摘要
针对基于彩色视觉导航的自动引导车的工作特点,对地面上预先铺设的彩色条带状路标图像信息进行了快速提取研究,提出了一种颜色分量近似的滤波方法。该方法简单、快速,减少了路标图像处理的计算量,提高了路标提取的实时性和鲁棒性。经在QDU-I型自动引导车上实际应用表明,该方法可以解决图像处理计算量大而影响自动引导车决策系统的实时性问题。
According to the working characteristics of an AGV based on color vision and the equality among the values of R, G and B of the gray scale, a new, simple and quick filtering approach was introduced to recognize the navigation landmark. This approach not only decreased the calculation load of the image processing but also made the navigation system more robust. It has a quick processing speed. The results of the practical application on the QDU-I AGV have demonstrated the efficiency of this approach.
出处
《农业机械学报》
EI
CAS
CSCD
北大核心
2006年第4期87-90,共4页
Transactions of the Chinese Society for Agricultural Machinery
基金
山东省教育厅资助项目(项目编号:J00g54)
青岛市科技局工业攻关项目(项目编号:03-2-GG-23)
关键词
自动引导车
彩色视觉
导航
颜色识别
Automated guided vehicle, Color vision, Navigation, Color recognition