交通标志识别为智能车辆行驶提供了有价值的道路环境信息.提出一种结合形状标记图和Gabor波的交通标志识别方法,交通标志识别过程如下:1)变换图像的RGB像素值来增强交通标志主特征颜色(红,蓝,黄)区域并进行分割,用形态学操作消除噪声点的影响；2)提取感兴趣区域的标记图作为其形状特征,用Euclidean距离来对其进行初分类；3)对交通标志感兴趣区域的灰度图像进行Gabor小波变换,获得其不同角度和尺度的小波图像,用二维独立分量分析法提取其主特征,并送入线性支持向量机来判断感兴趣区域所属的交通标志类型.实验结果表明,提出的算法能够稳定、有效地检测和识别智能车辆行驶环境中的多类交通标志.%Traffic sign recognition provides valuable information on road conditions for intelligent vehicles. The traffic sign recognition process was outlined as follows: 1) The main colors of traffic signs were enhanced by transforming the RGB pixel values of the image and then segmented by a threshold. Noise points of the binary image were filtered by morphological image processing. 2) The signature of the region of interest ( Rol) was extracted as a shape feature, and the shape of the Rol was primarily classified by Euclidean distance. 3 ) The gray images of traffic signs was transformed into various orientations and scale wavelet images by the Gabor wavelet, and the main features were extracted by a 2-dimensional independent component analysis (2DICA) algorithm while the linear support vector machine was applied to judge the type of traffic signs. Experimental results show that the proposed algorithm may stably and effectively detect and identify the roadside traffic signs.
展开▼
