水稻插秧机视觉导航信息获取试验  

Experiment on Acquisition of Navigation Information of Unmanned Rice Transplanter Based on Machine Vision

作　　者：迟德霞[1,2] 任文涛[2] 由佳翰 李萍[1,2] 

机构地区：[1]辽宁石油化工大学矿业工程学院,辽宁抚顺113001 [2]沈阳农业大学工程学院,沈阳110161

出　　处：《沈阳农业大学学报》2015年第5期575-580,共6页Journal of Shenyang Agricultural University

基　　金：沈阳市科技攻关项目(F13-098-3-00)

摘　　要：针对水稻插秧机视觉导航信息获取问题,提出了一种结合霍夫变换的坐标变换法将图像中位姿信息转换到世界坐标系中的导航信息获取方法。首先分析水稻秧苗基准线特征点在图像平面上的像素坐标与在世界坐标系中的映射关系,应用小孔成像模型和霍夫变换理论,建立水稻秧苗基准线在图像坐标系中的位姿与在世界坐标系中相对水稻插秧机的位姿间的关系模型。然后利用霍夫变换提取图像中水稻秧苗行位姿信息,通过坐标变换,转换成世界坐标系中的导航信息,获取世界坐标系中水稻插秧机位姿信息。采用人工铺设标志线模拟水稻秧苗,进行导航参数提取试验,对比算法提取和人工实测的导航参数来评价算法精度。结果表明:实测角度偏差(θw)和计算角度得偏差的误差均值为4.76°,方差为5.07°;实测位置偏差(λw)和计算得位置偏差误差均值为4.95mm,方差为5.42mm,说明该算法获取的导航信息有效。For getting the navigation parameter of the unmanned rice tranplanter based on machine vision, an algorithm converting the navigation parameters of the image coordinate into navigation parameters of the World Coordinate System with the Coordinates Transformation combined with the Hough Transformation was proposed. The mapping relation of the feature points of the rice seedlings in image coordinates and world coordinates was analyzed. The pose relation model of the rice seedlings directrix in image coordinates and world coordinates was constructed with the pin-hole camera model and the Hough Transformation.The navigation parameters in the images coordinate were acquired with Hough Transformation, and converted into World Coordinate System with coordinate transformation to get the navigation parameters in the World Coordinate System. The artificial lane was paved to imitate the rice seedlings, and the navigation information acquisition experiment was carried out. The navigation detected manually was compared with those acquired with the algorithm to evaluate the accuracy. The result showed the mean error of the heading angle 4.76°, the variance of the heading angle 5.07°, the mean error of the position offset4.95 mm, the variance of the position offset 5.42 mm. The algorithm was effective to acquire the navigation information.

关 键 词：水稻插秧机 视觉导航 导航信息 坐标变换 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]