欢迎您访问《智慧农业(中英文)》官方网站! English

Smart Agriculture ›› 2021, Vol. 3 ›› Issue (1): 75-85.doi: 10.12133/j.smartag.2021.3.1.202102-SA001

• 专题--作物表型前沿技术与应用 • 上一篇    下一篇

基于超体素聚类和局部特征的玉米植株点云雄穗分割

朱超1,2(), 吴凡1,2, 刘长斌3, 赵健翔1,2, 林丽丽1,2, 田雪莹1,2, 苗腾1,2()   

  1. 1.沈阳农业大学 信息与电气工程学院,辽宁 沈阳 110866
    2.辽宁省农业信息化工程技术研究中心,辽宁 沈阳 110866
    3.北京派得伟业科技发展有限公司,北京 100097
  • 收稿日期:2021-02-01 修回日期:2021-02-23 出版日期:2021-03-30
  • 基金项目:
    国家自然科学基金(31901399);辽宁省重点研发计划项目(2019JH2/10200002)
  • 作者简介:朱 超(1990-),男,博士,研究方向为作物表型检测技术。E-mail:20161008@stu.syau.edu.cn
  • 通信作者: 苗 腾(1985-),男,副教授,研究方向为数字植物技术和表型检测技术。电话:18740033355。E-mail:miaoteng@syau.edu.cn

Tassel Segmentation of Maize Point Cloud Based on Super Voxels Clustering and Local Features

ZHU Chao1,2(), WU Fan1,2, LIU Changbin3, ZHAO Jianxiang1,2, LIN Lili1,2, TIAN Xueying1,2, MIAO Teng1,2()   

  1. 1.College of Information and Electrical Engineering, Shenyang Agricultural University, Shenyang 110866, China
    2.Liaoning Engineering Research Center for Information Technology in Agriculture, Shenyang 110866, China
    3.Beijing PAIDE Science and Technology Development Company Limited, Beijing 100097, China
  • Received:2021-02-01 Revised:2021-02-23 Online:2021-03-30
  • Foundation items:National Natural Science Foundation of China(31901399);Liaoning Province Key Research and Development Plan Project (2019JH2/10200002)
  • About author:ZHU Chao, E-mail:20161008@stu.syau.edu.cn
  • Corresponding author:MIAO Teng, E-mail:miaoteng@syau.edu.cn

摘要:

针对当前三维点云处理方法在玉米植株点云中识别雄穗相对困难的问题,提出一种基于超体素聚类和局部特征的玉米植株点云雄穗分割方法。首先通过边连接操作建立玉米植株点云无向图,利用法向量差异计算边权值,并采用谱聚类方法将植株点云分解为多个超体素子区域;随后结合主成分分析方法和点云直线特征提取植株顶部的子区域;最后利用玉米植株点云的平面局部特征在顶部子区域中识别雄穗点云。对3种点云密度的15株成熟期玉米植株点云进行测试,采用F1分数作为分割精度判别指标,试验结果与手动分割真值相比,当点云密度为0.8、1.3和1.9个点/cm时,雄穗点云分割的平均F1分数分别为0.763、0.875和0.889,分割精度随点云密度增加而增高。结果表明,本研究提出的基于超体素聚类和局部特征的玉米植株点云雄穗分割方法具备在玉米植株点云中提取雄穗的能力,可为玉米高通量表型检测、玉米三维重建等研究和应用提供技术支持。

关键词: 玉米雄穗, 三维点云分割, 表型检测, 超体素聚类, 局部特征, 主成分分析

Abstract:

Accurate and high-throughput maize plant phenotyping is vital for crop breeding and cultivation research. Tassel-related phenotypic parameters are important agronomic traits. However, fully automatic and fine tassel organ segmentation of maize shoots from three-dimensional (3D) point clouds is still challenging. To address this issue, a tassel point cloud segmentation method based on point cloud super voxels clustering and local geometric features was proposed in this study. Firstly, the undirected graph of the maize plant point cloud was established, the edge weights were calculated by using the difference of normal vectors, and the spectral clustering method was used to cluster the point cloud to form multiple super voxel sub-regions. Then, the principal component analysis method was used to find the two end regions of the plant and based on the observation of the straight direction of the bottom stem regions, the top and bottom regions were distinguished by the point cloud linear features. Finally, the tassel points were identified based on the plane local features of the point cloud. The sub-regions of the top region of the plant were classified into leaf regions, tassel regions, and mixed regions by plane local features of the point cloud, the tassel points in the tassel sub-region, and the mixed region were the finally segmented tassel point clouds. In this study, 15 mature maize plants with 3 point cloud densities were tested. Compared with the ground truth segmented manually, the average F1 scores of the tassel segmentation were 0.763, 0.875 and 0.889 when the point cloud density was 0.8/cm, 1.3/cm, and 1.9/cm, respectively. The segmentation accuracy of this method increased with the increase of plant point cloud density. The increase of point cloud density and the number of point clouds mainly affected the calculation results of point cloud plane features in tassel segmentation. When the number of point clouds was small, the top leaf point cloud was relatively sparse. Therefore, the difference between the plane feature of the leaf point and the plane feature of the tassel point was not obvious, which led to the increase of the misclassification of the point cloud. However, the time complexity of the algorithm was O(n3), so the increase in the density and number of point clouds would lead to a significant increase in the running time. Considering the segmentation accuracy and running time, the research obtained the best effect on the mature maize plants with a point cloud density of 1.3/cm and an average number of 15,000. The segmentation F1 score reached 0.875 and the running time was 6.85 s. The results showed that this method could extract tassels from maize plant point cloud, and provided technical support for the research and application of high-throughput phenotyping and three-dimensional reconstruction of maize.

Key words: maize tassel, 3D point cloud segmentation, phenotyping, super voxels clustering, local features, principal component analysis

中图分类号: