基于激光点云的三维虚拟果园构建方法

doi:10.12133/j.smartag.SA202207002

摘要/Abstract

摘要：

针对果园管理数字化程度低、构建方法较为单一等问题，本研究提出了一种基于激光点云的三维虚拟果园构建方法。首先采用手持式三维点云采集设备（3D-BOX）结合即时定位与地图构建-激光测距与测绘（Simultaneous Localization and Mapping-Lidar Odometry and Mapping，SLAM-LOAM）算法获取果园点云数据集；然后通过统计滤波算法完成点云数据离群点与噪声点的去除，并结合布料模拟算法（Cloth Simulation Filtering，CSF）与DBSCAN（Density-Based Spatial Clustering of Applications with Noise）聚类算法，实现地面去除与果树聚类分割，进而使用VoxelGrid滤波器降采样；最后利用Unity3D引擎，构建虚拟果园漫游场景，将作业机械的实时GPS（Global Positioning System）数据从WGS-84坐标系转换为高斯投影平面坐标系，并通过LineRenderer显示实时轨迹，实现作业机械运动轨迹控制与作业轨迹的可视化展示。为验证虚拟果园构建方法的有效性，在海棠果园与芒果园开展果园构建方法测试。结果表明，所提出的点云数据处理方法对海棠果树与芒果树聚类分割的准确率分别达到了95.3%与98.2%；通过与实际芒果园的果树行距、株距对比，虚拟芒果园的平均行间误差约为3.5%，平均株间误差约为6.6%。并且将Unity3D构建出的虚拟果园与实际果园相比，该方法能够有效复现果园三维实际情况，得到了较好的可视化效果，为果园的数字化建模与管理提供了一种技术方案。

关键词: 虚拟果园, 点云处理, Unity3D, 轨迹可视化, 激光雷达, SLAM-LOAM

Abstract:

To solve the problems of low level of digitalization of orchard management and relatively single construction method, a three-dimensional virtual orchard construction method based on laser point cloud was proposed in this research. First, the hand-held 3D point cloud acquistion equipment (3D-BOX) combined with the lidar odometry and mapping (SLAM-LOAM) algorithm was used to complete the acquisition of the point cloud data set of orchard; then the outliers and noise points of the point cloud data were removed by using the statistical filtering algorithm, which was based on the K-neighbor distance statistical method. To achieve this, a distance threshold model for removing noise points was established. When a discrete point exceeded, it would be marked as an outlier, and the point was separated from the point cloud dataset to achieve the effect of discrete point filtering. The VoxelGrid filter was used for down sampling, the cloth simulation filtering (CSF) cloth simulation algorithm was used to calculate the distance between the cloth grid points and the corresponding laser point cloud, and the distinction between ground points and non-ground points was achieved by dividing the distance threshold, and when combined with the density-based spatial clustering of applications with noise (DBSCAN) clustering algorithm, ground removal and cluster segmentation of orchard were realized; finally, the Unity3D engine was used to build a virtual orchard roaming scene, and convert the real-time GPS data of the operating equipment from the WGS-84 coordinate system to the Gauss projection plane coordinate system through Gaussian projection forward calculation. The real-time trajectory of the equipment was displayed through the LineRenderer, which realized the visual display of the motion trajectory control and operation trajectory of the working machine. In order to verify the effectiveness of the virtual orchard construction method, the test of orchard construction method was carried out in the Begonia fruit and the mango orchard. The results showed that the proposed point cloud data processing method could achieve the accuracy of cluster segmentation of Begonia fruit trees and mango trees 95.3% and 98.2%, respectively. Compared with the row spacing and plant spacing of fruit trees in the actual mango orchard, the average inter-row error of the virtual mango orchard was about 3.5%, and the average inter-plant error was about 6.6%. And compared the virtual orchard constructed by Unity3D with the actual orchard, the proposed method can effectively reproduce the actual three-dimensional situation of the orchard, and obtain a better visualization effect, which provides a technical solution for the digital modeling and management of the orchard.

Key words: virtual orchards, point cloud processing, Unity3D, trajectory visualization, LiDAR, SLAM-LOAM

中图分类号:

冯涵, 张浩, 王梓, 江世界, 刘伟洪, 周凌卉, 王亚雄, 康峰, 刘星星, 郑永军. 基于激光点云的三维虚拟果园构建方法[J]. 智慧农业(中英文), 2022, 4(3): 12-23.

FENG Han, ZHANG Hao, WANG Zi, JIANG Shijie, LIU Weihong, ZHOU Linghui, WANG Yaxiong, KANG Feng, LIU Xingxing, ZHENG Yongjun. Three-Dimensional Virtual Orchard Construction Method Based on Laser Point Cloud[J]. Smart Agriculture, 2022, 4(3): 12-23.

图/表 16

图1

图2

图3

图4

图5

图6

图7

图8

表1

图9

图10

图11

图12

图13

表2

图14

参考文献 22

1	郑永军, 陈炳太, 吕昊暾, 等. 中国果园植保机械化技术与装备研究进展[J]. 农业工程学报, 2020, 36(20): 110-124.
	ZHENG Y, CHEN B, LYU H, et al. Research progress of orchard plant protection mechanization technology and equipment in China[J]. Transactions of the CSAE, 2020, 36(20): 110-124.
2	NI Z, BURKS T F. Three-dimensional dense reconstruction of plant or tree canopy based on stereo vision[J]. Agricultural Engineering International: CIGR Journal, 2018, 20(2): 248-262.
3	BERVEGLIERI A, TOMMASELLI A, LIANG X, et al. Vertical optical scanning with panoramic vision for tree trunk reconstruction[J]. Sensors, 2017, 17(12): ID 2791.
4	郑立华, 麦春艳, 廖崴, 等. 基于Kinect相机的苹果树三维点云配准[J]. 农业机械学报, 2016, 47(5): 9-14.
	ZHENG L, MAI C, LIAO W, et al. 3D point cloud registration of apple trees based on Kinect camera[J]. Transactions of the CSAM, 2016, 47(5): 9-14.
5	BERVEGLIERI A, TOMMASELLI A, LIANG X, et al. Vertical optical scanning with panoramic vision for tree trunk reconstruction[J]. Sensors, 2017, 17(12): ID 2791.
6	NEWCOMBE R A, FITZGIBBON A, IZADI S, et al. KinectFusion: Real-time dense surface mapping and tracking[C]// 10th IEEE International Symposium on Mixed and Augmented Reality. Piscataway, New York, USA: IEEE, 2011:127-136.
7	罗秋, 李国柱, 杨勇, 等. 地面三维激光扫描技术在文物三维重建中的应用——以金殿为例[J]. 城市勘测, 2020(3): 112-116.
	LUO Q, LI G, YANG Y, et al. Application of ground 3D laser scanning technology in the 3D reconstruction of cultural relics: A case study of the Golden Temple[J]. Urban Survey 2020(3): 112-116.
8	杨俊, 王志鹏, 祝凯, 等. 激光扫描与无人机一体化控制下的复杂体育场馆高精度三维重建[J]. 测绘通报, 2020(12): 21-26.
	YANG J, WANG Z, ZHU K, et al. High-precision three-dimensional reconstruction of complex sports venues under the integrated control of laser scanning and unmanned aerial vehicles[J]. Bulletin of Surveying and Mapping, 2020(12): 21-26.
9	王国利, 李群, 杨学博, 等. 基于机载激光雷达点云的森林场景建模[J]. 北京建筑大学学报, 2021, 37(2): 39-46.
	WANG G, LI Q, YANG X, et al. Modeling of forest scene based on airborne lidar point cloud[J]. Journal of Beijing University of Civil Engineering and Architecture, 2021, 37(2): 39-46.
10	WANG K, ZHOU J, ZHANG W H, et al. Mobile LiDAR scanning system combined with canopy morphology extracting methods for tree crown parameters evaluation in orchards[J]. Sensors, 2021,21(2): ID 33419182.
11	HU C, PAN S, ZHANG H, et al. Trunk model establishment and parameter estimation for a single tree using multistation terrestrial laser scanning[J]. IEEE Access, 2020, 8: 102263-102277.
12	INDIRABAI I, NAIR M V H, JAISHANKER R N, et al. Terrestrial laser scanner based 3D reconstruction of trees and retrieval of leaf area index in a forest environment[J]. Ecological Informatics, 2019, 53: ID 100986.
13	翟晓晓, 邵杰, 张吴明, 等. 基于移动LiDAR点云的树木三维重建[J]. 中国农业信息, 2019, 31(5): 84-89.
	ZHAI X, SHAO J, ZHANG W, et al. 3D reconstruction of trees based on mobile LiDAR point clouds[J]. China Agriculture Information 2019, 31(5): 84-89.
14	ZHENG L, FU Z. BALM: Bundle adjustment for LiDAR mapping[J/OL]. arXiv 2020: 8.
15	ZHANG J, SINGH S. LOAM: Lidar odometry and mapping in real-time. in robotics[C]// Robotics: Science and Systems Conference(RSS). New York City, USA: RSS, 2014.
16	RUSU R B, MARTON Z C, BLODOW N, et al. Towards 3D point cloud based object maps for household environments[J]. Robotics And Autonomous Systems, 2008, 56(11): 927-941.
17	罗方燕. PCL库点云统计去噪算法的应用研究[J]. 现代计算机(专业版), 2016(26): 63-66.
	LUO F. Application of statistical denoising algorithm of PCL library point cloud[J]. Modern Computer (Professional Edition), 2016(26): 63-66.
18	ZHANG W, QI J, WAN P, et al. An easy-to-use airborne LiDAR data filtering method based on cloth simulation[J]. Remote Sensing, 2016, 8(6): ID 501.
19	PROVOT X.Deformation constraints in a mass－spring model to describe rigid cloth behaviour[C]//Graphics interface. Mississauga, Canada: Canadian Information Processing Society, 1995: 147.
20	肖冰. 激光和多波束点云水陆地形数据整合研究[D]. 泰安: 山东农业大学, 2018.
	XIAO B. Research on the integration of land and water terrain data of laser and multi-beam point cloud[D]. Taian: Shandong Agricultural University, 2018.
21	ESTER M, KRIEGEL HP, SANDER J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise[C]// 2nd International Conference on Knowledge Discovery and Data Mining. Broadway, New York, USA: ACM Digital Library, 1996: 226-231.
22	胡凡成. 基于Unity 3D的实时数据驱动数字化车间研究[D]. 长沙: 湖南大学, 2018.
	HU F. Real-time data-driven digital shop floor research based on Unity 3D[D]. Changsha: Hunan University, 2018.

果园种类	实际树木数量/棵	分割得到树木数量/棵	正确分割树木数量/棵	正检率/%	准确率/%
芒果果园	43	43	41	100	95.3
海棠果园	57	56	56	98.2	98.2

点云数据	点云处理过程	预处理后点云	统计滤波	CSF布料滤波	降采样
海棠果园	点云数量/个	4,746,821	4,113,008	2,316,788	670,076
海棠果园	运行时间/s	约5	22.4	1.2	0.5
芒果园	点云数量/个	4,303,845	3,548,440	2,216,632	855,130
芒果园	运行时间/s	约5	20.9	1.1	0.5

[1]	李嘉位, 马为红, 李奇峰, 薛向龙, WANG Zhiquan. 复杂环境下肉牛三维点云重建与目标提取方法[J]. 智慧农业(中英文), 2022, 4(2): 64-76.
[2]	张建, 谢田晋, 杨万能, 周广生. 近地遥感技术在大田作物株高测量中的研究现状与展望[J]. 智慧农业(中英文), 2021, 3(1): 1-15.