基于图像边界提取的果园作业机器人自主导航系统

发布时间：2018-05-13 08:14

本文选题：果园机器人 + 自主导航　；参考：《农机化研究》2017年08期

【摘要】：针对果园中农业移动机器人的自主导航问题,提出了一种基于图像边界提取的自主导航系统。首先,通过摄像机采集果园场景图像,并利用均值偏移算法对图像中的像素点进行聚类;然后,采用基于图论的图像分割算法,根据预定义类别对图像进行分割;接着,提取出所需类的图像区域,并利用Canny算子对该区域图像的边缘进行检测和滤波;最后,利用Hough变换提取出该区域的边界线,从而获得机器人的行进路线。实验结果表明:该方案在不需要先验知识的情况下,能够快速、有效地获得最优路径。
[Abstract]:In order to solve the problem of autonomous navigation for agricultural mobile robots in orchards, an autonomous navigation system based on image boundary extraction is proposed. Firstly, the Orchard scene image is collected by the camera, and the pixel points in the image are clustered by the mean shift algorithm. Then, the image segmentation algorithm based on graph theory is used to segment the image according to the predefined category. The image region of the required class is extracted, and the edge of the region is detected and filtered by using Canny operator. Finally, the boundary line of the region is extracted by using Hough transform, and the moving path of the robot is obtained. The experimental results show that the proposed scheme can obtain the optimal path quickly and effectively without prior knowledge.
【作者单位】：四川工程职业技术学院电气信息工程系;电子科技大学计算机科学与工程学院;
【基金】：四川省科技厅计划项目(2015JY0178)
【分类号】：S24;TP391.41

【相似文献】