摘要
为研究农田作业机器人视觉导航信息的提取方法,以自然环境下采集的曲线特征较为明显的农田图像为研究背景,根据图像RGB颜色特征,利用颜色聚类算法,将导航路径从复杂的背景中提取出来.并对得到的二值图像进行形态学处理以消除噪声,然后对图像逐行扫描检测出导航路径的中心离散点,利用最小二乘法拟合出导航路径,并提出一种新的导航参数的获取方法.试验结果表明:该算法具有速度快、精确度高的优点;在作业环境具有较强的曲线特征等情况下有较好的检测效果.
Natural colorful field images are analyzed in RGB vector space to for agricultural robots. The navigation path is successfully recognized from th study the feasibility of lane detection e background. Perceptual color clustering and morphological image processing are used in preprocessing to obtain binary images and remove noise respectively. The guidance points are found from the average position information of the navigation path by progressive scanning. The best guidance lane is located using least - squares curve - fitting which is then used to guide the robot. The experimental results show this algorithm has high speed and remarkable precision. The better detecting performance is obtained especially in robot working environment that has curve features.
出处
《昆明理工大学学报（理工版）》
2008年第4期91-96,共6页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
2008年昆明理工大学研究生课外学术科技创新基金(项目编号:YCC0777)
关键词
视觉导航
RGB颜色空间
导航参数
农业机器人
vision navigation
RGB vector space
navigation parameter
agricultural robot
