基于动态图卷积网络的植物点云分割研究
Segmentation of Plant Point Cloud Segmentation Based on Dynamic Graph Convolution Network
DOI: 10.12677/CSA.2022.123070, PDF,   
作者: 钟旭升：广东工业大学，计算机学院，广东 广州
关键词: 点云分割；图卷积神经网络；Point Cloud Segmentation； Graph Convolution Neural Network
摘要: 叶片是植物进行光合作用和产生营养物质的重要器官，准确、快速地获取植物叶片参数对于了解植物生长规律、提高产量具有重要意义。本文使用图卷积神经网络GCNN作为基本框架，并在网络的各层更新图的构成。本文使用采集的864株植株点云数据作为数据集，并用相同的设备在该数据集上验证本文的模型，实验表明，本文的方法与以往的点云分割模型相比具有较大的性能提升。
Abstract: Leaf is an important organ for photosynthesis and nutrient production in plants. Accurate and rapid acquisition of plant leaf parameters is of great significance for understanding plant growth rules and improving yield. In this paper, graph convolution neural network (GCNN) is used as the basic framework and the graph composition is updated in each layer of the network. In this paper, the collected point cloud data of 864 plants are used as our data set, and the same equipment is used to verify the proposed model on the data set. Experiments show that the method we proposed has greater performance improvement than previous point cloud segmentation models.
文章引用：钟旭升. 基于动态图卷积网络的植物点云分割研究[J]. 计算机科学与应用, 2022, 12(3): 690-696. https://doi.org/10.12677/CSA.2022.123070

参考文献

[1] Himmelsbach, M., Luettel, T. and Wuensche, H. (2009) Real-Time Object Classification in 3D Point Clouds Using Point Feature Histograms. IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2009, St. Louis, 10-15 October 2009, 994-1000. [Google Scholar] [CrossRef] 
[2] 姜媛媛. 基于超体素区域增长的点云分割算法研究[D]: [硕士学位论文]. 西安: 西安电子科技大学, 2005.
[3] 孙红岩, 孙晓鹏, 李华. 基于K-means聚类方法的三维点云模型分割[J]. 计算机工程与应用, 2006(10): 42-45.
[4] Golbach, F., Kootstra, G., Damjanovic, S., et al. (2016) Validation of Plant Part Measurements Using a 3D Reconstruction Method Suitable for High-Throughput Seedling Phenotyping. Machine Vision & Applications, 27, 663-680. [Google Scholar] [CrossRef] 
[5] Qi, C.R., Su, H., Mo, K. and Guibas, L.J. (2017) Pointnet: Deep Learning on Point Sets for 3d Classification and Segmentation. arXiv:1612.00593 [cs.CV]
[6] Qi, C.R., Yi, L., Su, H. and Guibas, L.J. (2017) Pointnetþþ: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. In: Advances in Neural Information Processing Systems, 5105-5114.
[7] Li, Y., Bu, R., Sun, M., Wu, W., Di, X. and Chen, B. (2018) PointCNN: Convolution on X-Transformed Points. In: Advances in Neural Information Processing Systems, 820-830.
[8] Jiang, M., Wu, Y., Zhao, T., et al. (2018) PointSIFT: A SIFT-Like Network Module for 3D Point Cloud Semantic Segmentation. arXiv:1807.00652 [cs.CV]
[9] Li, J., Chen, B.M. and Lee, G.H. (2018) SO-Net: Self-Organizing Network for Point Cloud Analysis. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, 18-23 June 2018, Article ID: 00979. [Google Scholar] [CrossRef] 
[10] Behl, A., Paschalidou, D., Donne, S., et al. (2019) PointFlowNet: Learning Representations for Rigid Motion Estimation from Point Clouds. 2019 IEEE/CVF Conference on Computer Vi-sion and Pattern Recognition (CVPR), Long Beach, CA, 15-20 June 2019, Article ID: 00815. [Google Scholar] [CrossRef] 
[11] Wang, Y., Sun, Y., Liu, Z., et al. (2018) Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics, 38, 1-12. [Google Scholar] [CrossRef]