基于机器视觉的玉米行导航线提取方法

Extraction method of navigation line from corn line based on machine vision

提出一种利用玉米行快速、准确地提取农业机械导航线的方法。提取Cg灰度图像,利用最大类间方差法自动分割后,得到二值化图像,结合形态学和八邻域算子去除二值化图像的噪声。针对传统方法提取和分类特征点需要设置距离阈值的不足,利用高斯滤波算子对垂直投影曲线进行平滑处理,利用特征点的位置特征自动提取得到特征点,然后自动归类特征点,并利用稳健回归法线性拟合特征点得到导航线。统计试验表明:该算法处理一幅640×480像素的图片平均耗时108 ms,准确率为92%,具有实时性好、准确率高的特点;同时,算法对于杂草较多的复杂环境具有良好的鲁棒性,可为防治玉米病虫害的农业机械提供视觉导航。

It proposed a method for fast and accurate extraction of agricultural machinery navigation line by using corn lines.First,Cg grayscale images were extracted and binarization images were obtained by using the maximum variance method.The morphology and eight neighborhood operators were used to remove the noise of the binary image.Aiming at the lack of distance thresholds for traditional feature extraction and classification of feature points,used Gaussian filter operator to smooth the vertical projection curve,and the feature points were automatically extracted based on their location,and then the feature points were automatically classified.Finally,the navigation line was obtained by linear fitting of characteristic points with robust regression method.Statistical experiments show that the algorithm takes an average of 108 ms to process a 640-pixel by 480-pixel image,with an accuracy rate of 92%.It has the characteristics of good real-time performance and high accuracy.At the same time,the algorithm is of good robustness for complex environments with more weeds and can provide visual navigation for agricultural machinery to control corn pests and diseases.