基于颜色聚类和Hu不变矩的道路交通标志检测  

Traffic sign detection based on color clustering and Hu invariant moments

作　　者：卢阿娟[1] 陈普春[2] 刘丽[1] 田芳[1] 

机构地区：[1]西南石油大学电气信息学院,四川成都610500 [2]西南石油大学理学院,四川成都610500

出　　处：《物联网技术》2013年第5期43-46,共4页Internet of things technologies

摘　　要：介绍了一种基于颜色分割和区域描述的交通标志检测方法。该方法利用在RGB空间的颜色聚类算法分割出感兴趣色彩区域,然后进行形态学处理,最后结合Hu不变矩对道路交通标志进行识别。识别结果表明,基于颜色聚类和Hu不变矩的交通标志识别方法具有很强的抗图像平移、缩放和旋转识别能力,并具有实现简单、识别速度快、准确率高等特点,有较高的实用价值。A method of road traffic sign detection based on color segmentation and region descriptions is introduced. The method firstly uses color clustering algorithm in RGB space to segment the interested color area, and then conducts an morphological processing, and Finally recognize the traffic sign by using the Hu invariant moments. The results show that： the traffic sign recognition method based on color clustering and Hu invariant moments has a strong robustness to image translation, scaling and rotation, and this method has the features of simply implement, fast recognition and high accuracy, it has high practical value.

关 键 词：交通标志 颜色分割 聚类 HU不变矩 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]