Crane danger zone intrusion warning based on computer vision

doi:10.16265/j.cnki.issn1003-3033.2024.07.2028

Abstract

Abstract:

To address the complex scenarios of identifying danger zones in tower crane operations during construction, an early warning method of tower crane danger zone was proposed using computer vision technology. This method combined dynamic determination of tower crane danger zones with computer vision to detect personnel wearing situations of safety helmets and safety belt at the construction site and the inadvertent intrusion beneath the tower crane. Additionally, the YOLOv5 algorithm was adapted with attention models, and interactive window detection software was developed. Results indicate that the recognition accuracy of this model for human intrusion behavior and personal protective equipment exceeds 85%, demonstrating high precision. This method can be effectively applied in tower crane construction scenarios, optimizing fixed danger zone delineation to dynamic tower crane danger zones, and providing real-time monitoring of inadvertent personnel intrusion with warnings.

Key words: computer vision, tower crane danger zone, intrusion warning, YOLOv5, safety management

CLC Number:

X924.3安全监控系统

WU Lizhou, LI Hua, LI Dianbin, WU Yujin, LIU Panwang, XUE Xicheng. Crane danger zone intrusion warning based on computer vision[J]. China Safety Science Journal, 2024, 34(7): 139-146.

Figures/Tables 9

Table 1

Fig.1

Fig.2

Fig.3

Fig.4

Table 2

Fig.5

Fig.6

Fig.7

References 12

[1]	张鸿辉, 李润求. 2012—2018年建筑施工事故统计分析及对策[J]. 科技创新与应用, 2020(31): 135-137, 139.
	ZHANG Honghui, LI Runqiu. Statistical analysis and countermeasures of construction accidents in years 2012-2018[J]. Technology Innovation and Application, 2020(31): 135-137, 139.
[2]	华莹, 何军, 赵金城. 高层建筑施工现场危险区域识别及评估方法研究[J]. 施工技术, 2019, 48(6): 100-104.
	HUA Ying, HE Jun, ZHAO Jincheng. Research on identification and evaluation method of hazardous area of high-rise building construction site[J]. Construction Technology, 2019, 48(6): 100-104.
[3]	段品生, 周建亮, 范丽萍. 考虑安全风险的建筑工人运动风格刻画方法[J]. 铁道科学与工程学报, 2023, 20(8): 3128-3137.
	DUAN Pinsheng, ZHOU Jianliang, FAN Liping. A construction worker movement style portrayal approach considering safety risk[J]. Journal of Railway Science and Engineering, 2023, 20(8): 3128-3137.
[4]	王伟, 吕山可, 张雨果, 等. 基于BIM与机器视觉技术结合的建筑施工危险区域入侵预警研究[J]. 安全与环境工程, 2020, 27(2): 196-203.
	WANG Wei, LYU Shanke, ZHANG Yuguo, et al. Research on early warning of intrusion into hazardous construction area based on BIM and machine vision technology[J]. Safety and Environmental Engineering, 2020, 27(2): 196-203.
[5]	张充, 赵挺生, 蒋灵, 等. 塔式起重机结构安全监测参数选取及测点布置[J]. 中国安全科学学报, 2021, 31(8): 112-118. doi: 10.16265/j.cnki.issn1003-3033.2021.08.016
	ZHANG Chong, ZHAO Tingsheng, JIANG Ling, et al. Selection of safety monitoring parameters and layout of measuring points for tower crane[J]. China Safety Science Journal, 2021, 31(8): 112-118. doi: 10.16265/j.cnki.issn1003-3033.2021.08.016
[6]	任磊, 苗作华, 李自强, 等. 基于YOLOv3算法的危险区域工人识别[J]. 土木建筑工程信息技术, 2022, 14(2): 10-17.
	REN Lei, MIAO Zuohua, LI Ziqiang, et al. Worker identification in hazardous areas based on YOLOv3 algorithm[J]. Journal of Information Technology in Civil Engineering and Architecture, 2022, 14(2): 10-17.
[7]	CHIAN E, GOH Y, TIAN Jing, et al. Dynamic identification of crane load fall zone: a computer vision approach[J]. Safety Science, 2022, 156(12): DOI: 10.1016/j.ssci.2022.105904.
[8]	李华, 吴立舟, 薛曦澄, 等. 基于计算机视觉的高处临边作业安全巡检[J]. 中国安全科学学报, 2023, 33(9): 69-75. doi: 10.16265/j.cnki.issn1003-3033.2023.09.0202
	LI Hua, WU Lizhou, XUE Xicheng, et al. Computer vision based safety detection of high abutting edges[J]. China Safety Science Journal, 2023, 33(9): 69-75. doi: 10.16265/j.cnki.issn1003-3033.2023.09.0202
[9]	SADEGHI H, ZHANG Xueqing, MOHANDES S. Developing an ensemble risk analysis framework for improving the safety of tower crane operations under coupled Fuzzy-based environment[J]. Safety Science, 2023, 158(10): DOI:10.1016/j.ssci.2022.105957.
[10]	HU Songbo, FANG Yihai, MOEHLER R. Estimating and visualizing the exposure to tower crane operation hazards on construction sites[J]. Safety Science, 2023, 160(12): DOI: 10.1016/j.ssci.2022.106044.
[11]	田枫, 白欣宇, 刘芳, 等. 一种轻量化油田危险区域入侵检测算法[J]. 智能系统学报, 2022, 17(3): 634-642.
	TIAN Feng, BAI Xinyu, LIU Fang, et al. A lightweight intrusion detection algorithm for hazardous areas in oilfields[J]. CAAI Transactions on Intelligent Systems, 2022, 17(3): 634-642.
[12]	崔铁军, 郭大龙. 基于改进YOLOX的变电站工人防护设备检测研究[J]. 中国安全生产科学技术, 2023, 19(4): 201-206.
	CUI Tiejun, GUO Dalong. Research on detection of protection equipment for substation workers based on improved YOLOX[J]. Journal of Safety Science and Technology, 2023, 19(4): 201-206.

危险源	划分规则
塔吊	旋转状态时,机身为圆心、悬臂长为半径的圆形范围(悬臂工作平面)
	悬吊状态时,悬吊物外扩2 m
	吊钩垂直投影为圆心,5 m半径范围内

训练方法	P	R	mAP@ 0.5	mAP@ 0.5∶ 0.95	模型内存/ MB	运算时间/ h
YOLOv5	0.83	0.83	0.86	0.63	13.7	6.15
YOLOv5-CA	0.84	0.82	0.85	0.62	15.2	6.35
YOLOv5-CBAM	0.85	0.81	0.86	0.62	14.7	6.53
YOLOv5-ECA	0.83	0.82	0.85	0.61	13.7	6.30
YOLOv5-SE	0.83	0.82	0.85	0.61	14.7	6.60

[1]	JI Zhi'an, ZHOU Yunyi, ZHANG Yuyuan, GUO Xinran, SHI Kun. Industrial site unsafe behavior detection based on improved YOLOv5 [J]. China Safety Science Journal, 2024, 34(7): 38-43.
[2]	LIN Peng, XIANG Yunfei, FAN Qixiang, HE Wei, LIU Yuanguang. Evolution, challenges, and thoughts on intelligent management and control for infrastructure engineering safety [J]. China Safety Science Journal, 2024, 34(7): 8-19.
[3]	XU Na, LIANG Yanxiang, WANG Liang, ZHAO Lili, ZHOU Xueqing, ZHANG Bo. Research on knowledge management in coal mine construction safety field based on knowledge graph [J]. China Safety Science Journal, 2024, 34(5): 28-35.
[4]	ZHANG Shulin, ZHANG Ya'nan, TIAN Chao, YAN Xiang, LU Yi, SHI Shiliang. Study on flame image recognition of chemical industrial park fires based on convolutional neural network [J]. China Safety Science Journal, 2024, 34(1): 179-186.
[5]	CAO Yong. Research on intelligent warehousing system of civilian explosive materials [J]. China Safety Science Journal, 2023, 33(S2): 34-40.
[6]	ZHOU Peng, ZHANG Tingting, WANG Yu. Practice research on enterprise safety culture construction in Daqing oilfield [J]. China Safety Science Journal, 2023, 33(S1): 20-24.
[7]	SUN Diange. Research on the construction of civil airport safety management system based on digital twin technology [J]. China Safety Science Journal, 2023, 33(S1): 222-227.
[8]	WU Zhenzhen, YANG Wentao, WANG Xi, REN Xia. Research on assessment system of urban community safety development [J]. China Safety Science Journal, 2023, 33(S1): 249-255.
[9]	WANG Yaohan, SONG Zeyang, ZHANG Lidong. Research on safety sign classification based on CNN [J]. China Safety Science Journal, 2023, 33(S1): 263-269.
[10]	DENG Yongliang, ZHANG Ying, LUO Li, LI Yang, LIN Lingna. Research on subway operation safety risk management based on ontology technology [J]. China Safety Science Journal, 2023, 33(S1): 35-41.
[11]	LI Hua, WU Lizhou, XUE Xicheng, ZHONG Xingrun. Computer vision based safety inspection of high abutting edges [J]. China Safety Science Journal, 2023, 33(9): 69-75.
[12]	TONG Ruipeng, WANG Biao, SUN Ninghao, HU Xiangyang, WANG Qian. Theoretical construction and application of accident-cause-training method [J]. China Safety Science Journal, 2023, 33(8): 24-29.
[13]	ZHANG Lei, LI Xiwei, YAN Qianru, WANG Haosheng, LEI Weiqiang. Personnel detection algorithm in fully mechanized coal face based on improved YOLOv5s [J]. China Safety Science Journal, 2023, 33(7): 82-89.
[14]	WANG Zhe, LI Xiang, YANG Dongliang, LIU Dan. Fire detection model of wildland-urban interface based on YOLOv5s [J]. China Safety Science Journal, 2023, 33(6): 152-158.
[15]	ZHANG Liya, SUN Ninghao, DING Jungang, TONG Ruipeng. Research on characteristic safety management in oil and gas pipeline industry based on cultural self-confidence [J]. China Safety Science Journal, 2023, 33(6): 35-40.