Research on Lightweight Detection of Pests and Diseases Based on Improved YOLOv11

Accurate detection of pests and diseases is crucial for agricultural production, as it can effectively reduce the use of pesticides and increase crop yields. However, existing pest and disease detection algorithms still have shortcomings in terms of lightweight and detection accuracy. This article proposes a lightweight detection algorithm for pests and diseases based on improved YOLOv11. By introducing PP LCNet backbone network, MPDIoU loss function, multi-scale SimAM attention mechanism, and channel pruning technology, the detection accuracy and running efficiency of the model are significantly improved. The experimental results show that the improved algorithm performs well in pest and disease detection tasks, with high accuracy, recall, and model lightweighting, providing an effective solution for pest and disease detection in practical applications.