Vehicle behaviour estimation for abnormal event detection using distributed fiber optic sensing

TL;DR

This paper introduces a novel method for detecting single-lane traffic abnormalities by tracking vehicle paths and monitoring spectral centroid changes in vibrations using distributed fiber optic sensing, achieving 80% accuracy.

Contribution

The paper presents a new approach combining vehicle path estimation and spectral analysis for lane change detection using DFOS technology, addressing a key challenge in traffic monitoring.

Findings

Achieved 80% accuracy in lane change detection

Demonstrated effectiveness of spectral centroid monitoring

Validated method with real traffic data

Abstract

The distributed fiber-optic sensing (DFOS) system is a cost-effective wide-area traffic monitoring technology that utilizes existing fiber infrastructure to effectively detect traffic congestions. However, detecting single-lane abnormalities, that lead to congestions, is still a challenge. These single-lane abnormalities can be detected by monitoring lane change behaviour of vehicles, performed to avoid congestion along the monitoring section of a road. This paper presents a method to detect single-lane abnormalities by tracking individual vehicle paths and detecting vehicle lane changes along a section of a road. We propose a method to estimate the vehicle position at all time instances and fit a path using clustering techniques. We detect vehicle lane change by monitoring any change in spectral centroid of vehicle vibrations by tracking a reference vehicle along a highway. The evaluation of our proposed method with real traffic data showed 80% accuracy for lane change detection events that represent presence of abnormalities.