针对植物点云具有形状不规则、密度不均匀的特点，提出一种适用于植物的三维点云分割方法。将烟草、玉米、黄瓜这3种植物作为样本数据，以滤波等预处理方法去除离群点与背景点，以欧氏聚类算法分割植物群体，并用区域增长算法、边缘提取算法、超体素聚类算法以及基于凹凸性的方法来分割叶片器官。将所提出的方法用于分割烟草、玉米的三维点云，其覆盖率分别为87.5%、96.9%，从而验证了该方法的可行性与有效性，为自动提取作物叶器官表型研究提供了线索。
Aiming at the irregular shape and uneven density of plant point clouds, a three-dimensional point cloud segmentation method applied to plants is proposed. Three plants of tobacco, corn, and cucumber are used as sample data, in which outliers and background points are removed by filtering and other preprocessing methods. Plant population is segmented by the Euclidean clustering algorithm, and leaf organs are segmented by region growing algorithm, edge extraction algorithm, super voxel clustering algorithm, and segmentation algorithm based on unevenness. The proposed method is used to segment three-dimensional point clouds of tobacco and corn, and the coverage rates are 87.5% and 96.9%, respectively. This verifies the feasibility and effectiveness of the method and provides clues for the automatic extraction of plant leaf organ phenotypes.
[1] Alexandratos N. World food and agriculture to 2030/50, highlights and views from mid-2009[C]//How to Feed the World in 2050 A Technical Meeting of Experts, 2009:24-26.
[2] Houle D, Govindaraju D R, Omholt S. Phenomics:the next challenge[J]. Nature Reviews Genetics, 2010, 11(12):855-866.
[3] Jiang Y, Li C, Paterson A H. High throughput phenotyping of cotton plant height using depth images under field conditions[J]. Computers and Electronics in Agriculture, 2016, 130:57-68.
[4] 毛罕平, 张艳诚, 胡波. 基于模糊C均值聚类的作物病害叶片图像分割方法研究[J]. 农业工程学报, 2008, 24:136-140. Mao H P, Zhang Y C, Hu B. Segmentation of crop disease leaf images using fuzzy C-means clustering algorithm[J]. Journal of Agricultural Engineering, 2008, 24:136-140. (in Chinese)
[5] 李凯, 冯全, 张建华. 棉花苗叶片复杂背景图像的联合分割算法[J]. 计算机辅助设计与图形学学报, 2017, 29(10):1871-1880. Li K, Feng Q, Zhang J H. Co-segmentation algorithm for complex background image of cotton seedling leaves[J]. Journal of Computer-Aided Design & Computer Graphics, 2017, 29(10):1871-1880. (in Chinese)
[6] 孙俊, 宋佳, 武小红, 等. 基于改进Otsu算法的生菜叶片图像分割方法[J]. 江苏大学学报, 2018, 39(2):179-184. Sun J, Song J, Wu X H, et al. Image segmentation method of lettuce leaf based on improved Otsu algorithm[J]. Journal of Jiangsu University, 2018, 39(2):179-184. (in Chinese)
[7] Singh V, Misra A K. Detection of plant leaf diseases using image segmentation and soft computing techniques[J]. Information Processing in Agriculture, 2017, 4(1):41-49.
[8] Xie H, Fan Z, Li W, et al. Tobacco plant recognizing and counting based on SVM[C]//International Conference on Industrial Informatics, 2016:109-113.
[9] Hosoi F, Omasa K. Voxel-based 3-D modeling of individual trees for estimating leaf area density using high-resolution portable scanning LiDAR[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(12):3610-3618.
[10] Mccarthy C L, Hancock N H, Raine S R. Applied machine vision of plants:a review with implications for field deployment in automated farming operations[J]. Intelligent Service Robotics, 2010, 3(4):209-217.
[11] 喻垚慎. 基于点云数据的植物器官分割方法[D]. 南京:南京林业大学, 2016.
[12] Mortensen A K, Bender A, Whelan B, et al. Segmentation of lettuce in coloured 3D point clouds for fresh weight estimation[J]. Computers and Electronics in Agriculture, 2018, 154:373-381.
[13] 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, 2019, 57(3):1336-1346.
[14] Fang H, Zhu J, Hu P, et al. Image-based dynamic quantification and high-accuracy 3D evaluation of canopy structure of plant populations[J]. Annals of Botany, 2018, 121(5):1079-1088.
[15] Itakura K, Hosoi F. Automatic leaf segmentation for estimating leaf area and leaf inclination angle in 3D plant images[J]. Sensors, 2018, 18(10):3576.
[16] Junjie L Y L, John D. Point cloud based iterative segmentation technique for 3D plant phenotyping[C]//International Conference on Information and Automation, 2018:1072-1077.
[17] Jin S, Guan H, Zhang J, et al. Separating the structural components of maize for field phenotyping using terrestrial LiDAR data and deep convolutional neural networks[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 58(4):1-15.
[18] Mccarthy C L, Hancock N H, Raine S R. Applied machine vision of plants:a review with implications for field deployment in automated farming operations[J]. Intelligent Service Robotics, 2010, 3(4):209-17.
[19] Nguyen A, Le B. 3D Point Cloud Segmentation:a survey[C]//Robotics Automation and Mechatronics, 2013:225-230.
[20] 彭宝江, 钟若飞, 孙海丽, 等. 面向DEM构建的点云四叉树和R树混合索引研究[J]. 应用科学学报, 2018, 36(4):644-654. Peng B J, Zhong R F, Sun H L, et al. Hybrid index method based on quad tree and R-tree for DEM reconstruction of airborne point cloud[J]. Journal of Applied Sciences, 2018, 36(4):644-654. (in Chinse)
[21] Lin Y, Ruifang Z, Pujuan S, et al. Segmentation of crop organs through region growing in 3D space[C]//International Conference on Agro-geoinformatics, 2016:1-6.
[22] Vieira M, Shimada K. Surface mesh segmentation and smooth surface extraction through region growing[J]. Computer Aided Geometric Design, 2005, 22(8):771-792.
[23] Stein S C, Schoeler M, Papon J, et al. Object partitioning using local convexity[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, 304-311.
[24] 孙翔. 点云数据边缘提取及几何特征测量算法研究[D]. 秦皇岛:燕山大学, 2018.
[25] Charles R Q, Su H, Kaichun M, et al. PointNet:deep learning on point sets for 3D classification and segmentation[C]//Computer Vision and Pattern Recognition, 2017:77-85.
[26] Qi C R, Yi L, Su H, et al. PointNet++:deep hierarchical feature learning on point sets in a metric space[J]. Advances in Neural Information Processing Systems, 2017:30.
