基于改进 YOLOv7 的苹果叶病害目标检测

Abstract

Apple leaf diseases significantly threaten the yield and quality of apples. In order to detect apple leaf diseases in a timely and accurate manner, this study proposed a detection method for apple leaf diseases based on an improved YOLOv7 model. The method integrated a Similarity-based Attention Mechanism(SimAM) into the traditional YOLOv7 model. Additionally, the regression loss function is modified from Complete Intersection over Union (CIoU) to Structured Intersection over Union (SIoU). Experimental results demonstrates that the improved model exhibits an overall recognition precision of 92%, a recall rate of 99%, and a mean average precision (mAP) of 96.1%. These metrics show a respective improvement of 14.4%, 38.85%, and 18.69% compared to the preimproved YOLOv7. When compared with seven other target detection models in comparative experiments, the improved YOLOv7 model achieves higher accuracy, lower rates of missed and false detections in disease target detection. The model excels in detecting disease categories in complex environments and identifying small targets at early disease stages. It can provide technical support for effective detection of apple leaf diseases.