In professional downhill skiing competitions the results obtained by elite athletes are very close to each other: A few hundredths of a second can make the difference towards winning a race. The most important feedback for the athlete is the trainer. He gives instructions to the athlete about the optimal performance of the sequence of motions. However, the perception of trainer and athlete are always different: The athletes performs the technique and thereby he has a certain feeling of his movements, whereas the trainer observes the athlete and analyzes the movements due to his own experience and the common training doctrines. We found that wearable sensors could offer a new way for better matching the trainer's and athlete's view by providing new information beyond the human (visual) senses:
 |
- Dynamics: 3D accelerometers on athlete and ski
|

ADXL210E |
|
 |
- Forces: 3-point measurement at each foot in the boot
|

FSR 18.3mm |
|
 |
- Rotation: 3D gyroscopes on each ski
|

3x ADXRS300
|
|
 |
- Speed: Doppler-radar at ski-boot
|

Infineon KMY10 |
|
 |
- Edging-Angle: IR-sensor distance measurement boot-ground
|

Sharp GP2D12 |
Implementation
The acquired data is sampled by a multiplexed A/D converter. A PIC (18F252) micro-controller unit sends the data over an interface to a logging device which writes the recorded data to a persistent storage (Multimedia-Card). The stored data can later be processed by a software-front-end on a standard computer.
Data-Logging
The implementation of a FAT16 file system driver on the PIC allows to unplug the card from the sensing platform and load it directly into a cardreader of a PC where the SKI-analysis-software can read the data.
The state of the system can be controlled via an RS-232 display on the skier's wrist.
Sensor-/Video-Viewer Software: SKI - Synchronous Kinetics Integration

An analysis software prototype, referred to as SKI, was developed, so that video sequences and data recorded by the sensor platform can be viewed in a synchronized way. By using the
Java Reflection Framework new data-viewers derived from basic framework classes can be added to the software without any further changes of the entire framework. In SKI the user can associate video recordings of a ski with sensor data, and view those through di erent visualization representations.
In particular, the framework provides
- rotating bars indicating rotation movements primarily for gyroscope data,
|
 |
- a composition of all foot force measurements,
|
 |
- and, finally, an animated data plot showing the plain sensor values.
|
 |
All viewers can be played at adjustable speed synchronous to the video recording. Furthermore, simple operations, such as mean calculations or integration, allow simple data pre-processing.
Experiments

The described has been used in a real skiing environment: A student wore the sensors and several downhill runs were measured and video-taped on a race course. These experiments have been discussed and evaluation with different trainers from SWISSKI.
We believe, that trainers and athletes can enormously benefit from
emerging sensor technology. This technology can supply trainers with
valuable insights to the actual movements on the slopes of their athletes. Then,
trainers and athletes hopefully can better analyze and improve the skiing technique.
We certainly see also other application fields, where our hardware and software system could provide a benefit: basically, all fields where sensor have to analyzed using video as an annotation.
victims who already died, while for other victims, that are still alive, aid
may come too late. Our vision is to augment today's
avalanche beacons, which mountaineers are wearing anyway already, with sensing
capabilities.
Publications:
- Sensing and Monitoring Professional Skiing Athletes: Lessons Learned from a Collaboration with Ski Trainer's. Flori
an Michahelles and Bernt Schiele, In Pervasive Computing Magazin,
IEEE, July-September, Special Issue on Pervasive Computing in Sports, 2005. [pdf]
- Design, Implementation and Testing of a Wearable Sensing System for Profe
ssional Downhill Skiing in Cooperation with Trainers. Florian Michahelles, Erich Crameri, and Bernt Schiele. In 2nd Int
ernational Forum on Applied Wearable Computing (IFAWC 2005), Zurich, Switzerland, March
2005. [pdf]
Links:
Downloads:
- DataViewer SKI: site
- Java Media Framework (JMF) (required for SKI): site
- com.Ostermiller.util Java Utilities (required for SKI): site
Contact: