An Evaluation of Multi-Channel Sensors and Density Estimation Learning for Detecting Fire Blight Disease in Pear Orchards.

Abstract

Fire blight is an infectious disease found in apple and pear orchards. While managing the disease is critical to maintaining orchard health, identifying symptoms early is a challenging task which requires trained expert personnel. This paper presents an inspection technique that targets individual symptoms via deep learning and density estimation. We evaluate the effects of including multi-spectral sensors in the model's pipeline. Results show that adding near infrared (NIR) channels can help improve prediction performance and that density estimation can detect possible symptoms when severity is in the mid-high range.

Plant phenotyping relevance

ナシ園の火傷病症状を対象に、多チャンネルセンサー、深層学習、密度推定による植物病害状態の検出手法を評価しており、表現型取得・抽出が中心である。

Code and data availability

The paper's pear orchard multi-spectral image dataset, labels, and analysis code are not stated as publicly available anywhere in the supplied blocks. The only GitHub URLs cited (Label Studio, Segmentation Models Pytorch, Computing-Density-Maps) are generic third-party tools or cited prior work, not authors' paper-phen

No evidence-backed public reproduction asset is currently recorded.