Road Sign Detection – A Vision based Driver Support System

The study of traffic sign detection has been of great interests and often addressed by a three-stage procedure involving detection, tracking and classification. Road safety is an issue of national concern and its impacts is on the economy, public health and the general welfare of the people. We report on-going efforts to develop an intelligent agent for detecting and tracking traffic signs for vision based Driver Assistance System (DAS). This paper describes general framework for traffic sign detection and their subsystems. Almost all of the systems build using computer vision techniques consists of three important stages, color segmentation, sign detection and classification. We explore the important sub-systems of each of these stages, and identify their advantages and disadvantages. We propose a system based on the framework to detect circular and triangular road traffic signs making use of artificial intelligence techniques such as heuristics functions for detecting shapes. System is partially implemented and aims to help vehicle driver to have safer and enjoyable driving thereby concentrating on his actual workload.