The aim of this study is to evaluate a low-complexity fall detection algorithm, that use both acceleration and angular velocity signals to trigger an alert-system or to inflate an airbag jacket. The proposed fall detection algorithm is a threshold-based algorithm, using data from 3-accelerometers and 3-gyroscopes sensors mounted on the motorcycle. During the first step, the commonly fall accident configurations were selected and analyzed in order to identify the main causation factors. On the second step, these fall scenarios were replayed by a stuntman using an instrumented motorcycle. Both accelerations and rotational velocities were monitored. These measurements constitute a valuable experimental database to analyze and to understand motorcycle fall mechanism. Based on the analysis of this database, a fall detection algorithm has been developed. This paper presents initial results of a work in progress that aims to provide knowledge about the development of such passive safety systems.
