Deep Segmentation of Point Clouds of Wheat.

Deep Segmentation of Point Clouds of Wheat.
复制标题

DOI:
10.3389/fpls.2021.608732
复制
发表时间:
2021
影响因子:
5.6
通讯作者:
Doonan JH
Doonan JH
中科院分区:
生物学2区
文献类型:
--
作者:
Ghahremani M;Williams K;Corke FMK;Tiddeman B;Liu Y;Doonan JH

文献摘要

参考文献

被引文献

相似文献

植物的3D分析在对器官的相对结构和其他感兴趣的特征进行建模方面变得越来越有效。在本文中,我们介绍了一种新的基于模式的深度神经网络Pattern-Net,用于分割小麦的点云。本研究首次将小麦的点云数据分割成定义的器官,并在3D空间中直接分析其性状。点云没有规则的网格,因此其分割具有挑战性。Pattern-Net在邻居之间创建一个动态链接,使用K-最近邻居算法从多个抽象级别的3D点集中寻找稳定的模式。为此,不同的层相互连接,以从简单的模式创建复杂的模式,加强动态链接传播,减轻消失梯度问题,鼓励链接重用,并大大减少参数的数量。提出的深度网络能够分析和分解非结构化的复杂点云到语义上有意义的部分。小麦数据集上的实验验证了该方法在三维空间小麦分割中的有效性。
The 3D analysis of plants has become increasingly effective in modeling the relative structure of organs and other traits of interest. In this paper, we introduce a novel pattern-based deep neural network, Pattern-Net, for segmentation of point clouds of wheat. This study is the first to segment the point clouds of wheat into defined organs and to analyse their traits directly in 3D space. Point clouds have no regular grid and thus their segmentation is challenging. Pattern-Net creates a dynamic link among neighbors to seek stable patterns from a 3D point set across several levels of abstraction using the K-nearest neighbor algorithm. To this end, different layers are connected to each other to create complex patterns from the simple ones, strengthen dynamic link propagation, alleviate the vanishing-gradient problem, encourage link reuse and substantially reduce the number of parameters. The proposed deep network is capable of analysing and decomposing unstructured complex point clouds into semantically meaningful parts. Experiments on a wheat dataset verify the effectiveness of our approach for segmentation of wheat in 3D space.
DOI: 10.1016/j.compag.2014.09.021
发表时间: 2015-01-01
影响因子: 8.3
作者:
Jay, Sylvain;Rabatel, Gilles;Gorretta, Nathalie
通讯作者: Gorretta, Nathalie
DOI: 10.1016/j.fcr.2016.12.028
发表时间: 2017-03-01
影响因子: 5.8
作者:
Ferrante, Ariel;Cartelle, Julia;Slafer, Gustavo A.
通讯作者: Slafer, Gustavo A.
DOI: 10.1371/journal.pone.0168496
发表时间: 2016
期刊: PloS one
影响因子: 3.7
作者:
Chopin J;Laga H;Miklavcic SJ
通讯作者: Miklavcic SJ
DOI: 10.1186/s13007-018-0366-8
发表时间: 2018
期刊: Plant methods
影响因子: 5.1
作者:
Hasan MM;Chopin JP;Laga H;Miklavcic SJ
通讯作者: Miklavcic SJ
DOI: 10.3389/fpls.2019.00839
发表时间: 2019-07-11
影响因子: 5.6
作者:
Dieleman, J. Anja;De Visser, Pieter H. B.;Dueck, Tom A.
通讯作者: Dueck, Tom A.