Automated Rice Seedling Segmentation and Unsupervised Health Assessment Using Segment Anything Model with Multi-Modal Feature Analysis.

Abstract

This research presents a fully automated two-step method for segmenting rice seedlings and assessing their health by integrating spectral, morphological, and textural features. Driven by the global need for increased food production, the proposed method enhances monitoring and control in agricultural processes. Seedling locations are first identified by the excess green minus excess red index, which enables automated point-prompt inputs for the segment anything model to achieve precise segmentation and masking. Morphological features are extracted from the generated masks, while spectral and textural features are derived from corresponding red-green-blue imagery. Health assessment is conducted through anomaly detection using a one-class support vector machine, which identifies seedlings exhibiting abnormal morphology or spectral signatures suggesting stress. The proposed method is validated by visual inspection and Silhouette score, confirming effective separation of anomalies. For segmentation, the proposed method achieved mean dice scores ranging from 72.6 to 94.7. For plant health assessment, silhouette scores ranged from 0.31 to 0.44 across both datasets and various growth stages. Applied across three consecutive rice growth stages, the framework facilitates temporal monitoring of seedling health. The findings highlight the potential of advanced segmentation and anomaly detection techniques to support timely interventions, such as pruning or replacing unhealthy seedlings, to optimize crop yield.

Plant phenotyping relevance

イネ幼苗の画像セグメンテーションと形態・スペクトル・テクスチャ特徴に基づく健康状態推定を中心とする手法開発・検証研究であり、植物表現型の取得と異常判定が中核です。

Code and data availability

The paper uses two publicly available rice seedling image datasets as its phenotyping inputs: the Taiwan UAV Rice Seedling Dataset (GitHub) and the Heilongjiang seedling image dataset (Science Data Bank). No author analysis code, models, or checkpoints are reported as publicly available.