Publication detail

Classification of Traffic Signs by Convolutional Neural Networks

MÍVALT, F. NEJEDLÝ, P.

Original Title

Classification of Traffic Signs by Convolutional Neural Networks

English Title

Classification of Traffic Signs by Convolutional Neural Networks

Type

conference paper

Language

Czech

Original Abstract

The paper presented here describes traffic signs classification method based on a convolutional neural network (CNN). The CNN was trained and tested on the public database of German traffic signs with 43 mostly used traffic sign types. Proposed technique achieved overall classification F1 score 89.97 percent on a hidden testing dataset.

English abstract

The paper presented here describes traffic signs classification method based on a convolutional neural network (CNN). The CNN was trained and tested on the public database of German traffic signs with 43 mostly used traffic sign types. Proposed technique achieved overall classification F1 score 89.97 percent on a hidden testing dataset.

Keywords

Machine learning; Convolutional neural networks; Traffic signs recognition

Key words in English

Machine learning; Convolutional neural networks; Traffic signs recognition

Authors

MÍVALT, F.; NEJEDLÝ, P.

Released

26. 4. 2018

Publisher

Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních

Location

Brno

ISBN

978-80-214-5614-3

Book

Proceedings of the 24th Conference STUDENT EEICT 2018

Edition number

první

Pages from

188

Pages to

190

Pages count

3

URL

http://www.feec.vutbr.cz/EEICT/archiv/sborniky/EEICT_2018_sbornik.pdf

BibTex

@inproceedings{BUT147412,
  author="Filip {Mívalt} and Petr {Nejedlý}",
  title="Classification of Traffic Signs by Convolutional Neural Networks",
  booktitle="Proceedings of the 24th Conference STUDENT EEICT 2018",
  year="2018",
  number="první",
  pages="188--190",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních",
  address="Brno",
  isbn="978-80-214-5614-3",
  url="http://www.feec.vutbr.cz/EEICT/archiv/sborniky/EEICT_2018_sbornik.pdf"
}