In high-performance cycling, there is a need for advanced
technological means of assessing the cyclists’ performance
during training and competition, and the risk of overuse injuries.
Existing techniques rely on off-line, laboratory-based
analysis, as well as on outfitting the bike with various sensors
and transducers that give an estimate of the performance
during training and racing. We propose a radically different
approach, with the aim of determining the actual status
of the cyclist’s body in real-time and real-life conditions.
Our solution is based on body area wireless motion sensor
nodes that can collaboratively process the sensory information
and give immediate feedback to the cyclists. We study
experimentally the accuracy of such a system with respect to
the gold standard camera system. The biomechanics measures
of interest are the knee and ankle angles of the cyclists,
which give an indication of the correctness and efficiency of
the cycling technique. The results obtained from a series
of experiments with nine subjects show the accuracy of the
motion sensor system compared with the reference given by
the camera system. Furthermore, we analyse the wireless
characteristics of our system, the energy expenditure and
possible improvements.