請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49531完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 詹瀅潔(Ying-Chieh Chan) | |
| dc.contributor.author | Chun-Yen Cheng | en |
| dc.contributor.author | 鄭群嚴 | zh_TW |
| dc.date.accessioned | 2021-06-15T11:33:16Z | - |
| dc.date.available | 2022-08-31 | |
| dc.date.copyright | 2020-08-21 | |
| dc.date.issued | 2020 | |
| dc.date.submitted | 2020-08-12 | |
| dc.identifier.citation | [1] “傻傻分不清楚？人工智慧AI 機器學習 ML 深度學習DL,” 22 07 2017. [線上]. Available: https://kknews.cc/zh-tw/tech/zx5ygop.html. [2] 職業安全衛生法, 2019. [3] 營造安全衛生設施標準, 2014. [4] Brandon, “卷積神經網路的運作原理,” 18 08 2016. [線上]. Available: https://brohrer.mcknote.com/zh-Hant/how_machine_learning_works/how_convolutional_neural_networks_work.html. [5] “python 新手的救星--Anaconda介紹與安裝,” 16 06 2016. [線上]. Available: https://darren1231.pixnet.net/blog/post/328443678-python-%E6%96%B0%E6%89%8B%E7%9A%84%E6%95%91%E6%98%9F--anaconda%E4%BB%8B%E7%B4%B9%E8%88%87%E5%AE%89%E8%A3%9D. [6] “Jupyterlab：超強的下一代Jupyter Notebook,” 16 09 2019. [線上]. Available: https://kknews.cc/zh-tw/code/lmyoqne.html. [7] “聊一聊Inception系列（GoogLeNet、Inception、Xception）,” 17 05 2018. [線上]. Available: https://imlogm.github.io/%E6%B7%B1%E5%BA%A6%E5%AD%A6%E4%B9%A0/inception/. [8] “圖解十大 CNN 架構,” 02 08 2019. [線上]. Available: https://twgreatdaily.com/GgVXW2wBUcHTFCnf4DGv.html. [9] Lilac_Yue, “Xception,” 23 12 2017. [線上]. Available: http://blog.leanote.com/post/lilac_yue/Xception. [10] Y. James, “[資料分析 機器學習] 第3.4講：支援向量機(Support Vector Machine)介紹,” 03 11 2017. [線上]. Available: https://medium.com/jameslearningnote/%E8%B3%87%E6%96%99%E5%88%86%E6%9E%90-%E6%A9%9F%E5%99%A8%E5%AD%B8%E7%BF%92-%E7%AC%AC3-4%E8%AC%9B-%E6%94%AF%E6%8F%B4%E5%90%91%E9%87%8F%E6%A9%9F-support-vector-machine-%E4%BB%8B%E7%B4%B9-9c6c6925856b. [11] K. Chiu, “Tensorflow與Keras基本介紹,” 09 05 2019. [線上]. Available: https://medium.com/chiukevin0321/tensorflow%E8%88%87keras%E5%9F%BA%E6%9C%AC%E4%BB%8B%E7%B4%B9-621352fc7150. [12] 初級畫手, “物件導向（1）優點概說,” 06 04 2016. [線上]. Available: http://albusnote.blogspot.com/2016/04/1.html. [13] CH.Tseng, “偵測移動中的物體並取得其影像(一),” 02 06 2017. [線上]. Available: https://chtseng.wordpress.com/2017/06/02/%E5%81%B5%E6%B8%AC%E7%A7%BB%E5%8B%95%E4%B8%AD%E7%9A%84%E7%89%A9%E9%AB%94%E4%B8%A6%E5%8F%96%E5%BE%97%E5%85%B6%E5%BD%B1%E5%83%8F/. [14] CH.Tseng, “建立自己的YOLO辨識模型 – 以柑橘辨識為例,” 01 09 2018. [線上]. Available: https://chtseng.wordpress.com/2018/09/01/%E5%BB%BA%E7%AB%8B%E8%87%AA%E5%B7%B1%E7%9A%84yolo%E8%BE%A8%E8%AD%98%E6%A8%A1%E5%9E%8B-%E4%BB%A5%E6%9F%91%E6%A9%98%E8%BE%A8%E8%AD%98%E7%82%BA%E4%BE%8B/?fbclid=IwAR1_wsWNaajoI1UCyR2XZoeYuK2t5dsuAxXK14lajbvWveUqELN1wR. [15] qiaoguan, “Fall-detection,” 04 03 2019. [線上]. Available: https://github.com/qiaoguan/Fall-detection. [16] 黃玉立、馮靜安、徐雅媛、徐儆暉, “跌倒職業災害的危險因子分析,” 勞工安全衛生研究季刊, p. 15, 03 2013. [17] 潘儀聰、游志雲, “人因工程現場不良工作姿勢改善績效評估研究,” p. 214, 03 2009. [18] 石東生, 人因工程工作姿勢圖例, 勞動部勞動及職業安全衛生研究所, 2008. [19] 'ImageNet: VGGNet, ResNet, Inception, and Xception with Keras,' 20 03 2017. [Online]. Available: https://www.pyimagesearch.com/2017/03/20/imagenet-vggnet-resnet-inception-xception-keras/. [20] 王安祥, “勞工安全衛生管理人員學習背景與事業單位安全衛生績效之關聯性研究-以安全衛生管理能力為中介變項,” 國立中正大學碩士論文, p. 238, 07 2012. [21] 伍勝民, “營造工地安全衛生管理之探討,” 朝陽科技大學碩士論文, p. 96, 07 2019. [22] 趙國雄, “落實工程安全衛生管理對降低職業災害影響之研究-以捷運板橋環狀線為例,” 中華科技大學碩士論文, p. 89, 07 2018. [23] 廖心瑜, “虛擬實境於建築業墜落情境模擬之研究,” 中國科技大學碩士論文, p. 113, 07 2019. [24] 劉泓岑, “結合一維和二維卷基神經網路進行跌倒偵測,” 大同大學碩士論文, 07 2019. [25] 呂昆霖, “基於影像處理之年長者跌倒偵測系統,” 國立雲林科技大學碩士論文, 09 2018. [26] 許芳瑜, “基於多重協同攝影機視訊及深度學習技術之人體跌倒偵測,” 國立中正大學碩士論文, 06 2018. [27] N. Noury, A. Fleury, P. Rumeau, A.K. Bourke, G. Ó Laighin, V. Rialle, J.E. Lundy, 'Fall detection – Principles and Methods,' in Proceedings of the 29th Annual International Conference of the IEEE, Lyon, France, 2007. [28] 石福僑, 一個使用環場攝影機及多重辨識器的跌倒偵測系統, 2007. [29] C. Rita, P.Andrea, V. Roberto, 'A multi-camera vision system for fall detection and alarm generation,' Expert Systems, p. 24, 11 2007. [30] A. Bruno, R. Tiago, S. Joana, S. Inˆes, 'Accelerometer-Based Fall Detection for Smartphones,' Fraunhofer Portugal AICOS, p. 6, 2014. [31] I. Raul, M. Carlos, P. Inmaculada, 'Challenges, issues and trends in fall detection systems,' BioMedical Engineering OnLine, p. 24, 2013. [32] L. Mitja, K. Boštjan, 'Fall Detection and Activity Recognition with Machine Learning,' Informatica, p. 8, 2009. [33] R. Caroline, M. Jean, “Fall Detection from Human Shape and Motion History using Video Surveillance,” AINAW'07, 2007. [34] Y. Kanghyeok, Changbum R. Ahna, Mehmet C. Vuran, Sepideh S. Aria, 'Semi-supervised near-miss fall detection for ironworkers with a,' Automation in Construction, p. 194, 2016. [35] “安全衛生法規資料庫,” 02 2020. [線上]. Available: https://www.ilosh.gov.tw/menu/1188/15882/10514/. [36] “勞工安全衛生法規體系,” 02 2020. [線上]. Available: https://www.ilosh.gov.tw/menu/1223/1235/1237/%E5%8B%9E%E5%B7%A5%E5%AE%89%E5%85%A8%E8%A1%9B%E7%94%9F%E6%B3%95%E8%A6%8F%E9%AB%94%E7%B3%BB/. [37] “勞動統計名詞,” 02 2020. [線上]. Available: https://statdb.mol.gov.tw/html/com/st0803.htm. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/49531 | - |
| dc.description.abstract | 跌倒是職業災害的主要類型之一，在營造相關的產業中，跌倒佔了所有職業災害人次的15%，且營造業為職業災害高風險產業，對於跌倒需要保持更高的關注。在營造業內，由於環境因素，跌倒造成的傷害通常會較高，傷者也因此無法即時自行尋求救援，最後導致傷者無法及時接受適當的治療，可能留下後遺症甚至是死亡。在營造業實施有效的跌倒偵測系統，將能夠掌握珍貴的治療時間，降低跌倒發生造成的傷害。 近年來由人工智慧衍生出的機器學習與深度學習技術蓬勃發展，深度學習的技術能夠讓電腦自行從資料中學習，產生出對應的最佳成果，而影像辨識即為深度學習的一項應用。本研究透過深度學習技術對於人體進行影像辨識，以各種姿勢之人體影像以及營造業內工作姿勢作為訓練用資料，採用卷積神經網路建立跌倒辨識偵測模型。跌倒辨識偵測模型首先會透過物件偵測與動態偵測演算法識別追蹤影片中的人員，並進一步進行跌倒姿勢的辨識偵測，最後在偵測到跌倒時發出警報。本研究建立之跌倒辨識偵測模型，以影像辨識為基礎，在實驗結果中顯示，此模型對於跌倒姿勢的辨識具有81.30%的準確率，能夠有效的偵測跌倒，間接降低跌倒造成的傷害。 | zh_TW |
| dc.description.abstract | Occupational slips, trips and falls on the same level (STFL) is one of the main types of occupational disasters. STFL accounted for 15% of all occupational disasters in the construction industry. The construction industry is a high-risk industry for occupational disasters and needs to pay more attention to STFL. Due to environmental factors, injuries caused by STFL in the construction industry are usually higher, so the injured cannot immediately seek rescue on their own. Eventually, the injured person cannot receive treatment in time, which may cause sequelae or even death. Implementing an effective STFL detection system in the construction industry will increase treatment time and reduce injuries caused by STFL. In recent years, machine learning and deep learning technologies have flourished. Deep learning is that the computer learns from the data by itself and produces the corresponding best results, and image recognition is an application of deep learning. In this study, deep learning is used to recognize the human body image. The human body images in various postures and the working postures in the construction industry are used as training data. The convolutional neural network is used to establish a STFL recognition detection model. The STFL recognition detection model first recognizes the person in the tracking video through object detection and motion detection algorithms, then performs STFL pose recognition detection, and finally alerts when a STFL is detected. The STFL recognition detection model established in this study is based on image recognition. The experimental results show that this model has 81.30% accuracy for STFL posture recognition, which can effectively detect STFL and reduce injuries caused by STFL indirectly. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-15T11:33:16Z (GMT). No. of bitstreams: 1 U0001-1208202013220600.pdf: 2451903 bytes, checksum: 8f99dbe8a53ebddf522d373a11945179 (MD5) Previous issue date: 2020 | en |
| dc.description.tableofcontents | 摘要 i Abstract ii 目錄 iii 圖目錄 v 表目錄 vii 第一章 緒論 1 1.1 研究動機 1 1.2 研究目的 2 1.3 研究範圍 3 1.3.1 營造業 3 1.3.2 跌倒類型職業災害 3 1.4 論文架構 3 第二章 文獻回顧 5 2.1 營造業職業災害 5 2.1.1 職業災害相關定義 5 2.1.2 職業災害數據統計 6 2.1.3 職業災害相關法律 7 2.2 營造業內跌倒類型意外 9 2.2.1 跌倒意外數據統計 9 2.2.2 跌倒意外相關法令規範 9 2.3 深度學習簡介與工具介紹 10 2.3.1 CNN 11 2.3.2 YOLO 16 2.3.3 Python 17 2.3.4 TensorFlow 17 2.3.5 Keras 17 2.3.6 OpenCV 18 2.3.7 Anaconda 18 2.3.8 JupyterLab 19 2.4 相關文獻探討 20 第三章 模型建立過程 27 3.1 研究流程 27 3.2 資料蒐集 29 3.3 環境設定 30 3.4 模型建立 31 3.4.1 人體框選 31 3.4.2 跌倒辨識訓練 34 3.5 模型驗證 39 3.5.1 人體追蹤 39 3.5.2 跌倒判定 41 第四章 模型建立成果分析與討論 42 4.1 模型成果統計分析 42 4.2 跌倒警報 45 4.3 問題與討論 46 第五章 結論與建議 47 5.1 結論 47 5.2 建議 48 參考文獻 50 | |
| dc.language.iso | zh-TW | |
| dc.subject | 卷積神經網路 | zh_TW |
| dc.subject | 跌倒 | zh_TW |
| dc.subject | 職業安全衛生管理 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | STFL(Occupational slips | en |
| dc.subject | Convolutional neural network | en |
| dc.subject | Deep learning | en |
| dc.subject | Occupational safety and health management | en |
| dc.subject | trips and falls on the same level) | en |
| dc.title | 工地安全之跌倒偵測－以深度學習為工具 | zh_TW |
| dc.title | Fall Detection of Construction Site Safety: Using Deep Learning as a Tool | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 108-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳柏翰(Po-Han Chen),陳柏華(Albert Chen),吳翌禎(I-Chen Wu) | |
| dc.subject.keyword | 跌倒,職業安全衛生管理,深度學習,卷積神經網路, | zh_TW |
| dc.subject.keyword | STFL(Occupational slips, trips and falls on the same level),Occupational safety and health management,Deep learning,Convolutional neural network, | en |
| dc.relation.page | 54 | |
| dc.identifier.doi | 10.6342/NTU202003075 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2020-08-13 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 土木工程學研究所 | zh_TW |
| 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 | |
|---|---|---|---|
| U0001-1208202013220600.pdf 未授權公開取用 | 2.39 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。