Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks

Sangtae Kim, Kwangjin Lee, Seungho Doo, Byonghyo Shim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we propose a deep neural network model for target classification in automotive radar system. In the proposed network, we introduce transposed convolutional network (TCNet) which applies transposed convolution operations. We discuss the properties of transposed convolution and show that TCNet can reduce the network size and improve the classification performance for the systems in which the signals are sparse and memory is restricted like our automotive radar systems. In our experiment, we show that the proposed network outperforms other popularly used dimensionality reduction approaches in terms of classification accuracy.

Original languageEnglish
Title of host publicationConference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages2050-2054
Number of pages5
ISBN (Electronic)9781538692189
DOIs
Publication statusPublished - 2019 Feb 19
Event52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 - Pacific Grove, United States
Duration: 2018 Oct 282018 Oct 31

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2018-October
ISSN (Print)1058-6393

Conference

Conference52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
CountryUnited States
CityPacific Grove
Period18/10/2818/10/31

Fingerprint

Radar systems
Convolution
Data storage equipment
Experiments

Keywords

  • classification
  • convolutional neural networks
  • fast chirp FMCW radar
  • recurrent neural networks

ASJC Scopus subject areas

  • Signal Processing
  • Computer Networks and Communications

Cite this

Kim, S., Lee, K., Doo, S., & Shim, B. (2019). Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks. In M. B. Matthews (Ed.), Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 (pp. 2050-2054). [8645406] (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2018-October). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2018.8645406

Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks. / Kim, Sangtae; Lee, Kwangjin; Doo, Seungho; Shim, Byonghyo.

Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. ed. / Michael B. Matthews. IEEE Computer Society, 2019. p. 2050-2054 8645406 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2018-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, S, Lee, K, Doo, S & Shim, B 2019, Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks. in MB Matthews (ed.), Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018., 8645406, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2018-October, IEEE Computer Society, pp. 2050-2054, 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018, Pacific Grove, United States, 18/10/28. https://doi.org/10.1109/ACSSC.2018.8645406
Kim S, Lee K, Doo S, Shim B. Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks. In Matthews MB, editor, Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. IEEE Computer Society. 2019. p. 2050-2054. 8645406. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2018.8645406
Kim, Sangtae ; Lee, Kwangjin ; Doo, Seungho ; Shim, Byonghyo. / Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks. Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. editor / Michael B. Matthews. IEEE Computer Society, 2019. pp. 2050-2054 (Conference Record - Asilomar Conference on Signals, Systems and Computers).
@inproceedings{3d92b9dc095e4262b077ee8ff52bf780,
title = "Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks",
abstract = "In this paper, we propose a deep neural network model for target classification in automotive radar system. In the proposed network, we introduce transposed convolutional network (TCNet) which applies transposed convolution operations. We discuss the properties of transposed convolution and show that TCNet can reduce the network size and improve the classification performance for the systems in which the signals are sparse and memory is restricted like our automotive radar systems. In our experiment, we show that the proposed network outperforms other popularly used dimensionality reduction approaches in terms of classification accuracy.",
keywords = "classification, convolutional neural networks, fast chirp FMCW radar, recurrent neural networks",
author = "Sangtae Kim and Kwangjin Lee and Seungho Doo and Byonghyo Shim",
year = "2019",
month = "2",
day = "19",
doi = "10.1109/ACSSC.2018.8645406",
language = "English",
series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
pages = "2050--2054",
editor = "Matthews, {Michael B.}",
booktitle = "Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018",

}

TY - GEN

T1 - Moving Target Classification in Automotive Radar Systems Using Transposed Convolutional Networks

AU - Kim, Sangtae

AU - Lee, Kwangjin

AU - Doo, Seungho

AU - Shim, Byonghyo

PY - 2019/2/19

Y1 - 2019/2/19

N2 - In this paper, we propose a deep neural network model for target classification in automotive radar system. In the proposed network, we introduce transposed convolutional network (TCNet) which applies transposed convolution operations. We discuss the properties of transposed convolution and show that TCNet can reduce the network size and improve the classification performance for the systems in which the signals are sparse and memory is restricted like our automotive radar systems. In our experiment, we show that the proposed network outperforms other popularly used dimensionality reduction approaches in terms of classification accuracy.

AB - In this paper, we propose a deep neural network model for target classification in automotive radar system. In the proposed network, we introduce transposed convolutional network (TCNet) which applies transposed convolution operations. We discuss the properties of transposed convolution and show that TCNet can reduce the network size and improve the classification performance for the systems in which the signals are sparse and memory is restricted like our automotive radar systems. In our experiment, we show that the proposed network outperforms other popularly used dimensionality reduction approaches in terms of classification accuracy.

KW - classification

KW - convolutional neural networks

KW - fast chirp FMCW radar

KW - recurrent neural networks

UR - http://www.scopus.com/inward/record.url?scp=85062964777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062964777&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2018.8645406

DO - 10.1109/ACSSC.2018.8645406

M3 - Conference contribution

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 2050

EP - 2054

BT - Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018

A2 - Matthews, Michael B.

PB - IEEE Computer Society

ER -