Assistance System for Traffic Signs Inventory

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F15%3A43909407" target="_blank" >RIV/62156489:43110/15:43909407 - isvavai.cz</a>

Result on the web

<a href="https://ece.pefka.mendelu.cz/sites/default/files/imce/ece_2015_final.pdf" target="_blank" >https://ece.pefka.mendelu.cz/sites/default/files/imce/ece_2015_final.pdf</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Assistance System for Traffic Signs Inventory

Original language description

We can see arising trend in the automotive industry in last years -autonomous cars that are driven just by on-board computers. During the driverless ride, computer must process a wide set of information gained by GPS locators and computer vision system, including GPS position, driving speed and descriptions of lanes and traffic signs. The traffic signs tracking system must deal with real conditions with data that are frequently obtained in poor light condition, fog and heavy rain or are otherwise disturbed. Completely same problem is solved by mapping companies that are producing geospatial data for different information systems, navigations, etc. Examples of such companies can be TomTom or Mapy.cz. They are frequently using cars equipped with a wide range of measuring instruments including panoramic cameras. These measurements are frequently done during early morning hours when the traffic conditions are acceptable. However, in this time, the sun position is usually not optimal for the photography. Most of the traffic signs and other street objects are heavily underexposed. Hence, it is difficult to find an automatic approach that can identify them reliably. In this article, we focus on methods designed to deal with described conditions. An overview of the state-of-the-art methods is outlined. Further, where it is possible, we outline an implementation of described methods using well-known Open Computer Vision library. Finally, emphasis is placed on methods that can deal with low light conditions, fog or other situations that complicate the detection process.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2015

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Enterprise and Competitive Environment: Conference Proceedings

ISBN

978-80-7509-342-4

ISSN

—

e-ISSN

—

Number of pages

10

Pages from-to

1008-1017

Publisher name

Mendelova univerzita v Brně

Place of publication

Brno

Event location

Brno

Event date

Mar 5, 2015

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

000380464000109