Author(s)

Yuanyuan Wang ^1,2, Jiahui Cao ¹, Mingran Qi ¹, Sisi Liu ¹, Xiuchuan Chen ¹

Affiliation(s)

¹ School of Computer and Software Engineering, Huaiyin Institute of Technology, Huai'an, 223001, China
² Jiangsu Provincial Engineering Laboratory of Mobile Interconnection Technology for Internet of Things, Huai'an, 223001, China

Corresponding Author

Yuanyuan Wang

ABSTRACT

Smart Site is an emerging construction industry project management concept, whose main feature is the integration of modern information technology means to help construction safety. The construction industry is a safety accident-prone industry, and due to its complexity and specificity in the production process, it is difficult to truly conduct real-time inspection of safety hazards at construction sites by relying solely on supervisory and managerial safety officers and manual inspections.Aiming at the safety of construction site workers nowadays, in order to reduce potential hazards and considering the poor adaptability and high false detection rate of current fall detection methods, a technical study of fall detection at smart construction sites based on target detection is proposed. This study uses a home-made web public image dataset, the runtime window is optimised using PyQt5 GUI, the algorithm framework uses Yolo v5 training model, and the trained model achieves the recognition of different scenes and different poses of falls, providing a certain code theoretical basis and feasible model support for the development of a system related to abnormal behaviour detection of construction site workers. The experimental results show that the method proposed in this experiment has high accuracy in human fall detection, providing a certain code theoretical basis and feasibility model support for the development of the system related to abnormal behaviour detection of construction site workers in terms of accuracy of measurement, which is more suitable for construction units.

KEYWORDS

Smart site, behaviour recognition, deep learning, Yolov5, PyQt5

CITE THIS PAPER

Yuanyuan Wang, Jiahui Cao, Mingran Qi, Sisi Liu, Xiuchuan Chen, Research on Smart Site Safety Hazard Warning Technology Based on Yolov5. Frontiers in Computer Vision and Pattern Recognition (2023) Vol. 1: 9-16. DOI: http://dx.doi.org/10.23977/fcvpr.2023.010102.

REFERENCES

[1] Zhang Jiaxiang, Liu Ruhao, Jin Chenxi, and so on. Skeleton behavior recognition by combining spatiotemporal attention mechanisms and adaptive graph convolutional networks. Signal processing, 2021, 37 (7): 1226-1234.
[2] Wu Haoyuan, Xiong Xin, Min Weidong, Zhao Haoyu, Wang Wenxiang. Behavioral recognition method based on multilevel feature fusion and time domain extension. Computer Engineering and application: 1-10 [2022-02-13].
[3] Wang Lingling, Guo Shiqi, Zhou Ying, Chen Kunhui. Study on the indoor risk behavior monitoring and early warning system for the elderly. Information technology of civil and construction engineering: 1-9 [2022-01-22].
[4] Li M, Chen T, Du H. Human behavior recognition using range-velocity-time points IEEE Access, 2020, 8: 37914-37925.
[5] Xiaoye Zhao, Xunsheng Ji, Yuanxiang Li, Li Peng. Combining multi-scale directed depth motion maps and log-gabor filters for human action recognition. Journal of Harbin Institute of Technology (New Series), 2019, 26 (04): 89-96.
[6] Wang Z, Jiang K, Hou Y, et al. A survey on human behavior recognition using channel state information. Ieee Access, 2019, 7: 155986-156024.
[7] Jia J G, Zhou Y F, Hao X W, Li F. Two-stream temporal convolutional networks for skeleton-based human action recognition. Journal of Computer Science and Technology, 2020, 35 (3): 538-550.
[8] Pengcheng D, Siyuan C, Zhenyu Z, Zhigang Z, Jingqi M, Huan L. Human behavior recognition based on IC3D//2019 Chinese Control And Decision Conference (CCDC). IEEE, 2019: 3333-3337.
[9] Ushapreethi P, GG L P. Skeleton-based STIP feature and discriminant sparse coding for human action recognition. International Journal of Intelligent Unmanned Systems, 2020.
[10] Li S, Fang Z, Song W F, Hao A M, Qin H. Bidirectional optimization coupled lightweight networks for efficient and robust multi-person 2D pose estimation. Journal of Computer Science and Technology, 2019, 34 (3): 522-536.
[11] Bao W, Yang Y, Liang D, Zhu M. Multi-residual module stacked hourglass networks for human pose estimation. Journal of Beijing Institute of Technology, 2020, 29 (1): 110-119.
[12] Chen Lumeng, Cao Yan Yan, Huang Min, Xie Xingang. Flame detection method based on an improved YOLOv5. Computer Engineering: 1-17. 2020.
[13] Fan Wenshuo. Research and Design of fixed point detection technology based on image recognition. University of Electronic Science and Technology, 2021.
[14] Hua G, Li L, Liu S. Multipath affinage stacked—hourglass networks for human pose estimation. Frontiers of Computer Science, 2020, 14 (4): 1-12.
[15] Lu J, Nguyen M, Yan W Q. Deep learning methods for human behavior recognition//2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ). IEEE, 2020: 1-6.
[16] Lu Yong, Lu Zhaohe, Wang Xiaodong, Zhou Xingming. Review of research on human behavior perception techniques based on WiFi signals. Journal of Computer Science, 2019, 2: 231-251
[17] Sun Bo, Yang Lei, Guo Xiumei, Chen Ran, Zhang Tong, Jia Hao. ECG signal identification method based on hybrid CNN and SVM. Journal of Shandong Agricultural University (Natural Science Edition), 2020, 51 (02): 283-288.
[18] Zhao L, Wang N, Gong C, Yang J, Gao X. Estimating human pose efficiently by parallel pyramid networks. IEEE Transactions on Image Processing, 2021, 30: 6785-6800.

Sponsors, Associates, and Links

---

• Power Systems Computation
  
  
• Internet of Things (IoT) and Engineering Applications
  
  
• Computing, Performance and Communication Systems
  
  
• Journal of Artificial Intelligence Practice
  
  
• Advances in Computer, Signals and Systems
  
  
• Journal of Network Computing and Applications
  
  
• Journal of Web Systems and Applications
  
  
• Journal of Electrotechnology, Electrical Engineering and Management
  
  
• Journal of Wireless Sensors and Sensor Networks
  
  
• Journal of Image Processing Theory and Applications
  
  
• Mobile Computing and Networking
  
  
• Vehicle Power and Propulsion
  
  
• Knowledge Discovery and Data Mining Letters
  
  
• Big Data Analysis and Cloud Computing
  
  
• Electrical Insulation and Dielectrics
  
  
• Crypto and Information Security
  
  
• Journal of Neural Information Processing
  
  
• Collaborative and Social Computing
  
  
• International Journal of Network and Communication Technology
  
  
• File and Storage Technologies
  
  
• Frontiers in Genetic and Evolutionary Computation
  
  
• Optical Network Design and Modeling
  
  
• Journal of Virtual Reality and Artificial Intelligence
  
  
• Natural Language Processing and Speech Recognition
  
  
• Journal of High-Voltage
  
  
• Programming Languages and Operating Systems
  
  
• Visual Communications and Image Processing
  
  
• Journal of Systems Analysis and Integration
  
  
• Knowledge Representation and Automated Reasoning
  
  
• Review of Information Display Techniques
  
  
• Data and Knowledge Engineering
  
  
• Journal of Database Systems
  
  
• Journal of Cluster and Grid Computing
  
  
• Cloud and Service-Oriented Computing
  
  
• Journal of Networking, Architecture and Storage
  
  
• Journal of Software Engineering and Metrics
  
  
• Visualization Techniques
  
  
• Journal of Parallel and Distributed Processing
  
  
• Journal of Modeling, Analysis and Simulation
  
  
• Journal of Privacy, Trust and Security
  
  
• Journal of Cognitive Informatics and Cognitive Computing
  
  
• Lecture Notes on Wireless Networks and Communications
  
  
• International Journal of Computer and Communications Security
  
  
• Journal of Multimedia Techniques
  
  
• Automation and Machine Learning
  
  
• Computational Linguistics Letters
  
  
• Journal of Computer Architecture and Design
  
  
• Journal of Ubiquitous and Future Networks