Systems and methods of swimming analysis
Systems and methods of analyzing a user's motion during a swimming session are described. One or more motions sensors can collect motion data of the user. A processor circuit can make motion analysis based on the motion data. The processor circuit can determine if the user's arm swing is a genuine swim stroke. The processor circuit can also determine whether the user is swimming or turning. The processor circuit can also classify the user's swim stroke style. The processor circuit can also determine the user's swim stroke phase. The processor circuit can also determine the user's stroke orbit consistency.
1. A method for improving an accuracy of a wearable device while classifying a user's swim stroke style, the method comprising:
receiving, by a processor circuit of a wearable device, motion data from one or more motion sensors of the wearable device, wherein the one or more motion sensors comprises at least one of an accelerometer or a gyroscope;
determining, by the processor circuit, rotational data of the wearable device, wherein the rotational data is expressed in a frame of reference,
extracting, by the processor circuit, one or more features from the rotational data;
determining, by the processor circuit, the user's swim stroke style based on the one or more features; and
in response to determining the user's swim stroke style, determining, by the processor circuit, a level of orbit consistency for a plurality of swim strokes performed by the user based on the rotational data, wherein the level of orbit consistency measures a variation in direction of the plurality of swim strokes performed by the user; and
outputting, by the processor circuit, the determined swim stroke style and the level of orbit consistency for the plurality of swim strokes.
2. The method of claim 1 , wherein the frame of reference is a body-fixed frame of reference with respect to the wearable device.
3. The method of claim 1 , wherein the frame of reference is an inertial frame of reference.
4. The method of claim 1 , wherein the one or more features comprise at least one of:
a mean crown orientation of the wearable device,
a correlation of the user's arm rotation and the user's wrist rotation, or
a contribution of rotation about a crown of the wearable device to a total angular velocity.
5. The method of claim 4 , wherein the determining comprises performing a first-tier analysis on at least one of the features.
6. The method of claim 5 , wherein the first-tier analysis indicates an upwards mean crown orientation during a fastest part of a stroke for a backstroke or a downwards mean crown orientation during a fastest part of a stroke for a breaststroke.
7. The method of claim 5 , wherein the first-tier analysis indicates a positive correlation of arm and wrist rotations for a backstroke or a negative correlation of arm and wrist rotations for a breaststroke.
8. The method of claim 1 , wherein the one or more features comprise at least one of:
a relative arm rotation about a band of the wearable device during a pull phase,
a moment arm of the user,
a ratio of acceleration along a z axis to rotation about a y axis, wherein the z axis and the y axis are both either in an inertial frame of reference or a fixed body frame of reference with respect to the wearable device,
a mean gravity crown weighted by acceleration,
a correlation between an orientation of top of the band of the wearable device and rotation around the band of the wearable device,
a root mean square (RMS) of a crown rotation,
a minimum rotation around a crown of the wearable device,
a maximum rotation around the band of the wearable device, or
a maximum rotation about an x axis divided by a maximum rotation about a y axis, wherein the x axis and the y axis are both either in an inertial frame of reference or a fixed body frame of reference with respect to the wearable device.
9. The method of claim 8 , wherein the determining comprises performing a second-tier analysis on at least one of the features.
10. The method of claim 9 , wherein an outcome of the second-tier analysis indicates a butterfly stroke or a freestyle stroke.
11. A wearable device configured to classify a user's swim stroke style, the device comprising:
one or more motion sensors comprising at least one of an accelerometer or a gyroscope, the one or more motion sensors being configured to output motion data; and
a processor circuit in communication with the one or more motion sensors, the processor circuit being configured to:
receive the motion data from the one or more motion sensors;
determine rotational data of the wearable device, wherein the rotational data is expressed in a frame of reference;
extract one or more features from the rotational data;
determine the user's swim stroke style based on the one or more features;
in response to determining the user's swim stroke style, determine a level of orbit consistency for a plurality of swim strokes performed by the user based on the rotational data, wherein the level of orbit consistency measures a variation in direction of the plurality of swim strokes performed by the user; and
output the determined swim stroke style and the level of orbit consistency for the plurality of strokes.
12. The wearable device of claim 11 , wherein the frame of reference is a body-fixed frame of reference with respect to the wearable device.
13. The wearable device of claim 11 , wherein the frame of reference is an inertial frame of reference.
14. The wearable device of claim 11 , wherein the one or more features comprise at least one of:
a mean crown orientation of the wearable device,
a correlation of the user's arm rotation and the user's wrist rotation, or
a contribution of rotation about a crown of the wearable device to a total angular velocity.
15. The wearable device of claim 14 , wherein the determining comprises performing a first-tier analysis on at least one of the features.
16. The wearable device of claim 15 , wherein the first-tier analysis indicates an upwards mean crown orientation during a fastest part of a stroke for a backstroke or a downwards mean crown orientation during a fastest part of a stroke for a breaststroke.
17. The wearable device of claim 15 , wherein the first-tier analysis indicates a positive correlation of arm and wrist rotations for a backstroke or a negative correlation of arm and wrist rotations for a breaststroke.
18. The wearable device of claim 11 , wherein the one or more features comprise at least one of:
a relative arm rotation about a band of the wearable device during a pull phase,
a moment arm of the user,
a ratio of acceleration of the wearable device along a z axis to rotation of the wearable device about a y axis, wherein the z axis and the y axis are both either in an inertial frame of reference or a fixed body frame of reference with respect to the wearable device,
a mean gravity crown weighted by acceleration,
a correlation between an orientation of top of the band of the wearable device and rotation around the band of the wearable device,
a root mean square (RMS) of a crown rotation,
a minimum rotation around a crown of the wearable device,
a maximum rotation around the band of the wearable device, or
a maximum rotation of the wearable device about an x axis divided by a maximum rotation of the wearable device about the y axis, wherein the z axis and the y axis are both either in an inertial frame of reference or a fixed body frame of reference with respect to the wearable device.
19. The wearable device of claim 18 , wherein the determining comprises performing a second-tier analysis on at least one of the features.
20. The wearable device of claim 19 , wherein an outcome of the second-tier analysis indicates a butterfly stroke or a freestyle stroke.