典型文献
Power Plant Indicator Light Detection System Based on Improved YOLOv5
文献摘要：
Electricity plays a vital role in daily life and economic development. The status of the indicator lights of the power plant needs to be checked regularly to ensure the normal supply of electricity. Aiming at the problem of a large amount of data and different sizes of indicator light detection, we propose an improved You Only Look Once vision 5 (YOLOv5) power plant indicator light detection algorithm. The algorithm improves the feature extraction ability based on YOLOv5s. First, our algorithm enhances the ability of the network to perceive small objects by combining attention modules for multi-scale feature extraction. Second, we adjust the loss function to ensure the stability of the object frame during the regression process and improve the conver-gence accuracy. Finally, transfer learning is used to augment the dataset to improve the robustness of the algorithm. The experimental results show that the average accuracy of the proposed squeeze-and-excitation YOLOv5s (SE-YOLOv5s) algorithm is increased by 4.39％to 95.31％compared with the YOLOv5s algorithm. The proposed algorithm can better meet the engineering needs of power plant indicator light detection.
文献关键词：
中图分类号：
作者姓名：
Yunzuo Zhang;Kaina Guo
作者机构：
School of Infor-mation Science and Technology,Shijiazhuang Tiedao Uni-versity,Shijiazhuang 050043,China
文献出处：
引用格式：
[1]Yunzuo Zhang;Kaina Guo-.Power Plant Indicator Light Detection System Based on Improved YOLOv5)[J].北京理工大学学报（英文版）,2022(06):605-612
A类：
B类：
Power,Plant,Indicator,Light,Detection,System,Based,Improved,Electricity,plays,vital,role,daily,life,economic,development,status,indicator,lights,power,plant,needs,checked,regularly,ensure,normal,supply,electricity,Aiming,problem,large,amount,different,sizes,detection,improved,You,Only,Look,Once,vision,algorithm,improves,feature,extraction,YOLOv5s,First,our,enhances,network,perceive,small,objects,by,combining,attention,modules,multi,scale,Second,adjust,loss,function,stability,frame,during,regression,process,conver,gence,accuracy,Finally,transfer,learning,used,augment,dataset,robustness,experimental,results,show,that,average,proposed,squeeze,excitation,SE,increased,compared,can,better,meet,engineering
AB值：
0.595721
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
