Pre-Clustering Point Clouds of Crop Fields Using Scalable Methods

Abstract

In order to apply the recent successes of machine learning and automated plant phenotyping on a large scale using agricultural robotics, efficient and general algorithms must be designed to intelligently split crop fields into small, yet actionable, portions that can then be processed by more complex algorithms. In this paper, we notice a similarity between the current state-of-the-art for separating corn plants and a commonly used density-based clustering algorithm, Quickshift. Exploiting this similarity we propose a number of novel, application-specific algorithms with the goal of producing a general and scalable field segmentation algorithm. The novel algorithms proposed in this work are shown to produce quantitatively better results than the current state-of-the-art while being less sensitive to input parameters and maintaining the same algorithmic time complexity. When incorporated into field-scale phenotyping systems, the proposed algorithms should work as a drop-in replacement that can greatly improve the accuracy of results while ensuring that performance and scalability remain undiminished.

Plant phenotyping relevance

農業ロボティクス向けの作物分離・フィールドスケール植物フェノタイピング用クラスタリング手法を開発し、既存手法と定量比較しているため、方法が中心である。

Code and data availability

The paper explicitly states that the corn field point cloud data and implementations of the proposed clustering algorithms (Non-random RAIN, Z-Quickshift, GD Quickshift, GD Quickshift++) are publicly available at the authors' GitHub repository to facilitate replication of results.