Abstract
Construction accidents are a major cause of occupational fatalities globally. On-site hazard identification is crucial to prevent such accidents. CCTV is commonly used for safety surveillance on construction sites, and can be utilized for machine learning-based automatic hazard identification. A Construction Hazard Description System (CHDS) was developed in this study to systematically label site objects and describe hazard scenarios. CHDS builds on the ontology of Taiwan Occupational Safety and Health Administration (TOSHA) for hazard classification and construction accident risk scenarios. The system produces site images and associated hazard descriptions that can be used to train automated construction accident risk identification systems through machine learning. According to domain experts, CHDS is effective in assisting construction safety personnel in describing hazard images collected on site, achieving high accuracy rates in both attribute description and hazard classification. It is concluded the system has great potential in improving the task of captioning construction hazard images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
DGB (2018) Summary analysis of the preliminary statistical results of the 2016 industrial and commercial and service industry census. Directorate-General of Budget, Accounting and Statistics, Executive Yuan, R.O.C. (Taiwan), Published 27 Apr 2018, web document: https://www1.stat.gov.tw/public/Attachment/8427181926BYT9Y7B1.pdf. Accessed 24 Oct 2022
TOSHA (2020) 2020 Labor inspection annual report. Web document. https://www.osha.gov.tw/1106/1164/1165/1168/34345/. Occupational Safety and Health, Taiwan. Accessed 24 Oct 2022
MOL (2022) Enforcement rules of the Occupational Safety and Health Act. MOL regulation search system. https://laws.mol.gov.tw/. Accessed 24 Oct 2022
Jeong BY (1998) Occupational deaths and injuries in the construction industry. Appl Ergon 29(5):355–360. https://doi.org/10.1016/S0003-6870(97)00077-X
Ding L, Fang W, Luo H, Love PED, Ouyang X (2018) A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory. Autom Constr 86:118–124
Heinrich HW (1931) Industrial accident prevention. McGraw-Hill, New York
Widner JT (1973) Selected readings in safety. Academy Press, Macom
Occupational Health and Safety Management Systems-Requirements, OHSAS 18001:2007 (2007) British Standards Institution, London
Yeh GY (2009) Application of event tree analysis in occupational safety risk assessment. Master thesis, MS Program of Environment Engineering, National Central University
Chang RN (2012) Training of potential hazard identification on construction site using virtual reality. Master thesis. MS Program of Environmental Engineering, National Chiao Tung University
Wang H-H, Boukamp F (2011) Ontology-based representation and reasoning framework for supporting job hazard analysis. J Comput Civ Eng 25:442–456. https://doi.org/10.1061/(ASCE)CP.19435487.0000125
Liu H, Wang G, Huang T, He P, Skitmore M, Luo X (2020) Manifesting construction activity scenes via image captioning. Autom Constr 119:103334
Collinge WH, Farghaly K, Mosleh MD, Manu P, Cheung CM, Osorio-Sandoval CA (2022) BIM-based construction safety risk library. Autom Constr 141:104391. https://doi.org/10.1016/j.autcon.2022.104391
Li SC (2021) Image caption with object detection and self-attention mechanism. MS Program of Artificial Intelligence, National Yang Ming Chiao Tung University
Farhadi A, Hejrati M, Sadeghi MA, Young P, Rashtchian C, Hockenmaier J, Forsyth D (2010) Every picture tells a story: generating sentences from images. In: ECCV 2010. Lecture notes in computer science, vol 6314, pp 15–29
Mitchell M, Han X-F, Dodge J et al (2012) Midge: generating image descriptions from computer vision detections. In: EACL’12: proceedings of the 13th conference of the European chapter of the association for computational linguistics, pp 747–756
Hsiao WT, Yu WD (2020) Analysis and prevention of the critical factors causing safety hazards of building construction. To be present in the proceedings of the 2nd international conference on architecture, construction, environment, and hydraulics (ICACEH 2020), 25–27 Dec, Hsinchu, Taiwan
Chen X, Fang H, Lin T-Y, Vedantam R, Gupta S, Dollár P, Zitnick CL. Microsoft coco captions: data collection and evaluation server. ArXiv Preprint
Borst WN (1997) Construction of engineering ontologies for knowledge sharing and reuse. Universiteit Twente. https://research.utwente.nl/en/publications/construction-of-engineering-ontologies-for-knowledge-sharing-and-
Hodosh M, Young P, Hockenmaier J (2013) Framing image description as a ranking task: data, models and evaluation metrics. J Artif Intell Res 47:853–899. https://doi.org/10.1613/jair.3994
Young P, Lai A, Hodosh M, Hockenmaier J (2014) From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans Assoc Comput Linguist 2:67–78. https://doi.org/10.1162/tacl_a_00166
Acknowledgements
This project (MOST 111-2221-E-324-011-MY3) was funded by the National Science and Technology Council of Taiwan. The authors gratefully acknowledge her support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yu, WD., Hsiao, WT., Cheng, TM., Chiang, HS., Chang, CY. (2024). Describing Construction Hazard Images Identified from Site Safety Surveillance Video. In: Casini, M. (eds) Proceedings of the 3rd International Civil Engineering and Architecture Conference. CEAC 2023. Lecture Notes in Civil Engineering, vol 389. Springer, Singapore. https://doi.org/10.1007/978-981-99-6368-3_76
Download citation
DOI: https://doi.org/10.1007/978-981-99-6368-3_76
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6367-6
Online ISBN: 978-981-99-6368-3
eBook Packages: EngineeringEngineering (R0)