The Powered Two Wheelers fall detection using Multivariate CUmulative SUM (MCUSUM) control charts

This paper presents a simple and efficient methodology that uses both acceleration and angular velocity signals to detect a fall of Powered Two Wheelers (PTW). Detecting the rider´s fall (before the impact of the rider on the ground) can indeed be used to provide a signal in order to trigger inflation of an airbag jacket worn by the rider, reducing thus the injury severity. The fall detection is therefore formulated as a sequential anomaly detection problem. The paper investigates the popular method namely Multivariate CUmulative SUM (MCUSUM) control charts to detect such anomalies. The MCUSUM algorithm was applied on the data collected from three-accelerometer and three-gyroscope sensors mounted on the motorcycle. Experiments were performed on different scenarios from naturalistic to extreme (near fall and fall scenarios) riding situations. In the latter case, the riding scenarios were replayed by a stuntman. The results show the ability of the proposed methodology to analyze and understand the motorcycle fall behavior as well as to detect the fall with enough time to inflate an airbag jacket.