Traffic Sign Recognition System for Roadside Images in Poor Condition

Abstract

Abstract-Traffic sign detection and recognition is a difficult task, especially if we aim at detecting and recognizing signs in images captured under poor conditions. Complex backgrounds, obstructing objects, inappropriate distance of signs, shadow, and other lighting-related problems may make it difficult to detect and recognize signs in both rural and urban areas. In this paper we propose and test a system that employs image pre-processing, color filtering, color segmentation for traffic sign detection at the detection stage, feature extraction and trained neural networks for unique identification of signs at the recognition stage. The traffic sign detection and recognition system has been tested on actual roadside images taken under poor conditions. The images were selected in order to test the efficiency of the system under challenging conditions of inappropriate distance, traffic sign size, poor lighting and complex background. Suggestions are made for improving the performance of the system.

The Prototype of a Traffic Signs Recognition System Using Mobile Augmented Reality

“…Combining information from the risk factor classes and using SWRL (semantic web rule language), inference rules for risk assessment are created. The authors of [14] propose and test a traffic sign recognition system in poor conditions applied on the road signs in Thailand. After performance analysis they concluded that next step in future work is to apply ontology-based knowledge in order to improve traffic sign recognition.…”

Speed bump detection system by autothresholding method

“…Kullanılan yöntem işaret belirleme safhasında sırası ile RGB uzayında resim ön-işleme, renk filtrelemesi ve renk bölütlemesi tekniklerini kullanmaktadır. Sınıflandırma aşamasında ise özellik çıkarımı (feature extraction) ve eğitilmiş sinir ağları yapısını kullanmaktadır [2]. Zavadil ve arkadaşlarının 2012 yıl yaptığı trafik işareti tanıma ve sınıflandırma çalışmasında ise çeşitli siyah beyaz obje özelliklerinin karşılaştırılması tabanlı algoritmalar geliştirilmiştir [3].…”