基于图像玉米茎秆位置标记方法的研究

Study on Image-based Maize Stalk Position Labeling Method

为实现田间作业过程中对玉米茎秆的定位,提出了一种基于图像玉米茎秆位置的标记方法。以3~5叶期的玉米秧苗为观测对象,利用相机获取玉米秧苗的彩色图像。首先,根据玉米图像样本进行灰度化、加权滤波、直方图均衡进行预处理;对图像进行Ostu阈值分割,提取玉米秧苗区域信息;通过形态学处理去除噪点,得到最大连通域作为玉米秧苗区域。然后通过投影法,对该区域进行列向和横向向量求和,得到的最大值标记为玉米茎秆根部近似位置。对100株玉米秧苗图像进行测试,与图像手动标注位置进行对比,横向误差平均值为7.55,标准差平均值为1.04%,列向误差平均值10.85,标准差平均值为2.26%,实际误差平均值为12.33。该研究可为需要保护玉米秧苗的田间作业提供参考。

In order to locate maize stalks in field operations,an image-based maize stalk location labeling method was proposed.The camera was used to obtain the color images of corn seedlings at the 3~5 leaf stage.Firstly,the gray-scale,weighted filtering and histogram equalization of maize image samples were preprocessed.The image was segmented by Ostu threshold to extract seedling region information.The noise was removed by morphological processing,and the maximum connected domain was obtained as the maize seedling region.Then,through the projection method,the sum of column direction and transverse vector of this region is carried out,and the maximum value obtained is marked as the approximate position of the root of the corn stem.The images of 100 maize seedlings were tested and compared with manually marked positions in the images.The mean value of transverse error was 7.55,the mean value of standard deviation was 1.04%,the mean value of column error was 10.85,the mean value of standard deviation was 2.26%,and the mean value of actual error was 12.33.This study can provide reference for the field operation that needs to protect maize seedlings.