基于多模型表示的交通标志识别算法设计  

Traffic sign recognition algorithm design based on multi-modal representation

作　　者：谷明琴[1] 蔡自兴[1] 李仪[1] 任孝平[2] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083 [2]中国计量科学研究院力学与声学计量科学研究所,北京100013

出　　处：《控制与决策》2013年第6期844-848,共5页Control and Decision

基　　金：国家自然科学基金项目(90820302;61175064);国家博士点基金项目(195470);湖南省院士基金项目(2013FJ4030);湖南省自然科学基金项目(12JJ6058)

摘　　要：通过变换RGB空间颜色值并分割图像,利用标记图为特征的形状分类器检测城市环境中的交通标志.为了提高分类准确度,用两种模型表示方法分类交通标志:1)结合二元树复小波变换和二维独立分量分析提取特征,送入最近邻分类器中分类交通标志;2)提取交通标志的内部图形,利用模板匹配进行分类.最后,将两种分类结果融合输出.实验结果表明,所提出算法的整体识别率超过91%,平均处理帧率达到6.6帧/s,系统能够鲁棒、有效和实时地识别交通标志.@@@@The image segmentation based on transforming RGB color space and the shape classifier based on signature feature are used to detect traffic signs in urban scenes. For improving recognition accuracy, two modal representations are presented to classify the traffic sign. 1) The feature of traffic sign is extracted by dual-tree complex wavelet transform(DT-CWT) and 2D independent component analysis(2DICA), then sent to the nearest neighbor classifier to classify traffic sign. 2) The template matching based on intra pictograms of traffic sign is applied to recognition. The recognition results are fused by some decision rules. Experimental results show that, the overall recognition rate of the proposed algorithm is more than 91% and the average frame rate is up to 6.6fps, which indicates that the system is robust, effective and accurate to classify traffic signs.

关 键 词：交通标志识别 二元树复小波变换 二维独立分量分析 内部图形 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]