基于点云配准的盆栽金桔果实识别与计数方法

被引：10

作者：

朱启兵

张梦

刘振方

黄敏

李学成

机构：

[1] 江南大学轻工过程先进控制教育部重点实验室

来源：

农业机械学报 | 2022年 / 05期

关键词：

盆栽金桔; 果实识别; 点云配准; 点云分割; RGB-D相机;

D O I：

暂无

中图分类号：

TP391.41 []; S666.9 [其他];

学科分类号：

080203 ; 090201 ;

摘要：

为解决整株盆栽金桔果实识别及总体计数问题，提出了基于三维点云配准的金桔果实识别方法。首先，使用RGB-D相机采集植物多角度点云数据并进行背景去除和去噪处理。然后采用随机采样一致性(Random sample consensus, RANSAC)算法进行圆柱拟合获得旋转中心轴参数，将点云绕中心轴旋转固定角度完成初配准，之后采用点到面的迭代最近点(Iterative closest point, ICP)算法完成精配准得到完整点云。最后，对点云进行欧氏聚类分割，采用随机采样一致性算法对聚类后点云进行球形分割，获得每个果实的三维空间位置并计数。本研究对9株盆栽金桔(共149个果实)进行识别，总计识别查全率为85.91%,查准率为79.01%,F1值为82.32%,果实数量预测值和真实值的决定系数为0.97,平均绝对百分比误差为16.02%。实验结果表明，本文方法不依赖颜色信息，能够有效识别整株植物中未成熟的青色果实，可为果实识别与产量估计等研究提供参考。

引用

页码：209 / 216

页数：8

共 28 条

[11] Intact Detection of Highly Occluded Immature Tomatoes on Plants Using Deep Learning Techniques [J].

Mu, Yue ;

Chen, Tai-Shen ;

Ninomiya, Seishi ;

Guo, Wei .

SENSORS, 2020, 20 (10)

[12] Phenological Characteristics of Potted Kumquat under Protected Culture [J].

Chang, Yung-Chiung ;

Chang, Yu-Sen ;

Chen, Iou-Zen ;

Lin, Lian-Hsiung .

HORTICULTURAL SCIENCE & TECHNOLOGY, 2020, 38 (02) :130-145

[13] Fruit Morphological Measurement Based on Three-Dimensional Reconstruction [J].

Wang, Yawei ;

Chen, Yifei .

AGRONOMY-BASEL, 2020, 10 (04)

[14]

Three-dimensional photogrammetric mapping of cotton bolls in situ based on point cloud segmentation and clustering[J] . Shangpeng Sun,Changying Li,Peng W. Chee,Andrew H. Paterson,Yu Jiang,Rui Xu,Jon S. Robertson,Jeevan Adhikari,Tariq Shehzad.ISPRS Journal of Photogrammetry and Remote Sensing . 2020 (C)

[15] Improved Kiwifruit Detection Using Pre-Trained VGG16 With RGB and NIR Information Fusion [J].

Liu, Zhihao ;

Wu, Jingzhu ;

Fu, Longsheng ;

Majeed, Yaqoob ;

Feng, Yali ;

Li, Rui ;

Cui, Yongjie .

IEEE ACCESS, 2020, 8 :2327-2336

[16]

Using color and 3D geometry features to segment fruit point cloud and improve fruit recognition accuracy[J] . Gang Wu,Bin Li,Qibing Zhu,Min Huang,Ya Guo.Computers and Electronics in Agriculture . 2020 (C)

[17] In-Field Estimation of Orange Number and Size by 3D Laser Scanning [J].

Mendez, Valeriano ;

Perez-Romero, Antonio ;

Sola-Guirado, Ruben ;

Miranda-Fuentes, Antonio ;

Manzano-Agugliaro, Francisco ;

Zapata-Sierra, Antonio ;

Rodriguez-Lizana, Antonio .

AGRONOMY-BASEL, 2019, 9 (12)

[18]

Automatic recognition of juicy peaches on trees based on 3D contour features and colour data[J] . Gang Wu,Qibing Zhu,Min Huang,Ya Guo,Jianwei Qin.Biosystems Engineering . 2019 (C)

[19]

A Detection Method for Apple Fruits Based on Color and Shape Features[J] . Xiaoyang Liu,Dean Zhao,Weikuan Jia,Wei Ji 0001,Yueping Sun.IEEE Access . 2019

[20]

Apple detection algorithm for robotic harvesting using a rgb-d camera .2 Nguyen T T,Vandevoorde K,Kayacan E,et al. International Conference of Agricultural Engineering . 2014

← 1 2 3 →