张传伟,崔万豪

• 1:西安科技大学机械工程学院

摘要(Abstract)：

交通标志识别是智能车辆基于视觉传感感知道路信息的关键技术,针对传统识别技术不能满足实时性和准确性的要求,采用一种基于Gabor特征提取和支持向量机(SVM)交通标志识别方法。首先选定交通标志图像进行灰度化、图像增强处理,采用Gabor滤波技术进行特征提取,针对大量的特征信息采用主成分分析(PCA)降维,并用支持向量机分类识别。最后在Matlab平台上进行实验,验证该方法的识别率和识别时间。实验结果表明,该方法较传统方法识别精度高,实时性好。

关键词(KeyWords)： 交通标志识别;图像灰度化;图像增强;Gabor特征提取;主成分分析;支持向量机

Abstract:

Keywords:

基金项目(Foundation): 陕西省自然科学基金(2012JM7021)~~

作者(Author): 张传伟,崔万豪

DOI: 10.16652/j.issn.1004-373x.2018.17.030

参考文献(References)：

• [1]MOGELMOSE A,TRIVEDI M M,MOESLUND T B.Visionbased traffic signs detection and analysis for intelligent driver assistance systems:perspectives and survey[J].IEEE transactions on intelligent transportation systems,2012,13(4):1484-1497.
• [2]宋超,陈伟华.一种基于机器视觉的交通标识符自动识别方法[J].襄樊职业技术学院学报,2011,10(2):25-28.SONG Chao,CHEN Weihua.An automatic identification method of traffic identifier based on machine vision[J].Journal of Xiangfan Vocational and Technical College,2011,10(2):25-28.
• [3]宋文杰,付梦印,杨毅.一种面向无人驾驶汽车的高效交通标志识别方法[J].机器人,2015,37(1):102-111.SONG Wenjie,FU Mengyin,YANG Yi.An efficient traffic sign recognition method for driverless vehicles[J].Robot,2015,37(1):102-111.
• [4]郝博闻,梁宇峰,李文强,等.基于颜色空间和模板匹配的交通标志检测方法[J].智能计算机与应用,2016,6(4):20-22.HAO Bowen,LIANG Yufeng,LI Wenqiang,et al.Traffic sign detection methods based on color space and template matching[J].Intelligent computer and application,2016,6(4):20-22.
• [5]冯春贵,祝诗平,王海军,等.基于改进模板匹配的限速标志识别方法研究[J].西南大学学报(自然科学版),2013,35(4):167-172.FENG Chungui,ZHU Shiping,WANG Haijun,et al.Identification methods of speed limiting markers based on improved template matching[J].Journal of Southwest University(nature science),2013,35(4):167-172.
• [6]杨斐,王坤明,马欣,等.应用BP神经网络分类器识别交通标志[J].计算机工程,2003,29(10):120-121.YANG Fei,WANG Kunming,MA Xin,et al.Identification of traffic signs using BP neural network classifier[J].Computer engineering,2003,29(10):120-121.
• [7]KUMARSAHA S,CHAKRABORTY D,ALAMIN B.Neural network based sign recognition[J].International journal of computer applications,2013,50(10):35-41.
• [8]CIRESAN D,MEIER U,MASCI J,et al.Multicolumn deep neural network for traffic sign classification[J].Neural networks,2012,32(2):333-338.
• [9]王雁,穆春阳,马行.基于颜色标准化模型和HOG特征的交通标志检测[J].软件导刊,2015,14(3):142-144.WANG Yan,MU Chunyang,MA Xing.Traffic sign detection based on color standardization model and HOG feature[J].Software guide,2015,14(3):142-144.
• [10]SONG M L,TAO D P,CHEN C,et al.Color to gray:visual cue preservation[J].IEEE transactions on pattern analysis and machine intelligence,2010,32(9):1537-1552.
• [11]GONZALEZ R C.Digital image processing[M].2nd ed.Beijing:Publishing House of Electronics Industry,2006.
• [12]LIN Kezheng,XU Ying,ZHONG Yuan.Using 2DGabor values and kernel fisher discriminant analysis for face recognition[C]//Proceedings of the 2nd International Conference on Information Science and Engineering.Hangzhou,China:IEEE,2010:7624-7627.
• [13]WANG Xiaojie.Modular PCA based on within-class median for face recognition[C]//Proceedings of the 3rd IEEE International Conference on Computer Science and Information Technology.Chengdu,China:IEEE,2010:52-56.
• [14]何耀平,徐丽珍.自然场景下交通标志的自动识别算法[J].微计算机信息,2010,26(4):161-163.HE Yaoping,XU Lizhen.Automatic recognition algorithm of traffic signs in natural scenes[J].Microcomputer information,2010,26(4):161-163.
• [15]陈兴,贾银山.基于支持向量机的交通标志识别方法研究[J].科学技术与工程,2011,11(8):1751-1754.CHEN Xing,JIA Yinshan.Research on traffic sign recognition methods based on support vector machines[J].Science,technology and engineering,2011,11(8):1751-1754.