Where is my Device? - Detecting the Smart Device's Wearing Location in the Context of Active Safety for Vulnerable Road Users

TL;DR

This paper presents a sensor-based method to detect where pedestrians and cyclists wear their smart devices, enhancing safety algorithms by providing crucial context for active safety systems.

Contribution

It introduces a novel two-stage approach for detecting device wearing location using only device sensors, advancing self-awareness in wearable device applications.

Findings

Effective detection of wearing location in real-world scenarios

Improved context-awareness for safety algorithms

Validated on pedestrian and cyclist datasets

Abstract

This article describes an approach to detect the wearing location of smart devices worn by pedestrians and cyclists. The detection, which is based solely on the sensors of the smart devices, is important context-information which can be used to parametrize subsequent algorithms, e.g. for dead reckoning or intention detection to improve the safety of vulnerable road users. The wearing location recognition can in terms of Organic Computing (OC) be seen as a step towards self-awareness and self-adaptation. For the wearing location detection a two-stage process is presented. It is subdivided into moving detection followed by the wearing location classification. Finally, the approach is evaluated on a real world dataset consisting of pedestrians and cyclists.