[1]廖娟,汪鹞,尹俊楠,等.基于双目视觉的作物点云获取与分割定位方法[J].江苏农业学报,2019,(04):847-852.[doi:doi:10.3969/j.issn.1000-4440.2019.04.014]
　LIAO Juan,WANG Yao,YIN Jun nan,et al.Point cloud acquisition, segmentation and location method of crops based on binocular vision[J].,2019,(04):847-852.[doi:doi:10.3969/j.issn.1000-4440.2019.04.014]
点击复制

基于双目视觉的作物点云获取与分割定位方法()
分享到：

江苏农业学报[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2019年04期
页码:
847-852
栏目:
耕作栽培·资源环境
出版日期:
2019-08-31

文章信息/Info

Title:
Point cloud acquisition, segmentation and location method of crops based on binocular vision
作者:
廖娟; 汪鹞; 尹俊楠; 刘路; 张顺; 朱德泉
(安徽农业大学工学院, 安徽合肥230036)
Author(s):
LIAO Juan; WANG Yao; YIN Junnan; LIU Lu; ZHANG Shun; ZHU Dequan
(School of Engineering, Anhui Agricultural University, Hefei 230036, China)
关键词:
双目视觉; ZED相机; 作物定位; 3D点云; 点云分割
Keywords:
binocular vision;  ZED camera; crop location;  3D point cloud;  point cloud segmentation
分类号:
S126
DOI:
doi:10.3969/j.issn.1000-4440.2019.04.014
文献标志码:
A
摘要:
为了提高农业视觉导航系统对作物定位的精确性，提出了一种基于双目视觉的作物点云获取与分割定位方法。该方法采用ZED双目相机采集作物左右视图，通过视差原理获取作物的3D点云数据，利用点云离散程度和体素化网格方法对初始点云数据的离散点和冗余数据进行去除，然后在预处理后的点云图中利用基于点云法线角度差的区域生长分割出每株作物的点云簇，用每个点云簇中所有点的平均坐标值作为该株作物的三维坐标，结合视觉系统坐标系，计算出作物与相机的水平距离以及水平偏角，从而实现作物定位。试验结果表明，该方法测得的作物平均距离误差为189%，平均角度误差为217%，该算法可以对作物进行准确定位，为基于双目视觉导航的路径规划提供可靠的定位信息。
Abstract:
In order to improve the accuracy of crop positioning in agricultural visual navigation systems, a point cloud acquisition and segmentation and location method of crops based on binocular vision was proposed in this study. The left and right view images were taken by a ZED binocular camera, and 3D point cloud data of crops was obtained based on the parallax principle. Then, the outliers and redundant data of the initial point cloud data were removed by the point cloud dispersion degree and voxelization grid method, respectively. After that, region growth segmentation based on point cloud normal angle difference was used to segment crop point cloud clusters, and the average coordinate value of all points in each point cloud cluster was taken as the threedimensional coordinate of this plant. Combined with coordinate system of visual system, the horizontal distance between the crop and the camera and horizontal angle were calculated, which could provide location information on the distance and direction of the crop relative to the machinery. Experimental results showed that the average distance error of crops measured by this method was 189%, and the average angle error was 217%. This algorithm can locate crops accurately and provide reliable location information for the subsequent path planning based on binocular visual navigation.

参考文献/References:

[1]TARANNUM N, RHAMAN MK, KHAN SA, et al. A brief overview and systematic approach for using agricultural robot in developing countries[J]. Journal of Modern Science and Technology, 2015, 3(1): 88-101.
[2]姬长英, 周俊. 农业机械导航技术发展分析[J]. 农业机械学报，2014, 45(9)：44-54.
[3]HAMUDAE, GLAVINM, JONESE. A survey of image processing techniques for plant extraction and segmentation in the field[J]. Computers and Electronics in Agriculture, 2016, 125: 184-199.
[4]宋宇, 刘永博,刘路, 等．基于机器视觉的玉米根茎导航基准线提取方法[J]．农业机械学报, 2017, 48(2): 38-44.
[5]何勇, 蒋浩, 方慧, 等. 车辆智能障碍物检测方法及其农业应用研究进展[J]. 农业工程学报, 2018, 34(9):21-32.
[6]沈晓晨, 李霞, 王维新，等. 基于双目立体视觉的成熟棉花识别定位[J]．江苏农业科学，2017，45(16): 185-188.
[7]韩永华, 汪亚明, 康锋，等. 基于小波多分辨率分解的农田障碍物检测[J]. 农业机械学报, 2013, 44(6)：215-221.
[8]YUN C, KIM H J, JEON C W, et al. Stereovisionbased guidance line detection method for autoguidance system on furrow irrigated Fields[J]. IFACPapers, 2018, 51(17): 157-161.
[9]ZHAI Z, ZHU Z, DU Y, et al. Multicroprow detection algorithm based on binocular vision [J]. Biosystems Engineering, 2016, 150: 89-103.
[10]姬长英，沈子尧，顾宝兴，等. 基于点云图的农业导航中障碍物检测方法[J]. 农业工程学报, 2015, 31(7):173-179.
[11]麦春艳, 郑立华, 孙红, 等. 基于RGBD相机的果树三维重构与果实识别定位[J]. 农业机械学报, 2015,46 (S1): 35-40.
[12]BALL D, UPCROFT B, WYETH G, et al. Visionbased obstacle detection and navigation for an agricultural robot [J]. Journal of Field Robotics, 2016, 33(8): 1107-1130.
[13]翟志强, 杜岳峰, 朱忠祥, 等. 基于 Rank 变换的农田场景三维重建方法[J]. 农业工程学报, 2015, 31(20): 157-164.
[14]夏春华, 施滢, 尹文庆. 基于 TOF 深度传感的植物三维点云数据获取与去噪方法[J]. 农业工程学报, 2018, 34(6):168-174.
[15]郭保青, 余祖俊, 张楠, 等. 铁路场景三维点云分割与分类识别算法[J]. 仪器仪表学报, 2017, 38(9): 2103-2111.
[16]GAVREA B. A mean value theorem for the Chebyshev functional [J]. Mathematical Inequalities and Applications, 2015, 18(2): 751-757.
[17]李仁忠, 杨曼, 刘阳阳, 等. 一种散乱点云的均匀精简算法[J]. 光学学报, 2017, 37(7): 89-97.
[18]ROUHI R, JAFARI M, KASAEI S, et al. Benign and malignant breast tumors classification based on region growing and CNN segmentation[J]. Expert Systems with Applications, 2015, 42(3): 990-1002.
[19]李佳, 段平, 盛业华, 等. KD 树索引策略下紧支撑径向基函数的点云建模[J]. 系统仿真学报, 2016, 28(9): 2154-2158.
[20]GARCASANTILLNI D, GONZALO P. Online crop/weed discrimination through the Mahalanobis distance from images in maize fields[J]. Biosystems Engineering,2018, 166: 28-43.

备注/Memo

备注/Memo:
收稿日期：2018-12-12 基金项目：国家重点研发计划项目(2018YFD0700304);安徽省自然科学基金项目(1708085QF148); 安徽农业大学青年基金项目(2016ZR008) 作者简介：廖娟(1986-)，女,安徽安庆人，讲师，博士，研究方向为机器视觉、农业视觉导航。(E-mail)liaojuan308@163.com 通讯作者：朱德泉，(E-mail) zhudequan@ahau.edu.cn
更新日期/Last Update: 2019-08-31