Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
The present study proposes a method based on ski fixed inertial sensors to automatically compute spatio-temporal parameters (phase durations, cycle speed and cycle length) for the diagonal stride in classical cross-country skiing. The proposed system was validated against a marker-based motion capture system during indoor treadmill skiing. Skiing movement of 10 junior to world-cup athletes was measured for four different conditions. The accuracy (i.e. median error) and precision (i.e. interquartile range of error) of the system was below 6 ms for cycle duration and ski thrust duration and below 35 ms for pole push duration. Cycle speed precision (accuracy) was below 0.1 m/s (0.005 m/s) and cycle length precision (accuracy) was below 0.15 m (0.005 m). The system was sensitive to changes of conditions and was accurate enough to detect significant differences reported in previous studies. Since capture volume is not limited and setup is simple, the system would be well suited for outdoor measurements on snow.
Jacques Fellay, Christian Axel Wandall Thorball
, , , , , , ,