Real-Time Detection of Road Signs

Real-Time Detection of Road Signs

Abderrahim Salhi, Brahim Minaoui, Mohamed Fakir, Mohammed Sajieddine
Copyright: © 2015 |Pages: 11
DOI: 10.4018/JECO.2015070103
(Individual Articles)
No Current Special Offers


In order to realize an identification system of traffic road signs in real time, the authors have developed a performed detection method of these signs in real time. This method, presented in this paper, is implemented in two modules. The first is a pre-processing module based on video stream processing technics and the second, based on the polygonal approximation digital curves, identifies areas that may contain road signs using the particularity of their colors and contours. All algorithms implemented in this work are developed under the programming language C / C ++ using OpenCV library. The results of tests, realized on real videos of the traffic signs, show the performance improvement of the method developed in this work in terms of rate and speed of detection.
Article Preview


Real time traffic signs detection and recognition is a very important issue for Driver Assistance Systems and road safety. An automatic road sign detector system identifies road signs from images captured by an imaging sensor on a vehicle, and assists the driver to properly operate the vehicle. Problems in road sign detection are discussed by (Y.-Y. Nguwiand A.Z. Kouzani, 2006). These Problems are:

  • Lighting condition is a very difficult problem to regulate because it depends on the time of the day and also on the weather conditions.

  • Images may suffer from bluffing effect due to vibration of moving vehicle.

  • The direction of sign's face is not always ideal. It can be affected due to the viewing angle.

  • Colors on road sign may fade due to long exposure to the sun and rain.

  • Road signs may place one over the other.

  • Sign can be confused with other similar man-made objects such as commercial signs and building windows.

  • Obstacles, such as tree, street lamp, buildings, traffic lights, vehicles and pedestrians, may partially occlude road signs

A method for the prohibition traffic signs designed for drivers is proposed in (Xu Qingsong, SuJuan, Liu Tiantian, 2010). Prohibition traffic signs have many characteristics, such as brilliant colors, striking positions, special shapes, etc. The color information in HSI color space and the symmetry property of circles are used to detect signs, and the Histograms of Oriented Gradients feature and the nearest distance method are used to recognize them. There are three main reasons which will lead to miss detection for the proposed algorithm: far distance, serious occlusion and overlapping.

The system developed in this work focuses on the real-time detection of the road signs. It is composed of two modules: The first Module is a pre-processing module that consists to apply video stream processing technicsto the video streams of the trafficsignscoming from a CCD camera. The second Module is a detection Module which is designed to detect and extract zones may contain traffic signs in the video stream.It’s based on the particular color and geometry of traffic signs.This module uses image processing technics such as color segmentation, thresholdtechnic, Gaussian filter, canny edge detection (F.A. Aly and A.E. Alaa, 2004), (H. X. Liu, and B. Ran, 2001), (H. Fleyeh, and M. Dougherty, pp644-653) et (A. Escalera, L.E. Moreno, M.A Salichs, and J.M Armingol, 1997). The detection module allows to greatly reduce the amount of information to be processed.This allows faster processing and facilitating the realization of a system operating in real time.

The algorithms are designed to detect red triangular, red circular, blue circular and blue rectangular shapes. This choice of traffic signs covers a vast majority of common traffic signs and also the most important signals that advertise a danger on the road: a ban (speed limit) or require a driver to certain behaviour (blue signs). Figure 1 shows some examples of signs used in this work.

Figure 1.

Examples of the four types of panels considered in this work


Complete Article List

Search this Journal:
Volume 21: 1 Issue (2023)
Volume 20: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 19: 4 Issues (2021)
Volume 18: 4 Issues (2020)
Volume 17: 4 Issues (2019)
Volume 16: 4 Issues (2018)
Volume 15: 4 Issues (2017)
Volume 14: 4 Issues (2016)
Volume 13: 4 Issues (2015)
Volume 12: 4 Issues (2014)
Volume 11: 4 Issues (2013)
Volume 10: 4 Issues (2012)
Volume 9: 4 Issues (2011)
Volume 8: 4 Issues (2010)
Volume 7: 4 Issues (2009)
Volume 6: 4 Issues (2008)
Volume 5: 4 Issues (2007)
Volume 4: 4 Issues (2006)
Volume 3: 4 Issues (2005)
Volume 2: 4 Issues (2004)
Volume 1: 4 Issues (2003)
View Complete Journal Contents Listing