Detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning

Markus Stocker (Corresponding Author), Paula Silvonen, Mauno Rönkkö, Mikko Kolehmainen

Research output: Contribution to journalArticleScientificpeer-review

9 Citations (Scopus)

Abstract

Road vehicle detection and, to a lesser extent, classification have received considerable attention, in particular for the purpose of traffic monitoring by transportation authorities. A multitude of sensors and systems have been developed to assist people in traffic monitoring. Camera-based systems have enjoyed wide adoption over the last decade, partially substituting for more traditional techniques. Methods based on road-pavement vibration are not as common as camera-based systems. However, vibration sensors may be of interest when sensors must be out of sight and insensitive to environmental conditions, such as fog. We present and discuss our work on detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning. We describe the entire processing chain from sensor data acquisition to vehicle classification and discuss our results for the task of vehicle detection and the task of vehicle classification separately. Using data for a single vibration sensor, our results show a performance ranging between 94% and near 100% for the detection task (1340 samples) and between 43% and 86% for the classification task (experiment specific, between 454 and 1243 samples).
Original languageEnglish
Pages (from-to)125-137
JournalJournal of Intelligent Transportation Systems: Technology, Planning, and Operations
Volume20
Issue number2
DOIs
Publication statusPublished - 2015
MoE publication typeA1 Journal article-refereed

Fingerprint

Supervised Learning
Pavements
Learning systems
Machine Learning
Vibration
Sensor
Sensors
Vehicle Detection
Camera
Cameras
Traffic
Monitoring
Fog
Data Acquisition
Data acquisition
Entire
Processing
Experiment
Experiments

Keywords

  • digital signal processing
  • machine learning
  • road vehicle detection and classification
  • vibration sensors

Cite this

@article{4a103e68c1c449c3b5a6b7c3f3a466d8,
title = "Detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning",
abstract = "Road vehicle detection and, to a lesser extent, classification have received considerable attention, in particular for the purpose of traffic monitoring by transportation authorities. A multitude of sensors and systems have been developed to assist people in traffic monitoring. Camera-based systems have enjoyed wide adoption over the last decade, partially substituting for more traditional techniques. Methods based on road-pavement vibration are not as common as camera-based systems. However, vibration sensors may be of interest when sensors must be out of sight and insensitive to environmental conditions, such as fog. We present and discuss our work on detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning. We describe the entire processing chain from sensor data acquisition to vehicle classification and discuss our results for the task of vehicle detection and the task of vehicle classification separately. Using data for a single vibration sensor, our results show a performance ranging between 94{\%} and near 100{\%} for the detection task (1340 samples) and between 43{\%} and 86{\%} for the classification task (experiment specific, between 454 and 1243 samples).",
keywords = "digital signal processing, machine learning, road vehicle detection and classification, vibration sensors",
author = "Markus Stocker and Paula Silvonen and Mauno R{\"o}nkk{\"o} and Mikko Kolehmainen",
year = "2015",
doi = "10.1080/15472450.2015.1004063",
language = "English",
volume = "20",
pages = "125--137",
journal = "Journal of Intelligent Transportation Systems: Technology, Planning, and Operations",
issn = "1547-2450",
publisher = "Taylor & Francis",
number = "2",

}

Detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning. / Stocker, Markus (Corresponding Author); Silvonen, Paula; Rönkkö, Mauno; Kolehmainen, Mikko.

In: Journal of Intelligent Transportation Systems: Technology, Planning, and Operations, Vol. 20, No. 2, 2015, p. 125-137.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning

AU - Stocker, Markus

AU - Silvonen, Paula

AU - Rönkkö, Mauno

AU - Kolehmainen, Mikko

PY - 2015

Y1 - 2015

N2 - Road vehicle detection and, to a lesser extent, classification have received considerable attention, in particular for the purpose of traffic monitoring by transportation authorities. A multitude of sensors and systems have been developed to assist people in traffic monitoring. Camera-based systems have enjoyed wide adoption over the last decade, partially substituting for more traditional techniques. Methods based on road-pavement vibration are not as common as camera-based systems. However, vibration sensors may be of interest when sensors must be out of sight and insensitive to environmental conditions, such as fog. We present and discuss our work on detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning. We describe the entire processing chain from sensor data acquisition to vehicle classification and discuss our results for the task of vehicle detection and the task of vehicle classification separately. Using data for a single vibration sensor, our results show a performance ranging between 94% and near 100% for the detection task (1340 samples) and between 43% and 86% for the classification task (experiment specific, between 454 and 1243 samples).

AB - Road vehicle detection and, to a lesser extent, classification have received considerable attention, in particular for the purpose of traffic monitoring by transportation authorities. A multitude of sensors and systems have been developed to assist people in traffic monitoring. Camera-based systems have enjoyed wide adoption over the last decade, partially substituting for more traditional techniques. Methods based on road-pavement vibration are not as common as camera-based systems. However, vibration sensors may be of interest when sensors must be out of sight and insensitive to environmental conditions, such as fog. We present and discuss our work on detection and classification of vehicles by measurement of road-pavement vibration and by means of supervised machine learning. We describe the entire processing chain from sensor data acquisition to vehicle classification and discuss our results for the task of vehicle detection and the task of vehicle classification separately. Using data for a single vibration sensor, our results show a performance ranging between 94% and near 100% for the detection task (1340 samples) and between 43% and 86% for the classification task (experiment specific, between 454 and 1243 samples).

KW - digital signal processing

KW - machine learning

KW - road vehicle detection and classification

KW - vibration sensors

U2 - 10.1080/15472450.2015.1004063

DO - 10.1080/15472450.2015.1004063

M3 - Article

VL - 20

SP - 125

EP - 137

JO - Journal of Intelligent Transportation Systems: Technology, Planning, and Operations

JF - Journal of Intelligent Transportation Systems: Technology, Planning, and Operations

SN - 1547-2450

IS - 2

ER -