Rotating Stomata Measurement Based on Anchor-Free Object Detection and Stomata Conductance Calculation.

Abstract

Stomata play an essential role in regulating water and carbon dioxide levels in plant leaves, which is important for photosynthesis. Previous deep learning-based plant stomata detection methods are based on horizontal detection. The detection anchor boxes of deep learning model are horizontal, while the angle of stomata is randomized, so it is not possible to calculate stomata traits directly from the detection anchor boxes. Additional processing of image (e.g., rotating image) is required before detecting stomata and calculating stomata traits. This paper proposes a novel approach, named DeepRSD (deep learning-based rotating stomata detection), for detecting rotating stomata and calculating stomata basic traits at the same time. Simultaneously, the stomata conductance loss function is introduced in the DeepRSD model training, which improves the efficiency of stomata detection and conductance calculation. The experimental results demonstrate that the DeepRSD model reaches 94.3% recognition accuracy for stomata of maize leaf. The proposed method can help researchers conduct large-scale studies on stomata morphology, structure, and stomata conductance models.

Plant phenotyping relevance

植物葉の気孔を対象に、回転を考慮した検出と気孔形質・コンダクタンス算出を一体化する手法を開発しており、フェノタイピング手法が中心である。

Code and data availability

The paper's DeepRSD stomata detection and conductance calculation code is explicitly stated to be publicly hosted on GitHub at the authors' repository URL. No public dataset of the 2,192 maize stomata images is mentioned.