Model based 3D point cloud segmentation for automated selective broccoli harvesting*
Title: Model based 3D point cloud segmentation for automated selective broccoli harvesting*
Authors: Hector A. Montes (School of Computer Science, University of Lincoln); Grzegorz Cielniak (School of Computer Science, University of Lincoln); Tom Duckett (School of Computer Science, University of Lincoln);
Year: 2019
Citation: Montes, H. A., Cielniak, G., Duckett, T., (2019). Model based 3D point cloud segmentation for automated selective broccoli harvesting*. UK-RAS19 Conference: “Embedded Intelligence: Enabling & Supporting RAS Technologies” Proceedings, 24-27. doi: 10.31256/UKRAS19.7
Abstract:
In this paper we address the topic of feature matching in 3D point cloud data for accurate object segmentation. We present a matching method based on local features that operates on 3D point clouds to separate crops of broccoli heads from their background. We have implemented our approach and present experiments on datasets collected in cultivated broccoli fields, in which we analyse performance and matching capabilities and evaluate the usefulness of the system as a point feature-based segmentation method.