|Table of Contents|

A Weed Identification Method in Vegetable Greenhouses Based on Three-dimensional Point Cloud

《北方园艺》[ISSN:1001-0009/CN:23-1247/S]

Issue:
2021年02
Page:
153-158
Research Field:
Publishing date:

Info

Title:
A Weed Identification Method in Vegetable Greenhouses Based on Three-dimensional Point Cloud
Author(s):
XU Tao1; CHEN Yong1; ZHOU Weipeng2
(1.College of Mechanical and Electrical Engineering,Nanjing Forestry University,Nanjing,Jiangsu 210037;2.Zhenjiang Agricultural Science and Technology Limited Company,Zhenjiang,Jiangsu 212000)
Keywords:
vegetable greenhouse; three-dimensional point cloud; voxel filtering; Euclidean clustering; weed identification
PACS:
-
DOI:
10.11937/bfyy.20202654
Abstract:
In order to realize the purpose of automatic weeding in vegetable greenhouses,a new method for weed identification in vegetable greenhouses based on three-dimensional point cloud is proposed for the weed identification.This method used the RGB-D camera to obtain three-dimensional point cloud images of green vegetable fields and lettuce fields.We used the improved super green algorithm to remove backgrounds such as soilinit,voxel filtering method was used to reduce the number of point clouds while retaining the shape characteristics of the point cloud image,then we used the European clustering method to segment the point cloud clusters of a single vegetable and a single weed in the pre-processed point cloud image,and the Z coordinate values of their highest points were calculated.Finally,the Z coordinate value of depth information was combined to realize the vegetable greenhouse weed identify.The results showed that the weed recognition method based on three-dimensional point cloud could effectively identify weed,and the recognition rate was 86.48%.The method could accurately identify weed in the vegetable greenhouse,and provide an effective solution for the automatic weeding of the vegetable greenhouse.

References:

[1]姜威.基于Raspberry Pi的蔬菜大棚智能控制系统设计与实现[D].桂林:广西师范大学,2018.[2]王生生,王顺,张航,等.基于轻量和积网络及无人机遥感图像的大豆田杂草识别[J].农业工程学报,2019,35(6):81-89.[3]颜秉忠.机器视觉技术在玉米苗期杂草识别中的应用[J].农机化研究,2018,40(3):212-216.[4]王海华,朱梦婷,李莉,等.基于剪切波变换和无人机麦田图像的区域杂草识别方法[J].农业工程学报,2017,33(S1):99-106.[5]祖琴,张水发,曹阳,等.结合光谱图像技术和SAM分类法的甘蓝中杂草识别研究[J].光谱学与光谱分析,2015,35(2):479-485.[6]JAVIER A.An instance-based learning approach for thresholding in crop images under different outdoor conditions[J].Computers and Electronics in Agriculture,2016,127:669-679.[7]DIAN B,BAH E,DERICQUEBOUEBOURG H,et al.Deep learning based classification system for identifying weeds using high-resolution UAV imagery[J].Intelligent Computing,2018,44(1):176-187.[8]乔永亮,何东健,赵川源,等.基于多光谱图像和SVM的玉米田间杂草识别[J].农机化研究,2013(8):30-34.[9]李秋洁,郑加强,周宏平,等.基于变尺度格网索引与机器学习的行道树靶标点云识别[J].农业机械学报,2018,49(6):32-37.[10]徐胜勇,卢昆等.基于RGB-D相机的油菜分枝三维重构与角果识别定位[J].农业机械学报,2019,50(2):21-27.[11]杨斯,高万林,米家奇,等.基于RGB-D相机的蔬菜苗群体株高测量方法[J].农业机械学报,2019,50(S1):128-135.[12]仇瑞承,苗艳龙,季宇寒,等.基于RGB-D相机的单株玉米株高测量方法[J].农业机械学报,2017,48(S1):211-219.[13]XIONG X,YU L J,YANG W N,et al.A high-throughput stereo-imaging system for quantify rape leaf traits during the seeding stage[J].Plant Methods,2017,131:7.

Memo

Memo:
-
Last Update: 2021-05-27