Robustness of 3D point-based deep learning for plant organ segmentation against point density variation and noise

Abstract

We investigate the robustness of 3D point-based deep learning for organ segmentation of 3D plant models against varying reconstruction quality of the surface. The reconstruction quality is quantified in two ways: 1) The number of acquisitions for partial 3D scans and 2) the amount of noise. High quality models of real rosebush plants are used to collect point clouds in a controlled simulation environment as a way to degrade surface quality systematically. We show that the well-known 3D point-based neural network PointNet++ is capable of operating effectively on low quality and corrupted data for the task of plant organ segmentation. The results indicate that investing on developing deep learning methods has the potential of advancing applications of automated phenotyping, especially for low-quality 3D point clouds of plants. Keywords: plant phenotyping, organ segmentation, robustness analysis, point-based deep learning (a) (b) Figure 1: A 3D rosebush model from ROSE-X data set: (a) point cloud; (b) triangular mesh model.

Plant phenotyping relevance

3D植物モデルの器官セグメンテーション手法について、点密度とノイズに対する頑健性を体系的に評価しており、植物フェノタイピング用の計算手法の検証が中心である。

Code and data availability

The paper's phenotyping analysis is built entirely on the ROSE-X data set (11 annotated 3D rosebush point clouds), which the authors state is publicly available. However, the supplied text gives no authors' URL or repository link for ROSE-X itself (the only allowed URL is the HAL record of this paper), and no analysis/