An effective electricity worker identification approach based on Yolov3-Arcface
To address the issues of low efficiency and high complexity of detection models for electric power workers in distribution rooms, the electric power worker identification approach is proposed. The ArcFace loss function is used as the coordinate regression loss of the target box. According to the sco...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2024-02-01
|
Series: | Heliyon |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844024022151 |
_version_ | 1797267684511973376 |
---|---|
author | Qinming Liu Fangzhou Hao Qilin Zhou Xiaofeng Dai Zetao Chen Zengyu Wang |
author_facet | Qinming Liu Fangzhou Hao Qilin Zhou Xiaofeng Dai Zetao Chen Zengyu Wang |
author_sort | Qinming Liu |
collection | DOAJ |
description | To address the issues of low efficiency and high complexity of detection models for electric power workers in distribution rooms, the electric power worker identification approach is proposed. The ArcFace loss function is used as the coordinate regression loss of the target box. According to the score, the template box with the highest score is selected for prediction, which speeds up the rate of convergence. Dimensional clustering is used to set template boxes for bounding box prediction. The experimental results show that the improved YOLOv3 is a high-performance and lightweight model. The electric power worker identification approach proposed in this paper has a high-speed recognition process, accurate recognition results. The effectiveness of the approach is verified with better detection performance and robustness. |
first_indexed | 2024-03-07T23:38:27Z |
format | Article |
id | doaj.art-941515a1beb24cbfbeed6fb8fcfc840e |
institution | Directory Open Access Journal |
issn | 2405-8440 |
language | English |
last_indexed | 2024-04-25T01:20:30Z |
publishDate | 2024-02-01 |
publisher | Elsevier |
record_format | Article |
series | Heliyon |
spelling | doaj.art-941515a1beb24cbfbeed6fb8fcfc840e2024-03-09T09:27:29ZengElsevierHeliyon2405-84402024-02-01104e26184An effective electricity worker identification approach based on Yolov3-ArcfaceQinming Liu0Fangzhou Hao1Qilin Zhou2Xiaofeng Dai3Zetao Chen4Zengyu Wang5Tianhe Power Supply Bureau of Guangzhou Power Supply Bureau, Guangdong Power Co. Ltd., Guangzhou, 510000, ChinaTianhe Power Supply Bureau of Guangzhou Power Supply Bureau, Guangdong Power Co. Ltd., Guangzhou, 510000, ChinaTianhe Power Supply Bureau of Guangzhou Power Supply Bureau, Guangdong Power Co. Ltd., Guangzhou, 510000, ChinaTianhe Power Supply Bureau of Guangzhou Power Supply Bureau, Guangdong Power Co. Ltd., Guangzhou, 510000, ChinaTianhe Power Supply Bureau of Guangzhou Power Supply Bureau, Guangdong Power Co. Ltd., Guangzhou, 510000, ChinaCorresponding author.; Tianhe Power Supply Bureau of Guangzhou Power Supply Bureau, Guangdong Power Co. Ltd., Guangzhou, 510000, ChinaTo address the issues of low efficiency and high complexity of detection models for electric power workers in distribution rooms, the electric power worker identification approach is proposed. The ArcFace loss function is used as the coordinate regression loss of the target box. According to the score, the template box with the highest score is selected for prediction, which speeds up the rate of convergence. Dimensional clustering is used to set template boxes for bounding box prediction. The experimental results show that the improved YOLOv3 is a high-performance and lightweight model. The electric power worker identification approach proposed in this paper has a high-speed recognition process, accurate recognition results. The effectiveness of the approach is verified with better detection performance and robustness.http://www.sciencedirect.com/science/article/pii/S2405844024022151Power distribution roomFace recognitionYOLOv3ArcFaceDetection performance |
spellingShingle | Qinming Liu Fangzhou Hao Qilin Zhou Xiaofeng Dai Zetao Chen Zengyu Wang An effective electricity worker identification approach based on Yolov3-Arcface Heliyon Power distribution room Face recognition YOLOv3 ArcFace Detection performance |
title | An effective electricity worker identification approach based on Yolov3-Arcface |
title_full | An effective electricity worker identification approach based on Yolov3-Arcface |
title_fullStr | An effective electricity worker identification approach based on Yolov3-Arcface |
title_full_unstemmed | An effective electricity worker identification approach based on Yolov3-Arcface |
title_short | An effective electricity worker identification approach based on Yolov3-Arcface |
title_sort | effective electricity worker identification approach based on yolov3 arcface |
topic | Power distribution room Face recognition YOLOv3 ArcFace Detection performance |
url | http://www.sciencedirect.com/science/article/pii/S2405844024022151 |
work_keys_str_mv | AT qinmingliu aneffectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT fangzhouhao aneffectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT qilinzhou aneffectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT xiaofengdai aneffectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT zetaochen aneffectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT zengyuwang aneffectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT qinmingliu effectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT fangzhouhao effectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT qilinzhou effectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT xiaofengdai effectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT zetaochen effectiveelectricityworkeridentificationapproachbasedonyolov3arcface AT zengyuwang effectiveelectricityworkeridentificationapproachbasedonyolov3arcface |