PlantSegNet: 3D point cloud instance segmentation of nearby plant organs with identical semantics

Open Webpage

Ariyan Zarei, Bosheng Li, James C. Schnable, Eric Lyons, Duke Pauli, Kobus Barnard, Bedrich Benes

Published: 01 Jan 2024, Last Modified: 30 Oct 2025Comput. Electron. Agric. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A pipeline for generating procedural sorghum models, which we use to generate point clouds of sorghum fields.•A large-scale, annotated, and synthetic dataset of sorghum plants.•PlantSegNet model, a neural network structure for instance segmentation of nearby objects with identical semantics.•A demonstration of the effectiveness of training on synthetic data in learning an efficient feature embedding space for real data.