基于改进YOLOv3的电容器外观缺陷检测

针对部署于有限算力平台的YOLOv3 (you only look once v3)算法对电容器外观缺陷存在检测速度较慢的问题,提出了基于YOLOv3算法改进的轻量化算法MQYOLOv3.首先采用轻量化网络MobileNet v2作为特征提取模块,通过利用深度可分离式卷积替换一般卷积操作,使得模型的参数量大幅度降低进而...

Capacitor appearance defect detection based on improved YOLOv3

Aiming at the problem that the you only look once v3(YOLOv3) algorithm deployed on the limited computing power platform has a slow detection speed for the appearance defects of capacitors,an improved lightweight algorithm MQYOLv3based on YOLOv3algorithm is proposed.First,the lightweight network MobileNet v2is used as the feature extraction module,and by replacing the general convolution operation with the d eep separable convolution, the amount of model parameters is greatly reduced and the detection speed of the model is improved,but also bring the reduction of detection accuracy.Then,the spatial pyramid pooling str ucture is embedded in the network structure to realize the fusion of local and global features,the distance intersection over union (DIoU) loss func tion is introduced to optimize the intersection over union (IoU) loss function,and the Mish activation function is used optimize the Leaky ReLU activation function to improve the detection accuracy of the model.This paper uses a self-made capacitor appe arance defect data set for experiments.The mean average precision (mAP) of the lightweight MQYOLOv3algorithm is 87.96%,whic h is 1.16% lower than before optimization,and the detection speed is increased from 1.5FPS to 7.7FPS. Experiments show that the lightweight MQYOLOv3algorithm designed in this paper improves the detection spe ed while ensuring the detection accuracy.