Wearable sports trainers are built upon sensor systems recognizing the activities performed by its users. In snowboarding, one of the fastest growing sports in the world, traditional activity recognition approaches make use of insoles with integrated force-sensitive resistors. However, such insoles are usually uncomfortable to wear, tedious to calibrate, error-prone and their functionality is limited to the detection of turns. We have therefore developed an alternative snowboarding activity recognition system, which overcomes these downsides. It consists of a mobile computing device with a GPS receiver, and a gyroscope attached to the center of the snowboard. The system is easy to set up, as the gyroscope can be simply taped onto the snowboard without any user-specific calibrations. Experiments with seven riders in three Swiss ski resorts show that our activity recognition system is capable of withstanding harsh conditions on outdoor slopes. It detects turns, the basic elements of snowboarding, independently of user, snowboard, slope and snow characteristics. In addition to the mere detection of turns, our system can reveal whether the snowboarder is riding on the frontside or the backside of the board, whether she is going forwards or backwards and whether she is carving or skidding. Finally, first studies suggest that gyroscope-based activity recognition can also be applied to snowboarding-like sports such as skiing and skateboarding.
展开▼
