Traffic light detection using rotated principal component analysis for video-based car navigation system

Sung-Kwan Joo, Yongkwon Kim, Seong Ik Cho, Kyoungho Choi, Kisung Lee

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

This letter presents a novel approach for traffic light detection in a video frame captured by an in-vehicle camera. The algorithm consists of rotated principal component analysis (RPCA), modified amplitude thresholding with respect to the histograms of the PC planes and final filtering with a neural network. The proposed algorithm achieves an average detection rate of 96% and is very robust to variations in the image quality.

Original languageEnglish
Pages (from-to)2884-2887
Number of pages4
JournalIEICE Transactions on Information and Systems
VolumeE91-D
Issue number12
DOIs
Publication statusPublished - 2008 Dec 1

Fingerprint

Navigation systems
Telecommunication traffic
Principal component analysis
Railroad cars
Image quality
Cameras
Neural networks

Keywords

  • Car navigation system
  • Crossroad detection
  • Principal component analysis
  • Traffic light

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

Traffic light detection using rotated principal component analysis for video-based car navigation system. / Joo, Sung-Kwan; Kim, Yongkwon; Cho, Seong Ik; Choi, Kyoungho; Lee, Kisung.

In: IEICE Transactions on Information and Systems, Vol. E91-D, No. 12, 01.12.2008, p. 2884-2887.

Research output: Contribution to journalArticle

@article{11098b11fe724ebfaca98e42e0b81bee,
title = "Traffic light detection using rotated principal component analysis for video-based car navigation system",
abstract = "This letter presents a novel approach for traffic light detection in a video frame captured by an in-vehicle camera. The algorithm consists of rotated principal component analysis (RPCA), modified amplitude thresholding with respect to the histograms of the PC planes and final filtering with a neural network. The proposed algorithm achieves an average detection rate of 96{\%} and is very robust to variations in the image quality.",
keywords = "Car navigation system, Crossroad detection, Principal component analysis, Traffic light",
author = "Sung-Kwan Joo and Yongkwon Kim and Cho, {Seong Ik} and Kyoungho Choi and Kisung Lee",
year = "2008",
month = "12",
day = "1",
doi = "10.1093/ietisy/e91-d.12.2884",
language = "English",
volume = "E91-D",
pages = "2884--2887",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "12",

}

TY - JOUR

T1 - Traffic light detection using rotated principal component analysis for video-based car navigation system

AU - Joo, Sung-Kwan

AU - Kim, Yongkwon

AU - Cho, Seong Ik

AU - Choi, Kyoungho

AU - Lee, Kisung

PY - 2008/12/1

Y1 - 2008/12/1

N2 - This letter presents a novel approach for traffic light detection in a video frame captured by an in-vehicle camera. The algorithm consists of rotated principal component analysis (RPCA), modified amplitude thresholding with respect to the histograms of the PC planes and final filtering with a neural network. The proposed algorithm achieves an average detection rate of 96% and is very robust to variations in the image quality.

AB - This letter presents a novel approach for traffic light detection in a video frame captured by an in-vehicle camera. The algorithm consists of rotated principal component analysis (RPCA), modified amplitude thresholding with respect to the histograms of the PC planes and final filtering with a neural network. The proposed algorithm achieves an average detection rate of 96% and is very robust to variations in the image quality.

KW - Car navigation system

KW - Crossroad detection

KW - Principal component analysis

KW - Traffic light

UR - http://www.scopus.com/inward/record.url?scp=67650033083&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650033083&partnerID=8YFLogxK

U2 - 10.1093/ietisy/e91-d.12.2884

DO - 10.1093/ietisy/e91-d.12.2884

M3 - Article

VL - E91-D

SP - 2884

EP - 2887

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 12

ER -