自然环境下交通标志牌的检测与识别  

Detection and identification of traffic signs in natural environment

作　　者：彭泽民 叶青[1] Peng Zemin;Ye Qing(Changsha University of Science&Technology,Changsha Hunan,410000)

机构地区：[1]长沙理工大学电气与信息工程学院

出　　处：《电子测试》2020年第1期45-47,92,共4页Electronic Test

摘　　要：在社会经济飞速发展背景下,汽车的应用得到普及,已进入千家万户,汽车为人们出行带来了便利性,不过频发的交通事故也值得深思。而引起交通事故的原因之一即未及时检测到交通标志牌,故而探索出可快捷进行交通标志牌检测与识别的技术非常重要,该检测结合智能交通技术进行交通标志识别系统的设计,设计的识别方法即经提取标准图片与待识别图片的垂直、水平方位的灰度分布,完成Pearson相关系数计算工作,并通过一定阈值的设定,于待识别图片和所有标准图片里均作Pearson相关系数计算后,相关系数的值为最大,同时比阈值更大则认定成匹配成功来达到提醒与警示驾驶员的作用,将交通事故发生率控制到最低。Under the background of the rapid development of social economy,the application of automobile has been popularized,and has entered thousands of households.Automobile has brought convenience for people to travel,but frequent traffic accidents are also worth pondering.One of the causes of traffic accidents is that traffic signs are not detected in time,so it is very important to explore a technology that can quickly detect and identify traffic signs.This detection combines with intelligent transportation technology to design a traffic sign recognition system.The designed recognition method is to extract the vertical and horizontal gray distribution of the standard picture and the picture to be identified to complete pear Son correlation coefficient calculation work,and through a certain threshold setting,after Pearson correlation coefficient calculation in the image to be identified and all standard images,the value of correlation coefficient is the maximum,and at the same time,if it is larger than the threshold,it is considered as matching success to achieve the role of warning and warning drivers,and control the traffic accident rate to the minimum.

关 键 词：交通标志牌 Pearson相关系数 阈值 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] U463.6[自动化与计算机技术—计算机科学与技术]