while the user performs the exercise program. The analysis and scoring module may calculate scores in response to reference data related to at least one exercise prescribed for the user, and then compare processing results to the reference data. A feedback module may be included in the system which is programmed for creating and animating an avatar in response to the processing results of the analysis and scoring module. In certain aspects, the analysis and scoring module may be programmed for using a voxel basis function (VBF) technique in connection with performing pose matching analysis in association with the user performing the exercise program.

Claims (41)

1. A telehealth training system comprising:

a three-dimensional camera programmed for capturing image data associated with an exercise program performed by a user;

a computer-implemented body pose analysis and scoring module programmed for analyzing and scoring body poses of the user while the user performs the exercise program;

the analysis and scoring module programmed for calculating a score in response to:

reference data related to at least one exercise prescribed for the user, and

comparing processing results of the analysis and scoring module to the reference data;

a feedback module programmed for creating and animating an avatar in response to the processing results of the analysis and scoring module; and,

the analysis and scoring module programmed for using a voxel basis function (VBF) technique in connection with performing pose matching analysis in association with the user performing the exercise program.

2. The system of claim 1 , further comprising a module programmed for communicating at least a portion of the processing results of the analysis and scoring module to a data storage medium associated with at least one practitioner.

3. The system of claim 1 , further comprising a module programmed for communicating at least a portion of the processing results of the analysis and scoring module to a data storage medium associated with at least one payor.

4. The system of claim 1 , wherein the three-dimensional camera is operatively associated with at least one screen display located in an environment where the user performs the exercise program.

5. The system of claim 1 , further comprising a noise cancelling module programmed for reducing signal noise contained in a data stream captured by the three-dimensional camera.

6. The system of claim 1 , further comprising a background elimination module programmed for removing from image data captured by the three-dimensional camera at least one fixture in a field of view of the three-dimensional camera.

7. The system of claim 1 , further comprising a background elimination module programmed for removing from image data captured by the three-dimensional camera at least one moving object in a field of view of the three-dimensional camera.

8. The system of claim 1 , further comprising a skeleton estimation module programmed for generating at least one skeleton model for the user.

9. The system of claim 1 , wherein the feedback module is further programmed for communicating visual or audible encouragement to the user in response to the user performing the exercise program.

10. The system of claim 1 , further comprising the feedback module programmed for communicating at least one avatar movement or voice message in association with a positive script or a negative script.

11. The system of claim 10 , further comprising the feedback module programmed for using a randomizer for randomizing at least one script to promote the avatar moving or talking in a non-repetitive way.

12. The system of claim 1 , further comprising the analysis and scoring module programmed for using a piecewise continuous basis function (PCBF) technique in connection with the pose matching analysis.

13. The system of claim 1 , further comprising the analysis and scoring module programmed for using the voxel basis function (VBF) technique when skeleton model information is not available.

14. The system of claim 13 , further comprising the analysis and scoring module programmed for using a sequence of axis-aligned bounding boxes to track progression of the user through the exercise program.

15. A telehealth training method comprising:

capturing, by a three-dimensional camera, image data associated with an exercise program performed by a user;

analyzing, by an analysis and scoring module, body poses of the user while the user performs the exercise program;

calculating a score, by the analysis and scoring module, in response to:

reference data related to at least one exercise prescribed for the user, and

comparing processing results of the analysis and scoring module to the reference data;

creating and animating an avatar, by an avatar animation module, in response to the processing results of the analysis and scoring module; and

using a voxel basis function (VBF) technique in connection with performing the body pose analysis in association with the user performing the exercise program.

16. The method of claim 15 , further comprising communicating at least a portion of the processing results of the analysis and scoring module to a data storage medium associated with at least one practitioner.

17. The method of claim 15 , further comprising communicating at least a portion of the processing results of the analysis and scoring module to a data storage medium associated with at least one payor.

18. The method of claim 15 , further comprising using a noise canceling module for reducing signal noise contained in a data stream captured by the three-dimensional camera.

19. The method of claim 15 , further comprising using a background elimination module for removing from image data captured by the three-dimensional camera at least one fixture in a field of view of the three-dimensional camera.

20. The method of claim 15 , further comprising using a background elimination module for removing from image data captured by the three-dimensional camera at least one moving object in a field of view of the three-dimensional camera.

21. The method of claim 15 , further comprising using a skeleton estimation module for generating at least one skeleton model for the user.

22. The method of claim 15 , further comprising communicating visual or audible encouragement to the user in response to the user performing the exercise program.

23. The method of claim 15 , further comprising communicating at least one avatar movement or voice message in association with a positive script or a negative script.

24. The method of claim 23 , further comprising using a randomizer for randomizing at least one script to promote the avatar moving or talking in a non-repetitive way.

25. The method of claim 15 , further comprising using a piecewise continuous basis function (PCBF) technique in connection with the pose matching analysis.

26. The method of claim 15 , further comprising using the voxel basis function (VBF) technique when skeleton model information is not available.

27. The method of claim 26 , further comprising using a sequence of axis-aligned bounding boxes to track progression of the user through the exercise program.

Continuity (2)
Provisional Application 62781332 · Dec 18, 2018
Related Publication 20220072377A1 · Mar 10, 2022
References Cited (38)
US 6007459A · Burgess · 1999 [cited by applicant]
US 9011293B2 · Shavit et al. · 2015 [cited by applicant]
US 9283429B2 · Aragones et al. · 2016 [cited by applicant]
US 9302170B2 · Balakrishnan et al. · 2016 [cited by applicant]
US 9694241B2 · Balakrishnan et al. · 2017 [cited by applicant]
US 9747722B2 · Adler et al. · 2017 [cited by applicant]
US 9875664B2 · Dalal et al. · 2018 [cited by applicant]
US 9883838B2 · Kaleal, Iii et al. · 2018 [cited by applicant]
US 9892655B2 · Snow et al. · 2018 [cited by applicant]
US 9919186B2 · Aragones et al. · 2018 [cited by applicant]
US 9977874B2 · Aragones et al. · 2018 [cited by applicant]
US 9981193B2 · Adams et al. · 2018 [cited by applicant]
US 9987520B2 · Shavit et al. · 2018 [cited by applicant]
US 20090042695A1 · Chien et al. · 2009 [cited by applicant]
US 20100280418A1 · Klose · 2010 [cited by applicant]
US 20120268372A1 · Park et al. · 2012 [cited by applicant]
US 20130123667A1 · Komatireddy et al. · 2013 [cited by applicant]
US 20130178960A1 · Sheehan et al. · 2013 [cited by applicant]
US 20130252216A1 · Clavin et al. · 2013 [cited by applicant]
US 20140172377A1 · Taubin et al. · 2014 [cited by applicant]
US 20140270351A1 · Hoof et al. · 2014 [cited by applicant]
US 20140287389A1 · Kallmann et al. · 2014 [cited by applicant]
US 20160086500A1 · Kaleal, Iii · 2016 [cited by applicant]
US 20170004631A1 · Yang · 2017 [cited by applicant]
US 20170249401A1 · Eckart et al. · 2017 [cited by applicant]
US 20170266491A1 · Rissanen · 2017 [cited by examiner]
US 20180121728A1 · Wells et al. · 2018 [cited by applicant]
US 20180130373A1 · Bernard-Paroly et al. · 2018 [cited by applicant]
US 20180199861A1 · Ye et al. · 2018 [cited by applicant]
US 20180228430A1 · Perez Marcos et al. · 2018 [cited by applicant]
US 20180369637A1 · Hoang et al. · 2018 [cited by applicant]
US 20220105389A1 · Lianides · 2022 [cited by examiner]
CN 114035683A · 2022 [cited by applicant]
CN 114782945A · 2022 [cited by applicant]
CN 114035683B · 2024 [cited by applicant]
DE 102022112008A1 · 2023 [cited by applicant]
MX 2021007514A · 2021 [cited by applicant]
International Search Report and Written Opinion for corresponding International Application No. PCT/US19/67242 filed Dec. 18, 2019, dated Feb. 28, 2020, 15 pages. [cited by applicant]