Accurate 3D Grapevine Structure Extraction from High-Resolution Point Clouds

TL;DR

This paper improves 3D grapevine structure extraction from high-resolution point clouds by adapting the Smart-Tree algorithm and introducing a graph-based disambiguation method, leading to more accurate skeletonization for viticulture applications.

Contribution

It presents a novel adaptation of the Smart-Tree algorithm with a graph-based approach for better skeletonization of grapevines in 3D point clouds, addressing structural complexities.

Findings

15.8% improvement in F1 score over original Smart-Tree

Effective delineation of individual cane skeletons

Enhanced accuracy in 3D grapevine modelling

Abstract

Accurate 3D modelling of grapevines is crucial for precision viticulture, particularly for informed pruning decisions and automated management techniques. However, the intricate structure of grapevines poses significant challenges for traditional skeletonization algorithms. This paper presents an adaptation of the Smart-Tree algorithm for 3D grapevine modelling, addressing the unique characteristics of grapevine structures. We introduce a graph-based method for disambiguating skeletonization. Our method delineates individual cane skeletons, which are crucial for precise analysis and management. We validate our approach using annotated real-world grapevine point clouds, demonstrating improvement of 15.8% in the F1 score compared to the original Smart-Tree algorithm. This research contributes to advancing 3D grapevine modelling techniques, potentially enhancing both the sustainability and profitability of grape production through more precise and automated viticulture practices