Traffic sign recognition system

Gregor Jeraj (2011) Traffic sign recognition system. EngD thesis.

Abstract

More and more devices are used in assisting drivers on the road. One of them is traffic sign recognition system. It uses a front mounted video camera and informs the driver of incoming dangers and restrictions on the road, mainly by speech or special dashboard display. Traffic sign recognition system is used to avoid accidents, caused by drivers inability to properly recognize traffic sign. They are also a major part of autonomous vehicle systems since they are responsible for providing safe driving instructions. We proposed an intelligent traffic sign recognition system, which is based on two main parts: traffic sign location and classiffication module. First one performs color segmentations and locates traffic sign key points, which are later used to form traffic sign shape. Second module then uses neural network approach to classify shapes into traffic signs.

Item Type:

Thesis (EngD thesis)

Keywords:

neural networks, traffic signs, convolution, masks, traffic sign classification

Number of Pages:

Language of Content:

Slovenian

Mentor / Comentors:

Name and Surname	ID	Function
izr. prof. dr. Uroš Lotrič	270	Mentor

Link to COBISS:

http://www.cobiss.si/scripts/cobiss?command=search&base=50070&select=(ID=00008264020)

Institution:

University of Ljubljana

Department:

Faculty of Computer and Information Science

Item ID:

1301

Date Deposited:

15 Mar 2011 14:19

Last Modified:

13 Aug 2011 00:38

URI:

http://eprints.fri.uni-lj.si/id/eprint/1301

Actions (login required)

View Item