# Analysis and development of an automatic eCall for motorcycles: a one-class cepstrum approach

## TL;DR

This paper introduces an automatic eCall system for motorcycles using a one-class cepstrum approach to detect anomalies in vehicle dynamics, aiming to improve safety by accurately triggering emergency calls during crashes.

## Contribution

It presents a novel anomaly detection algorithm based on cepstral analysis specifically designed for two-wheeled vehicles, addressing the challenge of trigger accuracy in complex dynamics.

## Key findings

- The proposed method effectively detects crash events in real motorcycle data.
- Performance surpasses existing approaches in accuracy and reliability.
- The algorithm successfully distinguishes between normal driving and crash scenarios.

## Abstract

The automatic dial of an emergency call - eCall - in response to a road accident is a feature that is gaining interest in the intelligent vehicle community. It indirectly increases the driving safety of road vehicles, but presents the technical challenge of developing an algorithm which triggers the emergency call only when needed, a non-trivial task for two-wheeled vehicles due to their complex dynamics. In the present work, we propose an eCall algorithm that detects these anomalies in the data time series, thanks to the cepstral analysis. The main advantage of the proposed approach is the direct focus on the data dynamics, solving the limits of approaches based on the analysis of the instantaneous value of some signals combination. The algorithm is calibrated and tested against real driving data of ten different drivers, including seven real crash events, and performance are compared with known methods.