基于改进YOLOv7-Tiny的施工安全帽检测
Construction Safety Helmet Detection Based on Improved YOLOv7-Tiny
DOI: 10.12677/csa.2025.152034, PDF,   
作者: 赵 盛*, 蔡昌新#：长江大学电子信息与电气工程学院，湖北 荆州
关键词: 改进YOLOv7-Tiny；安全帽；注意力机制；WIoUV3；Improved YOLOv7-Tiny； Helmet； Attention Mechanism； WIoUv3
摘要: 为解决现有施工场地中，部署轻量化模型在资源受限的无GPU嵌入式平台面对密度大、目标小、环境复杂时检测安全帽精度低的问题，以YOLOv7-Tiny为基础，提出一种基于改进YOLOv7-Tiny的安全帽检测算法。通过对主干以及对SPPCSPC的改进，并且在颈部网络的不同位置加入SimAM注意力机制，同时采用WIoUv3为损失函数来改进头部网络。在SHWD安全帽数据集的实验结果表明，与原YOLOv7-Tiny模型相比，该模型的mAP提高了1.32%，证明该模型精确度相较于原模型有较大提升，能有效提高复杂施工场景下的检测精度。
Abstract: In order to solve the problem of low accuracy in detecting safety helmets on resource limited GPU free embedded platforms with high density, small targets, and complex environments in existing construction sites, a safety helmet detection algorithm based on improved YOLOv7-Tiny is proposed. By improving the backbone and SPPCSPC, and adding SimAM attention mechanism at different positions in the neck network, WIoUv3 is used as the loss function to improve the head network. The experimental results on the SHWD safety helmet dataset show that compared with the original YOLOv7-Tiny model, the mAP of this model has increased by 1.32%, proving that the accuracy of this model has been greatly improved compared to the original model and can effectively improve the detection accuracy in complex construction scenarios.
文章引用：赵盛, 蔡昌新. 基于改进YOLOv7-Tiny的施工安全帽检测[J]. 计算机科学与应用, 2025, 15(2): 71-82. https://doi.org/10.12677/csa.2025.152034

参考文献

[1] 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.
[2] 胡启军, 潘学鹏, 余洋, 等. 复杂作业环境下安全帽实时检测算法研究[J]. 安全与环境学报, 2024, 24(5): 1904-1912.
[3] Li, H., Li, X., Luo, X. and Siebert, J. (2017) Investigation of the Causality Patterns of Non-Helmet Use Behavior of Construction Workers. Automation in Construction, 80, 95-103. [Google Scholar] [CrossRef] 
[4] 李政谦, 潘健, 潘岚川, 等. 基于改进EfficientDet算法的安全帽佩戴检测[J]. 计算机应用与软件, 2023, 40(1): 196-204.
[5] 李华, 王岩彬, 益朋, 等. 基于深度学习的复杂作业场景下安全帽识别研究[J]. 中国安全生产科学技术, 2021, 17(1): 175-181.
[6] 宋晓凤, 吴云军, 刘冰冰, 等. 改进YOLOv5s算法的安全帽佩戴检测[J]. 计算机工程与应用, 2023, 59(2): 194-201.
[7] 王晓龙, 江波. 基于改进YOLOX-m的安全帽佩戴检测[J]. 计算机工程, 2023, 49(12): 252-261
[8] Wang, C., Bochkovskiy, A. and Liao, H.M. (2023) YOLOv7: Trainable Bag-Of-Freebies Sets New State-Of-The-Art for Real-Time Object Detectors. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, 17-24 June 2023, 7464-7475. [Google Scholar] [CrossRef] 
[9] 姚景丽, 程光, 万飞, 等. 改进YOLOv8的轻量化轴承缺陷检测算法[J]. 计算机工程与应用, 2024, 60(21): 205-214.
[10] 廖晓辉, 谢子晨, 辛忠良, 等. 基于轻量化YOLOv5的电气设备外部缺陷检测[J]. 郑州大学学报(工学版), 2024, 45(4): 117-124.
[11] 郭玲, 于海雁, 周志权. 基于SimAM注意力机制的近岸船舶检测方法[J]. 哈尔滨工业大学学报, 2023, 55(5): 14-21.
[12] Shi, Y., Wu, J., Zhao, S.X., et al. (2022) Rethinking the Detection Head Configuration for Traffic Object Detection. arXiv: 2210.03883.
https://arxiv.org/abs/2210.03883.pdf
[13] 杨杰, 蒋严宣, 熊欣燕. 结合Transformer和SimAM轻量化路面损伤检测算法[J]. 铁道科学与工程学报, 2024, 21(9): 3911-3920.
[14] Bochkovskiy, A., Wang, C.Y. and Liao, H.Y.M. (2020) YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv: 2004.10934.
https://arxiv.org/abs/2004.10934
[15] He, K., Zhang, X., Ren, S. and Sun, J. (2015) Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37, 1904-1916. [Google Scholar] [CrossRef] [PubMed]
[16] 徐印赟, 江明, 李云飞, 等. 基于改进YOLO及NMS的水果目标检测[J]. 电子测量与仪器学报, 2022, 36(4): 114-123
[17] Tong, Z., Chen, Y., Xu, Z., et al. (2023) Wise-IoU: Bounding Box Regression Loss with Dynamic Focusing Mechanism. arXiv: 2301.10051.
[18] 贾亮, 林铭文, 戚丽瑾, 等. 面向无人机航拍图像的多尺度目标检测研究[J]. 半导体光电, 2024, 45(3): 501-507+514.
[19] 孙迟, 刘晓文. 基于YOLOv7-Tiny改进的矿工安全帽检测[J]. 中国科技论文, 2023, 18(11): 1250-1256, 1274.