loading page

Robustness of 3D point-based deep learning for plant organ segmentation against point density variation and noise
  • David Rousseau,
  • Kaya Turgut,
  • Helin Dutagaci
David Rousseau
Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS), Université d'Angers, UMR IRHS, INRAe

Corresponding Author:[email protected]

Author Profile
Kaya Turgut
Department of Electrical-Electronics Engineering, Osmangazi University
Helin Dutagaci
Department of Electrical-Electronics Engineering, Osmangazi University

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.
03 Oct 2022Submitted to NAPPN 2023 Conference Papers
04 Oct 2022Published in NAPPN 2023 Conference Papers