Challenges in automatic and selective plant-clearing

TL;DR

This paper discusses the challenges of developing robust, cost-effective autonomous systems for selective plant clearing in forestry, focusing on spectral imagery limitations, database size, and environmental variability.

Contribution

It highlights the specific difficulties in applying AI for selective plant clearing and analyzes factors affecting system robustness in uncontrolled outdoor environments.

Findings

Spectral imagery lacks robustness under varying weather conditions.

The size of the reference database impacts AI system performance.

Environmental variability poses significant challenges for autonomous plant clearing.

Abstract

With the advent of multispectral imagery and AI, there have been numerous works on automatic plant segmentation for purposes such as counting, picking, health monitoring, localized pesticide delivery, etc. In this paper, we tackle the related problem of automatic and selective plant-clearing in a sustainable forestry context, where an autonomous machine has to detect and avoid specific plants while clearing any weeds which may compete with the species being cultivated. Such an autonomous system requires a high level of robustness to weather conditions, plant variability, terrain and weeds while remaining cheap and easy to maintain. We notably discuss the lack of robustness of spectral imagery, investigate the impact of the reference database's size and discuss issues specific to AI systems operating in uncontrolled environments.