根据三角形交通标志的颜色和形状特征，提出了一种适用于自然场景下三角形交通标志的检测与识别方法. 该方法首先利用颜色分割粗略提取标志区；其次提取标志区轮廓边缘和直线拟合，确定三角形标志的3个顶点，精确检测出完整的三角形标志区；最后设计一种分块特征提取方法对检测出的三角形标志和所有参考三角形标志进行特征提取，通过特征匹配识别出三角形交通标志类别. 实验结果表明，所提出的检测与识别方法能更有效地识别自然环境中三角形交通标志方法，且适用性强.
An approach is proposed to detect and recognize triangular traffic signs in natural scenes according to color and geometric features of the signs. The sign is first roughly extracted based on color segmentation.A straight line fitting method is used to detect the three sides of the triangular signs to obtain the complete triangular sign. A partitioning feature method is used to obtain feature vectors from all reference triangular traffic signs as well as the detected ones, then the detected triangular traffic sign is recognized by feature vector matching. Experimental results show that the proposed method is effective for recognizing triangular traffic signs in natural scenes.
[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): 50-52.
ZHU Shuangdong, LU Xiaofeng. A Survey of the research on traffic sign recognition [J]. Journal of Computer Engineering and Science,2006, 28(12): 50-52.(in Chinese)
[2]NGUWI Y Y, KOUZANI A Z. A Study on automatic cybernetics and intelligent systems [J]. IEEE Conference on Cybernetics and Intelligent Systems, 2006, 1(1): 372-377.
[3]SOETEDJO A, YAMADA K. An efficient algorithm for traffic sign detection [J]. Journal of Advanced Computational Intelligence and Intelligent Informatics, 2006, 10(3): 409-417.
[4]黄志勇，孙光民，李芳. 基于RGB视觉模型的交通标志分割[J]. 微电子学与计算机，2004, 21(10): 147-148.
HUANG Zhiyong, SUN Guangmin, LI Fang. Traffic sign segmentation based on RGB vision model [J]. Journal of Microelectronics and computer, 2004, 21(10):147-148.(in Chinese)
[5] ESCALERA A, MORENO LE, SALICHS M A. Road traffic sign detection and classification [J]. IEEE Transactions on Industrial Electronics, 1997, 44(6): 848-859.
[6] ESCALERA A, ARMINGOL J M. Traffic sign recognition and analysis for intelligent vehicles [J]. Image and Vision Computing, 2003, 21(3):247-258.
[7] MIGUEL A G, MANUEL O D. Complete vision-based traffic sign recognition supported by an I2V communication system [J]. Sensors, 2012, 12(2): 1148-1169.
[8] BARNES N, LOY G, FLETCHER L S. Real-time speed sign detection using the radial symmetry detector [J]. IEEE Transactions on Intelligent Transportation, 2008, 9(2): 322-332.
[9] TORRESEN J, BAKKE J, SEKANINA L. Efficient recognition of speed limit signs[J]. Proceedings of the 7th international IEEE conference on Intelligent Transportation Systems, 2004, 1(1): 652-656.
[10] PACLIK P, NOVOVICOVA J, DUIN R P W. A trainable similarity measure for image classification [J]. The 18th International Conference on Pattern Recognition, 2006, 1(1):391-394.
[11] MEUTER M, NUNN C, MICHAEL S G. A decision fusion and reasoning module for a traffic sign recognition system [J]. IEEE Transactions on Intelligent Transportation Systems, 2011, 20(12): 1126-1134.
[12]林川，潘盛辉，韩峻峰. 基于人类视觉系统的交通标志优化分割方法[J]. 武汉大学学报, 2011, 57(3): 236-240.
LIN Chuan, PAN Shenghui, HAN Junfeng. A method of traffic sign optimal segmentation based on human visual system [J]. Journal of Wuhan University: Nature Science, 2011, 57(3): 236-240. (in Chinese)
[13] ZHU Shuangdong. Two hierarchy classifier of recognition of traffic signs based on neural network[C]//5th World Congress on Intelligent Control and Automation, 2004: 5302-5306.
[14]朱金好，罗金萍. 基于决策树型的SVM交通标志识别 [J]. 长沙理工大学学报，2004, 20(2): 13-17.
ZHU Jinhao, LUO Xiaoping. Recognition of traffic sign images based on decision-tree based support vector machine [J]. Journal of Changsha University of Science and Technology: Natural Science, 2004, 20(2): 13-17. (in Chinese)
[15]许相莉， 张利彪，于哲舟.多粒度颜色特征在图像检索中的应用 [J]. 应用科学学报，2009, 27(1): 56-61.
XU Xiangli, ZHANG Libiao, YU Zhezhou. Application of multi granularity color features in image retrieval [J]. Journal of Applied Science, 2009, 27(1): 56-61. (in Chinese)
