530. 智能系统学报 第6卷 表1交通标志实时检测率和识别率 Processing,2008,88(12):2943-2955. Table 1 Detection and recognition rate of traffic signs [8]GAO X W,PODLADCHIKOVA L.SHAPOSHNIKOV D. et al.Recognition of traffic signs based on their colour and 交通 检测率 识别率 总体识别率 shape features extracted using human vision models[J]. 标志文献[6]本文 文献[6]本文文献[6]本文 Journal of Visual Communication and Image Representation, 类型 2006,17(4):675685. 算法算法 算法算法 算法算法 [9]LIM K H,SENG K P,ANG L M.Intra color-shape classi- 禁令90.396.3 92.597.5 83.593.9 fication for traffic sign recognition[C]//2010 International 警告85.395.5 82.198.1 70.093.7 Computer Symposium (ICS).Tainan,China,2010:642- 指示87.898.4 85.596.7 75.095.1 647. 限速89.696.092.197.8 [10]QIN Fei,FANG Bin,ZHAO Hengjun.Traffic sign seg- 82.593.9 mentation and recognition in scene images[C]//2010 In- 4结束语 terational Conference on Artificial Intelligence and Com- putational Intelligence (AICI).Chongqing,China,2010: 本文提出一种用于智能车辆行驶中感知交通标 262-267. [11]XIE Yuan,LIU Lifeng,LI Cuihua,et al.Unifying visual 志信息的算法.首先对获取的图像用颜色分割和形态 saliency with HOG feature learning for traffic sign detection 学操作获得交通标志的感兴趣区域，并提取其标记图 C]//Intelligent Vehicles Symposium,2009 IEEE. 作为形状特征，用Euclidean距离来对候选交通标志 X'an,China,2009:24-29. [12]RUTA A,LI Y,LIU X.Robust class similarity measure 进行初分类.在交通标志识别中，结合Gabor小波和 for traffic sign recognition[J].IEEE Transactions on Intel- 二维独立分量分析法提取交通标志感兴趣区域的主 ligent Transportation Systems,2010,11(4):846-855. 特征，用线性支持向量机来分类交通标志.在不同天 [13]KONCAR A,JANBN H,HALGAMUGE S.Gabor wavelet similarity maps for optimising hierarchical road sign classi- 气、光照等情况下，采集了包括禁令、警告、指示和限 fiers[J].Pattern Recognition Letters,2007,28(2):260- 速等32种交通标志视频图像，并用本文算法来检测 267. 和识别交通标志，检测率和识别率均在95%以上，说 [14]BAHLMANN C.ZHU Y,RAMESH V,et al.A system for traffic sign detection,tracking,and recognition using 明该算法能够有效地检测和识别交通标志. color,shape,and motion information[C]//Proceedings on Intelligent Vehicles Symposium 2005.Las Vegas,USA, 参考文献： 2005:255-260. [15]GB5768.2.道路交通标志和标线[S].北京：中国国家 [1]GARC I A,GARRIDO M,SOTELO M.Fast road sign de- 标准化管理员会，2009. tection using Hough transform for assisted driving of road ve- [16]杨福生，洪波著.独立分量分析的原理与应用[M].北 hicles[C]//Computer Aided Systems Theory-EUROCAST 京：清华大学出版社，2006：3346. 2005.Las Paimas de Gran Canaria,Spain,2005:543- 作者简介： 548. 谷明琴，女，1981年生，博士研究生，主 [2]BARNES N,ZELINSKY A,FLETCHER L S.Real-time 要研究方向为图像处理模式识别. speed sign detection using the radial symmetry detector[]. IEEE Transactions on Intelligent Transportation Systems, 2008,9(2):322-332. [3]MEUTER M,MULLER SS,NUNNY C,et al.Decision fusion and reasoning for traffic sign recognition[C]/The International IEEE Conference on Intelligent Transportation Systems,Funchal,Portugal,2010:324-329. 蔡自兴，男，1938年生，教授，博士 [4]LIU Wei,LIU Yujie,YU Hongfei,et al.Real-time speed 生导师，国际导航与运动控制科学院院 limit sign detection and recognition from image sequences 士、中国自动化学会理事.主要研究方 [C]//Artificial Intelligence and Computational Intelligence 向为人工智能、机器人、智能控制，发表 (AICI).Sanya,China,2010,1:262-267. 学术论文500余篇， [5]PRIETO M S,ALLEN A R.Using self-organising maps in the detection and recognition of road signs[J].Image and Vision Computing,2009,27(6):673-683. 6]MALDONADO-BASCON S,LAFUENTE-ARROYO S,GIL 何芬芬，女，1987年生，硕士研究生， JIMENEZ P,et al.Road-sign detection and recognition 主要研究方向为图像处理、模式识别： based on support vector machines[J].IEEE Transactions on Intelligent Transportation Systems,2007,8(2):264- 278. 7]GIL JE,NEZ P,BASC O N S M,et al.Traffic sign shape classification and localization based on the normalized FFT of the signature of blobs and 2-D homographies[J].Signal