基于改进YOLOv5的草莓病害检测

Detection of strawberry disease based on improved YOLOv5

为解决草莓病害识别技术落后,识别精度不高的问题,在YOLOv5的基础上,提出了一种改进YOLOv5的草莓病害检测算法.针对草莓病害特征引入了BoTNet模块,并将原有的NMS替换为GIoU-NMS,提升了对草莓病害的检测精度.改进后的YOLOv5算法相较于原算法,精确度提升了2.1%,平均精度AP上升了1.2%.实验结果表明,改进后的YOLOv5草莓病害检测算法提升了算法的效率和性能,检测效果优于传统的YOLOv5s算法.

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 detection algorithm improved the efficiency and performance of the algorithm,and the detection effect was better than the traditional YOLOv5s algorithm.