Skip to Main content Skip to Navigation
Book section

Leaves Segmentation in 3D Point Cloud

Abstract : This paper presents a 3D plant segmentation method with an emphasis on segmentation of the leaves. This method is part of a 3D plant phenotyping project with a main objective that deals with the development of the leaf area over time. First, a 3D point cloud of a plant is obtained with Structure from Motion technique and the cloud is then segmented into the main components of a plant: the stem and the leaves. As the main objective is to measure leaf area over time, an emphasis was placed on accurate segmentation and the labelling of the leaves. This article presents an original approach which starts by finding the stem in a 3D point cloud and then the leaves. Moreover, this method relies on the model of a plant as well as the agronomic rules to affect a unique label that do not change over time. This method is evaluated using two morphologically distinct plants, sunflower and sorghum.
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : William Gelard <>
Submitted on : Monday, December 17, 2018 - 2:35:34 PM
Last modification on : Wednesday, June 9, 2021 - 10:00:22 AM
Long-term archiving on: : Monday, March 18, 2019 - 3:03:48 PM


Files produced by the author(s)


  • HAL Id : hal-01957617, version 1


William Gélard, Ariane Herbulot, Michel Devy, Philippe Debaeke, Ryan Mccormick, et al.. Leaves Segmentation in 3D Point Cloud. Advanced Concepts for Intelligent Vision Systems 18th International Conference, ACIVS 2017, Antwerp, Belgium, September 18-21, 2017, Proceedings, pp.664-674, 2017. ⟨hal-01957617⟩



Record views


Files downloads