A Rapidly Deployable Classification System using Visual Data for the Application of Precision Weed Management

TL;DR

This paper presents a fast, adaptable weed classification system that uses visual data and plant clustering to operate in any field without prior weed species knowledge, reducing labeling effort significantly.

Contribution

It introduces a novel three-stage pipeline combining plant clustering and selective labeling for deployable weed classification without prior species assumptions.

Findings

Labels 12.3 times fewer images than traditional methods.

Reduces classification accuracy by only 14%.

Operates effectively across diverse fields.

Abstract

In this work we demonstrate a rapidly deployable weed classification system that uses visual data to enable autonomous precision weeding without making prior assumptions about which weed species are present in a given field. Previous work in this area relies on having prior knowledge of the weed species present in the field. This assumption cannot always hold true for every field, and thus limits the use of weed classification systems based on this assumption. In this work, we obviate this assumption and introduce a rapidly deployable approach able to operate on any field without any weed species assumptions prior to deployment. We present a three stage pipeline for the implementation of our weed classification system consisting of initial field surveillance, offline processing and selective labelling, and automated precision weeding. The key characteristic of our approach is the combination of plant clustering and selective labelling which is what enables our system to operate without prior weed species knowledge. Testing using field data we are able to label 12.3 times fewer images than traditional full labelling whilst reducing classification accuracy by only 14%.