Pre-Clustering Point Clouds of Crop Fields Using Scalable Methods

TL;DR

This paper introduces scalable, application-specific clustering algorithms for pre-processing crop field point clouds, improving segmentation accuracy and robustness for agricultural robotics applications.

Contribution

The paper proposes novel, scalable clustering algorithms tailored for crop field point clouds, outperforming current methods in accuracy and parameter sensitivity.

Findings

Quantitative improvement over state-of-the-art methods

Less sensitive to input parameters

Maintains same algorithmic time complexity

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.