建筑工地安全帽佩戴检测算法研究综述
A Review of Research on Algorithms for Detecting Safety Helmet Wearing on Construction Sites
DOI: 10.12677/CSA.2024.142018, PDF,    科研立项经费支持
作者: 彭 燕, 谢乐源, 吴宗义, 杨孟飞：重庆科技学院安全工程学院，重庆
关键词: 深度学习；目标检测；计算机视觉；安全帽；建筑工地；Deep Learning； Target Detection； Computer Vision； Safety Helmet； Construction Site
摘要: 为了减少建筑工地事故的发生，提高建筑项目的安全保障，基于深度学习的建筑工人安全帽佩戴目标检测方法成为了一个重要的研究领域。该方法通过利用建筑工地的监控实时提取图像和视频信息，并自动识别工人是否正确佩戴安全帽，具有较高的准确率与实时性，可提升建筑行业安全管理的智能化水平。本综述旨在综合分析近年来在深度学习环境下的安全帽佩戴检测算法研究现状，分别从数据集与评价指标、两阶段目标检测、单阶段目标检测及改进等方面总结归纳国内外学者的研究成果，分析这些方法的优点、局限性以及当前的难点，并给出建议和展望，为后续研究者提供参考和借鉴。
Abstract: In order to reduce the occurrence of construction site accidents and improve the safety and security of construction projects, the deep learning-based target detection method for construction workers’ helmet wearing has become an important research field. The method extracts image and video information in real time by utilizing the surveillance of the construction site and automatically identifies whether the worker is wearing the helmet correctly, which has high accuracy and real-time performance, and can improve the intelligent level of safety management in the construction industry. This review aims to comprehensively analyze the current research status of helmet wearing detection algorithms under deep learning environment in recent years, summarize and generalize the research results of scholars at home and abroad from the aspects of dataset and evaluation indexes, two-phase target detection, single-phase target detection, and improvement, respectively, and analyze the advantages, limitations, and current difficulties of these methods, as well as give suggestions and outlooks, so as to provide references and suggestions for the subsequent researchers.
文章引用：彭燕, 谢乐源, 吴宗义, 杨孟飞. 建筑工地安全帽佩戴检测算法研究综述[J]. 计算机科学与应用, 2024, 14(2): 173-182. https://doi.org/10.12677/CSA.2024.142018

参考文献

[1] 赵永强, 饶元, 董世鹏, 等. 深度学习目标检测方法综述[J]. 中国图象图形学报, 2020, 25(4): 629-654.
[2] 朱豪, 周顺勇, 刘学, 等. 基于深度学习的单阶段目标检测算法综述[J]. 工业控制计算机, 2023, 36(4): 101-103.
[3] 杨锋, 丁之桐, 邢蒙蒙, 等. 深度学习的目标检测算法改进综述[J]. 计算机工程与应用, 2023, 59(11): 1-15.
[4] 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] 
[5] 中华人民共和国住房和城乡建设部办公厅. 住房和城乡建设部办公厅关于2020年住房市政工程安全事故情况通报[EB/OL].
https://www.mohurd.gov.cn/gongkai/zhengce/zhengcefilelib/202210/20221026_768565.html, 2021-05-21.
[6] Everingham, M., Gool, L.V., Williams, C., et al. (2010) The Pascal Visual Object Classes (VOC) Challenge. International Journal of Computer Vision, 88, 303-338. [Google Scholar] [CrossRef] 
[7] Lin, T.Y., Maire, M., Belongie, S., et al. (2014) Microsoft COCO: Common Objects in Context. In: Fleet, D., Pajdla, T., Schiele, B. and Tuytelaars, T., Eds., Computer Vision—ECCV 2014, Springer, Cham, 740-755. [Google Scholar] [CrossRef] 
[8] Deng, J., Dong, W., Socher, R., et al. (2009) ImageNet: Alarge-Scale Hier-archical Image Database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, 20-25 June 2009, 248-255. [Google Scholar] [CrossRef] 
[9] Wojek, C., Dollar, P., Schiele, B. and Perona, P. (2012) Pedestrian Detection: An Evaluation of the State of the Art. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 743-761. [Google Scholar] [CrossRef] 
[10] Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B. and Hu, S. (2016) Traffic-Sign Detection and Classification in the Wild. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 27-30 June 2016, 2110-2118. [Google Scholar] [CrossRef] 
[11] Razakarivony, S. and Jurie, F. (2015) Vehicle Detection in Aerial Imagery: A Small Target Detection Benchmark. Journal of Visual Communication and Image Representation, 34, 187-203.
[12] 王英郦. 基于YOLOv5的施工现场安全帽佩戴监测算法[J]. 信息技术与信息化, 2022(7): 33-36.
[13] Girshick, R. (2015) Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 7-13 December 2015, 1440-1448. [Google Scholar] [CrossRef] 
[14] Ren, S., He, K., Girshick, R. and Sun, J. (2017) Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39, 1137-1149. [Google Scholar] [CrossRef] 
[15] Nong, S. and Ni, Z.H. (2017) Gesture Recognition Based on R-FCN in Complex Scenes. Journal of Huazhong University of Science and Technology, 45, 54-58
[16] 李政谦, 刘晖. 基于深度学习的安全帽佩戴检测算法综述[J]. 计算机应用与软件, 2022, 39(6): 194-202.
[17] Huang, S., Liu, L., Fu, X., et al. (2022) Overview of LiDAR Point Cloud Target Detection Methods Based on Deep Learning. Sensor Review, 42, 485-502. [Google Scholar] [CrossRef] 
[18] 董刚, 谢维成, 黄小龙, 等. 深度学习小目标检测算法综述[J]. 计算机工程与应用, 2023, 59(11): 16-27.
[19] Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Net-Works for Large-Scale Image Recognition. arXiv: 1409.1556v6.
[20] 邓姗姗, 黄慧, 马燕. 基于改进Faster R-CNN的小目标检测算法[J]. 计算机工程与科学, 2023, 45(5): 869-877.
[21] 朱玉华, 杜金月, 刘洋, 等. 基于改进Faster R-CNN的小目标安全帽检测算法研究[J]. 电子制作, 2022, 30(19): 64-66, 83.
[22] 徐守坤, 王雅如, 顾玉宛, 等. 基于改进Faster RCNN的安全帽佩戴检测研究[J]. 计算机应用研究, 2020, 37(3): 901-905.
[23] 罗海保. 基于改进Faster R-CNN的多尺度小目标检测算法研究[D]: [硕士学位论文]. 北京: 北京交通大学, 2020.
[24] Chen, S., Tang, W., Ji, T., Zhu, H., Ouyang, Y. and Wang, W. (2020) Detection of Safety Helmet Wearing Based on Improved Faster R-CNN. 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, 19-24 July 2020, 1-7. [Google Scholar] [CrossRef] 
[25] 杨成佳, 钱明. 基于小目标检测的YOLO算法研究综述[J]. 吉林工程技术师范学院学报, 2023, 39(3): 92-96.
[26] Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. (2016) You Only Look Once: Unified, Real-Time Object Detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 779-788. [Google Scholar] [CrossRef] 
[27] Hussain, M. (2023) YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Comple-mentary Nature toward Digital Manufacturing and Industrial Defect Detection. Machines, 11, Article 677. [Google Scholar] [CrossRef] 
[28] Redmon, J. and Farhadi, A. (2016) YOLO9000: Better, Faster, Stronger. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, 21-26 July 2017, 6517-6525. [Google Scholar] [CrossRef] 
[29] 方明, 孙腾腾, 邵桢. 基于改进YOLOv2的快速安全帽佩戴情况检测[J]. 光学精密工程, 2019, 27(5): 1196-1205.
[30] Redmon, J. and Farhadi, A. (2018) YOLOv3: An Incremental Improvement. arXiv: 1804.02767.
[31] Ouyang, L. and Wang, H. (2019) Vehicle Target Detection in Complex Scenes Based on YOLOv3 Algorithm. IOP Conference Series: Materials Science and Engineering, 569, Article ID: 052018. [Google Scholar] [CrossRef] 
[32] Bochkovskiy, A., Wang, C.Y. and Liao, H.Y.M. (2020) Yolov4: Optimal Speed and Accuracy of Object Detection. arXiv: 2004.10934.
[33] 石家玮, 杨莉琼, 方艳红, 等. 基于改进YOLOv4的安全帽佩戴检测方法[J]. 计算机工程与设计, 2023, 44(2): 518-525.
[34] 高腾, 张先武, 李柏. 深度学习在安全帽佩戴检测中的应用研究综述[J]. 计算机工程与应用, 2023, 59(6): 13-29.
[35] 施辉, 陈先桥, 杨英. 改进YOLO v3的安全帽佩戴检测方法[J]. 计算机工程与应用, 2019, 55(11): 213-220.
[36] Song, H. (2022) Multi-Scale Safety Helmet Detection Based onRSSE-YOLOv3. Sen-sors, 22, Article 6061. [Google Scholar] [CrossRef] [PubMed]
[37] 金雨芳, 吴祥, 董辉, 等. 基于改进YOLO v4的安全帽佩戴检测算法[J]. 计算机科学, 2021, 48(11): 268-275.
[38] 关雅琦. 基于优化YOLO v5的安全帽佩戴实时检测方法研究[D]: [硕士学位论文]. 武汉: 江汉大学, 2023.
[39] Liu, W., Anguelov, D., Erhan, D., et al. (2016) SSD: Single Shot MultiBox Detector. In: Leibe, B., Matas, J., Sebe, N. and Welling, M., Eds., Computer Vision—ECCV 2016, Springer, Cham, 21-37. [Google Scholar] [CrossRef] 
[40] Huang, Q.F., Zhang, Y.J., Huang, Y.G., et al. (2022) Two-Stage Container Keyhole Location Algorithm Based on Optimized SSD and Adaptive Threshold. Journal of Computational Methods in Sciences and Engineering, 22, 1559-1571. [Google Scholar] [CrossRef] 
[41] Gang, L., Zixuan, C., Sen, L., et al. (2022) An Improved SSD Method for Infrared Target Detection Based on Convolutional Neural Network. Journal of Computational Methods in Sciences and Engineering, 22, 1393-1408. [Google Scholar] [CrossRef]