■植物点云的3D语义分割是朝着自动植物表型和作物建模迈出的重要一步。由于传统的手工设计点云处理方法面临着泛化的挑战,当前的方法是基于深度神经网络,该深度神经网络根据训练数据学习执行3D分割。然而,这些方法需要一个大的带注释的训练集才能表现良好。特别是对于三维语义分割,培训数据的收集是高度劳动密集和耗时的。数据增强已被证明可以改善小型训练集上的训练。然而,目前尚不清楚哪些数据增强方法对3D植物部分分割有效。
■在拟议的工作中,五种新的数据增强方法(全球种植,亮度调节,叶子翻译,叶旋转,和叶子交叉)被提出并与五种现有方法(在线下采样,全球抖动,全局缩放,全球旋转,和全球翻译)。将该方法应用于PointNet,对三个番茄植物品种的点云进行3D语义分割(Merlice,Brioso,和园丁喜悦)。点云被分割成土壤基底,棍子,stemwork,和其他生物结构。
■在本文提出的数据增强方法中,叶子交叉显示出最有希望的结果,优于现有的结果。叶旋转(绕Z轴),叶子翻译,种植在3D番茄植物点云上也表现良好,除了全球抖动之外,它的表现优于大多数现有工作。提出的3D数据增强方法显着改善了由有限的训练数据引起的过拟合。改进的植物部分分割进一步使得能够更准确地重建植物架构。
UNASSIGNED: 3D semantic segmentation of plant point clouds is an important step towards automatic plant phenotyping and crop modeling. Since traditional hand-designed methods for point-cloud processing face challenges in generalisation, current methods are based on deep neural network that learn to perform the 3D segmentation based on training data. However, these methods require a large annotated training set to perform well. Especially for 3D semantic segmentation, the collection of training data is highly labour intensitive and time consuming. Data augmentation has been shown to improve training on small training sets. However, it is unclear which data-augmentation methods are effective for 3D plant-part segmentation.
UNASSIGNED: In the proposed work, five novel data-augmentation methods (global cropping, brightness adjustment, leaf translation, leaf rotation, and leaf crossover) were proposed and compared to five existing methods (online down sampling, global jittering, global scaling, global rotation, and global translation). The methods were applied to PointNet++ for 3D semantic segmentation of the point clouds of three cultivars of tomato plants (Merlice, Brioso, and Gardener Delight). The point clouds were segmented into soil base, stick, stemwork, and other bio-structures.
UNASSIGNED: Among the data augmentation methods being proposed in this paper, leaf crossover indicated the most promising result which outperformed the existing ones. Leaf rotation (around Z axis), leaf translation, and cropping also performed well on the 3D tomato plant point clouds, which outperformed most of the existing work apart from global jittering. The proposed 3D data augmentation approaches significantly improve the overfitting caused by the limited training data. The improved plant-part segmentation further enables a more accurate reconstruction of the plant architecture.