Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Dec 23:2021:9838929.
doi: 10.34133/2021/9838929. eCollection 2021.

Panicle-3D: Efficient Phenotyping Tool for Precise Semantic Segmentation of Rice Panicle Point Cloud

Liang Gong  1 , Xiaofeng Du  1 , Kai Zhu  1 , Ke Lin  1 , Qiaojun Lou  2 , Zheng Yuan  3 , Guoqiang Huang  3 , Chengliang Liu  1
Affiliations

Panicle-3D: Efficient Phenotyping Tool for Precise Semantic Segmentation of Rice Panicle Point Cloud

Liang Gong et al. Plant Phenomics. .

Abstract

The automated measurement of crop phenotypic parameters is of great significance to the quantitative study of crop growth. The segmentation and classification of crop point cloud help to realize the automation of crop phenotypic parameter measurement. At present, crop spike-shaped point cloud segmentation has problems such as fewer samples, uneven distribution of point clouds, occlusion of stem and spike, disorderly arrangement of point clouds, and lack of targeted network models. The traditional clustering method can realize the segmentation of the plant organ point cloud with relatively independent spatial location, but the accuracy is not acceptable. This paper first builds a desktop-level point cloud scanning apparatus based on a structured-light projection module to facilitate the point cloud acquisition process. Then, the rice ear point cloud was collected, and the rice ear point cloud data set was made. In addition, data argumentation is used to improve sample utilization efficiency and training accuracy. Finally, a 3D point cloud convolutional neural network model called Panicle-3D was designed to achieve better segmentation accuracy. Specifically, the design of Panicle-3D is aimed at the multiscale characteristics of plant organs, combined with the structure of PointConv and long and short jumps, which accelerates the convergence speed of the network and reduces the loss of features in the process of point cloud downsampling. After comparison experiments, the segmentation accuracy of Panicle-3D reaches 93.4%, which is higher than PointNet. Panicle-3D is suitable for other similar crop point cloud segmentation tasks.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
The structure of the point cloud acquisition platform.
Figure 2
Figure 2
(a) Point cloud before downsampling. (b) Point cloud after downsampling.
Figure 3
Figure 3
(a) Point cloud before being labeled. (b) Point cloud after being labeled;
Figure 4
Figure 4
Rice point cloud data argumentation.
Figure 5
Figure 5
The structure of the SE-Net module and the structure of the SE-Inception-PointConv module.
Figure 6
Figure 6
Structure of Panicle-3D.
Figure 7
Figure 7
IOU vs. epoch curve.
Figure 8
Figure 8
The segmentation results.
Figure 9
Figure 9
The comparison of Panicle-3D and PointNet (a) IoU vs. epoch (b) Acc vs. epoch.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Miao C., Pages A., Xu Z., Rodene E., Yang J., Schnable J. C. Semantic segmentation of sorghum using hyperspectral data identifies genetic associations. Plant Phenomics . 2020;2020, article 4216373:1–11. doi: 10.34133/2020/4216373. - DOI - PMC - PubMed
    1. Ookawa T., Inoue K., Matsuoka M., et al. Increased lodging resistance in long-culm, low-lignin gh2 rice for improved feed and bioenergy production. Scientific Reports . 2015;4(1, article 6567) doi: 10.1038/srep06567. - DOI - PMC - PubMed
    1. Liu E., Liu Y., Wu G., et al. Identification of a candidate gene for panicle length in Rice (Oryza sativa L.) via association and linkage analysis. Frontiers in Plant Science . 2016;7 doi: 10.3389/fpls.2016.00596. - DOI - PMC - PubMed
    1. Adam A., Chatzilari E., Nikolopoulos S., Kompatsiaris I. H-RANSAC: a hybrid point cloud segmentation combining 2D and 3D data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences . 2018;IV-2(2):1–8. doi: 10.5194/isprs-annals-IV-2-1-2018. - DOI
    1. Long J., Shelhamer E., Darrell T. Fully convolutional networks for semantic segmentation; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition ; 2015; Boston, MA, USA. pp. 3431–3440. - DOI - PubMed

LinkOut - more resources