Development of a robotic detection system for greenhouse pepper plant diseases

Abstract

Automation of disease detection and monitoring can facilitate targeted and timely disease control, which can lead to increased yield, improved crop quality and reduction in the quantity of applied pesticides. Further advantages are reduced production costs, reduced exposure to pesticides for farm workers and inspectors and increased sustainability. Symptoms are unique for each disease and crop, and each plant may suffer from multiple threats. Thus, a dedicated integrated disease-detection system and algorithms are required. The development of such a robotic detection system for two major threats of bell pepper plants: powdery mildew (PM) and Tomato spotted wilt virus (TSWV), is presented. Detection algorithms were developed based on principal component analysis using RGB and multispectral NIR-R-G sensors. High accuracy was obtained for pixel classification as diseased or healthy, for both diseases, using RGB imagery (PM: 95%, TSWV: 90%). NIR-R-G multispectral imagery yielded low classification accuracy (PM: 80%, TSWV: 61%). Accordingly, the final sensing apparatus was composed of a RGB sensor and a single-laser-beam distance sensor. A relatively fast cycle time (average 26.7 s per plant) operation cycle for detection of the two diseases was developed and tested. The cycle time was mainly influenced by sub-tasks requiring motion of the manipulator. Among these tasks, the most demanding were the determination of the required detection position and orientation. The time for task completion may be reduced by increasing the robotic work volume and by improving the algorithm for determining position and orientation.

Plant phenotyping relevance

植物病害の症状をRGB・マルチスペクトル画像で検出するロボット型フェノタイピングシステムとアルゴリズムの開発・評価が中心であり、植物状態の測定手法に該当する。

Code and data availability

公開本文の所在を確認できませんでした。非公開または購読が必要な可能性があります。

No evidence-backed public reproduction asset is currently recorded.