张国山,刘振

• 1:天津大学电气与自动化工程学院

摘要(Abstract)：

针对我国当前交通环境的多变性,尤其是雾霾天气的出现,提出了一种在雾霾天气下快速实现交通标志分类识别的算法.首先,将图像从RGB颜色空间转换到HSV空间,对S通道图像边缘检测,计算标志牌的圆形度、矩形度等,判定标志牌的形状,定位提取标志牌所在的区域,根据标志牌的颜色和形状的匹配唯一性,对标志牌进行初步分类,然后提取标志牌所在的区域进行模板匹配,读取标志牌的具体含义.实验结果表明:该算法能有效地提高雾霾等恶劣天气下交通标志的检测率,并能满足实时性需求.

关键词(KeyWords)： 交通标志;检测识别;图像去雾;HSV;边缘检测;模板匹配;雾霾天气

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金资助项目(61473202)

作者(Author): 张国山,刘振

参考文献(References)：

• [1]朱双东,陆晓峰.道路交通标志识别的研究现状及展望[J].计算机工程与科学,2006,28(12):50-53.
• [2]沙莎,肖学钢.一种多通道融合的交通标志检测方法[J].计算机工程,2009,35(6):202-205.
• [3]XU Haoran,GUO Jianming,LIU Qing,et al.Fast image dehazing using improved dark channel prior[C]//Information Science and Technology.Shenzhen:Chinese Academy of Sciences,2012:663-667.
• [4]NARASIMHAN S G,NAYAR S K.Contrast restoration of weather degraded images[J].IEEE Trans on Pattern Analysis and Machine Intelligence,2003,25(8):713-724.
• [5]TAN R T.Visibility in bad weather from a single image[C]//Computer Vision and Pattern Recognition.Portland OR:IEEE Computer Society,2008:1-8.
• [6]HE Kaiming,SUN Jian,TANG Xiaoou.Single image haze removal using dark channel Prior[C]//Computer Vision and Pattern Recognition.Columbus Ohio:IEEE Computer Society,2009:1956-1963.
• [7]TAREL J P,HAUTI魬RE N.Fast visibility restoration from a single color or gray level image[C]//Computer Vision.Kyoto:Institute of Electrical and Electronics Engineers(IEEE),2009:2201-2208.
• [8]CARSON Mark,SANTAY Darrin.NIST Net:A linux-based net work emulation tool[J].ACM SI GCOMM Computer Communications Review,2003,33(3):111-126.
• [9]ZHU Shuangdong.Two hierarchy classifier for recognition of traffic signs based on neural net work[C]//5th World Congress on Intelligent Control and Automation.Beijing:Chinese Academy of Sciences,2004:5302-5306.
• [10]蒋刚毅,郑义.基于数学形态学的交通标志自动识别[J].汕头大学学报:自然科学版,1998,13(1):90-96.
• [11]常发亮,黄翠,刘成云,等.基于高斯颜色模型和SVM的交通标志检测[J].仪器仪表学报,2014,35(1):43-49.
• [12]ANCUTI Cosmin.Codruta orniana ancuti and philippe bekaert deblurring by matching[J].Computer Graphics Forum,2009,28(2):619-628.