Granted Patent B2

US 12,657,755 · App. 18/141,872 · Granted Jun 16, 2026

Inventor: Dawson Toth (Elkton, MD)

Assignee: iFIT Inc.

G06T7/70G06T7/55G06V40/10H04N7/181G06T2207/10028G06T2207/30196

Abstract

Claims (58)

1 . A system for exercise tracking, the system comprising:

a first camera;

a second camera; and

a computing device in data communication with the first camera and the second camera, the computing device comprising:

a processor; and

a hardware storage device in data communication with the processor, the hardware storage device having instructions stored thereon that, when executed by the processor, cause the computing device to:

receive a first image from the first camera,

receive a second image from the second camera,

identify at least a part of a user body frame in the first image including a first plurality of nodes,

identify the user body frame in the second image including a second plurality of nodes, wherein a plurality of shared nodes includes at least two nodes of the first plurality of nodes identified in the second plurality of nodes,

correlate locations of the first plurality of nodes and the second plurality of nodes based on the plurality of shared nodes to identify a three-dimensional (3D) user body frame;

determine a single metric quantifying a match of a first movement of the 3D user body frame to a second movement of a workout exercise body frame;

compare the single metric quantifying the match to a first tolerance and a second tolerance different from the first tolerance; and

select at least one of suggesting a form correction and incrementing a repetition counter according to whether the single metric is within the first tolerance, within the second tolerance, or both.

2 . The system of claim 1 , wherein the first camera is a depth camera.

3 . The system of claim 1 , wherein the second camera is a depth camera.

4 . The system of claim 1 , further comprising a workout server in data communication with the computing device via a network.

5 . The system of claim 4 , wherein the workout server has a user account stored thereon, and wherein the instructions, when executed by the processor, further cause the computing device to:

store user body frame information of the 3D user body frame to the user account based at least in part on identifying the 3D user body frame; and

access the user body frame information from the user account for subsequent exercise tracking.

6 . The system of claim 5 , wherein the instructions, when executed by the processor, further cause the computing device to:

identify a user associated with the user account for the subsequent exercise tracking based at least in part on the stored user body frame information, a third image of the user from the first camera, and a fourth image of the user from the second camera.

7 . The system of claim 5 , wherein the user body frame information comprises a displacement between an initial location of at least one node of the 3D user body frame and an initial location of at least one corresponding node of the workout exercise body frame, displacements between initial locations of at least two nodes of the 3D user body frame, or a combination thereof.

8 . The system of claim 1 , the instructions further causing the computing device to:

obtain a workout exercise including the second movement of the workout exercise body frame; and

track the first movement of the 3D user body frame over time, wherein the single metric quantifying the match is determined based at least in part on comparing the first movement of the 3D user body frame to the second movement of the workout exercise body frame.

9 . The system of claim 8 , wherein the instructions further cause the computing device to:

suggest the form correction and increment the repetition counter based at least in part on the single metric quantifying the match satisfying the first tolerance and failing to satisfy the second tolerance.

10 . The system of claim 8 , wherein, to obtain the workout exercise, the instructions further cause the computing device to access a workout server.

11 . The system of claim 8 , wherein the instructions further cause the computing device to:

suggest the form correction based at least partially on the single metric quantifying the match not being within the second tolerance.

12 . The system of claim 11 , further comprising:

a display device in data communication with the computing device, wherein, to suggest the form correction, the instructions, when executed by the processor, cause the computing device to:

display, on the display device, the 3D user body frame, wherein a first portion of the 3D user body frame is displayed as a different color than a second portion of the 3D user body frame based at least in part on respective alignments of the first portion and the second portion with the workout exercise body frame, detection of the first portion and the second portion, or both.

13 . The system of claim 8 , wherein the instructions further cause the computing device to:

increment the repetition counter based at least partially on the single metric quantifying the match being within the first tolerance.

14 . The system of claim 8 , wherein, to obtain the workout exercise, the instructions further cause the computing device to:

align the 3D user body frame with the workout exercise body frame before a user begins the workout exercise.

15 . The system of claim 8 , wherein, to determine the single metric quantifying the match, the instructions, when executed by the processor, cause the computing device to:

compare the first movement of the 3D user body frame to the second movement of the workout exercise body frame, wherein a first match of a first portion of the 3D user body frame is weighted differently than a second match of a second portion of the 3D user body frame in determining the single metric based at least in part on the workout exercise.

16 . The system of claim 1 , wherein the single metric comprises a percentage of nodes of the 3D user body frame that match the second movement of the workout exercise body frame within a tolerance, a sum of displacements of the nodes of the 3D user body frame from corresponding nodes of the workout exercise body frame, an average of the displacements of the nodes of the 3D user body frame from the corresponding nodes of the workout exercise body frame, or any combination thereof.

17 . A system for exercise tracking, the system comprising:

a first camera;

a second camera; and

a computing device in data communication with the first camera and the second camera, the computing device comprising:

a processor; and

a hardware storage device in data communication with the processor, the hardware storage device having instructions stored thereon that, when executed by the processor, cause the computing device to:

receive a first image from the first camera,

receive a second image from the second camera,

identify at least a part of a user body frame in the first image including a first plurality of nodes,

identify the user body frame in the second image including a second plurality of nodes, wherein a plurality of shared nodes includes at least two nodes of the first plurality of nodes identified in the second plurality of nodes,

correlate locations of the first plurality of nodes and the second plurality of nodes based on the plurality of shared nodes to identify a 3D user body frame,

obtain a workout exercise including a first movement of a workout exercise body frame,

align the 3D user body frame with a frame of the workout exercise before a user begins the workout exercise,

track a second movement of the 3D user body frame,

determine a single metric quantifying a match in the second movement of the 3D user body frame to the first movement of the workout exercise body frame based at least in part on a comparison of the first movement to the second movement,

suggest a form correction based at least partially on the single metric not being within a first tolerance, and

increment a repetition counter based at least partially on the single metric being within a second tolerance.

Assignments (13)

Continuity (2)

References Cited (400)