Car Traffic Sign Annunciator

Abstract

Automatic detection and recognition of traffic signs is an essential part of automated driver assistance systems which contribute to the safety of the drivers, pedestrians and vehicles. This paper presents the advanced driver assistance system (ADAS) based on Raspberry pi for traffic sign detection, recognition and annunciation. Such a system presents a vital support for driver assistance in an intelligent automotive. The proposed algorithm is implemented in a real time embedded system using OpenCV library. Proposed method introduced a new method for detection and recognition of traffic signs. Firstly, Potential traffic signs regions are detected by colour segmentation method, then classified using HOG features and a linear SVM classifier to identify the traffic sign class. The proposed system shows good recognition rate under complex challenging lighting and weather conditions. Experimental results on the accuracy of the road sign detection are reported in this paper.