一种基于图像匹配的地面交通标志实时识别方法  

Method of Real Time Recognition of Ground Traffic Signs Based on Image Matching

作　　者：王棚飞 刘宏哲[1] 袁家政[1] 陈丽[1] 

机构地区：[1]北京市信息服务工程重点实验室北京联合大学,北京100101

出　　处：《计算机科学》2014年第6期317-323,共7页Computer Science

基　　金：国家自然基金:跨媒体社群图像语义理解(61372148);国家自然基金:基于超图形XGML的图像半结构化研究(61271369);北京市教育委员会创新团队项目(IDHT20140508;CIT&TCD20130513);北京市教育委员会科技面上项目:智能车实时交通标志识别关键技术研究(SQKM201411417004)资助

摘　　要：地面交通标志检测识别是智能驾驶领域的一个研究方向,实时性、准确率是该研究的重点。图像匹配的方法是常用的模式识别方法。文中介绍了一种结合先验知识和图像匹配的地面交通标志检测识别方法。算法包括两部分:预处理和检测识别。预处理阶段包括图像压缩、感兴趣区域提取、形态学处理、中值滤波和逆透视等步骤,实现图像降噪和正畸,为检测识别做准备。检测识别阶段包括轮廓提取、面积过滤、图像匹配等步骤,目的是判断待测图像是否含有地面交通标志及其种类。实验证明,该算法实时性好、鲁棒性强、准确率高。Ground traffic sign detection and recognition are the hotspot of the intelligent driving.Timeliness and accuracy are the requirements of the study.Image matching method is commonly used in detection and identification.This article introduced a method for ground traffic sign detection and recognition combined with image matching and prior knowledge.Algorithm consists of two parts,preprocessing ＆ detection and identification.Preprocessing stage includes image compression,region of interest extraction,morphological processing,median filtering and inverse filtering perspective,making image noise reduced and orthodontic so as to to prepare for the detection and identification.Detection and identification stages include contour extraction,filtration area,image matching,in order to determine whether the test image containing ground traffic signs and its species.Experimental results show that the algorithm has a better performance.

关 键 词：地面交通标志 检测 图像匹配 识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]