A high-precision soybean leaf disease detection model based on improved YOLOv8

In the detection of soybean diseases, the existing detection methods are less accurate and more traditional, therefore, an improved YOLOv8 soybean disease detection model DDV-YOLOv8 is proposed. The model adopts Dynamic Snake Convolution convolution (DSC) method and Variable Attention DAttention (DAT) module for feature extraction, and the extracted features are efficiently fused by one-time aggregated feature fusion module (VoV-GSCSP) to significantly improve detection performance of the model. The experimental results show that the accuracy of DDV-YOLOv8 reaches 99.0%, which is 4.3% higher than that of the original YOLOv8 model, and can better meet the current soybean disease detection needs.