Inattentive Driving Behavior Detection Based on Portable FMCW Radar

Chuanwei DIng; Rachel Chae; Jing Wang; Li Zhang; Hong Hong; Xiaohua Zhu; Changzhi Li

doi:10.1109/TMTT.2019.2934413

Inattentive Driving Behavior Detection Based on Portable FMCW Radar

Chuanwei DIng, Rachel Chae, Jing Wang, Li Zhang, Hong Hong, Xiaohua Zhu, Changzhi Li

Electrical and Computer Engineering

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

Monitoring driver's attentiveness is crucial for transportation safety. In this article, inattentive driving behavior detection based on frequency-modulated continuous-wave (FMCW) radar systems is proposed for this purpose. Seven typical driving behaviors which result in reduced attentiveness are involved in this study. Time-Doppler spectrogram and range-Doppler trajectory are utilized to analyze their features in multiple domains, including time, Doppler, range, and radar cross-section (RCS). These features are extracted as inputs to a machine learning classifier to obtain recognition results. Extensive experiments on a real car environment have been conducted to show its feasibility and superiority by obtaining an average accuracy rate of around 95%. The influences of radar center frequency, individual diversity, and radar view angle are also investigated.

Original language	English
Article number	8815861
Pages (from-to)	4031-4041
Number of pages	11
Journal	IEEE Transactions on Microwave Theory and Techniques
Volume	67
Issue number	10
DOIs	https://doi.org/10.1109/TMTT.2019.2934413
State	Published - Oct 2019

Keywords

Driving behavior monitoring
frequency-modulated continuous-wave (FMCW) radar
machine learning
range-Doppler
time-Doppler

Access to Document

10.1109/TMTT.2019.2934413

Fingerprint Dive into the research topics of 'Inattentive Driving Behavior Detection Based on Portable FMCW Radar'. Together they form a unique fingerprint.

Cite this

@article{56c9a6ad5d7a4173a7e7fcd906b0049a,

title = "Inattentive Driving Behavior Detection Based on Portable FMCW Radar",

abstract = "Monitoring driver's attentiveness is crucial for transportation safety. In this article, inattentive driving behavior detection based on frequency-modulated continuous-wave (FMCW) radar systems is proposed for this purpose. Seven typical driving behaviors which result in reduced attentiveness are involved in this study. Time-Doppler spectrogram and range-Doppler trajectory are utilized to analyze their features in multiple domains, including time, Doppler, range, and radar cross-section (RCS). These features are extracted as inputs to a machine learning classifier to obtain recognition results. Extensive experiments on a real car environment have been conducted to show its feasibility and superiority by obtaining an average accuracy rate of around 95%. The influences of radar center frequency, individual diversity, and radar view angle are also investigated.",

keywords = "Driving behavior monitoring, frequency-modulated continuous-wave (FMCW) radar, machine learning, range-Doppler, time-Doppler",

author = "Chuanwei DIng and Rachel Chae and Jing Wang and Li Zhang and Hong Hong and Xiaohua Zhu and Changzhi Li",

year = "2019",

month = oct,

doi = "10.1109/TMTT.2019.2934413",

language = "English",

volume = "67",

pages = "4031--4041",

journal = "IEEE Transactions on Microwave Theory and Techniques",

issn = "0018-9480",

publisher = "IEEE",

number = "10",

}

TY - JOUR

T1 - Inattentive Driving Behavior Detection Based on Portable FMCW Radar

AU - DIng, Chuanwei

AU - Chae, Rachel

AU - Wang, Jing

AU - Zhang, Li

AU - Hong, Hong

AU - Zhu, Xiaohua

AU - Li, Changzhi

PY - 2019/10

Y1 - 2019/10

N2 - Monitoring driver's attentiveness is crucial for transportation safety. In this article, inattentive driving behavior detection based on frequency-modulated continuous-wave (FMCW) radar systems is proposed for this purpose. Seven typical driving behaviors which result in reduced attentiveness are involved in this study. Time-Doppler spectrogram and range-Doppler trajectory are utilized to analyze their features in multiple domains, including time, Doppler, range, and radar cross-section (RCS). These features are extracted as inputs to a machine learning classifier to obtain recognition results. Extensive experiments on a real car environment have been conducted to show its feasibility and superiority by obtaining an average accuracy rate of around 95%. The influences of radar center frequency, individual diversity, and radar view angle are also investigated.

AB - Monitoring driver's attentiveness is crucial for transportation safety. In this article, inattentive driving behavior detection based on frequency-modulated continuous-wave (FMCW) radar systems is proposed for this purpose. Seven typical driving behaviors which result in reduced attentiveness are involved in this study. Time-Doppler spectrogram and range-Doppler trajectory are utilized to analyze their features in multiple domains, including time, Doppler, range, and radar cross-section (RCS). These features are extracted as inputs to a machine learning classifier to obtain recognition results. Extensive experiments on a real car environment have been conducted to show its feasibility and superiority by obtaining an average accuracy rate of around 95%. The influences of radar center frequency, individual diversity, and radar view angle are also investigated.

KW - Driving behavior monitoring

KW - frequency-modulated continuous-wave (FMCW) radar

KW - machine learning

KW - range-Doppler

KW - time-Doppler

UR - http://www.scopus.com/inward/record.url?scp=85077438314&partnerID=8YFLogxK

U2 - 10.1109/TMTT.2019.2934413

DO - 10.1109/TMTT.2019.2934413

M3 - Article

AN - SCOPUS:85077438314

VL - 67

SP - 4031

EP - 4041

JO - IEEE Transactions on Microwave Theory and Techniques

JF - IEEE Transactions on Microwave Theory and Techniques

SN - 0018-9480

IS - 10

M1 - 8815861

ER -