Publication detail

Automatic Traffic Sign Detection and Recognition Using Colour Segmentation and Shape Identification

HORÁK, K. DAVÍDEK, D. ČÍP, P.

Original Title

Automatic Traffic Sign Detection and Recognition Using Colour Segmentation and Shape Identification

English Title

Automatic Traffic Sign Detection and Recognition Using Colour Segmentation and Shape Identification

Type

journal article in Web of Science

Language

en

Original Abstract

The paper describes a colour-based segmentation method of European traffic signs for detection in an image and a feature-based recognition method for categorizing them into given classes. At first, we have performed analysis of several well-known colour spaces as the RGB, HSV and YCbCr often used for segmentation purposes. The HSV colour space has been chosen as the most convenient for segmentation step and colour-based models of traffic signs representatives were created. Next, the fast radial symmetry (FRS) detection method and the Harris corner detector were used to recognize circles, triangles and squares as main geometrical shapes of the traffic signs. For these purposes a new gallery of real-life images containing traffic signs has been created and analysed. Overall efficiency of our recognition method is approx. 93 % on our gallery and is usable for real-time implementations.

English abstract

The paper describes a colour-based segmentation method of European traffic signs for detection in an image and a feature-based recognition method for categorizing them into given classes. At first, we have performed analysis of several well-known colour spaces as the RGB, HSV and YCbCr often used for segmentation purposes. The HSV colour space has been chosen as the most convenient for segmentation step and colour-based models of traffic signs representatives were created. Next, the fast radial symmetry (FRS) detection method and the Harris corner detector were used to recognize circles, triangles and squares as main geometrical shapes of the traffic signs. For these purposes a new gallery of real-life images containing traffic signs has been created and analysed. Overall efficiency of our recognition method is approx. 93 % on our gallery and is usable for real-time implementations.

Keywords

Traffic sign, colour segmentation, shape recognition.

Released

01.08.2016

Publisher

EDP Sciences

Location

EDP Sciences - France

ISBN

2261236X

Book

Proceedings of the 3rd International Conference on Industrial Engineering and Applications 2016.

Edition

Volume 68

Edition number

17002

Pages from

1

Pages to

6

Pages count

6

URL

Documents

BibTex


@article{BUT127252,
  author="Karel {Horák} and Daniel {Davídek}",
  title="Automatic Traffic Sign Detection and Recognition Using Colour Segmentation and Shape Identification",
  annote="The paper describes a colour-based segmentation method of European traffic signs for detection in an image and a feature-based recognition method for categorizing them into given classes. At first, we have performed analysis of several well-known colour spaces as the RGB, HSV and YCbCr often used for segmentation purposes. The HSV colour space has been chosen as the most convenient for segmentation step and colour-based models of traffic signs representatives were created. Next, the fast radial symmetry (FRS) detection method and the Harris corner detector were used to recognize circles, triangles and squares as main geometrical shapes of the traffic signs. For these purposes a new gallery of real-life images containing traffic signs has been created and analysed. Overall efficiency of our recognition method is approx. 93 % on our gallery and is usable for real-time implementations.",
  address="EDP Sciences",
  booktitle="Proceedings of the 3rd International Conference on Industrial Engineering and Applications 2016.",
  chapter="127252",
  doi="10.1051/matecconf/20166817002",
  edition="Volume 68",
  howpublished="online",
  institution="EDP Sciences",
  number="17002",
  volume="68",
  year="2016",
  month="august",
  pages="1--6",
  publisher="EDP Sciences",
  type="journal article in Web of Science"
}