Research on apple leaf disease detection based on improved YOLOv5
[Objective]Propose a disease target detection algorithm based on improved YOLOv5 model,to achieve automatic recognition of apple leaf diseases and solve the problems of miss and false detection in the YOLOv5 detection model.[Methods]Based on the YOLOv5 model improved by convolutional neural network,weighted bidirectional feature pyramid network(BiFPN)feature fusion method was used to effectively improve the adverse effect of PANet on multi-scale feature fusion.The CBAM module was added to enable the network to more accurately locate and identify apple leaf diseases and establishing an algorithm model for detecting apple leaf diseases.The ATCSP module and top-down feature fusion method were used to enhance the detection performance of the model for multi-scale diseases.The model was compared with SSD,YOLOv4,YOLOv6,and YOLOv7 models.[Results]The improved YOLOv5 detection algorithm model significantly improved the accuracy of apple leaf disease detection.Compared with the original algorithm,accuracy(P)increased by 5.1%,reaching 90.8%;average precision mean(mAP)increased by 1.2%,reaching 93.4%;the model size reduced by 21.4 MB.The accuracy of improved YOLOV5 algorithm was 11.3,4.4,4.2,and 3.6 percentage points higher than SSD,YOLOv4,YOLOv6,and YOLOv7 models,respectively.[Conclusion]A convolutional neural network-based improved YOLOv5 apple leaf disease detection model was proposed.The improved YOLOv5 model had fast detection speed,high detection accuracy,and small size,which can achieve automatic recognition of apple leaf diseases.
国家科技期刊平台
NSTL
万方数据
