運用深度學習技術之影像語意分割於施工中電梯直井墜落風險監控

APPLICATION OF IMAGE SEMANTIC SEGMENTATION USING THE DEEP LEARNING TECHNIQUE IN MONITORING THE FALL RISK OF CONSTRUCTION WORKERS IN A BUILDING ELEVATOR SHAFT

廖珗洲(Hsien-Chou Liao)；余文德(Wen-Der Yu)；蕭文達(Wen-Ta Hsiao)；張憲寬(Hsien-Kuan Chang)；蔡智弓(Chi-Kong Tsai)；林楨中(Chen-Chung Lin)

機器學習 ； 語意分割 ； 電梯直井墜落 ； 安全監控 ； machine learning ； semantic segmentation ； falls in building elevator shafts ； fall safety monitoring.and-tie

技術學刊

36卷1期（2021 / 03 / 01）

1 - 12

繁體中文

營建施工意外一直高居世界各國產業職災之首，究其原因在於營建工地具有高度開放與動態特性。尤其是電梯直井在未安裝設備之前，因安全防護不足所導致之高空墜落事故，常是造成建築工地死亡事故的主要原因。雖然法令規範已要求裝設安全防護設施及個人防護裝備，理論上應有充足的安全保障；然而由於施工人員的不安全行為導致防護措施失效而造成之事故仍時有發生。為加強輔助職安人員電梯直井之安全管理，本研究提出以語意分割深度學習技術為基礎之人工智慧電腦視覺辨識方法，開發建築工地電梯直井安全監控輔助系統；自動警示因不當行為導致潛在安全危害，並降低職安管理人員之工作負擔。本研究建構完成之系統可應用於建築工地現場之各電梯直井安全區域監控，透過實驗室訓練測試結果發現，所提出方法不但訓練之召回率及精確率皆高於95%，甚至在工地實測之正確率與純淨度亦高於95%，可見其在產業實務之應用潛力。故本研究之成果應可作為營建施工安全管理之輔助方法，以達到即時且準確管控建築工地電梯直井施工安全並降低墜落事故發生之風險。

Construction accidents are the most significant contributor to occupational disasters among all industries worldwide. This is due to the highly open and dynamic characteristics of construction sites. The unprotected elevator shaft before the installation of mechanical equipment is especially risky for construction workers. Although the safety regulations require the employer to provide sufficient safety behavior facilities and the workers to wear personal protection devices, accidents still occur due to the unsafe practices of the workers. In order to improve the situation, this paper presents an image semantic segmentation method using the Deep Learning (DL) technique for monitoring the fall risk of construction workers near the building elevator shaft. Based on both the laboratory results and in-situ testing, it has been found that the Recall and Precision during the training process in laboratory and the Cleanness and Correctness obtained on site surpassed 95% high performance criteria. It has been concluded that the proposed method provides construction safety personnel an effective tool for monitoring the risks and preventing accidental falls for the construction workers.

1. 余文德,張憲寬,鄭紹材(2017)。整合即時定位系統與建築資訊模型技術於施工人員墜落風險即時防護模式之研究。中國土木水利工程學刊，29(4)，235-247。
   連結：
2. 林楨中,鄭慶武,楊啟男(2013)。中小型營造業施工安全重大職災初探。勞工安全衛生研究季刊，21(3)，277-303。
   連結：
3. 紀佳芬,楊漢聲,陳文雄,劉國青,張庭彰,丁心逸(2008)。營造業墜落重大墜落之情境分析與預防策略。勞工安全衛生研究季刊，16(4)，383-400。
   連結：
4. 曹常成,邱馨瑩,高崇洋,卓育賢(2011)。營造業中高齡勞工職災特性分析。勞工安全衛生研究季刊，19(3)，502-532。
   連結：
5. Brilakisa, I.,Park, M. W.,Jog, G.(2011).Automated Vision Tracking of Project Related Entities.Advanced Engineering Informatics,25(4),713-724.
6. Chen, L. C.,Zhu, Y.,Papandreou, G.,Schroff, F.,Adam, H.(2018).,未出版
7. Ding, L.,Fang, W.,Luo, H.,Love, P. E. D.,Zhong, B.,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.
8. Fang, Q.,Li, H.,Luo, X.,Ding, L.,Luo, H.,Rose, T. M.,An, W.(2018).Detecting Non-hardhat-use by a Deep Learning Method from Far-field Surveillance Videos.Automation in Construction,85,1-9.
9. 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.
10. Girshick, R.(2015).Fast R-CNN.Proceedings of the 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 7-13 December 2015,Washington, DC:
11. Girshick, R.,Donahue, J.,Darrell, T.,Malik, J.(2016).Region-based Convolutional Networks for Accurate Object Detection and Segmentation.IEEE Transactions on Pattern Analysis and Machine Intelligence,38(1),142-158.
12. Gu, Y.,Lo, A.,Niemegeers, I.(2009).A Survey of Indoor Positioning Systems for Wireless Personal Networks.IEEE Communications Surveys & Tutorials,11(1),13-32.
13. He, K. M.,Gkioxari, G.,Dollár, P.,Girshick, R.(2018).,未出版
14. Heinrich, H. W. 1931. Industrial Accident Prevention. New York, NY: McGraw-Hill.
15. Huang, G.,Liu, Z.,Maaten, L.,Weinberger, K. Q.(2018).,未出版
16. Krizhevsky, A.,Sutskever, I.,Hinton, G. E.(2012).Imagenet Classification with Deep Convolutional Neural Networks.Advances in Neural Information Processing Systems,25(2),1097-1105.
17. Lee, U. K.,Kim, J. H.,Cho, H. H.,Kang, K. I.(2009).Development of a Mobile Safety Monitoring System for Construction Sites.Automation in Construction,18(3),258-264.
18. Li, H.,Chan, G.,Wong, J. K. W.,Skitmore, M.(2016).Real-Time Locating Systems Applications in Construction.Automation in Construction,63,37-47.
19. 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 2017 Ninth International Conference on Advanced Computational Intelligence, Doha, Qatar, 4-6 February 2017,Washington, DC:
20. Li, K.,Zhao, X.,Bian, J.,Tan, M.(2018).,未出版
21. Li, N.,Calis, G.,Becerik-Gerber, B.(2012).Measuring and Monitoring Occupancy with an RFID Based System for Demand-driven HVAC Operations.Automation in Construction,24,89-99.
22. Li, N.,Li, S.,Becerik-Gerber, B.,Calis, G.(2012).Deployment Strategies and Performance Evaluation of a Virtual-Tag-Enabled Indoor Location Sensing Approach.Journal of Computing in Civil Engineering,26(5),574-583.
23. Liu, W.,Anguelov, D.,Erhan, D.,Szegedy, C.,Reed, S.,Fu, C. Y.,Berg, A. C.(2016).SSD: Single Shot MultiBox Detector.Proceedings of European Conference on Computer Vision
24. Michie, D.(1993).Turing’s Test and Conscious Thought.Artificial Intelligence,60(1),1-22.
25. Mneymneh, B. E.,Abbas, M.,Khoury, H.(2017).Automated Hardhat Detection for Construction Safety Applications.Procedia Engineering,196,895-902.
26. 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.
27. Park, M. W.,Brilakis, I.(2012).Construction Worker Detection in Video Frames for Initializing Vision Trackers.Automation in Construction,28,15-25.
28. Redmon, J.,Divvala, S.,Girshick, R.,Farhadi, A.(2016).You Only Look Once: Unified, Real-time Object Detection.Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, 779-788. Las Vegas, NV, 27-30 June 2016,Washington, DC:
29. Redmon, J.,Farhadi, A.(2018).,未出版
30. Ren, S.,He, K.,Girshick, R.,Sun, J..Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.Proceedings of IEEE Transactions on Pattern Analysis and Machine Intelligence,39(6),1137-1149.
31. 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 IEEE / WIC / ACM International Conference on Web Intelligence Workshops, Omaha, NE, 13-16 October 2016,Washington, DC:
32. Russell, S.,Norvig, J.P.(2010).Artificial Intelligence, A Modern Approach.New Jersey, NJ:Prentice Hall.
33. Szegedy, C.,Toshev, A.,Erhan, D.(2013).Deep Neural Networks for Object Detection.Proceedings of the 26th International Conference on Neural Information Processing Systems
34. Yang, J.,Shi, Z. K.,Wu, Z. Y.(2016).Vision-based Action Recognition of Construction Workers Using Dense Trajectories.Advanced Engineering Informatics,30(3),327-336.
35. 行政院勞動部職業安全衛生署，2017，「106 年勞動檢查年報」勞動部職業安全衛生署。2018 年 12 月 17 日取自： https://www.osha.gov.tw/1106/1164/1165/1168/22591/。
36. 行政院勞動部職業安全衛生署，2017，「105 年勞動檢查年報」，勞動部職業安全衛生署。2018 年 7 月 16 日取自： https://www.osha.gov.tw/1106/1164/1165/1168/18292/?cprint=pt。
37. 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,新北巿，台灣:。
38. 曹常成(1997)。我國營造業墜落安全防護現況。勞工安全衛生簡訊，23，7-10。
39. 機器之心（譯），2018，「語義分割網絡 DeepLab-v3 的架構設計思想和 TensorFlow 實現」（原作者：Silva, T.），機器之心。2020 年 3 月 23 日取自：https://www.jiqizhixin.com/articles/deeplab-v3。

1. 廖珗洲,張憲寬,林子怡,余文德,王榮進(2022)。AIoT影像感測器在建築物安全應用與效益研究。建築學報，122，1-20。