Review of Deep Learning Approaches for Recognizing Multiple Unsafe Behaviors in Workers

doi:10.3778/j.issn.1002-8331.2307-0168

Abstract

Abstract: With the development of deep learning, target detection and behavior recognition methods have made great progress in the field of worker unsafe behavior recognition, this paper systematically summarizes the relevant research work at home and abroad in recent years, elaborates the commonly used models and effects of target detection methods and behavior recognition methods, focuses on reviewing the application of the two types of methods in the recognition of unsafe behaviors and the relevant research on the combination of the two types of methods, and provides a comprehensive analysis and comparison on the advantages, limitations, recognized behavior categories and applicable scenarios of various methods are comprehensively analyzed and compared. On this basis, the optimization measures for target detection and behavior recognition in recent years are summarized, the commonly used optimization directions and means are summarized, the improvement methods successfully applied in unsafe behavior recognition are summarized, the difficulties and problems in this research field are sorted out, and the suggestions and future development trends are given, which will provide references and lessons for the research in this field.

Key words: deep learning, unsafe worker behavior, target detection, behavior recognition, construction site

摘要： 随着深度学习的发展，目标检测和行为识别方法在工人不安全行为识别领域取得了较大进展，对近年来国内外相关研究工作进行系统性归纳，详细阐述了目标检测方法和行为识别方法中的常用模型和效果，重点评述了两类方法在不安全行为识别上的应用和两类方法结合使用的相关研究，对各种方法的优势、局限性、识别行为类别及适用场景进行了全面分析对比。在此基础上，针对近年来目标检测和行为识别的优化措施，总结了常用的优化方向和手段，归纳了在不安全行为识别上成功应用的改进方法，梳理了该研究领域的难点和问题，并给出建议和未来发展趋势展望，为该领域的研究提供参考和借鉴。

关键词: 深度学习, 工人不安全行为, 目标检测, 行为识别, 施工现场

SU Chenyang, WU Wenhong, NIU Hengmao, SHI Bao, HAO Xu, WANG Jiamin, GAO Le, WANG Weitai. Review of Deep Learning Approaches for Recognizing Multiple Unsafe Behaviors in Workers[J]. Computer Engineering and Applications, 2024, 60(5): 30-46.

苏晨阳, 武文红, 牛恒茂, 石宝, 郝旭, 王嘉敏, 高勒, 汪维泰. 深度学习的工人多种不安全行为识别方法综述[J]. 计算机工程与应用, 2024, 60(5): 30-46.

References

[1] HEINRICH H W. Industrial prevention: a safety management approach[M]. New York: McGraw-Hill, 1980.
[2] 王林, 孙礼涛, 翁鸿飞, 等. 一种建筑施工现场不安全行为识别系统: CN212280116U[P]. 2021-01-05.
WANG L, SUN L T, WENG H F, et al. A system for identifying unsafe behaviors on construction sites: CN212280116U[P]. 2021-01-05.
[3] 卢颖, 吕希凡, 郭良杰, 等. 基于Kinect的地铁乘客不安全行为识别方法与实验[J]. 中国安全生产科学技术, 2021, 17(12): 162-168.
LU Y, LYU X F, GUO L J, et al. Kinect-based recognition method and experiments on unsafe behavior of subway passengers[J]. Journal of Safety Science and Technology, 2021, 17(12): 162-168.
[4] 杨赛烽. 基于Kinect的罐笼内矿工不安全行为识别方法研究[D]. 徐州: 中国矿业大学, 2019.
YANG S F. Research on unsafe behavior recognitionmethod of miners in cage based on Kinect[D]. Xuzhou: China University of Mining and Technology, 2019.
[5] 赵江平, 王垚. 基于图像识别技术的不安全行为识别[J]. 安全与环境工程, 2020, 27(1): 158-165.
ZHAO J P, WANG Y. Unsafe behavior recognition based on image recognition technology[J]. Safety and Environmental Engineering, 2020, 27(1): 158-165.
[6] 刘浩, 刘海滨, 孙宇, 等. 煤矿井下员工不安全行为智能识别系统[J]. 煤炭学报, 2021, 46(S2): 1159-1169.
LIU H, LIU H B, SUN Y, et al. Intelligent recognition system of unsafe behavior of underground coal miners[J]. Journal of China Coal Society, 2021, 46(S2): 1159-1169.
[7] 王超, 徐楚昕, 董杰, 等. 基于ST-GCN的空中交通管制员不安全行为识别[J]. 中国安全科学学报, 2023, 33(5): 42-48.
WANG C, XU C X, DONG J, et al. Unsafe behavior recognition of air traffic controllers based on ST-GCN[J]. China Safety Science Journal, 2023, 33(5): 42-48.
[8] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[9] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[10] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[11] HE K, GKIOXARI G, DOLLáR P, et al. Mask R-CNN[C]//Proceedings of the IEEE International Conferenceon Computer Vision, 2017: 2961-2969.
[12] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas Nevada, 2016: 779-788.
[13] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 7263-7271.
[14] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767,2018.
[15] BOCHKOVSKIY A, WANG C Y, LIAO H Y. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.
10934,2020.
[16] WANG C Y, BOCHKOVSKIY A, LIAO H Y. YOLOv7: trainable bag-of-freebies sets new state-of-the-artfor real-time object detectors[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023: 7464-7475.
[17] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, October 11-14, 2016: 21-37.
[18] JI S, XU W, YANG M, et al. 3D convolutional neural networks for human action recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 35(1): 221-231.
[19] CARREIRA J, ZISSERMAN A. Quo Vadis, action recognition? a new model and the kinetics dataset[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017: 4724-4733.
[20] YAN S, XIONG Y, LIN D. Spatial temporal graph convolutional networks for skeleton-based action recognition[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[21] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[22] SIMONYAN K, ZISSERMAN A. Two-stream convolutionalnetworks for action recognition in videos[C]//Advances in Neural Information Processing Systems, 2014.
[23] FEICHTENHOFER C, FAN H, MALIK J, et al. Slowfast networks for video recognition[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 6202-6211.
[24] 裴利沈, 赵雪专. 群体行为识别深度学习方法研究综[J]. 计算机科学与探索, 2022, 16(4): 775-790.
PEI L S, ZHAO X Z. Survey of collective activity recognition based on deep learning[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(4): 775-790.
[25] 孙勇. 建筑工人不安全行为智能检测系统研究与设计实现[D]. 深圳: 深圳大学, 2020.
SUN Y. Research and design of intelligent detection system for construction workers’ unsafe behavior[D]. Shenzhen: Shenzhen University, 2020.
[26] 张博, 宋元斌, 吴冰, 等. 两阶段Faster R-CNN用于施工现场人车碰撞危险自动分析[J]. 制造业自动化, 2022, 44(6): 24-27.
ZHANG B, SONG Y B, WU B, et al. Two-stage faster R-CNN for analyzing worker-truck collision hazard[J]. Manufacturing Automation, 2022, 44(6): 24-27.
[27] 常捷, 张国维, 陈文江, 等. 基于YOLO-v3算法的加油站不安全行为检测[J]. 中国安全科学学报, 2023, 33(2): 31-37.
CHANG J, ZHANG G W, CHEN W J, et al. Gas station unsafe behavior detection based on YOLO-v3 algorithm[J]. China Safety Science Journal, 2023, 33(2): 31-37.
[28] 王晨. 面向作业安防的智能检测技术研究与实现[D]. 西安: 西安工业大学, 2022.
WANG C. Research and implementation of intelligent detection technology for job security[D]. Xi’an: Xi’an Technological University, 2022.
[29] 谢定坤. 模态融合的施工现场工人不安全行为识别方法研究[D]. 武汉: 华中科技大学, 2020.
XIE D K. A thesis submitted in partial fulfillment of the requirements for the degree of master of engineering[D]. Wuhan: Huazhong University of Science and Technology, 2020.
[30] 范冰倩, 董秉聿, 王彪, 等. 基于深度学习的地铁施工作业人员不安全行为识别与应用[J]. 中国安全科学学报, 2023, 33(1): 41-47.
FAN B Q, DONG B Y, WANG B, et al. Identification and application of unsafe behaviors of subway construction workers based on deep learning[J]. China Safety Science Journal, 2023, 33(1): 41-47.
[31] 杨鹏, 孟宪兴, 王志泉, 等. 基于计算机视觉的化工企业人员不安全行为自动识别技术研究[J]. 山东化工, 2021, 50(14): 134-135.
YANG P, MENG X X, WANG Z Q, et al. Research on Automatic Identification of Unsafe Behavior of Chemical Enterprises Based on Computer Vision[J]. Shandong Chemical Industry, 2021, 50(14): 134-135.
[32] 程明皓. 基于改进YOLO算法的加油站监控场景目标检测研究[D]. 大庆: 东北石油大学, 2023.
CHENG M H. Research on target detection in gas station monitoring scenarios based on improved yolo algorithm[D]. Daqing: Northeast Petroleum University, 2023.
[33] SON H, KIM C. Integrated worker detection and tracking for the safe operation of construction machinery[J]. Automation in Construction, 2021, 126: 103670.
[34] 温廷新, 王贵通, 孔祥博, 等. 基于迁移学习与残差网络的矿工不安全行为识别[J]. 中国安全科学学报, 2020, 30(3): 41-46.
WEN T X, WANG G T, KONG X B, et al. Identification of miners’ unsafe behaviors based on transfer learning and residual network[J]. China safety sciencejournal, 2020, 30(3): 41-46.
[35] 张雷, 冉凌鎛, 代婉婉, 等. 基于融合网络的井下人员行为识别方法[J]. 工矿自动化, 2023, 49(3): 45-52.
ZHANG L, RAN L B, DAI W W, et al. Behavior recognition method for underground personnel based on fusion network[J]. Journal of Mine Automation, 2023, 49(3): 45-52.
[36] 刘耀, 焦双健. ST-GCN在建筑工人不安全动作识别中的应用[J]. 中国安全科学学报, 2022, 32(4): 30.
LIU Y, JIAO S J. Application of ST-GCN in unsafe action identification of construction workers[J]. China Safety Science Journal, 2022, 32(4): 30.
[37] KONG T, FANG W, LOVE P E D, et al. Computer vision and long short-term memory: learning to predictunsafe behaviour in construction[J]. Advanced Engineering Informatics, 2021, 50: 101400.
[38] 黄珍珍, 肖硕, 王钰, 等. 铁路工人人体行为识别模型[J]. 中国安全科学学报, 2022, 32(6): 17-22.
HUANG Z Z, XIAO S, WANG Y, et al. Human activity recognition model of railway workers[J]. China Safety Science Journal, 2022, 32(6): 17-22.
[39] DUAN P, GOH Y M, ZHOU J. Personalized stabilitymonitoring based on body postures of construction workers working at heights[J]. Safety Science, 2023, 162: 106104.
[40] 饶天荣, 潘涛, 徐会军. 基于交叉注意力机制的煤矿井下不安全行为识别[J]. 工矿自动化, 2022, 48(10): 48-54.
RAO T Y, PAN T, XU H J. Unsafe action recognition in underground coal mine based on cross-attention mechanism[J]. Journal of Mine Automation, 2022, 48(10): 48-54.
[41] LEE B, HONG S, KIM H. Determination of workers’ compliance to safety regulations using a spatio-temporal graph convolution network[J]. Advanced Engineering Informatics, 2023, 56: 101942.
[42] 高治军, 顾巧瑜, 陈平, 等. 基于CNN-LSTM双流融合网络的危险行为识别[J]. 数据采集与处理, 2023, 38(1): 132-140.
GAO Z J, GU Q Y, CHEN P, et al. Dangerous behavior recognition based on cnn-lstm dual-stream fusion network[J]. Journal of Data Acquisition and Processing, 2023, 38(1): 132-140.
[43] 苏洪超. 工业环境中人员不安全行为识别研究[D]. 大连: 海事大学, 2021.
SU H C. On identification of human unsafe behavior in industrial environment[D]. Dalian: Dalian Maritime University, 2021.
[44] 郁润. 基于计算机视觉的施工现场工人不安全行为识别方法研究[D]. 北京: 清华大学, 2019.
YU R. Computer-vision-based method for the recognition of construction workers’ unsafe behaviors[D]. Beijing: Tsinghua University, 2019.
[45] 张萌. 基于深度学习的脚手架高空作业险态智能识别方法研究[D]. 镇江: 江苏大学, 2022.
ZHANG M. Research on intelligent identification method of dangerous state of scaffold high-altitude operation based on deep learning[D]. Zhenjiang: Jiangsu University, 2022.
[46] 孟维, 王计斌, 魏东迎. 基于深度学习的人体行为识别方法研究[J]. 江苏通信, 2022, 38(4): 112-116.
MENG W, WANG J B, WEI D Y. Research on human behavior recognition method based on deep learning[J]. Jiangsu Communication, 2022, 38(4): 112-116.
[47] 何赟泽, 周辉, 吴兴辉, 等. 面向水域人员的不安全行为识别算法与应用[J]. 中国测试, 2023(10): 104-110.
HE Y Z, ZHOU H, WU X H, et al. Unsafe behavior recognition algorithm and application for water personnel[J]. China Measurement & Test, 2023(10): 104-110.
[48] ZHANG X, SU X, YU J, et al. Combine object detection with skeleton-based action recognition to detect Smoking Behavior[C]//Proceedings of the 2021 The 5th International Conference on Video and Image Processing, 2021: 111-116.
[49] 徐达炜. 基于注意力和人体关键点的井下矿工不安全行为识别算法研究[D]. 徐州: 中国矿业大学, 2021.
XU D W. Research on unsafe behavior recognition method based on attention and key points of miners[D]. Xuzhou: China University of Mining and Technology, 2021.
[50] 吴晨. 电力作业场景下异常人体行为识别的研究[D]. 无锡: 江南大学, 2022.
WU C. Research on abnormal human behavior recognition in electric power operation[D]. Wuxi: Jiangnan University, 2022.
[51] 李雯静, 刘鑫. 基于深度学习的井下人员不安全行为识别与预警系统研究[J]. 金属矿山, 2023(3): 177-184.
LI W J, LIU X. Research on underground personnel unsafe behavior identification and early warning system based on deep learning[J]. Metal Mine, 2023(3): 177-184.
[52] 毛晓东. 基于目标检测与动作识别算法的电梯危险行为监测[J]. 机械设计与制造, 2023(11): 144-148.
MAO X D. Elevator dangerous behavior monitoring based on object detection and action recognition algorithm[J]. Machinery Design & Manufacture, 2023(11): 144-148.
[53] 万子伦. 基于改进Faster-RCNN的多尺度人脸口罩检测算法研究[D]. 郑州: 河南大学, 2022.
WAN Z L. Research on multi-scale face mask detection algorithm based on improved Faster R-CNN[D]. Zhengzhou: Henan University, 2022.
[54] 吴海波. 复杂背景下红外目标检测的深度学习方法[D]. 西安: 西安工业大学, 2023.
WU H B. Deep learning methods of infrared target detection in complex background[D]. Xi’an: Northwestern Polytechnical University, 2023.
[55] 王永归. 基于计算机视觉的智能建造中3D目标检测研究[D]. 西安: 陕西科技大学, 2023.
WANG Y G. Research on 3D object detection in intelligent construction based on computer vision[D]. Xi’an: Shaanxi University of Science & Technology, 2023.
[56] 贺艺斌, 田圣哲, 兰贵龙. 基于改进Faster-RCNN算法的行人检测[J]. 汽车实用技术, 2022, 47(5): 34-37.
HE Y B, TIAN S Z, LAN G L. Pedestrian detection based on improved FASTER-RCNN algorithm[J]. Automobile Applied Technology, 2022, 47(5): 34-37.
[57] 王小玉. 基于改进Faster-RCNN行人检测算法的研究[D]. 哈尔滨: 哈尔滨理工大学, 2022.
WANG X Y. Research on pedestrian detection algorithm based on improved faster-rcnn[D]. Harbin: Harbin University of Science and Technology, 2022.
[58] 赵留阳. 基于知识蒸馏的轻量化Faster-RCNN算法研究[D]. 淮南: 安徽理工大学, 2022.
ZHAO L Y. Research on lightweight faster-rcnn algorithm based on knowledge distillation[D]. Huainan: Anhui University of Science and Technology, 2022.
[59] 过铭涛. 基于改进YOLOv3的目标检测模型研究与应用[D]. 南京: 南京邮电大学, 2022.
GUO M T. Research and application of target detection model based on improved yolov3[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2022.
[60] 曹梓铭. 基于YOLOv4的多场景小目标检测[D]. 南京: 南京邮电大学, 2022.
CAO Z M. Multi-scene small object detection via yolov4[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2022.
[61] 晏天文. 基于深度学习的小物体目标检测算法研究[D]. 南京: 南京邮电大学, 2022.
YAN T W. Research on small object detection algorithmbased on deep learning[D]. Nanjing: Nanjing University of Posts and Telecommunications, 2022.
[62] 余海坤. 资源受限下目标检测网络轻量化方法研究[D]. 西安: 西安工业大学, 2023.
YU H K. Research on object detection network lightweight method with constrained resources[D]. Xi’an: Xi’an Technological University, 2023.
[63] 贾世娜. 基于改进YOLOv5的小目标检测算法研究[D]. 南昌: 南昌大学, 2022.
JIA S N. Research on small target detection algorithm based on improved yolov5[D]. Nanchang: Nanchang University, 2022.
[64] 贾君霞, 史珂鑫. 改进型SSD道路行人目标检测算法[J]. 国外电子测量技术, 2022, 41(12): 26-32.
JIA J X, SHI K X. Improved pedestrian target detection algorithm for ssd roads[J]. Foreign Electronic Measurement Technology, 2022, 41(12): 26-32.
[65] 金磊. 基于多尺度注意力机制的人体行为识别方法研究[D]. 西安: 西安电子科技大学, 2022.
JIN L. Research on human action recognition with multi-scale attention mechanism[D]. Xi’an: Xidian University, 2022.
[66] 陈泯融, 彭俊杰, 曾国强. 基于多流融合网络的3D骨架人体行为识别[J]. 华南师范大学学报(自然科学版), 2023, 55(1): 94-101.
CHEN M R, PENG J J, ZENG G Q. 3D skeleton-based human action recognition based on multi-stream fusion network[J]. Journal of South China Normal University (Natural Science Edition), 2023, 55(1): 94-101.
[67] 申军轶. 基于3D卷积的人体动态异常行为识别[D]. 包头: 内蒙古科技大学, 2022.
SHEN J Y. Recognition of human dynamic abnormal behaviorbased on 3D convolution[D]. Baotou: Inner Mongolia University of Science and Technology, 2022.
[68] 高闻. 基于轻量级神经网络的人体行为识别方法研究[D]. 太原: 太原理工大学, 2022.
GAO W. Research on human action recognition method based on lightweight neural network[D]. Taiyuan: Taiyuan University of Technology, 2022.
[69] 吴松平. 融合时间序列与空间特征的视频人体行为识别研究[D]. 贵阳: 贵州大学, 2022.
WU S P. Research on video human behavior recognition by fusing time series and spatial features[D]. Guiyang: Guizhou University, 2022.
[70] 余金锁, 卢先领. 基于分割注意力的特征融合CNN-BiLSTM人体行为识别算法[J]. 电子测量与仪器学报, 2022, 36(2): 89-95.
YU J S, LU X L. Human action recognition algorithm of feature fusion CNN-BiLSTM based[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(2): 89-95.
[71] 闫雨寒, 陈天, 刘忠育, 等. 基于双重注意力和3DResNet-BiLSTM行为识别方法[J]. 计算机应用与软件, 2023, 40(2): 192-196.
YAN Y H, CHEN T, LIU Z Y, et al. Action recognitionmethod based on double attention and 3d resnet-bilstm[J]. Computer Applications and Software, 2023, 40(2): 192-196.
[72] 程昱昊. 基于轻量型神经网络的矿工不安全行为识别算法研究[D]. 徐州: 中国矿业大学, 2022.
CHENG Y H. Research on miners' unsafe behavior recognition algorithm based on lightweight neural network[D]. Xuzhou: China University of Mining and Technology, 2022.
[73] 龚苏明, 陈莹. 时空特征金字塔模块下的视频行为识别[J]. 计算机科学与探索, 2022, 16(9): 2061-2067.
GONG S M, CHEN Y. Video action recognition based on spatio-temporal feature pyramid module[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(9): 2061-2067.
[74] 孙琪翔, 何宁, 张聪聪, 等. 基于轻量级图卷积的人体骨架动作识别方法[J]. 计算机工程, 2022, 48(5): 306-313.
SUN Q X, HE N, ZHANG C C, et al. Human skeleton action recognition method based on lightweight graph convolution[J]. Computer Engineering, 2022, 48(5): 306-313.
[75] 蒋俊蕊, 魏延, 王晶仪, 等. 基于人体时空骨架特征的图卷积行为识别算法[J]. 重庆师范大学学报 (自然科学版), 2022, 39(4): 124-133.
JIANG J R, WEI Y, WANG J Y, et al. Graph convolutional behavior recognition algorithm based on human spatio-temporal skeletal features[J]. Journalof Chongqing Normal University (Natural Science), 2022, 39(4): 124-133.
[76] 王宪伦, 王广宇, 孙宇轩. 基于双流图卷积网络的人体行为识别算法[J]. 传感器与微系统, 2023, 42(7): 140-143.
WANG X L, WANG G Y, SUN Y X. Human behavior recognition algorithm based on two-stream gcn[J]. Transducer and Microsystem Technologies, 2023, 42(7): 140-143.
[77] 李昊朋. 基于机器视觉的工厂人员行为识别研究[D]. 西安: 西安工业大学, 2023.
LI H P. Research on behavior recognition of factory personnel based on machine vision[D]. Xi’an: Xi’an Technological University, 2023.
[78] 毛臻臻. 基于时空特征的行为识别[D]. 无锡: 江南大学, 2022.
MAO Z Z. Action recognition based on spatio-temporal features[D]. Wuxi: Jiangnan University, 2022.
[79] 张仁路, 高丙朋. 基于时序时空双流卷积的异常行为识别[J]. 现代电子技术, 2023, 46(3): 81-87.
ZHANF R L. GAO B P. Abnormal behavior recognitionbased on time?series spatiotemporal two-stream convolution[J]. Modern Electronics Technique, 2023, 46(3): 81-87.
[80] 屈文谦. 电网施工现场运动目标检测与不安全行为识别研究[D]. 南昌: 南昌大学, 2022.
QU W Q. Research on motion target detection and unsafe behavior recognition in power grid construction site[D]. Nanchang: Nanchang University, 2022.
[81] 刘斌, 贾浩强, 杨一, 等. 基于改进OpenPose算法的矿工危险行为识别研究[J]. 电视技术, 2023, 47(2): 20-23.
LIU B, JIA H Q, YANG Y, et al. Research on miners’ dangerous behavior recognition based on improved openpose algorithm[J]. Video Engineering, 2023, 47(2): 20-23.
[82] LI L, ZHANG P, YANG S, et al. YOLOv5-sfe: an algorithm fusing spatio-temporal features for detecting and recognizing workers’ operating behaviors[J]. Advanced Engineering Informatics, 2023, 56: 101988.
[83] 刘艺超, 唐哲, 方汀, 等. 基于改进YOLOv5算法的现场不安全行为识别方法研究[J]. 科学技术创新, 2023(8): 5-8.
LIU Y C, TANG Z, FANG T, et al. Research on unsafe behavior recognition method based on improved YOLOv5 algorithm[J]. Scientific and Technologicalinnovation Information, 2023(8): 5-8.
[84] 余益鸿, 周传德, 孟明辉, 等. 基于改进YOLOv5算法的升降机人员不安全行为识别方法[J]. 重庆科技学院学报 (自然科学版), 2022, 24(2): 79-83.
YU Y H, ZHOU C D, MENG M H, et al. Unsafe behavior recognition method of lift personnel based on improved YOLOv5 algorithm[J]. Journal of Chongqing University of Science and Technology (Natural Sciences Edition), 2022, 24(2): 79-83.
[85] 杜俊凤. 基于计算机视觉的建筑工人临边作业不安全行为识别研究[D]. 成都: 四川师范大学, 2021.
DU J F. Unsafe behavior recognition of construction workers workingon the edge of buildings based on computer vision[D]. Chengdu: Sichuan Normal University, 2021.
[86] 马莉, 王卓, 代新冠, 等. 基于双流 CNN 与 Bi-LSTM的施工人员不安全行为轻量级识别模型[J]. 西安科技大学学报, 2022, 42(04): 809-817.
MA L, WANG Z, DAI X G, et al. Lightweight unsafe behavior recognition model of construction workers based on two-stream CNN and Bi-LSTM[J]. Journal of Xi’an University of Science and Technology, 2022, 42(4): 809-817.
[87] 赖永倩. 基于视频的井场工人违规行为识别算法研究[D]. 大庆: 东北石油大学, 2023.
LAI Y Q. Research on video based recognition algorithm for violation behavior of well site workers[D]. Daqing: Northeast Petroleum University, 2023.
[88] 张社荣, 梁斌杰, 马重刚, 等. 水利工程施工人员不安全行为识别方法[J]. 水力发电学报, 2023(8): 98-109.
ZHANG S R, LIANG B J, MA Z G, et al. Unsafe behavior recognition method of construction workers inwater conservancy project[J]. Journal of Hydroelectric Engineering, 2023(8): 98-109.
[89] CAO X, ZHANG C, WANG P, et al. Unsafe mining behavior identification method based on an improved st-gcn[J]. Sustainability, 2023, 15(2): 1041.
[90] 朱国庆. 基于深度学习的人员不安全行为识别研究[D]. 大连: 大连海事大学, 2022.
ZHU G Q. Personnel unsafe behavior identification based on deep learning[D]. Dalian: Dalian Maritime University, 2022.
[91] CHEN J, KAO S, HE H, et al. Run, don’t walk: chasing higher flops for faster neural networks[C]//Proceedings of the IEEE/CVF Conference on ComputerVision and Pattern Recognition, 2023: 12021-12031.