Research on detection and early warning of unsafe behavior in metro construction based on video monitoring

被引：0
|
作者：
Xie Y. [1 ,2 ]
Zhang J. [3 ]
Li T. [3 ]
Liu J. [3 ]
机构：
[1] School of Traffic and Transportation Engineering, Changsha University of Science and Technology, Changsha
[2] Wuhan Engineering Consulting Bureau, Wuhan
[3] School of Information and Safety Engineering, Zhongnan University of Economics and Law, Wuhan
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2019年 / 47卷 / 10期
关键词：
HOG (histogram of oriented gradient) eigenvalue; Metro construction; Support vector machine; Unsafe behavior; Video monitoring;
D O I：
10.13245/j.hust.191009
中图分类号：
学科分类号：
摘要：
To solve the detection problem of unsafe behavior in metro construction, a comprehensive detection framework was proposed from the perspective of the subway constructors＇unsafe behavior. The detection of unsafe human behavior could be divided into three aspects, which were personal detection, intrusive detection and multi-person cooperative work detection. By using SVM (support vector machine) and HOG (histogram of oriented gradient) feature combination method, personal detection could be judged. By using multi-source data fusion method based on video monitoring, sensors and feedback information from field personnel, intrusive detection could be judged. By using multi-monitoring cooperative detection method, the number and interval of personnel in the image could be judged. The construction of Suzhou Metro Line 3 was taken as an example to analyze the problem of dim light and uneven light in the metro tunnel site. © 2019, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：46 / 51
页数：5
相关论文
共 15 条
  • [1] Winge S., Albrechtsen E., Mostue B.A., Causal factors and connections in construction accidents, Safety Science, 112, pp. 130-141, (2019)
  • [2] Qiao W., Liu Q., Li X., Et al., Using data mining techniques to analyze the influencing factor of unsafe behaviors in Chinese underground coal mines, Resources Policy, 59, pp. 210-216, (2018)
  • [3] Chi S., Caldas C.H., Image-based safety assessment: automated spatial safety risk identification of earth-moving and surface mining activities, Journal of Construction Engineering and Management, 138, 3, pp. 341-351, (2011)
  • [4] Jain U., Rastogi R., Risk assessment for pedestrian safety evaluation at mid-block crossings under mixed traffic conditions, Institute of Transportation Engineers, 88, 11, pp. 44-49, (2018)
  • [5] Ball K., Workplace surveillance: an overview, Labor History, 51, 1, pp. 87-106, (2010)
  • [6] Cheng T., Teizer J., Migliaccio G.C., Et al., Automated task-level activity analysis through fusion of real time location sensors and worker＇s thoracic posture data, Automation in Construction, 29, pp. 24-39, (2013)
  • [7] Zhang Y., Luo H., Skitmore M., Et al., Optimal camera placement for monitoring safety in metro station construction work, Journal of Construction Engineering and Management, 145, 1, pp. 1-42, (2018)
  • [8] Guo H., Yu Y., Skitmore M., Visualization technology-based construction safety management: a review, Automation in Construction, 73, pp. 135-144, (2017)
  • [9] Nummiaro K., Koller-Meiter E., Van Gool L., An adaptive color-based particle filter, Image and Vision Computing, 21, 1, pp. 99-110, (2003)
  • [10] Han S.U., Lee S.H., A vision-based motion capture and recognition framework for behavior-based safety management, Automation in Construction, 35, pp. 131-141, (2013)
12