Hockey players wear boot and stick sensors to up their game

Data-hungry athletes can’t get enough of wearables, from the golf gadgets pros use to analyse their swing, to fitness trackers basketball players strap on during practice. But ice hockey has been slower to adapt. Engineer Michael Hardegger wanted to find a way to pull data out of a player’s natural movements and show amateurs what they’re doing wrong.

by Aviva Rutkin, New Scientist May 29, 2015

“In hockey, there are some specific things we know are optimal. For example, some beginners have their hands too high on the stick,” he says. “This system tells you what you can improve.”

To do this, Hardegger’s team fitted traditional hockey equipment with a range of sensors. Instruments on the skates monitor where a player’s feet are and how fast they’re moving. The stick, too, has sensors that can track pressure, strain, and motion.

A smartphone app crunches all the data, letting players review their technique and compare it to a professional’s. An algorithm can pick out different types of movement – like jumps, turns, and power stroke – as well as the characteristics of a shot in the net.

The prototype got its first test early this year at public ice rinks, where players practised skating and shooting while wearing the augmented gear. The testers included eight professional players from the Swiss National League team EHC Olten, as well as the researchers themselves.

Their results will be presented later this month at the Body Sensors Network conference at the Massachusetts Institute of Technology.

The system could be invaluable for amateurs, says Kim Blair, who works on sports technology at MIT. In sports, it can be very difficult to unlearn a bad habit: a coach might correct you during practice, but by the next day, you’ve forgotten what you were doing wrong. “Intermediate or continuous feedback could be super helpful,” he says.

“If you’re looking at the performance an athlete on the field or on ice, it’s easier if you’ve got data on the athlete as opposed to watching a video.”

For similar stories, visit the Sport Topic Guide, New Scientist

Enhancing Action Recognition through Simultaneous Semantic Mapping from Body-Worn Motion Sensors, Michael Hardegger, Long-Van Nguyen-Dinh, Alberto Calatroni, Gerhard Tröster, Daniel Roggen. Proceedings of the 2014 ACM International Symposium on Wearable Computers, ISWC, Seattle WA. http://dx.doi.org/10.1145/2634317.2634323