Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning

Ryan A. Kerekes; Thomas P. Karnowski; Mike Kuhn; Michael R. Moore; Brad Stinson; Ryan Tokola; Adam Anderson; Jason M. Vann

doi:10.1109/VTCSpring.2017.8108568

Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning

Ryan A. Kerekes, Thomas P. Karnowski, Mike Kuhn, Michael R. Moore, Brad Stinson, Ryan Tokola, Adam Anderson, Jason M. Vann

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

Vehicle counting, time-of-travel analysis, and other traffic studies frequently require the classification and identification of vehicles in a roadway. Unfortunately, many current technologies for identifying vehicles, such as image-based methods that use cameras and machine vision, are not appropriate for studies that require low-power consumption and low cost. Additionally, privacy issues are becoming a larger concern with the increasing controversy surrounding the public collection of imagery. In this work we evaluate a multi-modal sensing approach to vehicle classification and identification using an ensemble of sensors measurements including electromagnetic emanations and acoustic signatures. A novel kernel regression method is also used for signal learning to classify and identify vehicles without the need of invasive images. Multi-mode sensing, as well as signal learning, is shown to significantly increase the classification rate of specific vehicle classes.

Original language	English
Title of host publication	2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509059324
DOIs	https://doi.org/10.1109/VTCSpring.2017.8108568
State	Published - Nov 14 2017
Event	85th IEEE Vehicular Technology Conference, VTC Spring 2017 - Sydney, Australia Duration: Jun 4 2017 → Jun 7 2017

Publication series

Name	IEEE Vehicular Technology Conference
Volume	2017-June
ISSN (Print)	1550-2252

Conference

Conference	85th IEEE Vehicular Technology Conference, VTC Spring 2017
Country/Territory	Australia
City	Sydney
Period	06/4/17 → 06/7/17

Funding

This manuscript has been authored by UT-Battelle, LLC, under Contract No. DE-AC0500OR22725 with the U.S. Department of Energy. The United States Government retains and the publisher, by accepting the article for publication, acknowledges that the United States Government retains a nonexclusive, paid-up, irrevocable, worldwide license to publish or reproduce the published form of this manuscript, or allow others to do so, for the United States Government purposes. The Department of Energy will provide public access to these results of federally sponsored research in accordance with the DOE Public Access Plan(http://energy.gov/downloads/doe-public-access-plan).The authors are with the Oak Ridge National Laboratory, Oak Ridge, TN 37831 USA.

Funders	Funder number
UT-Battelle

Keywords

Acoustic
Classification
Electromagnetic
Machine learning
Surveillance

Access to Document

10.1109/VTCSpring.2017.8108568

Cite this

Kerekes, R. A., Karnowski, T. P., Kuhn, M., Moore, M. R., Stinson, B., Tokola, R., Anderson, A., & Vann, J. M. (2017). Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning. In 2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings Article 8108568 (IEEE Vehicular Technology Conference; Vol. 2017-June). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTCSpring.2017.8108568

@inproceedings{fc9482e5834e4b0e8065d3b1341ab8e0,

title = "Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning",

abstract = "Vehicle counting, time-of-travel analysis, and other traffic studies frequently require the classification and identification of vehicles in a roadway. Unfortunately, many current technologies for identifying vehicles, such as image-based methods that use cameras and machine vision, are not appropriate for studies that require low-power consumption and low cost. Additionally, privacy issues are becoming a larger concern with the increasing controversy surrounding the public collection of imagery. In this work we evaluate a multi-modal sensing approach to vehicle classification and identification using an ensemble of sensors measurements including electromagnetic emanations and acoustic signatures. A novel kernel regression method is also used for signal learning to classify and identify vehicles without the need of invasive images. Multi-mode sensing, as well as signal learning, is shown to significantly increase the classification rate of specific vehicle classes.",

keywords = "Acoustic, Classification, Electromagnetic, Machine learning, Surveillance",

author = "Kerekes, {Ryan A.} and Karnowski, {Thomas P.} and Mike Kuhn and Moore, {Michael R.} and Brad Stinson and Ryan Tokola and Adam Anderson and Vann, {Jason M.}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 85th IEEE Vehicular Technology Conference, VTC Spring 2017 ; Conference date: 04-06-2017 Through 07-06-2017",

year = "2017",

month = nov,

day = "14",

doi = "10.1109/VTCSpring.2017.8108568",

language = "English",

series = "IEEE Vehicular Technology Conference",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings",

}

Kerekes, RA , Karnowski, TP, Kuhn, M, Moore, MR, Stinson, B, Tokola, R, Anderson, A & Vann, JM 2017, Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning. in 2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings., 8108568, IEEE Vehicular Technology Conference, vol. 2017-June, Institute of Electrical and Electronics Engineers Inc., 85th IEEE Vehicular Technology Conference, VTC Spring 2017, Sydney, Australia, 06/4/17. https://doi.org/10.1109/VTCSpring.2017.8108568

Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning. / Kerekes, Ryan A.; Karnowski, Thomas P.; Kuhn, Mike et al.
2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. 8108568 (IEEE Vehicular Technology Conference; Vol. 2017-June).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning

AU - Kerekes, Ryan A.

AU - Karnowski, Thomas P.

AU - Kuhn, Mike

AU - Moore, Michael R.

AU - Stinson, Brad

AU - Tokola, Ryan

AU - Anderson, Adam

AU - Vann, Jason M.

PY - 2017/11/14

Y1 - 2017/11/14

N2 - Vehicle counting, time-of-travel analysis, and other traffic studies frequently require the classification and identification of vehicles in a roadway. Unfortunately, many current technologies for identifying vehicles, such as image-based methods that use cameras and machine vision, are not appropriate for studies that require low-power consumption and low cost. Additionally, privacy issues are becoming a larger concern with the increasing controversy surrounding the public collection of imagery. In this work we evaluate a multi-modal sensing approach to vehicle classification and identification using an ensemble of sensors measurements including electromagnetic emanations and acoustic signatures. A novel kernel regression method is also used for signal learning to classify and identify vehicles without the need of invasive images. Multi-mode sensing, as well as signal learning, is shown to significantly increase the classification rate of specific vehicle classes.

AB - Vehicle counting, time-of-travel analysis, and other traffic studies frequently require the classification and identification of vehicles in a roadway. Unfortunately, many current technologies for identifying vehicles, such as image-based methods that use cameras and machine vision, are not appropriate for studies that require low-power consumption and low cost. Additionally, privacy issues are becoming a larger concern with the increasing controversy surrounding the public collection of imagery. In this work we evaluate a multi-modal sensing approach to vehicle classification and identification using an ensemble of sensors measurements including electromagnetic emanations and acoustic signatures. A novel kernel regression method is also used for signal learning to classify and identify vehicles without the need of invasive images. Multi-mode sensing, as well as signal learning, is shown to significantly increase the classification rate of specific vehicle classes.

KW - Acoustic

KW - Classification

KW - Electromagnetic

KW - Machine learning

KW - Surveillance

UR - http://www.scopus.com/inward/record.url?scp=85040574927&partnerID=8YFLogxK

U2 - 10.1109/VTCSpring.2017.8108568

DO - 10.1109/VTCSpring.2017.8108568

M3 - Conference contribution

AN - SCOPUS:85040574927

T3 - IEEE Vehicular Technology Conference

BT - 2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 85th IEEE Vehicular Technology Conference, VTC Spring 2017

Y2 - 4 June 2017 through 7 June 2017

ER -

Kerekes RA , Karnowski TP, Kuhn M, Moore MR, Stinson B, Tokola R et al. Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning. In 2017 IEEE 85th Vehicular Technology Conference, VTC Spring 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. 8108568. (IEEE Vehicular Technology Conference). doi: 10.1109/VTCSpring.2017.8108568

Vehicle Classification and Identification Using Multi-Modal Sensing and Signal Learning

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this