請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86207
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 謝尚賢(Shang-Hsien Hsieh) | |
dc.contributor.advisor | 謝尚賢(Shang-Hsien Hsieh | shhsieh@ntu.edu.tw | ), | |
dc.contributor.author | Yi-Han Lai | en |
dc.contributor.author | 賴意函 | zh_TW |
dc.date.accessioned | 2023-03-19T23:42:20Z | - |
dc.date.copyright | 2022-09-06 | |
dc.date.issued | 2022 | |
dc.date.submitted | 2022-09-01 | |
dc.identifier.citation | [1] Bureau of Labor Insurance, Ministry of Labor, Taiwan. Occupational injuries ratio per thousandth under labor insurance by industry. Accessed Jun 2022, https://statdb.mol.gov.tw/statis/jspProxy.aspx?sys=220&ym=11000&ymt=11000&kind=21&type=1&funid=q080522&cycle=4&outmode=0&compmode=0&outkind=2&fldspc=1,19,&cod03=1&rdm=R85042. [2] Occupational Safety and Health Administration, Ministry of Labor, Taiwan. Number of fatalities in various disaster types. Accessed Jun 2022, https://laws.ilosh.gov.tw/ciakp/statistics/general. [3] Occupational Safety and Health Administration, Ministry of Labor, Taiwan. Standards for construction safety and health installations (Taiwan) number 19/174. Accessed Jun 2022, https://law.moj.gov.tw/LawClass/LawSingle.aspx?pcode=N0060014&flno=19. [4] OSHA. Safety and Health Regulations for Construction: Scope, application, and definitions applicable to this subpart, Occupational Safety and Health Administration. Accessed Jun 2022, https://www.osha.gov/laws-regs/regulations/standardnumber/1926/1926.500. [5] Sijie Zhang, Kristiina Sulankivi, Markku Kiviniemi, Ilkka Romo, Charles M Eastman, and Jochen Teizer. BIM-based fall hazard identification and prevention in construction safety planning. Safety Science, 72:31–45, 2015. [6] Weili Fang, Lieyun Ding, Hanbin Luo, and Peter ED Love. Falls from heights: A computer vision-based approach for safety harness detection. Automation in Construction, 91:53–61, 2018. [7] Aritra Pal and Shang-Hsien Hsieh. Vision Based Construction Site Monitoring: A Review from Construction Management Point of View, pages 44–55. 2020. [8] Normadiana Mohammad Hanapi, Mohd Mawardi Mohd Kamal, Muhammad Isha Ismail, and Indra Akmal Putera Abdullah. Identifying root causes and mitigation measures of construction fall accidents. Gading Journal for Social Sciences, 17(01):65–79, 2013. [9] Evan A Nadhim, Carol Hon, Bo Xia, Ian Stewart, and Dongping Fang. Falls from height in the construction industry: A critical review of the scientific literature. International Journal of Environmental Research and Public Health, 13(7):638, 2016. [10] Houtan Jebelli, Changbum R Ahn, and Terry L Stentz. Fall risk analysis of construction workers using inertial measurement units: Validating the usefulness of the postural stability metrics in construction. Safety Science, 84:161–170, 2016. [11] Jia Qi, Raja RA Issa, Svetlana Olbina, and Jimmie Hinze. Use of building information modeling in design to prevent construction worker falls. Journal of Computing in Civil Engineering, 28(5):A4014008, 2014. [12] Jun Wang, Nipesh Pradhananga, and Jochen Teizer. Automatic fall risk identification using point cloud data in construction excavation. In Computing in Civil and Building Engineering, pages 981–988. 2014. [13] Muhammad Khan, Rabia Khalid, Sharjeel Anjum, Si Van-Tien Tran, and Chansik Park. Fall Prevention from Scaffolding Using Computer Vision and IoT-Based Monitoring. Journal of Construction Engineering and Management, 148(7):04022051, 2022. [14] Xiaochun Luo, Heng Li, Dongping Cao, Yantao Yu, Xincong Yang, and Ting Huang. Towards efficient and objective work sampling: Recognizing workers’ activities in site surveillance videos with two-stream convolutional networks. Automation in Construction, 94:360–370, 2018. [15] Simon JD Prince. Computer vision: models, learning, and inference. Cambridge University Press, 2012. [16] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. Nature, 521(7553):436–444, 2015. [17] Suman Paneru and Idris Jeelani. Computer vision applications in construction: Current state, opportunities & challenges. Automation in Construction, 132:103940, 2021. [18] Xiongwei Wu, Doyen Sahoo, and Steven CH Hoi. Recent advances in deep learning for object detection. Neurocomputing, 396:39–64, 2020. [19] Navneet Dalal and Bill Triggs. Histograms of oriented gradients for human detection. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1:886–893, 2005. [20] William S Noble. What is a support vector machine? Nature Biotechnology, 24(12):1565–1567, 2006. [21] Yang Cao, Changhu Wang, Zhiwei Li, Liqing Zhang, and Lei Zhang. Spatial-bag-of-features. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages 3352–3359, 2010. [22] Qi Fang, Heng Li, Xiaochun Luo, Lieyun Ding, Hanbin Luo, Timothy M Rose, and Wangpeng An. Detecting non-hardhat-use by a deep learning method from far-field surveillance videos. Automation in Construction, 85:1–9, 2018. [23] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. Advances in Neural Information Processing Systems, 28, 2015. [24] Weili Fang, Botao Zhong, Neng Zhao, Peter Ed Love, Hanbin Luo, Jiayue Xue, and Shuangjie Xu. A deep learning-based approach for mitigating falls from height with computer vision: Convolutional neural network. Advanced Engineering Informatics, 39:170–177, 2019. [25] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. Mask R-CNN. IEEE International Conference on Computer Vision, pages 2961–2969, 2017. [26] Mani Golparvar-Fard, Feniosky Pena-Mora, and Silvio Savarese. Automated progress monitoring using unordered daily construction photographs and IFC-based building information models. Journal of Computing in Civil Engineering, 29(1):04014025, 2015. [27] Richard Hartley and Andrew Zisserman. Multiple View Geometry in Computer Vision. Cambridge university press, 2003. [28] Jacob J Lin, Amir Ibrahim, Shubham Sarwade, and Mani Golparvar-Fard. Bridge inspection with aerial robots: Automating the entire pipeline of visual data capture, 3D mapping, defect detection, analysis, and reporting. Journal of Computing in Civil Engineering, 35(2):04020064, 2021. [29] Qian Wang and Min-Koo Kim. Applications of 3D point cloud data in the construction industry: A fifteen-year review from 2004 to 2018. Advanced Engineering Informatics, 39:306–319, 2019. [30] Soumitry J Ray and Jochen Teizer. Computing 3D blind spots of construction equipment: Implementation and evaluation of an automated measurement and visualization method utilizing range point cloud data. Automation in Construction, 36:95–107, 2013. [31] Jun Wang, Sijie Zhang, and Jochen Teizer. Geotechnical and safety protective equipment planning using range point cloud data and rule checking in building information modeling. Automation in Construction, 49:250–261, 2015. [32] Mani Golparvar-Fard, Feniosky Peña-Mora, and Silvio Savarese. Integrated sequential as-built and as-planned representation with D4AR tools in support of decision-making tasks in the AEC/FM industry. Journal of Construction Engineering and Management, 137(12):1099–1116, 2011. [33] Vacharapoom Benjaoran and Sdhabhon Bhokha. An integrated safety management with construction management using 4D CAD model. Safety Science, 48(3):395–403, 2010. [34] Sijie Zhang, Jochen Teizer, Jin-Kook Lee, Charles M Eastman, and Manu Venu-gopal. Building information modeling (BIM) and safety: Automatic safety checking of construction models and schedules. Automation in Co nstruction, 29:183–195,2013. [35] Sepehr Alizadehsalehi, Ibrahim Yitmen, Tolga Celik, and David Arditi. The effectiveness of an integrated BIM/UAV model in managing safety on construction sites. International Journal of Occupational Safety and Ergonomics, 26(4):829–844, 2020. [36] Alexandre Boulch, Bertrand Le Saux, and Nicolas Audebert. Unstructured point cloud semantic labeling using deep segmentation networks. Eurographics Workshop on 3D Object Retrieval, 3:1–8, 2017. [37] Karl Weiss, Taghi M Khoshgoftaar, and DingDing Wang. A survey of transfer learning. Journal of Big Data, 3(1):1–40, 2016. [38] Meina Kan, Junting Wu, Shiguang Shan, and Xilin Chen. Domain adaptation for face recognition: Targetize source domain bridged by common subspace. International Journal of Computer Vision, 109(1):94–109, 2014. [39] Jason Yosinski, Jeff Clune, Yoshua Bengio, and Hod Lipson. How transferable are features in deep neural networks? Advances in Neural Information Processing Systems, 27, 2014. [40] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C Lawrence Zitnick. Microsoft coco: Common objects in context. In European Conference on Computer Vision, pages 740–755. Springer, 2014. [41] Noah Snavely, Steven M Seitz, and Richard Szeliski. Modeling the world from internet photo collections. International Journal of Computer Vision, 80(2):189–210,2008. [42] David G Lowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2):91–110, 2004. [43] Martin A Fischler and Robert C Bolles. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6):381–395, 1981. [44] Bill Triggs, Philip F McLauchlan, Richard I Hartley, and Andrew W Fitzgibbon. Bundle adjustment—A modern synthesis. International Workshop on Vision Algorithms, pages 298–372, 1999. [45] Leihui Li, Riwei Wang, and Xuping Zhang. A tutorial review on point cloud registrations: principle, classification, comparison, and technology challenges. Mathematical Problems in Engineering, 2021. [46] Paul J Besl and Neil D McKay. Method for registration of 3-D shapes. In Sensor fusion IV: control paradigms and data structures, volume 1611, pages 586–606. Spie, 1992. [47] Yebin Liu, Xun Cao, Qionghai Dai, and Wenli Xu. Continuous depth estimation for multi-view stereo. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 2121–2128. IEEE, 2009. [48] Occupational Safety and Health Administration, Ministry of Labor, Taiwan. Key points and precautions for safety inspection of scaffolding, Number 6. Accessed Jun 2022, https://laws.mol.gov.tw/FLAW/FLAWDAT0202.aspx?id=FL083843. [49] Martin Ester, Hans-Peter Kriegel, Jörg Sander, Xiaowei Xu, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd, volume 96, pages 226–231, 1996. [50] Michael Hahsler, Matthew Piekenbrock, and Derek Doran. dbscan: Fast density-based clustering with r. Journal of Statistical Software, 91:1–30, 2019. [51] Lin Li, Fan Yang, Haihong Zhu, Dalin Li, You Li, and Lei Tang. An improved RANSAC for 3D point cloud plane segmentation based on normal distribution transformation cells. Remote Sensing, 9(5):433, 2017. [52] Ruwen Schnabel, Roland Wahl, and Reinhard Klein. Efficient RANSAC for point cloud shape detection. In Computer Graphics Forum, volume 26, pages 214–226. Wiley Online Library, 2007. [53] Michael Ying Yang and Wolfgang Förstner. Plane detection in point cloud data. In Proceedings of the 2nd int conf on machine control guidance, Bonn, volume 1, pages 95–104, 2010. [54] Hongjo Kim, Hyoungkwan Kim, Yong Won Hong, and Hyeran Byun. Detecting construction equipment using a region-based fully convolutional network and transfer learning. Journal of computing in Civil Engineering, 32(2):04017082, 2018. [55] Mapillary. OpenSfM, 2020. [56] CloudCompare. CloudCompare, 2022 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/86207 | - |
dc.description.abstract | 從高處墜落一直以來是全球建築業安全事故的主要原因,其中許多發生在施工架和未受保護的開口。研究人員已嘗試利用建築資訊模型(Building Information Modeling, BIM)和時程規劃表通過模擬的方式,從模型中找出潛在的墜落危險,並在安全規劃階段採取相關措施。最近也有許多研究開發了基於電腦視覺以及機器學習的方法來辨識有關工地開口的問題。然而即使倚靠建築資訊模型來進行安全規劃以及利用電腦視覺來促進違規檢測,上述兩種方法都無法改善現階段的安全檢查仍然依賴耗時且費力的人工走動檢查的特性。因此,主要的挑戰是實現建築資訊模型以及現實模型之間訊息的雙向利用,例如在建築資訊模型中加入現場的狀況或是在現實模型以及深度學習方法中加入建築資訊模型的先驗知識。本研究提出一種結合建築資訊模型、現實模型和深度學習的集合方法,以系統性地進行安全規劃和檢查。具體來說,提出的方法首先在建築資訊模型上開發基於規則的安全檢查模組,用於辨識設計規劃階段的潛在墜落危險,為整體系統提供先驗訊息。接著,利用一組有組織的一般相機、360相機、或是空拍機所拍攝的影像,透過三維重建(Structure from Motion, SfM)以及多視立體(Multi-View Stereo, MVS)將這些影像建置成現實模型。接下來,對同一組影像進行語義分割來辨識施工架以及開口,並將結果反投影到三維的現實模型中。最後,本研究提出演算法來分析這些物件的相互關係,並將分析結果可視化以供檢查。本研究經工地實際案例測試後,驗證提出之方法能成功辨識現實模型中的施工架以及開口。其中實驗結果顯示,二維的語意分割在施工架以及開口上的表現,平均精度(Average Precision, AP)可分別達到90.02% 和 89.62%,在三維的點雲模型中施工架的準確率為78%左右。此外,在估計施工架與相鄰結構體的距離成果,達到低於5公分的誤差,這些成果展現所提出的方法能夠有效支持在建築資訊模型和現實模型中的自動墜落安全檢測。 | zh_TW |
dc.description.abstract | Falls from height has been the leading cause of construction safety accidents across countries, many related to scaffolding and uncovered openings. Researchers have tried utilizing Building Information Modeling (BIM) with the schedule to find potential falling hazards through simulations and react in the safety planning phase. Also, recent studies developed computer vision-based machine learning approaches to identify the opening related subjects. While BIM supports safety planning and vision-based methods facilitate violation detection, safety inspection still relies on time-consuming and labor-intensive job walks that fall short of leveraging either approach. The main challenge remains to enable bidirectional information utilization between BIM and reality models, such as onsite situation awareness in BIM and prior BIM knowledge usage in reality models and deep learning methods. This research proposes an integrated approach incorporating BIM, reality model, and deep learning to systematically conduct safety planning and inspection. Specifically, a rule-based safety checking application on BIM is developed for identifying the potential fall hazards in the design phase, providing prior information to the system. Afterward, given a set of organized point-and-shoot, 360 or drone images, the system uses a typical Structure from Motion (SfM) and Multi-View Stereo (MVS) pipeline to generate the reality model. Next, the semantic segmentation is adopted to the same images set to recognize the scaffolding and opening, and the results will be back-projected to the reality model. Finally, the interrelationships of these elements are analyzed, and the results are visualized for inspection. We have evaluated the proposed method on a real-world construction site and successfully identified the scaffolding and opening in the reality model. The experimental results demonstrate that the average precision of 2D image segmentation on scaffolding and opening achieved 90.02% and 89.62%, respectively; and the accuracy of 3D point cloud segmentation on scaffolding obtained around 78%. Also, the distance between scaffolding and structure obtained approximately 5cm error, which exhibits the proposed method's capability to support the automatic fall hazard detection in BIM and point clouds. | en |
dc.description.provenance | Made available in DSpace on 2023-03-19T23:42:20Z (GMT). No. of bitstreams: 1 U0001-2908202214595700.pdf: 61630853 bytes, checksum: 3d1801a3cfb5205869445f516e9ec47b (MD5) Previous issue date: 2022 | en |
dc.description.tableofcontents | Chapter 1 Introduction 1 1.1 Background and Motivation . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Research Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3 Organization of Thesis . . . . . . . . . . . . . . . . . . . . . . . . . 5 Chapter 2 Literature Review 6 2.1 Falls From Height . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Computer Vision-based Approaches for Construction Safety . . . . . 8 2.2.1 Object Detection and Segmentation . . . . . . . . . . . . . . . . . . 9 2.2.2 Image-based 3D Reconstruction . . . . . . . . . . . . . . . . . . . 10 2.3 Building Information Model-based Approaches for Construction Safety 11 2.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 Chapter 3 Methodology 15 3.1 System Workflow . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 3.2 Fall Hazard Detection with BIM . . . . . . . . . . . . . . . . . . . . 18 3.2.1 Rule-Based Detection System . . . . . . . . . . . . . . . . . . . . . 18 3.2.2 Occupancy and Progress Detection . . . . . . . . . . . . . . . . . . 20 3.3 Object Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . 21 3.4 Fall Hazard Localization with 3D Reality Model . . . . . . . . . . . 23 3.4.1 Point Cloud Generation . . . . . . . . . . . . . . . . . . . . . . . . 23 3.4.2 Image Back Projection . . . . . . . . . . . . . . . . . . . . . . . . 27 3.5 Object Relation Detection . . . . . . . . . . . . . . . . . . . . . . . 28 Chapter 4 Experiments 31 4.1 Construction Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . 31 4.2 Fall Hazard Detection with BIM . . . . . . . . . . . . . . . . . . . . 33 4.2.1 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . 33 4.2.2 Detection Results . . . . . . . . . . . . . . . . . . . . . . . . . . . 34 4.3 Object Segmentation . . . . . . . . . . . . . . . . . . . . . . . . . . 38 4.3.1 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . 38 4.3.2 Scaffolding and Opening Segmentation Results . . . . . . . . . . . 39 4.4 Fall Hazard Localization with Point Cloud . . . . . . . . . . . . . . 43 4.4.1 Implementation Details . . . . . . . . . . . . . . . . . . . . . . . . 43 4.4.2 Point Cloud Generation . . . . . . . . . . . . . . . . . . . . . . . . 44 4.4.3 Back Projection Results . . . . . . . . . . . . . . . . . . . . . . . . 47 4.5 Object Relation Detection . . . . . . . . . . . . . . . . . . . . . . . 51 4.5.1 Distance Estimation Results . . . . . . . . . . . . . . . . . . . . . 52 Chapter 5 Conclusion 55 5.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 References 60 | |
dc.language.iso | en | |
dc.title | 基於建築資訊模型以及三維重建模型結合影像分割輔助工地墜落安全檢測 | zh_TW |
dc.title | BIM and reality model-driven fall hazard recognition using semantic segmentation | en |
dc.type | Thesis | |
dc.date.schoolyear | 110-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 林之謙(Jacob J. Lin) | |
dc.contributor.oralexamcommittee | 陳俊杉(Chuin-Shan Chen),吳日騰(Rih-Teng Wu),周慧瑜 | |
dc.subject.keyword | 墜落危險檢測,建築資訊模型,三維重建,電腦視覺, | zh_TW |
dc.subject.keyword | Fall Hazard Recognition,Building Information Modeling (BIM),3-Dimensional Reconstruction,Computer Vision, | en |
dc.relation.page | 67 | |
dc.identifier.doi | 10.6342/NTU202202931 | |
dc.rights.note | 同意授權(全球公開) | |
dc.date.accepted | 2022-09-01 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
dc.date.embargo-lift | 2022-09-06 | - |
顯示於系所單位: | 土木工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
U0001-2908202214595700.pdf | 60.19 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。