Real-time and lightweight detection of grape diseases based on Fusion Transformer YOLO.

Abstract

Introduction Grapes are prone to various diseases throughout their growth cycle, and the failure to promptly control these diseases can result in reduced production and even complete crop failure. Therefore, effective disease control is essential for maximizing grape yield. Accurate disease identification plays a crucial role in this process. In this paper, we proposed a real-time and lightweight detection model called Fusion Transformer YOLO for 4 grape diseases detection. The primary source of the dataset comprises RGB images acquired from plantations situated in North China. Methods Firstly, we introduce a lightweight high-performance VoVNet, which utilizes ghost convolutions and learnable downsampling layer. This backbone is further improved by integrating effective squeeze and excitation blocks and residual connections to the OSA module. These enhancements contribute to improved detection accuracy while maintaining a lightweight network. Secondly, an improved dual-flow PAN+FPN structure with Real-time Transformer is adopted in the neck component, by incorporating 2D position embedding and a single-scale Transformer Encoder into the last feature map. This modification enables real-time performance and improved accuracy in detecting small targets. Finally, we adopt the Decoupled Head based on the improved Task Aligned Predictor in the head component, which balances accuracy and speed. Results Experimental results demonstrate that FTR-YOLO achieves the high performance across various evaluation metrics, with a mean Average Precision (mAP) of 90.67%, a Frames Per Second (FPS) of 44, and a parameter size of 24.5M. Conclusion The FTR-YOLO presented in this paper provides a real-time and lightweight solution for the detection of grape diseases. This model effectively assists farmers in detecting grape diseases.

Plant phenotyping relevance

ブドウ葉・植物画像から病害状態を推定するリアルタイム画像解析モデルを開発し、精度と速度を評価しており、病害表現型の取得手法が中心である。

Code and data availability

The supplied blocks describe a self-collected grape disease image dataset (4,800 images) and the FTR-YOLO model, but contain no public deposit, availability URL, or code release for the dataset, images, or analysis code. The Data availability statement section is listed in the outline but its text is not present in the

No evidence-backed public reproduction asset is currently recorded.