摘要
针对电子行业制造机器人对电子元器件检测精度低和速度慢的问题,提出基于改进YOLOv4的电子元器件检测方法。对网络结构进行改进,利用深度可分离卷积代替PAN网络中的传统卷积,提高检测速度;利用一种具有线性瓶颈的逆残差结构代替CSP darknet53主干网络,降低模型参数,进一步提高检测效率;在检测网络YOLO head前添加注意力机制,提高检测精度。模拟工业传送带环境建立了电子元器件数据集并进行数据增强,相较于原算法,精度(mAP)提高了1.31%,速度提高了16.34 fps,权重大小从245下降到41.20 MB。研究可为相关电子行业制造机器人的研制提供技术参考。
Aiming at the problem of low accuracy and slow speed of electronic components detection by manufacturing robots in the electronics industry, an electronic component detection method based on improved YOLOv4 is proposed. The network structure was improved by using depth-separable convolution instead of the traditional convolution in PAN networks to improve the detection speed. An inverse residual structure with a linear bottleneck was used instead of the CSP darknet53 backbone network to reduce the model parameters and further improve the detection efficiency. An attention mechanism was added before the YOLO head of the detection network to improve the detection accuracy. A data set of electronic components was established to simulate the industrial environment with conveyor belt and the data was enhanced. Compared with the original algorithm, the accuracy(mAP) is increased by 1.31%, the speed is increased by 16.34 fps, and the weight size is reduced from 245 to 41.20 MB. The research can provide technical reference for the development of manufacturing robots in the electronics industry.
作者
张明路
郭策
吕晓玲
张艳
Zhang Minglu;Guo Ce;Lv Xiaoling;Zhang Yan(School of Mechanical Engineering,Hebei University of Technology,Tianjin 300132,China)
出处
《电子测量与仪器学报》
CSCD
北大核心
2021年第10期17-23,共7页
Journal of Electronic Measurement and Instrumentation
基金
国家重点研发计划(2017YFB1303701)
国家重点自然基金(61733001)项目资助。
关键词
目标检测
深度学习
可分离卷积
注意力机制
电子元器件
object detection
deep learning
separable convolution
attention mechanism
electronic components
