College of Information and Electrical Engineering, Shenyang Agricultural University, Dongling Road, Shenhe District, Liaoning Province, Shenyang 110161, China.
Beijing Research Center for Information Technology in Agriculture, 11#Shuguang Huayuan Middle Road, Haidian District, Beijing 100097, China.
Gigascience. 2021 May 7;10(5). doi: 10.1093/gigascience/giab031.
The 3D point cloud is the most direct and effective data form for studying plant structure and morphology. In point cloud studies, the point cloud segmentation of individual plants to organs directly determines the accuracy of organ-level phenotype estimation and the reliability of the 3D plant reconstruction. However, highly accurate, automatic, and robust point cloud segmentation approaches for plants are unavailable. Thus, the high-throughput segmentation of many shoots is challenging. Although deep learning can feasibly solve this issue, software tools for 3D point cloud annotation to construct the training dataset are lacking.
We propose a top-to-down point cloud segmentation algorithm using optimal transportation distance for maize shoots. We apply our point cloud annotation toolkit for maize shoots, Label3DMaize, to achieve semi-automatic point cloud segmentation and annotation of maize shoots at different growth stages, through a series of operations, including stem segmentation, coarse segmentation, fine segmentation, and sample-based segmentation. The toolkit takes ∼4-10 minutes to segment a maize shoot and consumes 10-20% of the total time if only coarse segmentation is required. Fine segmentation is more detailed than coarse segmentation, especially at the organ connection regions. The accuracy of coarse segmentation can reach 97.2% that of fine segmentation.
Label3DMaize integrates point cloud segmentation algorithms and manual interactive operations, realizing semi-automatic point cloud segmentation of maize shoots at different growth stages. The toolkit provides a practical data annotation tool for further online segmentation research based on deep learning and is expected to promote automatic point cloud processing of various plants.
三维点云是研究植物结构和形态最直接、最有效的数据形式。在点云研究中，将单个植物的点云分割到器官直接决定了器官级表型估计的准确性和三维植物重建的可靠性。然而，目前缺乏针对植物的高精度、自动化和鲁棒的点云分割方法。因此，对大量芽的高通量分割具有挑战性。虽然深度学习可以解决这个问题，但缺乏用于构建训练数据集的 3D 点云注释软件工具。
我们提出了一种基于最优传输距离的玉米芽自上而下的点云分割算法。我们应用玉米芽点云注释工具包 Label3DMaize，通过一系列操作，包括茎分割、粗分割、细分割和基于样本的分割，实现了不同生长阶段玉米芽的半自动点云分割和注释。该工具包分割一个玉米芽大约需要 4-10 分钟，如果只需要粗分割，则消耗总时间的 10-20%。细分割比粗分割更详细，尤其是在器官连接区域。粗分割的准确率可达 97.2%，细分割的准确率可达 97.2%。
Label3DMaize 集成了点云分割算法和手动交互操作，实现了不同生长阶段玉米芽的半自动点云分割。该工具包为进一步基于深度学习的在线分割研究提供了实用的数据注释工具，并有望促进各种植物的自动点云处理。
