A neural network approach to target classification for active safety system using microwave radar

Seongkeun Park; Jae Pil Hwang; Euntai Kim; Heejin Lee; Ho Gi Jung

doi:10.1016/j.eswa.2009.07.070

A neural network approach to target classification for active safety system using microwave radar

Seongkeun Park, Jae Pil Hwang, Euntai Kim, Heejin Lee, Ho Gi Jung

Department of Electrical and Electronic Engineering

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

22 Citations (Scopus)

Abstract

As a sensor in the active safety system of vehicles, the microwave radar (MWR) would be a good choice for the localization of the nearby targets but could be a bad choice for their classification or identification. In this paper, a target classification system using a 24 GHz microwave radar sensor is proposed for the active safety system. The basic idea of this paper is that the pedestrians and the vehicles have different reflection characteristics for a microwave. A multilayer perceptron (MLP) neural network is employed to classify the targets and the probabilistic fusion is conduct over time to improve the classification accuracy. Some experiments are performed to show the validity of the proposed system.

Original language	English
Pages (from-to)	2340-2346
Number of pages	7
Journal	Expert Systems with Applications
Volume	37
Issue number	3
DOIs	https://doi.org/10.1016/j.eswa.2009.07.070
Publication status	Published - 2010 Mar 15

Bibliographical note

Funding Information:
This work is supported by Mando Co., Active Protection Pedestrian System Project.

All Science Journal Classification (ASJC) codes

Engineering(all)
Computer Science Applications
Artificial Intelligence

Access to Document

10.1016/j.eswa.2009.07.070

Cite this

@article{3137ff60f7e34577bb015c4d541ae195,

title = "A neural network approach to target classification for active safety system using microwave radar",

abstract = "As a sensor in the active safety system of vehicles, the microwave radar (MWR) would be a good choice for the localization of the nearby targets but could be a bad choice for their classification or identification. In this paper, a target classification system using a 24 GHz microwave radar sensor is proposed for the active safety system. The basic idea of this paper is that the pedestrians and the vehicles have different reflection characteristics for a microwave. A multilayer perceptron (MLP) neural network is employed to classify the targets and the probabilistic fusion is conduct over time to improve the classification accuracy. Some experiments are performed to show the validity of the proposed system.",

author = "Seongkeun Park and {Pil Hwang}, Jae and Euntai Kim and Heejin Lee and {Gi Jung}, Ho",

note = "Funding Information: This work is supported by Mando Co., Active Protection Pedestrian System Project.",

year = "2010",

month = mar,

day = "15",

doi = "10.1016/j.eswa.2009.07.070",

language = "English",

volume = "37",

pages = "2340--2346",

journal = "Expert Systems with Applications",

issn = "0957-4174",

publisher = "Elsevier Limited",

number = "3",

}

TY - JOUR

T1 - A neural network approach to target classification for active safety system using microwave radar

AU - Park, Seongkeun

AU - Pil Hwang, Jae

AU - Kim, Euntai

AU - Lee, Heejin

AU - Gi Jung, Ho

N1 - Funding Information: This work is supported by Mando Co., Active Protection Pedestrian System Project.

PY - 2010/3/15

Y1 - 2010/3/15

N2 - As a sensor in the active safety system of vehicles, the microwave radar (MWR) would be a good choice for the localization of the nearby targets but could be a bad choice for their classification or identification. In this paper, a target classification system using a 24 GHz microwave radar sensor is proposed for the active safety system. The basic idea of this paper is that the pedestrians and the vehicles have different reflection characteristics for a microwave. A multilayer perceptron (MLP) neural network is employed to classify the targets and the probabilistic fusion is conduct over time to improve the classification accuracy. Some experiments are performed to show the validity of the proposed system.

AB - As a sensor in the active safety system of vehicles, the microwave radar (MWR) would be a good choice for the localization of the nearby targets but could be a bad choice for their classification or identification. In this paper, a target classification system using a 24 GHz microwave radar sensor is proposed for the active safety system. The basic idea of this paper is that the pedestrians and the vehicles have different reflection characteristics for a microwave. A multilayer perceptron (MLP) neural network is employed to classify the targets and the probabilistic fusion is conduct over time to improve the classification accuracy. Some experiments are performed to show the validity of the proposed system.

UR - http://www.scopus.com/inward/record.url?scp=70449521179&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449521179&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2009.07.070

DO - 10.1016/j.eswa.2009.07.070

M3 - Article

AN - SCOPUS:70449521179

SN - 0957-4174

VL - 37

SP - 2340

EP - 2346

JO - Expert Systems with Applications

JF - Expert Systems with Applications

IS - 3

ER -

A neural network approach to target classification for active safety system using microwave radar

Abstract

Bibliographical note

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this