利用多时序激光点云数据提取棉花表型参数方法

doi:10.12133/j.smartag.2021.3.1.202102-SA003

Smart Agriculture ›› 2021, Vol. 3 ›› Issue (1): 51-62.doi: 10.12133/j.smartag.2021.3.1.202102-SA003

• 专题--作物表型前沿技术与应用 • 上一篇下一篇

利用多时序激光点云数据提取棉花表型参数方法

阳旭^1,²(), 胡松涛¹, 王应华⁴, 杨万能^3,⁴, 翟瑞芳¹()

^1.华中农业大学信息学院，湖北武汉 430070
^2.深圳市财富趋势科技股份有限公司，湖北武汉 430070
^3.华中农业大学作物遗传改良国家重点实验室，湖北武汉 430070
^4.华中农业大学植物科学技术学院，湖北武汉 430070

收稿日期:2021-02-01 修回日期:2021-02-26 出版日期:2021-03-30
基金资助:
中央高校基本科研业务费资助(2662019PY085);国家自然科学基金面上项目(31770397)
作者简介:阳旭（1993－），男，硕士，工程师，研究方向为数据处理。E-mail：yang_9325@163.com。
通信作者: 翟瑞芳（1979－），女，博士，副教授，研究方向为LiDAR数据处理。电话：027-87288509。E-mail：rfzhai@mail.hzau.edu.cn

Cotton Phenotypic Trait Extraction Using Multi-Temporal Laser Point Clouds

YANG Xu^1,²(), HU Songtao¹, WANG Yinghua⁴, YANG Wanneng^3,⁴, ZHAI Ruifang¹()

^1.College of Informatics, Huazhong Agricultural University, Wuhan 430070, China
^2.Shenzhen Fortune Trend Technology Co. , Ltd. , Wuhan 430070, China
^3.National Key Laboratory of Crop Genetic Improvement, Huazhong Agricultural University, Wuhan 430070, China
^4.College of Plant Science & Technology, Huazhong Agricultural University, Wuhan 430070, China

Received:2021-02-01 Revised:2021-02-26 Online:2021-03-30
corresponding author: ZHAI Ruifang, E-mail：rfzhai@mail.hzau.edu.cn
About author:YANG Xu, E-mail：yang_9325@163.com
Supported by:
Central University Basic Scientific Research Business Expense Grant (2662019PY085);National Natural Science Foundation of China(31770397)

摘要/Abstract

摘要：

当前，能够实现作物表型参数高效、准确的测量和作物生育期表型参数的动态量化研究是表型研究和育种中亟待解决的问题之一。本研究以棉花为研究对象，采用三维激光扫描LiDAR技术获取棉花植株的多时序点云数据，针对棉花植株主干的几何特性，利用随机抽样一致算法（RANSAC）结合直线模型完成主干提取，并对剩余的点云进行区域增长聚类，实现各叶片的分割；在此基础上，完成植株体积、株高、叶长、叶宽等性状参数的估计。针对多时序棉花激光点云数据，采用匈牙利算法完成相邻时序作物点云数据的对齐、叶片器官对应关系的建立。同时，对各植株表型参数动态变化过程进行了量化。本研究针对3株棉花的4个生长点的点云数据，分别完成了主干提取、叶片分割，以及表型参数测量和动态量化。试验结果表明，本研究所采用的主干提取及叶片分割方法能够实现棉花的枝干和叶片分割。提取的株高、叶长、叶宽等表型参数与人工测量值的决定系数均趋近于1.0；同时，本研究实现了棉花表型参数的动态量化过程，为三维表型技术的实现提供了一种有效的方法。

关键词: 棉花表型参数, LiDAR, 主干提取, 叶片分割, 点云数据对齐, 三维表型

Abstract:

To cope with the challenges posed by the rapid growth of world population and global environmental changes, scholars should employ genetic and phenotypic analyses to breed crop varieties with improved responses to limited resource environments and soil conditions to increase crop yield and quality. Therefore, the efficient, accurate, and non-destructive measurement of crop phenotypic traits, and the dynamic quantification of phenotypic traits are urgently needed for crop phenotypic research, and breeding as well as for modern agricultural development. In this study, cotton plants were taken as research objects, and the multi-temporal point cloud data of cotton plants were collected by using three-dimensional laser scanning technology. The multi-temporal point clouds of three cotton plants at four time points were collected. First, RANSAC algorithm was implemented for main stem extraction on the original point cloud data of cotton plants, then region growing based clustering was carried out for leaf segmentation. Plant height was estimated by calculating the end points of the segmented main stem. Leaf length and width measurements were conducted on the segmented leaf parts. In addition, the volume was also estimated through the convex hull of the original point cloud of plant cotton. Then, multi-temporal point clouds of plants were registered, and organ correspondence was constructed with the Hungarian method. Finally, dynamic quantification of phenotypic traits including plant volume, plant height, leaf length, leaf width, and leaf area were calculated and analyzed. The overall performance of the approaches achieved a matching rate through a series of experiments, and the traits extracted by using of point cloud showed high correlation with the manually measured ones. The relative error between plant height and manual measurement results did not exceed 1.0%. The estimated leaf length and width on point clouds were highly correlated with the manually measured ones, and the coefficient of determination was nearly 1.0. The proposed 3D phenotyping methodology can be introduced and used to other crops for phenotyping.

Key words: cotton phenotypic traits, LiDAR, stem extraction, leaf segmentation, point cloud registration, 3D phenotyping

中图分类号:

TP391.4

阳旭, 胡松涛, 王应华, 杨万能, 翟瑞芳. 利用多时序激光点云数据提取棉花表型参数方法[J]. 智慧农业(中英文), 2021, 3(1): 51-62.

YANG Xu, HU Songtao, WANG Yinghua, YANG Wanneng, ZHAI Ruifang. Cotton Phenotypic Trait Extraction Using Multi-Temporal Laser Point Clouds[J]. Smart Agriculture, 2021, 3(1): 51-62.

参考文献

1	BRIGLIA N, WILLIAMS K, WU D, et al. Image-based assessment of drought response in grapevines[J]. Frontiers in Plant Science, 2020, 11: 595.
2	ROSE J C, PAULUS S, KUHLMANN H. Accuracy analysis of a multi-view stereo approach for phenotyping of tomato plants at the organ level[J]. Sensors, 2015, 15: 9651-9665.
3	GUAN H, LIU M, MA X, et al. Three-dimensional reconstruction of soybean canopies using multisource imaging for phenotyping analysis[J]. Remote Sensing, 2018, 10(8): ID 1206.
4	WANG Y, WEN W, WU S, et al. Maize plant phenotyping: Comparing 3D laser scanning, multi-view stereo reconstruction, and 3D digitizing estimates[J]. Remote Sensing, 2018, 11(1): ID 63.
5	MASUDA T. 3D shape reconstruction of plant roots in a cylindrical tank from multiview images[C]// 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Piscataway, New York, USA: IEEE, 2019: 2149-2157.
6	NGUYEN T, SLAUGHTER D, MAX N, et al. Structured light-based 3D reconstruction system for plants[J]. Sensors, 2015, 15(8). 18587-18612.
7	NI X, LI C, JIANG H, et al. Three-dimensional photogrammetry with deep learning instance segmentation to extract berry fruit harvestability traits[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2021, 171: 297-309.
8	JIANG Y, LI C, TAKEDA F, et al. 3D point cloud data to quantitatively characterize size and shape of shrub crops[J]. Horticulture Research, 2019, 6(1): 43-59.
9	JIN S, SU Y, WU F, et al. Stem-leaf segmentation and phenotypic trait extraction of individual maize using terrestrial LiDAR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2018, 57(3): 1336-1346.
10	SUN S, LI C, CHEE P W, et al. Three-dimensional photogrammetric mapping of cotton bolls in situ based on point cloud segmentation and clustering[J]. Journal of Photogrammetry and Remote Sensing, 2020, 160: 195-207.
11	刘守阳, 金时超, 郭庆华, 等. 基于数字化植物表型平台(D3P)的田间小麦冠层光截获算法开发[J]. 智慧农业(中英文), 2020, 2(1): 87-98.
11	LIU S, JIN S, GUO Q, et al. An algorithm for estimating field wheat canopy light interception based on digital plant phenotyping platform[J]. Smart Agriculture, 2020, 2(1): 87-98.
12	马福峰, 耿楠, 张志毅. 基于邻域几何特征约束的植株三维形态配准方法研究[J]. 计算机应用与软件, 2016, 33(9): 184-189.
12	MA F, GENG N, ZHANG Z. On 3D plant morphology registration method based on geometrical feature constraint of neighborhood[J]. Computer Applications and Software, 2016, 33(9): 184-189.
13	CHAUDHURY A B M, BARRON J L. Junction-based correspondence estimation of plant point cloud data using subgraph matching[J]. IEEE Geoscience & Remote Sensing Letters, 2016, 13(8): 1119-1123.
14	YANG L, ZHAI R, YANG X, et al. Segmentation of plant organs point clouds through super voxel-based region growing methodology[J]. Computer Engineering and Applications, 2019, 55(16): 197-203..
15	LI D, CAO Y, TANG X, et al. Leaf segmentation on dense plant point clouds with facet region growing[J]. Sensors, 2018, 18(11): ID 3625.
16	GELARD W, DEVY M, HERBULOT A, et al. Model-based segmentation of 3D point clouds for phenotyping sunflower plants[C]// 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications Porto. Portugal, 2017: ID hal-02733980.
17	梁秀英, 周风燃, 陈欢, 等. 基于运动恢复结构的玉米植株三维重建与性状提取[J]. 农业机械学报, 2020, 51(6): 209-219.
17	LIANG X, ZHOU F, CHEN H, et al. Three-dimensional maize plants reconstruction and traits extraction based on structure from motion[J].Transactions of the CSAM, 2020, 51(6): 209-219.
18	WAHABZADA M, PAULUS S, KERSTING K, et al. Automated interpretation of 3D laserscanned point clouds for plant organ segmentation[J]. BMC Bioinformatics, 2015, 16(1): ID 248.
19	喻垚慎, 云挺, 杨绪兵. 基于激光点云数据的植物器官多维特征分割方法[J]. 数据采集与处理, 2015, 30(5): 1054-1061.
19	YU Y, YUN T, YANG X. Multi dimension feature segmentation method of foliage organs based on laser point cloud data[J]. 2015, 30(5): 1054-1061.
20	SU Y, WU F, AO Z, et al. Evaluating maize phenotype dynamics under drought stress using terrestrial LiDAR[J]. Plant Methods, 2019, 15(1): ID 11.
21	CHAUDHURY AYAN, WARD CHRISTOPHER, TALASAZ ALI. Machine vision system for 3D plant phenotyping[J]. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019, 16(6): 2009-2022.
22	SUN S, LI C, PATERSON A H, et al. In-field high throughput phenotyping and cotton plant growth analysis using LiDAR[J]. Frontiers in Plant Science, 2018, 9: 1-17.
23	AN N, WELCH S, MARKELZ R, et al. Quantifying time-series of leaf morphology using 2D and 3D photogrammetry methods for high-throughput plant phenotyping[J]. Computers & Electronics in Agriculture, 2017, 135: 222-232.
24	阳旭. 基于多时相点云数据的作物表型参数获取及动态量化方法研究[D]. 湖北: 华中农业大学, 2019.
24	YANG X. Research on crop phenotypic parameters acquisition and dynamic quantification method based on multi-temporal point cloud data[D]. Hubei: Huazhong Agricultural University, 2019.
25	RUSU R B, HOLZBACH A, BLODOW N, et al. Fast geometric point labeling using conditional random fields[C]// 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, New York, USA: IEEE, 2009: 7-12.
26	史蒲娟, 翟瑞芳, 常婷婷, 等. 基于单目视觉和激光扫描技术的油菜植株模型重建及株型参数测量[J]. 华中农业大学学报, 2017, 36(3): 63-68.

[1]	胡松涛, 翟瑞芳, 王应华, 刘志, 朱剑忠, 任荷, 杨万能, 宋鹏. 基于多源数据的马铃薯植株表型参数提取[J]. 智慧农业(中英文), 2023, 5(1): 132-145.
[2]	刘理民, 何雄奎, 刘伟洪, 刘紫嫣, 韩虎, 李扬帆. 果园自主导航兼自动对靶喷雾机器人[J]. 智慧农业(中英文), 2022, 4(3): 63-74.
[3]	范道全, 张美娜, 潘健, 吕晓兰. 基于靶标叶面积密度参数的变量喷雾控制系统开发与性能试验[J]. 智慧农业(中英文), 2021, 3(3): 60-69.
[4]	刘守阳, 金时超, 郭庆华, 朱艳, Baret Fred. 基于数字化植物表型平台（D3P）的田间小麦冠层光截获算法开发[J]. 智慧农业(中英文), 2020, 2(1): 87-98.

利用多时序激光点云数据提取棉花表型参数方法

Cotton Phenotypic Trait Extraction Using Multi-Temporal Laser Point Clouds

在线阅读

知网下载

本地下载

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价