Augmented reality guided musculoskeletal exercises
An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.
1. A method comprising:
providing an augmented reality (AR) graphic for display on a client device of a user, the AR graphic comprising a plurality of segments of a target musculoskeletal form to start an exercise program;
receiving video data captured by a camera of the client device, the camera positioned such that the user is within a field of view of the camera;
determining, by the client device, a musculoskeletal form indicating a position of a plurality of segments of a body of the user, by processing the video data;
comparing a position of one or more segments of the plurality of segments of the body of the user with a position of one or more segments of the plurality of segments of the target musculoskeletal form;
determining, by the client device, a level of similarity between the musculoskeletal form and the target musculoskeletal form based on the comparison; and
responsive to determining that the level of similarity is within a threshold value, by the client device, starting the exercise program on the client device and providing a notification for display on the client device indicating that the exercise program has started.
2. The method of claim 1 , further comprising:
providing, using the video data, a visual representation of the user for display on the client device, wherein providing the AR graphic for display comprises overlaying the AR graphic on the visual representation of the user, the AR graphic being at least partially transparent.
3. The method of claim 2 , further comprising:
generating the visual representation of the user in 3D using depth information of the video data, and wherein the AR graphic is displayed in 3D.
4. The method of claim 1 , further comprising:
providing instructions for display on the client device, the instructions indicating a target orientation of the client device to capture the video data for the exercise program.
5. The method of claim 1 , further comprising:
determining an image of the user indicative of the target musculoskeletal form starting the exercise program; and
generating the AR graphic using the image of the user.
6. The method of claim 1 , further comprising:
responsive to determining that the level of similarity is not within the threshold value, providing guidance indicative of proper musculoskeletal form starting the exercise program for display on the client device.
7. The method of claim 1 , wherein determining the musculoskeletal form of the user comprises:
identifying a first segment and a second segment of the plurality of segments of the body of the user by processing the video data; and
determining an angle of the first segment relative to the second segment.
8. The method of claim 7 , wherein determining the level of similarity between the musculoskeletal form and the target musculoskeletal form based on the comparison comprises:
determining a difference between the angle and a target angle of the one or more segments of the plurality of segments of the AR graphic.
9. The method of claim 8 , wherein determining that the level of similarity is within the threshold value comprises:
comparing the difference against a threshold angle of error.
10. A method comprising:
providing, by an exercise feedback system, an augmented reality (AR) graphic for display on a client device of a user, the AR graphic comprising a plurality of segments of a target musculoskeletal form to start an exercise program;
receiving, from the client device by the exercise feedback system, video data captured by a camera of the client device, the camera positioned such that the user is within a field of view of the camera;
determining a musculoskeletal form indicating a position of a plurality of segments of a body of the user, by processing the video data;
comparing a position of one or more segments of the plurality of segments of the body of the user with a position of one or more segments of the plurality of segments of the target musculoskeletal form; and
providing, by the exercise feedback system to the client device, an indication that a level of similarity between the musculoskeletal form of the user and the target musculoskeletal form based on the comparison is within a threshold value, wherein the client device is configured to start the exercise program on the client device for the exercise responsive to receiving the indication.
11. The method of claim 10 , further comprising:
generating, using the video data, a visual representation of the user for display on the client device, wherein the AR graphic is configured to be overlaid on the visual representation of the user, the AR graphic being at least partially transparent.
12. The method of claim 10 , further comprising:
determining an image of the user indicative of the target musculoskeletal form starting the exercise program; and
generating the AR graphic using the image of the user.
13. The method of claim 10 , wherein determining the musculoskeletal form of the user comprises:
identifying a first segment and a second segment of the plurality of segments of the body of the user by processing the video data;
determining an angle of the first segment relative to the second segment; and
wherein determining the level of similarity between the musculoskeletal form and the target musculoskeletal form based on the comparison comprises determining a difference between the angle and a target angle of the one or more segments of the plurality of segments of the AR graphic.
14. A non-transitory computer-readable storage medium storing instructions that when executed by a processor cause the processor to perform steps including:
providing an augmented reality (AR) graphic for display on a client device of a user, the AR graphic comprising a plurality of segments of a target musculoskeletal form to start an exercise program;
receiving video data captured by a camera of the client device, the camera positioned such that the user is within a field of view of the camera;
determining, by the client device, a musculoskeletal form indicating a position of a plurality of segments of a body of the user, by processing the video data;
comparing a position of one or more segments of the plurality of segments of the body of the user with a position of one or more segments of the plurality of segments of the target musculoskeletal form;
determining, by the client device, a level of similarity between the musculoskeletal form and the target musculoskeletal form based on the comparison; and
responsive to determining that the level of similarity is within a threshold value, by the client device, starting the exercise program on the client device and providing a notification for display on the client device indicating that the exercise program has started.
15. The computer-readable storage medium of claim 14 , wherein the steps further comprise:
providing, using the video data, a visual representation of the user for display on the client device, wherein providing the AR graphic for display comprises overlaying the AR graphic on the visual representation of the user, the AR graphic being at least partially transparent.
16. The computer-readable storage medium of claim 15 , wherein the steps further comprise:
generating the visual representation of the user in 3D using depth information of the video data, and wherein the AR graphic is displayed in 3D.
17. The computer-readable storage medium of claim 14 , wherein the steps further comprise:
determining an image of the user indicative of the target musculoskeletal form starting the exercise program; and
generating the AR graphic using the image of the user.
18. The computer-readable storage medium of claim 14 , wherein determining the musculoskeletal form of the user comprises:
identifying a first segment and a second segment of the plurality of segments of the body of the user by processing the video data; and
determining an angle of the first segment relative to the second segment.
19. The computer-readable storage medium of claim 18 , wherein determining the level of similarity between the musculoskeletal form and the target musculoskeletal form based on the comparison comprises:
determining a difference between the angle and a target angle of the one or more segments of the plurality of segments of the AR graphic.
20. The computer-readable storage medium of claim 19 , wherein determining that the level of similarity is within the threshold value comprises:
comparing the difference against a threshold angle of error.