# HALF: Histogram of Angles in Linked Features for 3D Point Cloud Data Segmentation of Plants for Robust Sensing

## TL;DR

This paper introduces HALF, a new method for analyzing 3D plant data that improves plant structure segmentation without needing large labeled datasets.

## Contribution

HALF introduces a novel histogram-based method for plant 3D point cloud segmentation with a competitive algorithm for phytomer classification.

## Key findings

- HALF effectively segments plant structures like leaves and stems from 3D point clouds.
- The Sequential Competitive Segmentation Algorithm improves phytomer-level classification accuracy.
- HALF is demonstrated to be a low-cost and efficient tool for plant phenotyping and precision agriculture.

## Abstract

This paper presents a novel method, Histogram of Angles in Linked Features (HALF), designed for the segmentation of 3D point cloud data of plants for robust sensing. The proposed method leverages local angular features extracted from 3D measurements obtained via sensing technologies such as laser scanning, LiDAR, or photogrammetry. HALF enables efficient identification of plant structures—leaves, stems, and knots—without requiring large-scale labeled datasets, making it highly suitable for applications in plant phenotyping and structural analysis. To enhance robustness and interpretability, we extend HALF to a convolution-based mathematical framework and introduce the Sequential Competitive Segmentation Algorithm (SCSA) for phytomer-level classification. Experimental results using 3D point cloud data of soybean plants demonstrate the feasibility of our method in sensor-based plant monitoring systems. By providing a low-cost and efficient approach for plant structure analysis, HALF contributes to the advancement of sensor-driven plant phenotyping and precision agriculture.