GCW-YOLOv8n: Lightweight Safety Helmet Wearing Detection Algorithm

doi:10.3778/j.issn.1002-8331.2409-0334

Abstract

Abstract: China is a major industrial country in the world. In various construction environments, the falling of construction materials and collisions on construction sites are the main causes of casualties. Accidents caused by head injuries often occur, and wearing safety helmets can ensure the safety of construction personnel to the greatest extent possible. In order to solve the problems of poor timeliness and low management efficiency of manual management, the existing models have strict requirements for computing power, large memory requirements, and handling of load and data transmission delay of industrial equipment, and to achieve edge computing and real-time control, a modified helmet wearing detection algorithm based on YOLOv8n is proposed. Firstly, a new GS-C2f module is proposed, which introduces GhostConv and SE (squeeze and excitation) attention mechanism, effectively reducing the computational complexity of the model and helping the network extract features effectively. Secondly, the CBAM attention mechanism is introduced in the Neck section to enhance the model focus on effective features. Finally, Wise-IoUv3 is introduced to further improve the accuracy of the model. Through experiments, compared with the original YOLOv8n model, this model achieves a 21.24% reduction in computational parameters and a 0.01 improvement in recognition accuracy, achieving satisfactory results between model accuracy and complexity.

Key words: YOLOv8n, safety helmet wearing detection, GhostConv, CBAM attention mechanism

摘要： 我国是世界工业大国，在各种施工环境下，施工材料的坠落以及施工现场的碰撞是造成伤亡事故的主要原因。因头部伤害而导致的伤亡事故时有发生，而佩戴安全帽可以最大程度上保证施工人员的安全。为解决人工管理的时效性差、管理效率低下，现有模型对算力需求较为严苛，内存需求大，以及工业设备在处理负载和数据传输延迟的问题，实现边缘计算、实时管控，提出一种基于YOLOv8n的改进安全帽佩戴检测算法。提出了一种新的GS-C2f模块，该模块引入GhostConv及SE（squeeze-and-excitation）注意力机制，有效降低了模型计算量及其复杂度，同时帮助网络有效提取特征。在Neck部分引入CBAM注意力机制，使模型加强对有效特征的关注。引入Wise-IoUv3进一步提高模型的精度。经实验，该模型对比原YOLOv8n模型，在计算参数下降21.24%的同时，识别精度提升了0.01，在模型精度和复杂度之间均取得了令人满意的效果。

关键词: YOLOv8n, 安全帽佩戴检测, GhostConv, CBAM注意力机制

XU Zhuang, QIAN Yurong, YAN Feng. GCW-YOLOv8n: Lightweight Safety Helmet Wearing Detection Algorithm[J]. Computer Engineering and Applications, 2025, 61(3): 144-154.

徐壮, 钱育蓉, 颜丰. GCW-YOLOv8n：轻量级安全帽佩戴检测算法[J]. 计算机工程与应用, 2025, 61(3): 144-154.

References

[1] 唐凯, 陈陆, 张洲境, 等. 我国建筑施工行业生产安全事故统计分析及对策[J]. 建筑安全, 2020, 35(9): 40-43.
TANG K, CHEN L, ZHANG Z J, et al. Statistical analysis and countermeasures of production safety accidents in my country’s construction industry[J]. Construction Safety, 2020, 35(9): 40-43.
[2] KELM A, LAU?AT L, MEINS-BECKER A, et al. Mobile passive radio frequency identification (RFID) portal forautomated and rapid control of personal protective equipment (PPE) on construction sites[J]. Automation in Construction, 2013, 36: 38-52.
[3] DONG S, HE Q, LI H, et al. Automated PPE misuse identification and assessment for safety performance enhancement[C]//Proceedings of the 2015 International Conference on Construction and Real Estate Management, 2015: 204-214.
[4] 朱富云, 戴相龙, 傅靖, 等. 基于视频监控的变电站内安全帽检测算法研究[J]. 电网与清洁能源, 2018, 34(12): 71-76. ZHU F Y, DAI X L, FU J, et al. Research on hard hat detection algorithm in substation based on video surveillance[J]. Power System and Clean Energy, 2018, 34(12): 71-76.
[5] 贾峻苏, 鲍庆洁, 唐慧明. 基于可变形部件模型的安全头盔佩戴检测[J]. 计算机应用研究, 2016, 33(3): 953-956.
JIA J S, BAO Q J, TANG H M. Method for detecting safety helmet based on deformable part model[J]. Application Research of Computers, 2016, 33(3): 953-956.
[6] ZHENG Q, TIAN X, YU Z, et al. MobileRaT: a lightweight radio transformer method for automatic modulation classification in drone communication systems[J]. Drones, 2023, 7(10): 596.
[7] ZHENG Q, SERGIO S, TIAN X, et al. A real-time constellation image classification method of wireless communication signals based on the lightweight network MobileViT[J]. Cognitive Neurodynamics, 2023, 18(2): 659-671.
[8] SHAOQING R, KAIMING H, ROSS G, et al. Faster R-CNN: towards real-time object detection with regionproposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[9] LIU W, ANGUELOV D, ERHAN D, et al. SSD: singles hot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, October 11-14, 2016: 21-37.
[10] REDMON J, DIVVALA K S, GIRSHICK B R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[11] 张锦, 屈佩琪, 孙程, 等. 基于改进YOLOv5的安全帽佩戴检测算法[J]. 计算机应用, 2022, 42(4): 1292-1300.
ZHANG J, QU P Q, SUN C, et al. Safety helmet wearing detection algorithm based on improved YOLOv5 [J]. Journal of Computer Applications, 2022, 42(4): 1292-1300.
[12] 苏鹏, 刘美, 马思群. 基于改进YOLOX-s的安全帽检测[J]. 计算机系统应用, 2023, 32(7): 145-154.
SU P, LIU M, MA S Q. Safety helmet detection based on improved YOLOX-s[J]. Computer Systems & Applications, 2023, 32(7): 145-154.
[13] 韩飞腾, 刘永强, 房玉东, 等. 基于注意力机制的安全帽佩戴状态检测模型[J]. 中国安全生产科学技术, 2024, 20(8): 196-202.
HAN F T, LIU Y Q, FANG Y D, et al. Detection model for wearing status of safety helmet based on attention mechanism[J]. Journal of Safety Science and Technology, 2024, 20(8): 196-202.
[14] 王亚军, 孙占冬. 基于深度学习的安全帽佩戴检测算法研究[J]. 中阿科技论坛 (中英文), 2024(7): 85-89.
WANG Y J, SUN Z D. Research on safety cap wearing detection algorithm based on deep learning[J]. China-Arab States Science and Technology Forum, 2024(7): 85-89.
[15] 杨国亮, 洪鑫芳, 盛杨杨, 等. 基于表观特征增强及融合的安全帽检测算法[J/OL]. 计算机工程与应用: 1-12[2024-10-26]. https://kns-cnki-net.webvpn.xju.edu.cn:8040/kcms/detail/11.2127.TP.20240819.1123.014.html.
YANG G L, HONG X F, SHENG Y Y, et al. Helmet detection algorithm based on appearance feature enhancement and fusion[J/OL]. Computer Engineering and Applications: 1-12[2024-10-26]. https://kns-cnki-net.webvpn.xju.edu.cn:8040/kcms/detail/11.2127.TP.20240819.1123.014.html.
[16] 丁玲, 缪小然, 胡建峰, 等. 改进 YOLOv8s与DeepSORT的矿工帽带检测及人员跟踪[J].计算机工程与应用, 2024, 60(5): 328-335.
DING L, MIAO X R, HU J F, et al. Improved miner chin strap detection and personnel tracking with YOLOv8s and DeepSORT[J]. Computer Engineering and Applications, 2024, 60(5): 328-335.
[17] 肖振久, 严肃, 曲海成. 基于多重机制优化YOLOv8的复杂环境下安全帽检测方法[J]. 计算机工程与应用, 2024, 60(21): 172-182.
XIAO Z J, YAN S, QU H C. Safety helmet detection method in complex environment based on multi-mechanism optimization of YOLOv8[J]. Computer Engineering and Applications, 2024, 60(21): 172-182.
[18] 李永辉, 袁亮, 何丽, 等. 化工园区场景下安全帽佩戴状态检测算法研究[J]. 计算机工程与应用, 2024, 60(12): 111-117.
LI Y H, YUAN L, HE L, et al. Research on safety helmet wearing detection algorithmin chemical industry park scenarios[J]. Computer Engineering and Applications, 2024, 60(12): 111-117.
[19] 李猛坤, 袁晨, 王琪, 等. 基于改进Yolov8算法的在线听课行为识别模型研究[J/OL]. 计算机工程: 1-10[2024-06-08]. https://kns-cnki-net.webvpn.xju.edu.cn:8040/kcms/detail/31.1289.tp.20240312.1739.002.html.
LI M K, YUAN C, WANG Q, et al. Research on online listening behavior recognition model based on improved Yolov8 algorithm[J/OL]. Computer Engineering: 1-10 [2024-06-08]. https://kns-cnki-net.webvpn.xju.edu.cn:8040/kcms/detail/31.1289.tp.20240312.1739.002.html.
[20] HAN K, WANG Y H, TIAN Q, et al. Ghostnet: more features from cheap operations[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1580-1589.
[21] JIE H, LI S, SAMUEL A, et al. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7132-7141.
[22] WOO S, PARK J, LEE J Y, et al. ?CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV), 2018: 3-19.
[23] TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv: 2301.10051, 2023.
[24] WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-artf or realtime object detectors[C]//Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition,2023: 7464-7475.
[25] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[26] JOCHER G, STOKEN A, BOROVEC J, et al. Ultralyti cs/yolov5: v5[EB/OL]. (2022-11-22) [2024-01-28]. https://github.com/ultralytics/yolov5.
[27] 孙光灵, 黄磊, 吴倩. 基于KD-YOLO的轻量化安全帽佩戴检测方法[J]. 淮北师范大学学报 (自然科学版), 2024, 45(2): 41-48.
SUN G L, HUANG L, WU Q. Lightweight safety helmet wearing detection method based on KD-YOLO[J]. Journal of Huaibei Normal University (Natural Sciences), 2024, 45(2): 41-48.
[28] 李冰涛, 李大海. 面向小目标的YOLOv5s安全帽佩戴检测[J]. 计算机系统应用, 2023, 32(8): 221-229.
LI B T, LI D H. YOLOv5s-based helmet wearing detection for small targets[J]. Computer Systems & Applications, 2023, 32(8): 221-229.
[29] 李明山, 韩清鹏, 张天宇, 等. 改进SSD的安全帽检测方法[J]. 计算机工程与应用, 2021, 57(8): 192-197.
LI M S, HAN Q P, ZHANG T Y, et al. Safety helmet detection method of improved SSD[J]. Computer Engineering and Applications, 2021, 57(8): 192-197.
[30] 肖体刚, 蔡乐才, 高祥, 等. 改进YOLOv3的安全帽佩戴检测方法[J]. 计算机工程与应用, 2021, 57(12): 216-223.
XIAO T G, CAI L C, GAO X, et al. Improved YOLOv3 helmet wearing detection method[J]. Computer Engineering and Applications, 2021, 57(12): 216-223.
[31] 王坡, 罗红旗. 改进YOLOv5的安全帽佩戴检测算法[J]. 现代计算机, 2023, 29(24): 40-45.
WANG P, LUO H Q. Improved helmet wearing detection method of YOLOv5[J]. Modern Computer, 2023, 29(24): 40-45.
[32] 韩锟栋, 张涛, 彭玻, 等. 基于改进 YOLOv5 的安全帽检测算法 [J]. 现代电子技术, 2024, 47(5): 85-92.
HAN K D, ZHANG T, PENG B, et al. Safety helmet detection algorithm based on improved YOLOv5[J]. Modern Electronics Technique, 2024, 47(5): 85-92.
[33] 张欣毅, 张运楚, 王菲, 等. 改进 YOLOv7 的轧钢车间安全帽佩戴检测算法[J]. 计算机测量与控制, 2024, 32(7): 15-22.
ZHANG X Y, ZHANG Y C, WANG F, et al. Improved helmet wearing detection algorithm in steel rolling workshop for YOLOv7[J]. Computer Measurement& Control, 2024, 32(7): 15-22.