摘要
为了实现对仓储环境下货物的精确检测,提出了一种可用于智能仓储机器人的轻量化仓储货物检测方法(EYOLOv4-Lite)。该方法以YOLOv4为基础,引入MobileNetv3重构特征提取网络,在PANet中以深度可分离卷积代替标准卷积,减少模型参数量和运算量。融入改进的convolutional block attention module(CBAM),进一步提升网络检测性能,改进的CBAM采用自适应的一维卷积代替通道注意力模块中的全连接层,采用具有膨胀卷积的残差结构扩大空间注意力模块中的感受野。最后,在RPC商品数据集上进行了网络训练和实验测试,其参数量为11.25 MB,检测时间为14.4 ms,每秒传输帧数达到69.2,平均检测精度为95.43%。实验结果表明,改进后的E-YOLOv4-Lite模型具有精度高、实时性好和轻量化的优点,能够更好地满足仓储环境中的货物检测需求。
To achieve accurate detection of items in the warehousing environment,a lightweight warehousing cargo detection method(E-YOLOv4-Lite)is proposed for use in intelligent warehousing robots.This technique builds on YOLOv4 by introducing the MobileNetv3 network to reconstruct the feature extraction network,replacing standard convolution in PANet with deep separable convolution,and reducing the number of model parameters and processing.The improved convolutional block attention module(CBAM)is integrated to improve network detection performance further.In the channel attention module,the improved CBAM replaces the full connection layer with adaptive one-dimensional convolution,and in the spatial attention module,the residual structure with expansive convolution is used to expand the receptive field.Finally,the network training and experimental tests are conducted through the RPC commodity data set,the number of parameters is 11.25 MB,the detection time is 14.4 ms,the frames per second is 69.2,and the mean average precision is 95.43%.The experimental results reveal that the improved E-YOLOv4-Lite model has the advantages of high accuracy,good real-time performance,and lightweight,allowing it to better meet the needs of cargo detection in storage environments.
作者
王晨
袁庆霓
白欢
李恒
宗文泽
Wang Chen;Yuan Qingni;Bai Huan;Li Heng;Zong Wenze(Key Laboratory of Advanced Manufacturing Technology of the Ministry of Education,Guizhou University,Guiyang 550025,Guizhou,China;School of Mechanical Engineering,Guizhou University,Guiyang 550025,Guizhou,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第24期66-72,共7页
Laser & Optoelectronics Progress
基金
国家自然科学基金(51865004)
贵州省科技厅(黔科合支撑[2020]4Y140号)
贵州大学研究生创新人才计划项目(2021)
横向课题“基于专利分析的工业机器人技术研究”(K19-0204-001)。
关键词
图像处理
目标检测
注意力机制
轻量化
商品数据集
image processing
object detection
attention mechanism
lightweight
product dataset
作者简介
通信作者:袁庆霓,qnyuan@gzu.edu.cn。
