基于颜色和边缘信息的交通标志检测  

Traffic Sign Detection Based on Color and Boundary Feature

作　　者：简楹[1] 

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004

出　　处：《山西电子技术》2011年第3期6-7,共2页Shanxi Electronic Technology

基　　金：广西科学基金项目(桂科基0991022);广西千亿元产业重大科技攻关工程项目(桂科攻0996028)

摘　　要：根据我国交通标志的颜色和几何属性,提出了一种适用于自然背景下的交通标志检测方法。该方法采用RGB彩色分量差对自然背景下的禁令标志图像进行分割,结合最小二乘法对像素坐标进行椭圆拟合,再根据边界的圆形度参数判断是否为圆形区域。实验证明了该方法的有效性与鲁棒性。According to the color and geometric properties of traffic signs in our country,an efficient traffic sign detection method applying to natural scenes is proposed in this paper.In this method,an improved image segmentation algorithm based on RGB model is implemented on segmenting traffic signs in natural scenes and combined with the least squares to fit pixel coordinates in oval,then to judge whether it is in the circular area by the circular degree parameters of the boundary.The experimental results show the feasibility and robustness of the proposed algorithm.

关 键 词：标志检测 RBG模型 椭圆拟合 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]