Traffic Light Recognition for Autonomous Driving Vehicle: Using Mono Camera and ITS

Mun Kyu Lee; Jeong Won Pyo; Sang Hyeon Bae; Sung Hyeon Joo; Tae Yong Kuc

doi:10.18178/joig.10.3.102-108

Traffic Light Recognition for Autonomous Driving Vehicle: Using Mono Camera and ITS

Mun Kyu Lee
, Jeong Won Pyo
, Sang Hyeon Bae
, Sung Hyeon Joo
, Tae Yong Kuc

Sungkyunkwan University

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

4 Scopus citations

Abstract

This paper introduces a system of real-time Traffic Light (TL) recognition, which is an essential element for unmanned autonomous vehicles when driving through urban city. The system of TL recognition is an integrating system that fuses a binary processing method, a network model method, and an ITS information. By using two algorithms that processes results through a mono camera, we enhance our recognition accuracy when ITS information is not confirmed properly. We evaluated the individual and integrated TL recognition performance of the system in actual testbed to ensure that our system is satisfied the performance for our autonomous driving scenario. The result of the experiment met our autonomous driving scenario conditions.

Original language	English
Pages (from-to)	102-108
Number of pages	7
Journal	Journal of Image and Graphics(United Kingdom)
Volume	10
Issue number	3
DOIs	https://doi.org/10.18178/joig.10.3.102-108
State	Published - Sep 2022
Externally published	Yes

Keywords

autonomous driving
deep learning
image processing
ITS
traffic light recognition

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.18178/joig.10.3.102-108

Cite this

@article{a4dcbbb508e34adc83a81967478e1276,

title = "Traffic Light Recognition for Autonomous Driving Vehicle: Using Mono Camera and ITS",

abstract = "This paper introduces a system of real-time Traffic Light (TL) recognition, which is an essential element for unmanned autonomous vehicles when driving through urban city. The system of TL recognition is an integrating system that fuses a binary processing method, a network model method, and an ITS information. By using two algorithms that processes results through a mono camera, we enhance our recognition accuracy when ITS information is not confirmed properly. We evaluated the individual and integrated TL recognition performance of the system in actual testbed to ensure that our system is satisfied the performance for our autonomous driving scenario. The result of the experiment met our autonomous driving scenario conditions.",

keywords = "autonomous driving, deep learning, image processing, ITS, traffic light recognition",

author = "Lee, \{Mun Kyu\} and Pyo, \{Jeong Won\} and Bae, \{Sang Hyeon\} and Joo, \{Sung Hyeon\} and Kuc, \{Tae Yong\}",

note = "Publisher Copyright: {\textcopyright} 2022 Journal of Image and Graphics.",

year = "2022",

month = sep,

doi = "10.18178/joig.10.3.102-108",

language = "English",

volume = "10",

pages = "102--108",

journal = "Journal of Image and Graphics(United Kingdom)",

issn = "2301-3699",

publisher = "University of Portsmouth",

number = "3",

}

TY - JOUR

T1 - Traffic Light Recognition for Autonomous Driving Vehicle

T2 - Using Mono Camera and ITS

AU - Lee, Mun Kyu

AU - Pyo, Jeong Won

AU - Bae, Sang Hyeon

AU - Joo, Sung Hyeon

AU - Kuc, Tae Yong

PY - 2022/9

Y1 - 2022/9

N2 - This paper introduces a system of real-time Traffic Light (TL) recognition, which is an essential element for unmanned autonomous vehicles when driving through urban city. The system of TL recognition is an integrating system that fuses a binary processing method, a network model method, and an ITS information. By using two algorithms that processes results through a mono camera, we enhance our recognition accuracy when ITS information is not confirmed properly. We evaluated the individual and integrated TL recognition performance of the system in actual testbed to ensure that our system is satisfied the performance for our autonomous driving scenario. The result of the experiment met our autonomous driving scenario conditions.

AB - This paper introduces a system of real-time Traffic Light (TL) recognition, which is an essential element for unmanned autonomous vehicles when driving through urban city. The system of TL recognition is an integrating system that fuses a binary processing method, a network model method, and an ITS information. By using two algorithms that processes results through a mono camera, we enhance our recognition accuracy when ITS information is not confirmed properly. We evaluated the individual and integrated TL recognition performance of the system in actual testbed to ensure that our system is satisfied the performance for our autonomous driving scenario. The result of the experiment met our autonomous driving scenario conditions.

KW - autonomous driving

KW - deep learning

KW - image processing

KW - ITS

KW - traffic light recognition

UR - https://www.scopus.com/pages/publications/85147009983

U2 - 10.18178/joig.10.3.102-108

DO - 10.18178/joig.10.3.102-108

M3 - Article

AN - SCOPUS:85147009983

SN - 2301-3699

VL - 10

SP - 102

EP - 108

JO - Journal of Image and Graphics(United Kingdom)

JF - Journal of Image and Graphics(United Kingdom)

IS - 3

ER -

Traffic Light Recognition for Autonomous Driving Vehicle: Using Mono Camera and ITS

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this