Road Surface Classification Based on Radar Imaging Using Convolutional Neural Network

Shahrzad Minooee Sabery; Aleksandr Bystrov; Peter Gardner; Ana Stroescu; Marina Gashinova

doi:10.1109/JSEN.2021.3087336

Road Surface Classification Based on Radar Imaging Using Convolutional Neural Network

Shahrzad Minooee Sabery^*, Aleksandr Bystrov, Peter Gardner, Ana Stroescu, Marina Gashinova

^*Corresponding author for this work

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

Abstract

The development of an automotive surface recognition system is an important and yet unsolved task. In the current study we are considering a novel approach to surface classification based on the analysis of the real road surface images obtained using the 79 GHz imaging radar and demonstrate the advantage of millimeter wave radar for surface discrimination for automotive sensing. The proposed experimental technique in combination with a convolutional neural network provides high surface classification accuracy.

Original language	English
Article number	9448150
Pages (from-to)	18725-18732
Number of pages	8
Journal	IEEE Sensors Journal
Volume	21
Issue number	17
Early online date	7 Jun 2021
DOIs	https://doi.org/10.1109/JSEN.2021.3087336
Publication status	Published - 1 Sept 2021

Bibliographical note

Funding Information:
This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) and Jaguar Land Rover Plc under Grant EP/N012372/1 and Grant EP/P020615/1; and in part by the University of Birmingham.

Publisher Copyright:
© 2001-2012 IEEE.

Keywords

convolutional neural network
electromagnetic scattering
Millimeter wave radar
radar imaging
radar remote sensing

ASJC Scopus subject areas

Instrumentation
Electrical and Electronic Engineering

Access to Document

10.1109/JSEN.2021.3087336

10 MHz to 1.1 THz Vector Network Analyser
Constantinou, C., Lancaster, M., Gashinova, M., Gardner, P., Wang, Y. & Hanham, S.
Engineering & Physical Science Research Council
1/09/17 → 31/08/23
Project: Research Councils

Cite this

@article{89cd3fc684154511bbbea9660b4fcc9c,

title = "Road Surface Classification Based on Radar Imaging Using Convolutional Neural Network",

abstract = "The development of an automotive surface recognition system is an important and yet unsolved task. In the current study we are considering a novel approach to surface classification based on the analysis of the real road surface images obtained using the 79 GHz imaging radar and demonstrate the advantage of millimeter wave radar for surface discrimination for automotive sensing. The proposed experimental technique in combination with a convolutional neural network provides high surface classification accuracy.",

keywords = "convolutional neural network, electromagnetic scattering, Millimeter wave radar, radar imaging, radar remote sensing",

author = "Sabery, {Shahrzad Minooee} and Aleksandr Bystrov and Peter Gardner and Ana Stroescu and Marina Gashinova",

note = "Funding Information: This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) and Jaguar Land Rover Plc under Grant EP/N012372/1 and Grant EP/P020615/1; and in part by the University of Birmingham. Publisher Copyright: {\textcopyright} 2001-2012 IEEE.",

year = "2021",

month = sep,

day = "1",

doi = "10.1109/JSEN.2021.3087336",

language = "English",

volume = "21",

pages = "18725--18732",

journal = "IEEE Sensors Journal",

issn = "1530-437X",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

number = "17",

}

TY - JOUR

T1 - Road Surface Classification Based on Radar Imaging Using Convolutional Neural Network

AU - Sabery, Shahrzad Minooee

AU - Bystrov, Aleksandr

AU - Gardner, Peter

AU - Stroescu, Ana

AU - Gashinova, Marina

N1 - Funding Information: This work was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) and Jaguar Land Rover Plc under Grant EP/N012372/1 and Grant EP/P020615/1; and in part by the University of Birmingham. Publisher Copyright: © 2001-2012 IEEE.

PY - 2021/9/1

Y1 - 2021/9/1

N2 - The development of an automotive surface recognition system is an important and yet unsolved task. In the current study we are considering a novel approach to surface classification based on the analysis of the real road surface images obtained using the 79 GHz imaging radar and demonstrate the advantage of millimeter wave radar for surface discrimination for automotive sensing. The proposed experimental technique in combination with a convolutional neural network provides high surface classification accuracy.

AB - The development of an automotive surface recognition system is an important and yet unsolved task. In the current study we are considering a novel approach to surface classification based on the analysis of the real road surface images obtained using the 79 GHz imaging radar and demonstrate the advantage of millimeter wave radar for surface discrimination for automotive sensing. The proposed experimental technique in combination with a convolutional neural network provides high surface classification accuracy.

KW - convolutional neural network

KW - electromagnetic scattering

KW - Millimeter wave radar

KW - radar imaging

KW - radar remote sensing

UR - http://www.scopus.com/inward/record.url?scp=85111024768&partnerID=8YFLogxK

U2 - 10.1109/JSEN.2021.3087336

DO - 10.1109/JSEN.2021.3087336

M3 - Article

AN - SCOPUS:85111024768

SN - 1530-437X

VL - 21

SP - 18725

EP - 18732

JO - IEEE Sensors Journal

JF - IEEE Sensors Journal

IS - 17

M1 - 9448150

ER -

Road Surface Classification Based on Radar Imaging Using Convolutional Neural Network

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Projects

10 MHz to 1.1 THz Vector Network Analyser

Cite this