基于机器视觉的果树行中心线检测算法研究

Algorithms of Machine Vision-based Centerline Detection of Fruit Tree Rows

针对果树空间层次复杂造成直线检测算法失效的问题,提出了运用图像透视原理筛选边界点的方法来提取果树行边界。使用最小二乘法拟合边界直线,计算相邻果树行的中心线作为移动机器人的导航路径。试验结果表明,该算法能够快速准确地提取出果树行中心线,平均每幅图像处理时间小于600ms。

A vision-based algorithm to detect the centerline of fruit tree rows was put forward in this paper. As the com- plicated layers of trees often cause line detection algorithm＇ s failure, a method according to the principle of image per- spective was proposed to select road boundary points. Then the least square was adopted to fit these points and the fitted boundary lines were used to calculate the centerline out. The experimental results showed that the algorithm can effectively extract the centerline of fruit tree rows and it took no more than 600 ms for image processing on average.