Liu Yifan, Yu Qiudong, Geng Shuze
College of Information Technology Engineering, Tianjin University of Technology and Education, Tianjin, China.
Front Plant Sci. 2024 Feb 23;15:1269423. doi: 10.3389/fpls.2024.1269423. eCollection 2024.
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.
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.
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.
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.
葡萄在其整个生长周期中容易感染各种病害，未能及时控制这些病害会导致产量下降，甚至颗粒无收。因此，有效的病害防治对于实现葡萄产量最大化至关重要。准确的病害识别在这一过程中起着关键作用。在本文中，我们提出了一种名为融合变压器YOLO的实时轻量级检测模型，用于检测4种葡萄病害。数据集的主要来源包括从中国北方种植园采集的RGB图像。
首先，我们引入了一种轻量级高性能VoVNet，它利用了幽灵卷积和可学习下采样层。通过将有效的挤压和激励块以及残差连接集成到OSA模块中，对该主干进行了进一步改进。这些增强措施有助于在保持轻量级网络的同时提高检测精度。其次，在颈部组件中采用了一种改进的双流PAN+FPN结构与实时变压器，通过将二维位置嵌入和单尺度变压器编码器合并到最后一个特征图中。这种修改实现了实时性能，并提高了检测小目标的准确性。最后，我们在头部组件中采用了基于改进的任务对齐预测器的解耦头，它平衡了准确性和速度。
实验结果表明，FTR-YOLO在各项评估指标上均取得了高性能，平均精度均值（mAP）为90.67%，每秒帧数（FPS）为44，参数大小为24.5M。
本文提出的FTR-YOLO为葡萄病害检测提供了一种实时轻量级解决方案。该模型有效地帮助农民检测葡萄病害。
