Physical activity quantification and monitoring
Certain aspects provide a method of generating a physical activity model, including: receiving, via a motion capture device, motion data corresponding to a plurality of key states associated with a physical activity sequence; for each respective key state in the plurality of key states: determining a plurality of joint positions associated with the respective key state; determining a plurality of body segment positions associated with the respective key state based on the plurality of joint positions; determining a plurality of inter-state differentiation variables for the respective key state; determining one or more state characteristic metrics for the respective key state; and determining a classifier for the respective key state based on the one or more state characteristic metrics; and defining a physical activity model based on the one or more state characteristic metrics and the classifier associated with each key state.
1. An apparatus, comprising:
a processor; and
a memory coupled to the processor, the memory comprising instructions that, when executed by the processor, cause the processor to:
access training motion data of a physical activity sequence,
determine a sequence of a plurality of key states in the training motion data, each of the plurality of key states comprising a specific state that in-part defines the physical activity sequence,
determine at least one state characteristic metric for each of the plurality of key states, the at least one state characteristic metric comprising at least one variable configured to identify a state of the plurality of key states, and
determine a physical activity model based on the at least one state characteristic metric associated with each of the plurality of key states.
2. The apparatus of claim 1 , the physical activity sequence comprising an exercise performed by a human body.
3. The apparatus of claim 1 , the instructions, when executed by the processor, to cause the processor to, for each of the plurality of key states, determine at least one body segment position associated with at least one joint position.
4. The apparatus of claim 3 , the instructions, when executed by the processor, to cause the processor to, for each of the plurality of key states, determine a plurality of inter-state differentiation variables comprising variables used to differentiate between the plurality of key states.
5. The apparatus of claim 4 , the plurality of inter-state differentiation variables determined based on one or more of the at least one body segment position or the at least one joint position.
6. The apparatus of claim 4 , the at least one state characteristic metric comprising a subset of the plurality of inter-state differentiation variables used to identify a state of the plurality of key states.
7. The apparatus of claim 6 , wherein the at least one inter-state differentiation variable comprises a plurality of inter-state differentiation variables,
the instructions, when executed by the processor, to cause the processor to:
determine a statistical significance of each of the plurality of inter-state differentiation variables for identifying a respective state of the plurality of key states, and
determine the at least one characteristic metric as a subset of the plurality of inter-state differentiation variables based on the statistical significance.
8. The apparatus of claim 1 , the instructions, when executed by the processor, to cause the processor to, for each of the plurality of key states, determine a classifier based on the at least one state characteristic metric, the classifier configured to determine a probability that one of the plurality of key states is in captured motion data.
9. The apparatus of claim 8 , the physical activity model based on the at least one state characteristic metric and the classifier associated with each of the plurality of key states.
10. The apparatus of claim 1 , the plurality of key states determined by at least one of:
user input via a graphical user interface selecting at least one of the plurality of key states, or
automatically based on analysis of the training motion data based on indicators of a transition between at least two of the plurality of key states.
11. A method, comprising, via a processor of a computing device:
accessing training motion data of a physical activity sequence;
determining a sequence of a plurality of key states in the training motion data, each of the plurality of key states comprising a specific state that in-part defines the physical activity sequence;
determining at least one state characteristic metric for each of the plurality of key states, the at least one state characteristic metric comprising at least one variable configured to identify a state of the plurality of key states; and
determining a physical activity model based on the at least one state characteristic metric associated with each of the plurality of key states.
12. The method of claim 11 , the physical activity sequence comprising an exercise performed by a human body.
13. The method of claim 11 , comprising determining at least one body segment position associated with at least one joint position.
14. The method of claim 13 , comprising determining a plurality of inter-state differentiation variables comprising variables used to differentiate between the plurality of key states.
15. The method of claim 14 , the plurality of inter-state differentiation variables determined based on one or more of the at least one body segment position or the at least one joint position.
16. The method of claim 14 , the at least one state characteristic metric comprising a subset of the plurality of inter-state differentiation variables used to identify a state of the plurality of key states.
17. The method of claim 16 , wherein the at least one inter-state differentiation variable comprises a plurality of inter-state differentiation variables, comprising:
determining a statistical significance of each of the plurality of inter-state differentiation variables for identifying a respective state of the plurality of key states; and
determining the at least one characteristic metric as a subset of the plurality of inter-state differentiation variables based on the statistical significance.
18. The method of claim 11 , comprising determining a classifier based on the at least one state characteristic metric, the classifier configured to determine a probability that one of the plurality of key states is in captured motion data.
19. The method of claim 18 , the physical activity model based on the at least one state characteristic metric and the classifier associated with each of the plurality of key states.
20. The method of claim 11 , the plurality of key states determined by at least one of:
user input via a graphical user interface selecting at least one of the plurality of key states, or
automatically based on analysis of the training motion data based on indicators of a transition between at least two of the plurality of key states.