請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97604完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林晃巖 | zh_TW |
| dc.contributor.advisor | Hoang-Yan Lin | en |
| dc.contributor.author | 蘇湲煒 | zh_TW |
| dc.contributor.author | Yuan-Wei Su | en |
| dc.date.accessioned | 2025-07-03T16:12:48Z | - |
| dc.date.available | 2025-07-04 | - |
| dc.date.copyright | 2025-07-03 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-06-23 | - |
| dc.identifier.citation | [1]勞動部勞動及職業安全衛生研究所計畫研究報告(2018)，「職業性肌肉骨骼傷病防治之健康管理模式探討研究」。
[2]中華民國「職業安全衛生法」第六條第二項第一款。 [3] David, Geoffrey C. "Ergonomic methods for assessing exposure to risk factors for work-related musculoskeletal disorders." Occupational medicine 55.3 (2005): 190-199. [4] Yung-Che Li et al. "Baseball Swing Pose Estimation Using OpenPose." 2021 IEEE International Conference on Robotics, Automation and Artificial Intelligence (RAAI). [5] Vladimir Guzov et al. "Human POSEitioning Syst em (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensors." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 4318-4329. [6] N. H. H. M. Hamidi, N. A. Z. Abidin, R. Aminuddin, C. C. Sheng, K. A. F. A. Samah and S. D. N. M. Nasir, "A Real-Time System for Monitoring Student Drowsiness in the Classroom Using the Deep Learning Model YOLOv8," 2024 5th International Conference on Artificial Intelligence and Data Sciences (AiDAS), Bangkok, Thailand, 2024, pp. 105-110, [7] Debapriya Maji et al. "YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2637-2646. [8] Jinbao Wang et al. " Deep 3D human pose estimation: A review." Computer Vision and Image Understanding Volume 210, September 2021, 103225. [9] Rawal Khirodkar et al. "Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation." IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 3122-3131 [10] Jiali, Wenshuo Su, and Zhaopeng Wang. "Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation." Proceedings of the AAAI Conference on Artificial Intelligence 34(07) (2020): 11354–11361. [11] Jia Ding, Songtao Niu, Zhenyu Nie, and Wenxuan Zhu. "Research on Human Posture Estimation Algorithm Based on YOLO-Pose." Sensors 24, no. 10 (2024): 3036. [12] A. Viswakumar, V. Rajagopalan, T. Ray and C. Parimi, "Human Gait Analysis Using OpenPose," 2019 Fifth International Conference on Image Information Processing (ICIIP), Shimla, India, 2019, pp. 310-314 [13] Hao-Shu Fang, et al. "AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time." IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 6, pp. 7157–7173, 1 June 2023. [14] Lin Zou, Yubo Zhang, Xu Liu, Yufeng Lu, and Chengwei Huang "A method for transformer substation personnel behavior recognition based on improved AlphaPose algorithm", Proc. SPIE 13416, Fourth International Conference on Advanced Algorithms and Neural Networks (AANN 2024), 134160U (8 November 2024) [15] Ding J, Niu S, Nie Z, Zhu W. "Research on Human Posture Estimation Algorithm Based on YOLO-Pose. " Sensors. 2024; 24(10):3036. [16] Muhammed Kocabas, Nikos Athanasiou, Michael J. Black. "VIBE: Video Inference for Human Body Pose and Shape Estimation." EEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 5253-5263 [17] Baradel, F. et al. (2025). "Multi-HMR: Multi-person Whole-Body Human Mesh Recovery in a Single Shot. " In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision – ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol 15081. Springer, Cham. [18] Deyu Chen, Yifan Song, Feng Liang, et al. "3D human body reconstruction based on SMPL model." Visual Computer 39 (2023): 1893–1906. [19] Zhe Sun, Qing Ke, Hossein Rahmani, Mohammed Bennamoun, Guodong Wang, and Jun Liu. "Human Action Recognition From Various Data Modalities: A Review." IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 3, pp. 3200–3225, 1 March 2023. [20] Bobick, Aaron F., and James W. Davis. "The recognition of human movement using temporal templates." IEEE Transactions on pattern analysis and machine intelligence 23.3 (2001): 257-267. [21] Pavan, M., Jyothi, K. (2022). Human Action Recognition in Still Images Using SIFT Key Points. In: Reddy, V.S., Prasad, V.K., Mallikarjuna Rao, D.N., Satapathy, S.C. (eds) Intelligent Systems and Sustainable Computing. Smart Innovation, Systems and Technologies, vol 289. Springer, Singapore. https://doi.org/10.1007/978-981-19-0011-2_29 [22] Khan, M.A., Zhang, YD., Khan, S.A. et al. " A resource conscious human action recognition framework using 26-layered deep convolutional neural network." Multimed Tools Appl 80, 35827–35849 (2021). [23] Sánchez-Caballero, A., Fuentes-Jiménez, D. & Losada-Gutiérrez, C."Real-time human action recognition using raw depth video-based recurrent neural networks." Multimed Tools Appl 82, 16213–16235 (2023). https://doi.org/10.1007/s11042-022-14075-5 [24] Vidhi Jain et al. "Ambient intelligence-based multimodal human action recognition for autonomous systems." ISA Transactions Volume 132, January 2023, Pages 94-108. [25] Tariq Ahmad, Liang Jin, Xiaohong Zhang, Shiguang Lai, Guoying Tang, and Liang Lin. "Graph Convolutional Neural Network for Human Action Recognition: A Comprehensive Survey." IEEE Transactions on Artificial Intelligence, vol. 2, no. 2, pp. 128–145, April 2021. doi: 10.1109/TAI.2021.3076974. [26] Q. Wang, K. Zhang and M. A. Asghar, "Skeleton-Based ST-GCN for Human Action Recognition With Extended Skeleton Graph and Partitioning Strategy," in IEEE Access, vol. 10, pp. 41403-41410, 2022, doi: 10.1109/ACCESS.2022.3164711. [27] Kim W-J, Park H-J, Jeong B-Y. "A Cross-Sectional Descriptive Study of Musculoskeletal Disorders (MSDs) of Male Shipbuilding Workers and Factors Associated the Neck, Shoulder, Elbow, Low Back, or Knee MSDs. "Applied Sciences. 2022; 12(7):3346. [28] Melhorn, J. Mark, Larry K. Wilkinson, and Michael Dean O'Malley. "Successful management of musculoskeletal disorders." Human and Ecological Risk Assessment 7.7 (2001): 1801-1810. [29] Da Costa, Bruno R., and Edgar Ramos Vieira. "Risk factors for work‐related musculoskeletal disorders: a systematic review of recent longitudinal studies." American journal of industrial medicine 53.3 (2010): 285-323. [30] 勞動部勞動及職業安全衛生研究所(2022)，「勞動環境安全衛生認知調查」。 [31] David, Geoffrey C. "Ergonomic methods for assessing exposure to risk factors for work-related musculoskeletal disorders." Occupational medicine 55.3 (2005): 190-199. [32] 勞動部職業安全衛生署(2020)，「人因性危害預防計畫指引」。 [33] Lind CM, Abtahi F, Forsman M."Wearable Motion Capture Devices for the Prevention of Work-Related Musculoskeletal Disorders in Ergonomics—An Overview of Current Applications, Challenges, and Future Opportunities." Sensors. 2023; 23(9):4259. [34] Mudiyanselage SE, Nguyen PHD, "Rajabi MS, Akhavian R. Automated Workers’ Ergonomic Risk Assessment in Manual Material Handling Using sEMG Wearable Sensors and Machine Learning. " Electronics. 2021; 10(20):2558. [35] Vignais, Nicolas, et al. "Innovative system for real-time ergonomic feedback in industrial manufacturing." Applied ergonomics 44.4 (2013): 566-574. [36] Amanzadeh, Parisan, et al. "Investigating basics and principles of ergonomics in the sheet." Multidisciplinary Science Journal 7.2 (2025): 2025081-2025081. [37] T A Pawitra, L D Fathimahhayati and M A Fariza. "ULA Outperforms RULA in Evaluating MSD Risks of Oyster Mushroom Farmers: Implications for Safer Farming Practices." IOP Conf. Ser.: Earth Environ. Sci. 1242 012009. 2023 [38] Arthur van der Have ,Sam Van Rossom,Ilse Jonkers,” Musculoskeletal-Modeling-Based, Full-Body Load-Assessment Tool for Ergonomists (MATE): Method Development and Proof of Concept Case Studies”, Int. J. Environ. Res. Public Health 2023, 20(2), 1507. [39] Klussmann, André, et al. "The Key Indicator Method for Manual Handling Operations (KIM-MHO)-evaluation of a new method for the assessment of working conditions within a cross-sectional study." BMC musculoskeletal disorders 11 (2010): 1-8. [40] Tsung-Ching Lu. "Development of an Occupational Musculoskeletal Disorders Evaluation System Based on Mobile APP." 2024 International Conference on Advanced Robotics and Mechatronics (ICARM), Tokyo, Japan, 2024, pp. 1002–1008. doi: 10.1109/ICARM62033.2024.10715772. [41] StubbornHuang, “The 17 key points of the MS COCO human skeleton,” StubbornHuang Blog, Mar. 22, 2020. [Online]. [42] S. Kılıççeken, B. Çubukçu, and U. Yüzgeç, “Real-time 2D human skeleton monitoring system,” in Proc. Int. Symp. Multidiscip. Stud. Innov. Technol. (ISMSIT), Ankara, Turkey, 2019, pp. 1–4. [43] G. S. Faber, I. Kingma, and J. H. van Dieën, “Effect of initial horizontal object position on peak L5/S1 moments in manual lifting is dependent on task type and familiarity with alternative lifting strategies,” Ergonomics, vol. 54, no. 1, pp. 72–81, 2010. [44] I. Kingma, T. Faber, A. van Dieën, and J. van Dieën, “The effect of lifting strategy on lumbar spine forces and moments,” Journal of Biomechanics, vol. 128, p. 110640, 2021. [45] Centeno-Schultz Clinic, “L5-S1 or Lumbosacral Joint: What is it and what should you be wary of?” Centeno-Schultz, May 10, 2022. [46] Centers for Disease Control and Prevention, Observation-based posture assessment: Review of current practice and recommendations for improvement. Atlanta, GA: CDC, 2014. [47] 勞動部勞動及職業安全衛生研究所計畫研究報告(2025)，「應用影像偵測技術評估抬舉作業時下背傷病風險研究」，ISBN: 978-626-7743-19-5。 [48] EOMDR, “KIM LHC (Lifting, Holding, Carrying),” EOMDR, Mar. 10, 2022. [Online]. Available: https://eomdr.com/2022/03/10/kim_lhc/ | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/97604 | - |
| dc.description.abstract | 在當今的勞動環境中，人工物料搬運已是普遍及常見的工作項目，尤其常在物流業、貨運業及碼頭業等作業現場，而此類作業經常要求從事重複的抬舉、搬運、推拉等動作，這些活動有高風險導致肌肉骨骼的損傷。為了避免此類健康危害，「職業安全衛生法」明確要求雇主針對可能引發肌肉骨骼疾病的重複性作業，制定並執行預防措施，並針對擁有100人以上員工的事業單位，規定必須進行「人因性危害預防計畫」。
傳統的「人因性危害預防計畫」主要使用問卷調查法抑或是量表觀察法，然而這些方法普遍存在著評估成本高、主觀性強等問題，因此本研究旨在利用影像偵測技術整合現有的影像辨識骨架模型，並引入自行設計能夠適用於不同身高、體型的個人骨架校正方式，最後取用關鍵指標法（Key Indicator Method, KIM）的評量精神與其部分的評估方式，實現簡易的下背傷病風險評估演算法。 此演算法於模擬實驗中的結果顯示，針對16種不同的搬運姿勢所得出的精確率皆達到 90% 以上，並且透過我們的人員骨架校正方法，也顯著改善搬運時腰部彎曲角度的觀測精度，並且在最後我們將演算法與圖形介面整合，開發出一套基於AI影像辨識的下背傷病風險評估與監測系統。該系統不只可以生成下背評估的量表，還能在監測系統上實時給予作業人員警示。 本研究所提出的技術能夠準確預測和分析作業人員的姿勢變化及其潛在風險，從而預防不良姿勢、高重複動作和過度負荷引起的職業性肌肉骨骼傷害健康風險，同時有效避免相關職業傷害。 | zh_TW |
| dc.description.abstract | In today's work environment, manual material handling has become a common and prevalent task, particularly in industries such as logistics, freight, and dock operations. These tasks often require repetitive lifting, carrying, pushing, and pulling, activities that carry a high risk of musculoskeletal injuries. To mitigate these health hazards, the Occupational Safety and Health Act explicitly mandates that employers implement preventive measures for repetitive tasks that could lead to musculoskeletal disorders. For organizations with over 100 employees, a "Prevention Plan for Ergonomic Hazards" is required.
Traditional prevention plans for ergonomic hazards primarily rely on questionnaire surveys or observation-based scales. However, these methods are often associated with high assessment costs and strong subjectivity. This study aims to integrate existing skeleton recognition models using image detection technology and introduce a self-designed personal skeletal correction method adaptable to different heights and body types. It also incorporates the evaluation principles and partial assessment methods of the Key Indicator Method (KIM) to develop an algorithm for lower back assessment. The algorithm's results from simulated experiments show that the accuracy for 16 different handling postures exceeded 90%. Furthermore, the proposed skeletal correction method significantly improved the observational accuracy of lower back bending angles during handling tasks. Finally, we integrated the algorithm with a graphical user interface to develop an AI-based image recognition system for lower back injury risk assessment and monitoring. This system not only generates lower back assessment scales but also provides real-time alerts through the monitoring system. The proposed technology can accurately predict and analyze workers' posture changes and potential risks, thereby preventing occupational musculoskeletal injuries caused by poor posture, high repetition, and excessive load. This effectively reduces the occurrence of work-related injuries. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-07-03T16:12:48Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-07-03T16:12:48Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員審定書 i
誌謝 ii 摘要 v Abstract vi 目次 viii 圖次 xi 表次 xv 第一章 緒論與研究動機 1 第一節 研究背景 1 第二節 肌肉骨骼傷害風險評估方法技術現況與挑戰 1 第三節 研究動機與本文架構 2 第二章 文獻回顧 4 第一節 人體姿勢估計 4 一、 自上而下(Top-down)檢測方法 7 二、 自下而上(Bottom-up)檢測方法 8 三、 自上而下結合自下而上檢測方法 9 第二節 人體骨架辨識 11 一、 2D骨架辨識模型 11 二、 3D骨架辨識模型 14 三、 骨架辨識模型比較與分析 17 第三節 動作辨識 18 一、傳統電腦視覺技術 18 二、 深度學習與時間序列方法 19 第四節 肌肉骨骼疾病風險評估及評估工具 24 一、 肌肉骨骼傷害與風險評估工具與適用性 25 二、 評估工具選擇 29 三、關鍵指標法與關鍵指標法-下背負重處理檢核表(KIM-LHC) 32 第五節 文獻回顧結論 34 第三章 YOLO-Pose誤差驗證與量測 35 第一節 實驗設計 35 一、 實驗場域設計 35 二、關節點誤差量測實驗流程設計 37 三、腰部及膝部彎曲角度誤差量測實驗流程設計 40 第二節 誤差驗證與量測 42 一、 關節點誤差量測與分析 42 二、 腰部及膝部彎曲角度量測與分析 47 第三節 量測與驗證結論 49 第四章 下背傷病風險評估系統設計 50 第一節 YOLO-Pose人員及關節辨識模組 51 第二節 ST-GCN辨識模組 55 第三節 風險評估模組 58 第四節 演示系統開發 61 一、圖形化使用者介面（GUI） 61 二、輸出影片範例說明 62 第五節 研究限制 64 第五章 模擬實驗及性能驗證結果與分析 65 第一節 實驗設計 65 一、 L5/S1脊椎參考點定位誤差評估實驗 65 二、 ST-GCN搬運動作辨識模擬實驗 68 三、 系統運行效能之每秒幀數(FPS)驗證 73 第二節 L5/S1脊椎參考點定位誤差評估實驗結果與分析 75 第三節 ST-GCN搬運動作辨識模擬實驗結果與分析 77 第四節 系統運行效能之每秒幀數(FPS)驗證結果與分析 79 第六章 結論與未來展望 82 第一節 結論 82 第二節 未來展望 83 附錄一(圖片來源:[48]) 85 參考文獻 87 | - |
| dc.language.iso | zh_TW | - |
| dc.subject | 影像偵測 | zh_TW |
| dc.subject | 人體動作分析 | zh_TW |
| dc.subject | 人因工程 | zh_TW |
| dc.subject | 電腦視覺 | zh_TW |
| dc.subject | 關鍵指標法 | zh_TW |
| dc.subject | Image Detection | en |
| dc.subject | Ergonomics | en |
| dc.subject | Human Motion Analysis | en |
| dc.subject | Computer Vision | en |
| dc.subject | Key Indicator Method | en |
| dc.title | 基於AI影像辨識的下背傷病風險評估與監測系統 | zh_TW |
| dc.title | A Lower Back Injury Risk Assessment and Monitoring System Based on AI Image Recognition | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 黃耀輝;林貞宏 | zh_TW |
| dc.contributor.oralexamcommittee | Yao-Hui Huang;Jhen-Hong Lin | en |
| dc.subject.keyword | 人體動作分析,關鍵指標法,影像偵測,電腦視覺,人因工程, | zh_TW |
| dc.subject.keyword | Human Motion Analysis,Key Indicator Method,Image Detection,Computer Vision,Ergonomics, | en |
| dc.relation.page | 93 | - |
| dc.identifier.doi | 10.6342/NTU202501202 | - |
| dc.rights.note | 同意授權(全球公開) | - |
| dc.date.accepted | 2025-06-24 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 光電工程學研究所 | - |
| dc.date.embargo-lift | 2030-01-01 | - |
| 顯示於系所單位： | 光電工程學研究所 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-2.pdf 此日期後於網路公開 2030-01-01 | 5.65 MB | Adobe PDF |
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。