Automatic detection and quantification of swimming
A wearable device for tracking swim activities of a user is provided. The wearable device may include one or more sensors configured to generate sensor data, and based on the sensor data, the wearable device may determine swim metrics such as swim stroke count, swim stroke type, swim lap count, and swim speed. The determined swim metrics may be filtered based on one or more swim periods during which the user is likely to have been swimming. The wearable device may determine such swim periods based on the sensor data and/or the determined swim metrics.
1. A computer-implemented method comprising:
obtaining, via one or more motion sensors of a wearable computing device worn by a user, sensor data, the sensor data comprising motion data including a motion signature;
determining, via one or more processors, the user is performing a kicking motion associated with swimming based, at least in part, on comparing peaks extracted from the motion signature of the sensor data to predefined thresholds corresponding to a plurality of activities, the plurality of activities including swimming;
determining, via the one or more processors, the user is swimming based at least in part on determining that the user is performing the kicking motion associated with swimming and without any user input indicating the user is swimming, has begun swimming, or has finished swimming being provided via a user interface;
determining, via the one or more processors, one or more swim metrics in response to determining the user is swimming, the one or more swim metrics being determined based, at least in part, on the sensor data, wherein determining the one or more swim metrics in response to determining the user is swimming includes:
turning on, via the one or more processors, one or more additional sensors of the wearable computing device such that the one or more additional sensors begin collecting additional data;
extracting, via the one or more processors, the peaks from the motion data; and
determining, via the one or more processors, the one or more swim metrics based, at least in part, on the peaks extracted from the motion data and the additional data using a sensor fusion algorithm; and
causing, via the one or more processors, the one or more swim metrics to be displayed on a display screen for viewing by the user.
2. The computer-implemented method of claim 1 , wherein determining the user is performing the kicking motion associated with swimming based, at least in part, on comparing the peaks extracted from the motion signature of the sensor data to the predefined thresholds corresponding to the plurality of activities includes:
comparing, via the one or more processors, the peaks extracted from the motion signature of the motion data to peaks in predefined motion data in the predefined thresholds, the peaks in the predefined motion data being indicative of the kicking motion associated with swimming; and
determining, via the one or more processors, the motion data corresponds to the predefined motion data indicative of the kicking motion associated with swimming when the peaks extracted from the motion signature correspond to one or more of the peaks in the predefined motion data indicative of the kicking motion associated with swimming.
3. The computer-implemented method of claim 1 , wherein determining the user is performing the kicking motion associated with swimming based, at least in part, on comparing the peaks extracted from the motion signature of the sensor data to the predefined thresholds corresponding to the plurality of activities includes:
extracting, via the one or more processors, the peaks from the motion data by converting the motion signature from a time domain to a frequency domain, each of the peaks representing an amplitude at a respective frequency in the motion signature; and
determining, via the one or more processors, the user is performing the kicking motion based, at least in part, on the peaks extracted from the motion data corresponding to one or more of the predefined thresholds indicative of the user performing the kicking motion associated with swimming.
4. The computer-implemented method of claim 3 , wherein
the motion data includes acceleration data; and
the peaks include one or more acceleration peaks corresponding to the one or more of the predefined thresholds indicative of the user performing the kicking motion associated with swimming.
5. The computer-implemented method of claim 3 , wherein extracting the peaks from the motion data comprises extracting the peaks from the motion data comprises by converting the motion signature from the time domain to the frequency domain using a Fast Fourier Transform.
6. The computer-implemented method of claim 1 , wherein: the motion data includes acceleration data; and the peaks include one or more acceleration peaks indicative of the user performing the kicking motion associated with swimming.
7. The computer-implemented method of claim 1 , wherein the one or more swim metrics include at least one of swim stroke count, swim stroke type, swim kick count, swim lap count, swim lap duration, swim lap start time, swim lap end time, or swim speed.
8. The computer-implemented method of claim 1 , wherein the plurality of activities further includes one or more of biking, hiking, running, jogging, walking, sitting, lying down, sleeping, elliptical, weight training, or typing.
9. A wearable computing device comprising:
a housing configured to be in contact with a user;
one or more motion sensors at least partially positioned within the housing, the motion sensors being configured to generate sensor data, the sensor data comprising motion data including a motion signature; and
one or more processors positioned within the housing, the one or more processors being configured to:
obtain, via the one or more motion sensors, the sensor data;
determine the user wearing the wearable computing device is performing a kicking motion associated with swimming based, at least in part, on comparing peaks extracted from the motion signature of the sensor data to predefined thresholds corresponding to a plurality of activities, the plurality of activities including swimming;
determine the user is swimming based at least in part on determining that the user is performing the kicking motion associated with swimming and without any user input indicating the user is swimming, has begun swimming, or has finished swimming being provided via a user interface; and
determine one or more swim metrics based, at least in part, on the sensor data in response to determining the user is swimming; and
one or more additional sensors, wherein to determine the one or more swim metrics in response to determining the user is swimming, the one or more processors are configured to:
turn on the one or more additional sensors of the wearable computing device such that the one or more additional sensors begin collecting additional data;
extract one or more features from the motion data; and
determine the one or more swim metrics based, at least in part, on the one or more features extracted from the motion data and the additional data from the one or more additional sensors using a sensor fusion algorithm.
10. The wearable computing device of claim 9 ,
wherein to determine the user is performing the kicking motion associated with swimming based, at least in part, on comparing the peaks extracted from the motion signature of the sensor data to the predefined thresholds corresponding to the plurality of activities, the one or more processors are configured to:
extract the peaks from the motion data by converting the motion signature from a time domain to a frequency domain, each of the peaks representing an amplitude at a respective frequency in the motion signature; and
determine the user is performing the kicking motion based, at least in part, on the peaks extracted from the motion data corresponding to one or more of the predefined thresholds indicative of the user performing the kicking motion associated with swimming.
11. The wearable computing device of claim 10 , wherein the motion data includes acceleration data, and the peaks include one or more acceleration peaks corresponding to the one or more of the predefined thresholds indicative of the user performing the kicking motion.
12. The wearable computing device of claim 9 , wherein: the one or more swim metrics include a kick count; the motion data includes accelerometer data; and the peaks extracted from the acceleration data includes one or more acceleration peaks indicative of the user performing the kicking motion associated with swimming.
13. The wearable computing device of claim 9 , wherein to determine the user is wearing the wearable computing device is performing the kicking motion associated with swimming based, at least in part, on comparing the peaks extracted from the motion signature of the sensor data to the predefined thresholds corresponding to the plurality of activities, the one or more processors are configured to:
compare the peaks extracted from the motion signature of the motion data to peaks in predefined motion data in the predefined thresholds, the peaks in the predefined motion data being indicative of the kicking motion associated with swimming; and
determine the motion data corresponds to the predefined motion data indicative of the kicking motion associated with swimming when the peaks extracted from the motion signature correspond to one or more of the peaks in the predefined motion data indicative of the kicking motion associated with swimming.
14. The wearable computing device of claim 9 , wherein the one or more swim metrics include at least one of swim stroke count, swim stroke type, swim kick count, swim lap count, swim lap duration, swim lap start time, swim lap end time, or swim speed.
15. The wearable computing device of claim 9 , wherein the one or more processors are configured to cause a display screen of the wearable computing device to display the one or more swim metrics.
16. The wearable computing device of claim 9 , wherein the one or more processors are further configured to:
determine the user wearing the wearable computing device is no longer performing the kicking motion associated with swimming when the peaks extracted from the motion signature correspond more with one or more of the predefined thresholds that correspond to one or more other activities of the plurality of activities than one or more of the predefined thresholds corresponding to the kicking motion associated with swimming; and
cease determining the one or more swim metrics in response to determining the user is no longer performing the kicking motion associated with swimming.
17. A non-transitory computer-readable medium storing computer-executable instructions that, when executed by one or more processors, cause the one or more processors to:
obtain sensor data from one or more motion sensors of a wearable computing device worn by a user, the sensor data comprising motion data including a motion signature;
determine the user wearing the wearable computing device is performing a kicking motion associated with swimming based, at least in part, on comparing peaks extracted from the motion signature of the sensor data to predefined thresholds corresponding to a plurality of activities, the plurality of activities including swimming;
determining, via the one or more processors, the user is swimming based at least in part on determining that the user is performing the kicking motion associated with swimming and without any user input indicating the user is swimming, has begun swimming, or has finished swimming being provided via a user interface;
determine one or more swim metrics in response to determining the user is swimming, the one or more swim metrics being determined based, at least in part, on the sensor data, wherein determining the one or more swim metrics in response to determining the user is swimming includes:
turning on, via the one or more processors, one or more additional sensors of the wearable computing device such that the one or more additional sensors begin collecting additional data;
extracting, via the one or more processors, the peaks from the motion data; and
determining, via the one or more processors, the one or more swim metrics based, at least in part, on the peaks extracted from the motion data and the additional data using a sensor fusion algorithm; and
causing, via the one or more processors, the one or more swim metrics to be displayed on a display screen for viewing by the user.