文章基本信息

标题：Efficiently Recognition and Tracking of Traffic Signs Using SVM
本地全文：下载
作者：Sameer Inamdar ; Akshay Mande ; Sagar Bhagat 等
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2017
卷号：5
期号：2
页码：1635
DOI：10.15680/IJIRCCE.2017.0502074
出版社：S&S Publications
摘要：The number of cars is speedily growing. In parallel, the quantity of approaches and site visitor’sindicators have multiplied. As a result of accelerated site visitor’s indicators, the drivers are anticipated to gainknowledge of all the visitor’s indicators and to pay concentration to them while driving. A process that can routinelyrecognize the site visitors signs has been need to decrease traffic accidents and to pressure extra freely.We introduce anew system for traffic sign recognition and tracking. Such a system presents a vital support for driver assistance in anintelligent automotive. First, to generate traffic sign applicant regions a colour based segmentation method is applied.Secondly, the extracted HoG feature’s are used to encode the detected traffic signs and then generate the featurevector. To identify the traffic sign class this vector is used as an input to an SVM classifier. Finally, In tracking methodperform a monocular tracking step in order to have a continuous capture of the traffic sign while accelerating theexecution time. Our method affords under different challenging conditions with high precision rates.
关键词：Traffic signs recognition; Traffic signs detection; Traffic signs classification; Traffic signs tracking;SVM; HOG