Transferring PointNet++ Segmentation from Virtual to Real Plants - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Transferring PointNet++ Segmentation from Virtual to Real Plants

Abstract

One of the biggest challenges of deep neural network to perform segmentation of point clouds is the requirement of large amount of annotated data, which is expensive in terms of manual labour and time. For the case of plants, there is a scarcity of datasets to train the networks to perform organ segmentation for automated phenotyping applications. In this work, we explore how the use of virtual plants as modelled by stochastic L-systems can circumvent this problem. We investigate the effect of point density and how the complexity of the plant model affect the transfer of learning from virtual to real plants on a segmentation task based on PointNet++.
Fichier principal
Vignette du fichier
cvppa2021.pdf (292.59 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03540304 , version 1 (23-01-2022)

Identifiers

  • HAL Id : hal-03540304 , version 1

Cite

Ayan Chaudhury, Peter Hanappe, Romain Azaïs, Christophe Godin, David Colliaux. Transferring PointNet++ Segmentation from Virtual to Real Plants. ICCV 2021 - International Conference on Computer Vision, Oct 2021, Montreal, Canada. pp.1-3. ⟨hal-03540304⟩
211 View
242 Download

Share

Gmail Mastodon Facebook X LinkedIn More