Moving target classification in automotive radar systems using convolutional recurrent neural networks

Sangtae Kim; Seunghwan Lee; Seungho Doo; Byonghyo Shim

doi:10.23919/EUSIPCO.2018.8553185

Moving target classification in automotive radar systems using convolutional recurrent neural networks

Sangtae Kim
, Seunghwan Lee
, Seungho Doo
, Byonghyo Shim

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

40 Citations (Scopus)

Abstract

Moving target classification is a key ingredient to avoid accident in autonomous driving systems. Recently, fast chirp frequency modulated continuous wave (FMCW) radar has been popularly used to recognize moving targets due to its ability to discriminate moving objects and stationary clutter. In order to protect vulnerable road users such as pedestrians and cyclists, it is essential to identify road users in a very short period of time. In this paper, we propose a deep neural network that consists of convolutional recurrent units for target classification in automotive radar system. In our experiment, using the real data measured by the fast chirp FMCW-based high range resolution radar, we show that the proposed network is capable of learning the dynamics in time-series image data and outperforms the conventional classification schemes.

Original language	English
Title of host publication	2018 26th European Signal Processing Conference, EUSIPCO 2018
Publisher	European Signal Processing Conference, EUSIPCO
Pages	1482-1486
Number of pages	5
ISBN (Electronic)	9789082797015
DOIs	https://doi.org/10.23919/EUSIPCO.2018.8553185
Publication status	Published - 2018 Nov 29
Event	26th European Signal Processing Conference, EUSIPCO 2018 - Rome, Italy Duration: 2018 Sept 3 → 2018 Sept 7

Publication series

Name	European Signal Processing Conference
Volume	2018-September
ISSN (Print)	2219-5491

Other

Other	26th European Signal Processing Conference, EUSIPCO 2018
Country/Territory	Italy
City	Rome
Period	18/9/3 → 18/9/7

Bibliographical note

Publisher Copyright:
© EURASIP 2018.

Keywords

Classification
Fast chirp FMCW radar
Recurrent neural networks
convolutional neural networks

ASJC Scopus subject areas

Signal Processing
Electrical and Electronic Engineering

Access to Document

10.23919/EUSIPCO.2018.8553185

Cite this

Kim, S., Lee, S., Doo, S., & Shim, B. (2018). Moving target classification in automotive radar systems using convolutional recurrent neural networks. In 2018 26th European Signal Processing Conference, EUSIPCO 2018 (pp. 1482-1486). Article 8553185 (European Signal Processing Conference; Vol. 2018-September). European Signal Processing Conference, EUSIPCO. https://doi.org/10.23919/EUSIPCO.2018.8553185

Moving target classification in automotive radar systems using convolutional recurrent neural networks. / Kim, Sangtae; Lee, Seunghwan; Doo, Seungho et al.
2018 26th European Signal Processing Conference, EUSIPCO 2018. European Signal Processing Conference, EUSIPCO, 2018. p. 1482-1486 8553185 (European Signal Processing Conference; Vol. 2018-September).

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

Kim, S, Lee, S, Doo, S & Shim, B 2018, Moving target classification in automotive radar systems using convolutional recurrent neural networks. in 2018 26th European Signal Processing Conference, EUSIPCO 2018., 8553185, European Signal Processing Conference, vol. 2018-September, European Signal Processing Conference, EUSIPCO, pp. 1482-1486, 26th European Signal Processing Conference, EUSIPCO 2018, Rome, Italy, 18/9/3. https://doi.org/10.23919/EUSIPCO.2018.8553185

@inproceedings{8be93c4d3ef34a8e95ccb49a3680ab22,

title = "Moving target classification in automotive radar systems using convolutional recurrent neural networks",

abstract = "Moving target classification is a key ingredient to avoid accident in autonomous driving systems. Recently, fast chirp frequency modulated continuous wave (FMCW) radar has been popularly used to recognize moving targets due to its ability to discriminate moving objects and stationary clutter. In order to protect vulnerable road users such as pedestrians and cyclists, it is essential to identify road users in a very short period of time. In this paper, we propose a deep neural network that consists of convolutional recurrent units for target classification in automotive radar system. In our experiment, using the real data measured by the fast chirp FMCW-based high range resolution radar, we show that the proposed network is capable of learning the dynamics in time-series image data and outperforms the conventional classification schemes.",

keywords = "Classification, Fast chirp FMCW radar, Recurrent neural networks, convolutional neural networks",

author = "Sangtae Kim and Seunghwan Lee and Seungho Doo and Byonghyo Shim",

note = "Publisher Copyright: {\textcopyright} EURASIP 2018.; 26th European Signal Processing Conference, EUSIPCO 2018 ; Conference date: 03-09-2018 Through 07-09-2018",

year = "2018",

month = nov,

day = "29",

doi = "10.23919/EUSIPCO.2018.8553185",

language = "English",

series = "European Signal Processing Conference",

publisher = "European Signal Processing Conference, EUSIPCO",

pages = "1482--1486",

booktitle = "2018 26th European Signal Processing Conference, EUSIPCO 2018",

}

TY - GEN

T1 - Moving target classification in automotive radar systems using convolutional recurrent neural networks

AU - Kim, Sangtae

AU - Lee, Seunghwan

AU - Doo, Seungho

AU - Shim, Byonghyo

PY - 2018/11/29

Y1 - 2018/11/29

N2 - Moving target classification is a key ingredient to avoid accident in autonomous driving systems. Recently, fast chirp frequency modulated continuous wave (FMCW) radar has been popularly used to recognize moving targets due to its ability to discriminate moving objects and stationary clutter. In order to protect vulnerable road users such as pedestrians and cyclists, it is essential to identify road users in a very short period of time. In this paper, we propose a deep neural network that consists of convolutional recurrent units for target classification in automotive radar system. In our experiment, using the real data measured by the fast chirp FMCW-based high range resolution radar, we show that the proposed network is capable of learning the dynamics in time-series image data and outperforms the conventional classification schemes.

AB - Moving target classification is a key ingredient to avoid accident in autonomous driving systems. Recently, fast chirp frequency modulated continuous wave (FMCW) radar has been popularly used to recognize moving targets due to its ability to discriminate moving objects and stationary clutter. In order to protect vulnerable road users such as pedestrians and cyclists, it is essential to identify road users in a very short period of time. In this paper, we propose a deep neural network that consists of convolutional recurrent units for target classification in automotive radar system. In our experiment, using the real data measured by the fast chirp FMCW-based high range resolution radar, we show that the proposed network is capable of learning the dynamics in time-series image data and outperforms the conventional classification schemes.

KW - Classification

KW - Fast chirp FMCW radar

KW - Recurrent neural networks

KW - convolutional neural networks

UR - https://www.scopus.com/pages/publications/85059818371

U2 - 10.23919/EUSIPCO.2018.8553185

DO - 10.23919/EUSIPCO.2018.8553185

M3 - Conference contribution

AN - SCOPUS:85059818371

T3 - European Signal Processing Conference

SP - 1482

EP - 1486

BT - 2018 26th European Signal Processing Conference, EUSIPCO 2018

PB - European Signal Processing Conference, EUSIPCO

T2 - 26th European Signal Processing Conference, EUSIPCO 2018

Y2 - 3 September 2018 through 7 September 2018

ER -

Moving target classification in automotive radar systems using convolutional recurrent neural networks

Abstract

Publication series

Other

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this