Abstract
Riding posture as well as leg motion is very important for cycling. To improve riding skills, it is very useful for riders to show their riding posture during cycling. In this study, we aim for developing a method to estimate a rider's posture only using sensors attached to a bicycle or the rider. For the first step, we propose a method to estimate hand grip position. The method uses Support Vector Machine based on the observed data from a 6-axis force/torque sensor installed at an ahead stem. Through the experiments, our estimation method achieved both high precision and high recall.
