基於電腦視覺技術之防墜落設施安全狀態辨識研究

IDENTIFITION OF THE STATUS OF SAFETY FACILITIES BASED ON COMPUTER VISION TECHNOLOGY

10.6652/JoCICHE.202204_34(2).0001

余文德(Wen-Der Yu)；張憲寬(Hsien-Kuan Chang)；蔡宛穎(Wan-Ying Tsai)

施工安全管理 ； 開口安全辨識 ； 深度學習 ； 電腦視覺 ； construction safety management ； openness identification ； deep learning ； computer visualization

中國土木水利工程學刊

34卷2期（2022 / 04 / 01）

109 - 120

繁體中文

營建工程常由於開放且動態不確定的施工環境以及緊迫的施工進度要求，導致勞工安全經常被忽略。儘管政府部門非常注重此一議題，但很難完全地排除施工意外發生。其中，營造重大職災死亡災害發生之類型，以「墜落與滾落」為最常見。因此，對於預防營建職災發生應首重墜落事故之預防。本研究以更快速區域卷積式（Faster R-CNN）深度學習類神經網路為基礎，結合簡易之星狀圖形辨識標記，以建構有效之工地開口安全防護設施狀態辨識方法。利用營建工地常見之攝影機所取得的即時影像資料之視覺辨識分析，達到開口安全防護設施安全無虞之目的，作為降低墜落事故之目標。本研究經標記圖形選擇、資料收集、訓練參數分析及網路訓練後，以實際工地影像資料進行測試，經訓練參數調整後，包括電梯直井、地板開口及施工圍籬等三類目標之最終誤報率介於2.1%至8.4%間。此一結果證明本研究所提出之方法，具有監控安全設施危害狀態之實務應用潛力。

The construction managers tend to overlook the safety issue due to the dynamic and open site environment and the tight schedule. Despite the tremendous efforts spent by the Government labor safety agencies; the construction accidents are hardly eliminated completely. Falls from height due to temporary construction openness has been the most common accidents on site. As a result, this research aims at developing a fall prevention method by integrating a deep learning neural networks-based computer visualization technique and a specially designed tag to identify the openness status of fall protection facilities on site. The Faster Region based Convolutional Neural Networks (Faster R-CNN) is adopted and a specially designed Star-shape tag is selected for implementation of the proposed method. Such a method can determine the openness status of the safety facility images obtained from a regular Closed-Circuit Television (CCTV) camera set up on site. After tuning with various network parameters, the field-testing results show that the proposed method can achieve False Positive Rate with 2.1% ~ 8.4% for three types of safety facility openings, i.e., elevator shaft openness, floor openness, and safety fence openness. Such an outstanding performance implies profound potentials for practical application in monitoring the status of safety protection facilities on construction sites.

1. 余文德,廖珗洲,蕭文達,張憲寬,吳定餘,林楨中(2020)。混合式機器學習方法於施工人員個人安全裝備即時辨識之應用。技術學刊，35(4)，155-165。
   連結：
2. Brilakisa, I.,Park, M. W.,Jog, G.(2011).Automated vision tracking of project related entities.Advanced Engineering Informatics,25(4),713-724.
3. Ding, L.,Fang, W.,Luo, H.,Love, P. E. D.,Ouyang, X.(2018).A deep hybrid learning model to detect unsafe behavior: Integrating convolution neural networks and long short-term memory.Automation in Construction,86,118-124.
4. Fang, Q.,Li, H.,Luo, X.,Ding, L.,An, W.(2018).Detectingnon-hardhat-use by a deep learning method from far-field surveillance videos.Automation in Construction,85,1-9.
5. Fang, W. L.,Ding, L. Y.,Luo, H. B.,Love P. E. D.(2018).Falls from heights: A computer vision-based approach for safety harness detection.Automation in Construction,91,53-61.
6. Han, Y.,Yin, Z.,Liu, J.,Jin, R.,Gidado, K.,Painting, N.,Yang, Y.,Yan, L.(2019).Defining and testing a safety cognition framework incorporating safety hazard perception.Journal of Construction Engineering and Management,145(12),04019081.
7. Heinrich, H. W., Industrial Accident Prevention, McGraw-Hill, New York, U.S.A. (1931).
8. Ioffe, S.,Szegedy, C..,未出版
9. Kletz, T. A.(1991).Plant Design for Safety: A User-Friendly Approach.New York, U.S.A:Hemisphere.
10. Krizhevsky, A.,Sutskever, I.,Hinton, G. E.(2012).Imagenet classification with deep convolutional neural networks.Advances in Neural Information Processing Systems
11. Li, J.,Liu, H. M.,Wang, T. Z.,Jiang, M.,Wang, S.,Li, K.,Zhao, X. K.(2017).Safety helmet wearing detection based on image processing and machine learning.Proceedings of the Ninth International Conference on Advanced Computational Intelligence,Doha, Qatar:
12. Michie, D.(1993).Turing’s test and conscious thought.Artificial Intelligence,60(1),1-22.
13. Mneymneh, B. E.,Abbas, M.,Khoury, H.(2018).Evaluation of computer vision techniques for automated hardhat detection in indoor construction safety applications.Frontiers in Engineering Management,5(2),227-239.
14. Mneymneh, B. E.,Abbas, M.,Khoury, H.(2017).Automated hardhat detection for construction safety applications.Procedia Engineering,196,895-902.
15. NIOSH(2010).Prevention Through Design—Plan for National Initiative.Department of Health and Human Services, Centers for Disease Control and Prevention, National Institute for Occupational Safety and Health.
16. OSHA (Occupational Safety and Health Administration). “Construction focus four training,” Accessed Aug. 17 (2020). https://www.osha.gov/dte/outreach/construction/focus_four/index.html.
17. Pranowo, N. A. P.,Santoso, A. J.(2020).Automatic detection and calculation of palm oil fresh fruit bunches using faster R-CNN.International Journal of Applied Science and Engineering,17(2),121-134.
18. Redmon, J.,Divvala, S.,Girshick, R.,Farhadi, A.(2016).You only look once: Unified, realtime object detection.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
19. Redmon, J.,Farhadi, A..,未出版
20. Ren, S.,He, K.,Girshick, R.,Sun, J.(2017).Faster R-CNN: towards real-time object detection with region proposal networks.IEEE Transactions on Pattern Analysis and Machine Intelligence,39(6),1137-1149.
21. Rubaiyat, A. H. M.,Toma, T. T.,Kalantari-Khandani, M.,Rahman, S. A.,Chen, L. W.,Ye, Y. F.,Pan, C. S.(2016).Automatic detection of helmet uses for construction safety.Proceedings of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence Workshops
22. Russell, S.,Norvig, P.(2010).Artificial Intelligence, A Modern Approach.New York, U.S.A.:Prentice Hall.
23. Szegedy, C.,Vanhoucke, V.,Ioffe, S.,Shlens, J.,Wojna, Z..,未出版
24. Wang, W.,Shi, P.,Chu, H.,Deng, L.,Yan, B.(2021).Deep learning framework for total stress detection of steel components.ASCE, J. Bridge Eng.,26(1),04020113.
25. Widner, J. T.(1973).Selected readings in safety.Macom, Ga:Academy Press.
26. Yang, J.,Shi, Z. K.,Wu, Z. Y.(2016).Vision-based action recognition of construction workers using dense trajectories.Advanced Engineering Informatics,30,327-336.
27. Yu, W.-D.,Liao, H.-C.,Hsiao, W.-T.,Chang, H.-K.,Tsai, C.-K.,Lin, C.-C.(2020).Automatic safety monitoring of construction hazard working zone: A semantic segmentation based deep learning approach.Proceedings of the 2020 the 7th International Conference on Automation and Logistics (ICAL), ACM International Conference Proceeding Series
28. 行政院勞動部職業安全衛生署，「108 年勞動檢查年報」，勞動部職業安全衛生署 (2020)。2020 年 8 月 5日取自： https://www.osha.gov.tw/1106/1164/1165/1168/29804/
29. 行政院勞動部職業安全衛生署，「107 年勞動檢查年報」，勞動部職業安全衛生署 (2019)。2020 年 8 月 5日取自： https://www.osha.gov.tw/1106/1164/1165/1168/25237/
30. 吳誌銘,鄭紹材,余文德,林楨中(2012)。建築工程電梯直井內材料運送作業防墜護欄之改良。技術學刊，27(3)，109-119。
31. 林楨中(2001)。行政院勞工委員會勞工安全衛生研究所研究報告行政院勞工委員會勞工安全衛生研究所研究報告,台北台灣:。
32. 林楨中,余文德(2020)。行政院勞動部勞動及職業安全衛生研究所委託研究計畫成果報告行政院勞動部勞動及職業安全衛生研究所委託研究計畫成果報告,台北台灣:。
33. 林楨中,鄭慶武(2017)。行政院勞工委員會勞工安全衛生研究所委託研究計畫成果報告行政院勞工委員會勞工安全衛生研究所委託研究計畫成果報告,台北台灣:。