摘要
提出了一种用于室外移动机器人的道路标志自动统计识别方法。针对我国道路标志图像的基本特征,全面分析转弯道路标志图案后发现:图像的全局特征更易被检测到,而且更不易受到噪声和较小局部失真的影响。提出以全局特征为立足点,采用图像的灰度均值为主要特征量的特征选择与提取方法。在此基础上,分析道路标志图案的分块机理,采用投影和方向特征的处理方法,得到了9个转弯道路标志的特征不变量值。试验结果表明,有噪声的情况下,该方法能够实现对道路标志图案的快速、准确识别,具有较好的抗干扰能力。
A new statistical recognition method of the road signs was proposed. In view of the basic characteristics of the road signs,and through a comprehensive analysis to turn road signs, we found that the image global features are more likely to be detected and not liable to be disturbed by noise and local distortion. An approach to the image feature selection and extraction based on the global feature was presented, in which the mean gray-scale of the image was taken as the major feature value. In what follows, the statistical recognition method was developed to accomplish these steps: the image was divided into several blocks; projective method with directional feature was adopted; the invariant of the feature marks was established and corresponding invariant values of nine turn road signs was computed. The experimental results show that the statistical approach has a good anti-interference ability by which the road sign in an image with moderate noise can be accurately and quickly recognized.
出处
《计算机科学》
CSCD
北大核心
2009年第10期265-267,共3页
Computer Science
基金
教育部科技创新工程重大项目培育项目(708067)
教育部长江学者与创新团队发展计划项目(531105050037)资助
关键词
车辆工程
室外移动机器人
统计识别
道路标志提取
方向投影特征
Vehicle engineering, Outdoor mobile robots, Statistical recognition, Road sign extraction, Directional projective feature