Smart Device based Initial Movement Detection of Cyclists using Convolutional Neuronal Networks

TL;DR

This paper proposes a convolutional neural network approach using smart device sensors to detect the initial movement of cyclists, enhancing safety in future interconnected traffic systems.

Contribution

It introduces a residual network architecture for cyclist movement detection using accelerometer and gyroscope data from smart devices.

Findings

High accuracy in initial movement detection

Effective use of residual CNN architecture

Potential for real-time cyclist safety alerts

Abstract

For future traffic scenarios, we envision interconnected traffic participants, who exchange information about their current state, e.g., position, their predicted intentions, allowing to act in a cooperative manner. Vulnerable road users (VRUs), e.g., pedestrians and cyclists, will be equipped with smart device that can be used to detect their intentions and transmit these detected intention to approaching cars such that their drivers can be warned. In this article, we focus on detecting the initial movement of cyclist using smart devices. Smart devices provide the necessary sensors, namely accelerometer and gyroscope, and therefore pose an excellent instrument to detect movement transitions (e.g., waiting to moving) fast. Convolutional Neural Networks prove to be the state-of-the-art solution for many problems with an ever increasing range of applications. Therefore, we model the initial movement detection as a classification problem. In terms of Organic Computing (OC) it be seen as a step towards self-awareness and self-adaptation. We apply residual network architectures to the task of detecting the initial starting movement of cyclists.