Research on real-time detection algorithm of safety helmets in complex operating environment

Tong Xiao, Guodong He, Mingxing Fang, Shaoguo Xie

Abstract


In order to solve the problems of low detection accuracy when the background of safety helmets is complex at construction sites,
and the safety helmet target is too small to be easily detected, this paper proposes a real-time detection algorithm for safety helmets in complex working environments based on the YOLOv5 framework. An improved YOLOv5 detection algorithm is proposed to address the issues
of missing safety helmets and low detection accuracy in the construction environment. Adding an attention mechanism to the YOLOv5 backbone network, adding a detection layer at the neck of the network, and integrating an ASFF module at the neck of the network have better
detection performance when facing complex backgrounds and dense helmet detection; The experimental results show that compared to the
original YOLOv5 model, the improved average accuracy has increased by 2.4%, reaching 91.3%, effectively improving the detection ability
of safety helmets in complex environments.

Keywords


YOLOv5s; CoordAtt; ASFF: henlmet

Full Text:

PDF

Included Database


References


[1] LI Z Q, LIU H. Helmet wearing detection algorithm based on deep learning[J]. Computer Applications and Software, 2022,

39(6):194-202.

[2] DAI J F, LI Y, HE K M, SUN J. R-FCN: object detection via region-based fully convolutional networks[C]// Proceedings of the

30th International Conference on Neural Information Processing Systems, Barcelona Spain, 5-12 Dec, 2016. New York: Curran Associates

Inc, 2016: 379- 387.

[3] Ming Q L, Yao C H, X B L. Dilated Light-Head R-CNN using tri-center loss for driving behavior recognition[J]. Image and Vision

Computing,2019,90(C):108-121.

[4] Li J , Liang X , Shen S , et al. Scale-Aware Fast R-CNN for Pedestrian Detection[J]. IEEE Transactions on Multimedia,

2017,20(4):985-996.

[5] HE K,GKIOXARI G,DOLLAR P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence,2020,42(2):386-397

[6] LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector[C]//European conference on computer vision.

Springer, Cham,2016:21-37.

[7] GE Z，LIU S，WANG F, et al. YOLOX: Exceeding YOLO Series in 2021[J]. 10.48550/arXiv.2107.08430, 2021.

[8] DUAN K，BAI S，XIE L, et al. CenterNet: Keypoint Triplets for Object Detection[C]//Proceedings of the IEEE/ CVF international conference on computer vision. 2019: 6569-657

[9] BOCHKOVSKIY A, WANG C Y, LIAO H-Y M. YOLOv4: Optimal Speed and Accuracy of Object Detection[J].In IEEE Confer_x005fence on Computer Vision and Pattern Recognition(CVPR),2020

[10] SUN G D，LI C，ZHANG H.Safety helmet wearing detection method fused with self-attention mechanism[J].Computer Engineering and Applications，2022，58（20）：300-304.

[11] FU D S, GAO L, HU T, et al. Research on safety helmet detection algorithm of power workers based on improved YOLOv5[J].

Journal of Physics(Conference Series),2022, 2171:012006.

[12] WANG Y L. Construction site helmet wearing monitoring algorithm based on YOLOv5[J]. Information Technology and Informa_x005ftization2022733-36.

[13] Huang, Ke and Zhang, Limin. ‘Helmet-wearing Detection with Intelligent Learning Approach’. Journal of Intelligent & Fuzzy

Systems, 2023




DOI: https://doi.org/10.18686/esta.v10i6.661

Refbacks

  • There are currently no refbacks.


Copyright (c) 2023 Tong Xiao,Guodong He,Mingxing Fang ,Shaoguo Xie