期刊
PLANT PHENOMICS
卷 2022, 期 -, 页码 -出版社
AMER ASSOC ADVANCEMENT SCIENCE
DOI: 10.34133/2022/9787643
关键词
-
资金
- Shanghai Rising-Star Program [21QA1400100]
- Shanghai Natural Science Foundation [20ZR1400800]
- Shanghai Sailing Program [21YF1401400]
- Fundamental Research Funds for the Central Universities of China [2232020D-49]
Phenotyping of plant growth is crucial for understanding complex genetic traits, breeding, and intelligent agriculture. This study introduces Voxelized Farthest Point Sampling (VFPS) as a new point cloud downsampling strategy and presents PSegNet, a deep learning network specifically designed for segmentation of plant point clouds. After training on datasets prepared with VFPS, PSegNet achieves state-of-the-art segmentation results both quantitatively and qualitatively, outperforming mainstream networks like PointNet++, ASIS, SGPN, and PlantNet.
Phenotyping of plant growth improves the understanding of complex genetic traits and eventually expedites the development of modern breeding and intelligent agriculture. In phenotyping, segmentation of 3D point clouds of plant organs such as leaves and stems contributes to automatic growth monitoring and reflects the extent of stress received by the plant. In this work, we first proposed the Voxelized Farthest Point Sampling (VFPS), a novel point cloud downsampling strategy, to prepare our plant dataset for training of deep neural networks. Then, a deep learning network-PSegNet, was specially designed for segmenting point clouds of several species of plants. The effectiveness of PSegNet originates from three new modules including the Double-Neighborhood Feature Extraction Block (DNFEB), the Double-Granularity Feature Fusion Module (DGFFM), and the Attention Module (AM). After training on the plant dataset prepared with VFPS, the network can simultaneously realize the semantic segmentation and the leaf instance segmentation for three plant species. Comparing to several mainstream networks such as PointNet++, ASIS, SGPN, and PlantNet, the PSegNet obtained the best segmentation results quantitatively and qualitatively. In semantic segmentation, PSegNet achieved 95.23%, 93.85%, 94.52%, and 89.90% for the mean Prec, Rec, F1, and IoU, respectively. In instance segmentation, PSegNet achieved 88.13%, 79.28%, 83.35%, and 89.54% for the mPrec, mRec, mCov, and mWCov, respectively.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据