Traffic Light Detection Using Rotated Principal Component Analysis for Video-Based Car Navigation System

被引：3

作者：

Joo, Sung-Kwan ^{[1
]}

Kim, Yongkwon ^{[1
]}

Cho, Seong Ik ^{[2
]}

Choi, Kyoungho ^{[3
]}

Lee, Kisung ^{[1
]}

机构：

[1] Korea Univ, Seoul, South Korea

[2] ETRI, Taejon, South Korea

[3] Mokpo Natl Univ, Mokpo, South Korea

来源：

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS | 2008年 / E91D卷 / 12期

关键词：

car navigation system; traffic light; crossroad detection; principal component analysis;

D O I：

10.1093/ietisy/e91-d.12.2884

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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 ill the image quality.

引用

页码：2884 / 2887

页数：4

共 9 条

[1]

Barlow M, 2001, J CLIMATE, V14, P2105, DOI 10.1175/1520-0442(2001)014<2105:EPDVAU>2.0.CO

[2]

[3]

Bishop CM., 1995, Neural networks for pattern recognition

[4]

Hwang TH, 2006, LECT NOTES COMPUT SC, V4319, P682

[5]

Jain A. K., 1988, FUNDAMENTALS DIGITAL

[6]

Jeong SG, 2001, ISIE 2001: IEEE INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS PROCEEDINGS, VOLS I-III, P1466, DOI 10.1109/ISIE.2001.931922

[7] Design and implementation of 4S-Van: A mobile mapping system [J].

Lee, Seung-Yong ;

Choi, Kyoung-Ho ;

Joo, In-Hak ;

Cho, Seong-Ik ;

Park, Jong-Hyun .

ETRI JOURNAL, 2006, 28 (03) :265-274

[8]

Lindner F, 2004, 2004 IEEE INTELLIGENT VEHICLES SYMPOSIUM, P49

[9]

Narzt W, 2004, LECT NOTES COMPUT SC, V3196, P440

← 1 →