Detection of strawberry disease based on improved YOLOv5
In order to solve the problem of backward strawberry disease recognition technology and low recognition accuracy,this paper proposes an improved strawberry disease detection algorithm based on YOLOv5.According to the characteristics of strawberry diseases,BoTNet module is introduced,and the original NMS is replaced by GIoU-NMS,which improves the detection accuracy of strawberry diseases.Compared with the original algorithm,the accuracy of the improved YOLOv5 algorithm is increased by 2.1 percentage points,and the average accuracy AP is increased by 1.2 percentage points.Experimental results showed that the improved YOLOv5 strawberry disease de-tection algorithm improved the efficiency and performance of the algorithm,and the detection effect was better than the traditional YOLOv5s algorithm.
国家科技期刊平台
NSTL
万方数据
