Using self-organising maps in the detection and recognition of road signs

Miguel S. Prieto, Alastair R. Allen

Research output: Contribution to journalArticle

65 Citations (Scopus)

Abstract

Road sign recognition is a part of driver support systems. Its main aim is the increase of traffic safety by calling the driver's attention to the presence of key traffic signs. Additionally, a vision-based system able to detect and classify traffic signs from road images in real-time would also be useful as a support tool for guidance and navigation of intelligent vehicles. This paper proposes a new method for the detection and recognition of traffic signs using self-organising maps (SOM). This method first detects potential road signs by analysing the distribution of red pixels within the image, and then identifies these road signs from the distribution of dark pixels in their pictograms. Additionally, a novel hybrid system combining programmable hardware and artificial neural networks for embedded machine vision is introduced, and a prototype of this system is used in the implementation of the application. The experiments indicate a good performance of the new approach using SOM in both speed and classification accuracy. (C) 2008 Elsevier B.V. All rights reserved.

Original languageEnglish
Pages (from-to)673-683
Number of pages10
JournalImage and Vision Computing
Volume27
Issue number6
DOIs
Publication statusPublished - 4 May 2009

Keywords

  • road sign detection
  • road sign recognition
  • self-organising map
  • classification
  • classifiers

Cite this

Using self-organising maps in the detection and recognition of road signs. / Prieto, Miguel S.; Allen, Alastair R.

In: Image and Vision Computing, Vol. 27, No. 6, 04.05.2009, p. 673-683.

Research output: Contribution to journalArticle

@article{ee7c54b67e6d49be8c61e3b8a8462ee2,
title = "Using self-organising maps in the detection and recognition of road signs",
abstract = "Road sign recognition is a part of driver support systems. Its main aim is the increase of traffic safety by calling the driver's attention to the presence of key traffic signs. Additionally, a vision-based system able to detect and classify traffic signs from road images in real-time would also be useful as a support tool for guidance and navigation of intelligent vehicles. This paper proposes a new method for the detection and recognition of traffic signs using self-organising maps (SOM). This method first detects potential road signs by analysing the distribution of red pixels within the image, and then identifies these road signs from the distribution of dark pixels in their pictograms. Additionally, a novel hybrid system combining programmable hardware and artificial neural networks for embedded machine vision is introduced, and a prototype of this system is used in the implementation of the application. The experiments indicate a good performance of the new approach using SOM in both speed and classification accuracy. (C) 2008 Elsevier B.V. All rights reserved.",
keywords = "road sign detection, road sign recognition, self-organising map, classification, classifiers",
author = "Prieto, {Miguel S.} and Allen, {Alastair R.}",
year = "2009",
month = "5",
day = "4",
doi = "10.1016/j.imavis.2008.07.006",
language = "English",
volume = "27",
pages = "673--683",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",
number = "6",

}

TY - JOUR

T1 - Using self-organising maps in the detection and recognition of road signs

AU - Prieto, Miguel S.

AU - Allen, Alastair R.

PY - 2009/5/4

Y1 - 2009/5/4

N2 - Road sign recognition is a part of driver support systems. Its main aim is the increase of traffic safety by calling the driver's attention to the presence of key traffic signs. Additionally, a vision-based system able to detect and classify traffic signs from road images in real-time would also be useful as a support tool for guidance and navigation of intelligent vehicles. This paper proposes a new method for the detection and recognition of traffic signs using self-organising maps (SOM). This method first detects potential road signs by analysing the distribution of red pixels within the image, and then identifies these road signs from the distribution of dark pixels in their pictograms. Additionally, a novel hybrid system combining programmable hardware and artificial neural networks for embedded machine vision is introduced, and a prototype of this system is used in the implementation of the application. The experiments indicate a good performance of the new approach using SOM in both speed and classification accuracy. (C) 2008 Elsevier B.V. All rights reserved.

AB - Road sign recognition is a part of driver support systems. Its main aim is the increase of traffic safety by calling the driver's attention to the presence of key traffic signs. Additionally, a vision-based system able to detect and classify traffic signs from road images in real-time would also be useful as a support tool for guidance and navigation of intelligent vehicles. This paper proposes a new method for the detection and recognition of traffic signs using self-organising maps (SOM). This method first detects potential road signs by analysing the distribution of red pixels within the image, and then identifies these road signs from the distribution of dark pixels in their pictograms. Additionally, a novel hybrid system combining programmable hardware and artificial neural networks for embedded machine vision is introduced, and a prototype of this system is used in the implementation of the application. The experiments indicate a good performance of the new approach using SOM in both speed and classification accuracy. (C) 2008 Elsevier B.V. All rights reserved.

KW - road sign detection

KW - road sign recognition

KW - self-organising map

KW - classification

KW - classifiers

U2 - 10.1016/j.imavis.2008.07.006

DO - 10.1016/j.imavis.2008.07.006

M3 - Article

VL - 27

SP - 673

EP - 683

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 6

ER -