农林环境机器视觉导航路径生成算法及应用

Algorithms of Path Guidance Line Based on Computer Vision and Their Applications in Agriculture and Forestry Environment

提出两种自然环境中的路径导航线生成算法:对于矮小作物规则分布的农田场景,在标准Hough变换的基础上,预先检测共线点峰值的限定偏角阈值,以迅速检测关键信息;对于林地环境及类林地环境的高大作物农田场景,寻找树干与地面的交点,形成机器人行走的左右边界,再求两边交点的中值产生一列点簇。对该列点簇进行Hough变换检测直线作为导航线,或应用最小二乘法拟合左右边界,求其中线作为路径导航线。Matlab对比仿真表明,几种算法对各自适用的场景具有可靠稳定的路径辨识能力,可对图像进行有效的批量处理。

Two advanced algorithms of generating path guidance line are proposed： the Hough transform-based is to pre-limit the angular value of possible collinear points before peak detection.This enables swift key-info abstraction in orderly-planted fields while offsetting imperfections brought by previous image segmentation,the solution to generate guidance line in forestry environments and locate points of trunk-and-earth intersection,then a dot array in the middle of the two point series is obtained.Then two methods are applied to process the dot array： either to detect a line for guidance using Hough transform or to least-square fit the two point series,so a line through the center is acquired to be the guidance path.Simulations and comparisons through Matlab show that the two algorithms are able to robustly recognize paths in their respective fit scenes and effectively process images in batches.