請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80993完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 丁肇隆(Chao-Lung TING) | |
| dc.contributor.author | Yi-Hsuan Liu | en |
| dc.contributor.author | 劉奕煊 | zh_TW |
| dc.date.accessioned | 2022-11-24T03:25:16Z | - |
| dc.date.available | 2021-09-17 | |
| dc.date.available | 2022-11-24T03:25:16Z | - |
| dc.date.copyright | 2021-09-17 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-09-06 | |
| dc.identifier.citation | [1] 內政部. 統計主題專區. https://reurl.cc/ZGNvjW. [2] 衛生福利部國民健康署. 老人跌倒的問題有多嚴重? https://reurl.cc/kZogLL,2019. [3] World Health Organization. Falls. https://www.who.int/newsroom/factsheets/detail/falls/, 2021. [4] CREW TAIWAN. 認識長照程咬金： 老人跌倒後遺症與嚴重性. https://www.crew.com.tw/2018/solutionpreventingelderlyfalling/. [5] Alice C Scheffer, Marieke J Schuurmans, Nynke Van Dijk, Truus Van Der Hooft, andSophia E De Rooij. Fear of falling: measurement strategy, prevalence, risk factorsand consequences among older persons. Age and ageing, 37(1):19–24,2008. [6] Imen Charfi, Johel Miteran, Julien Dubois, Mohamed Atri, and Rached Tourki. Optimized spatiotemporal descriptors for realtime fall detection: comparison of support vector machine and adaboostbased classification. Journal of Electronic Imaging,22(4):041106, 2013. [7] Bogdan Kwolek and Michal Kepski. Human fall detection on embedded platform using depth maps and wireless accelerometer. Computer methods and programs in biomedicine, 117(3):489–501, 2014. [8] Edouard Auvinet, Caroline Rougier, Jean Meunier, Alain StArnaud, and Jacqueline Rousseau. Multiple cameras fall dataset. DIRO-Université de Montréal, Tech. Rep, 1350, 2010. [9] ThuyTrang Nguyen, Myeong-Chan Cho, and Tae-Soo Lee. Automatic fall detection using wearable biomedical signal measurement terminal. In 2009 annual international conference of the ieee engineering in medicine and biology society, pages 5203–5206. IEEE, 2009. [10] Lina Tong, Quanjun Song, Yunjian Ge, and Ming Liu. Hmmbased human fall detection and prediction method using triaxial accelerometer. IEEE Sensors Journal, 13(5):1849–1856, 2013. [11] Ying-Wen Bai, Siao-Cian Wu, and Cheng-Lung Tsai. Design and implementation of a fall monitor system by using a 3-axis accelerometer in a smart phone. IEEE Transactions on Consumer Electronics, 58(4):1269–1275, 2012. [12] Mohamad Daher, Ahmad Diab, Maan El Badaoui El Najjar, Mohamad Ali Khalil, and François Charpillet. Elder tracking and fall detection system using smart tiles. IEEE Sensors Journal, 17(2):469–479, 2016. [13] Guodong Feng, Jiechao Mai, Zhen Ban, Xuemei Guo, and Guoli Wang. Floor pressure imaging for fall detection with fiberoptic sensors. IEEE Pervasive Computing, 15(2):40–47, 2016. [14] Bo Yu Su, KC Ho, Marilyn J Rantz, and Marjorie Skubic. Doppler radar fall activity detection using the wavelet transform. IEEE Transactions on Biomedical Engineering, 62(3):865–875, 2014. [15] Edouard Auvinet, Franck Multon, Alain Saint-Arnaud, Jacqueline Rousseau, and Jean Meunier. Fall detection with multiple cameras: An occlusionresistant method based on 3d silhouette vertical distribution. IEEE transactions on information technology in biomedicine, 15(2):290–300, 2010. [16] Xin Ma, Haibo Wang, Bingxia Xue, Mingang Zhou, Bing Ji, and Yibin Li. Depthbased human fall detection via shape features and improved extreme learning machine. IEEE journal of biomedical and health informatics, 18(6):1915–1922, 2014. [17] Viet Dung Nguyen, Minh Thao Le, Anh Duc Do, Hoang Hai Duong, Toan Dat Thai, and Duc Hoa Tran. An efficient camerabased surveillance for fall detection of elderly people. In 2014 9th IEEE Conference on Industrial Electronics and Applications, pages 994–997. IEEE, 2014. [18] Miao Yu, Adel Rhuma, Syed Mohsen Naqvi, Liang Wang, and Jonathon Chambers. A posture recognitionbased fall detection system for monitoring an elderly person in a smart home environment. IEEE transactions on information technology in biomedicine, 16(6):1274–1286, 2012. [19] Glen Debard, Peter Karsmakers, Mieke Deschodt, Ellen Vlaeyen, Eddy Dejaeger, Koen Milisen, Toon Goedemé, Bart Vanrumste, and Tinne Tuytelaars. Camerabased fall detection on real world data. In Outdoor and largescale realworld scene analysis, pages 356–375. Springer, 2012. [20] Keinosuke Fukunaga and Patrenahalli M. Narendra. A branch and bound algorithm for computing knearest neighbors. IEEE transactions on computers, 100(7):750–753, 1975. [21] Robert M Haralick, Stanley R Sternberg, and Xinhua Zhuang. Image analysis using mathematical morphology. IEEE transactions on pattern analysis and machine intelligence, (4):532–550, 1987. [22] Jasper RR Uijlings, Koen EA Van De Sande, Theo Gevers, and Arnold WM Smeulders. Selective search for object recognition. International journal of computer vision, 104(2):154–171, 2013. [23] Tommy Huang. 深度學習什麼是one stage，什麼是two stage 物件偵測. https://reurl.cc/rg5K0y, (2018). [24] Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster rcnn: Towards realtime object detection with region proposal networks. Advances in neural information processing systems, 28:91–99, 2015. [25] Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision, pages 2980–2988, 2017. [26] 白裳. 一文读懂faster rcnn. https://zhuanlan.zhihu.com/p/31426458, (2017). [27] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016. [28] Sinno Jialin Pan and Qiang Yang. A survey on transfer learning. IEEE Transactions on knowledge and data engineering, 22(10):1345–1359, 2009. [29] 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. [30] Bryan C Russell, Antonio Torralba, Kevin P Murphy, and William T Freeman. Labelme: a database and webbased tool for image annotation. International journal of computer vision, 77(13):157–173, 2008. [31] Tsung-Yi Lin, Piotr Dollár, Ross Girshick, Kaiming He, Bharath Hariharan, and Serge Belongie. Feature pyramid networks for object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2117–2125, 2017. [32] Pieter-Tjerk De Boer, Dirk P Kroese, Shie Mannor, and Reuven Y Rubinstein. A tutorial on the crossentropy method. Annals of operations research, 134(1):19–67, 2005. [33] Daniel Bolya, Chong Zhou, Fanyi Xiao, and Yong Jae Lee. Yolact: Realtime instance segmentation. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9157–9166, 2019. [34] Kerem Turgutlu. Semantic segmentation —unet. https://medium.com/@keremturgutlu/semanticsegmentationunetpart1d8d6f6005066,(2018). [35] Vladimir N Vapnik. An overview of statistical learning theory. IEEE transactions on neural networks, 10(5):988–999, 1999. [36] Derek Anderson, James M Keller, Marjorie Skubic, Xi Chen, and Zhihai He. Recognizing falls from silhouettes. In 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, pages 6388–6391. IEEE, 2006. [37] S-G Miaou, Pei-Hsu Sung, and Chia-Yuan Huang. A customized human fall detection system using omnicamera images and personal information. In 1st Transdisciplinary Conference on Distributed Diagnosis and Home Healthcare, 2006.D2H2., pages 39–42. IEEE, 2006. [38] 林育弘. 基於影像處理及卷積式類神經網路之居家照護系統. 臺灣大學工程科學及海洋工程學研究所學位論文, pages 1–92, 2018. [39] Christoph Feichtenhofer, Haoqi Fan, Jitendra Malik, and Kaiming He. Slowfast networks for video recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 6202–6211, 2019. [40] Gunnar Johansson. Visual perception of biological motion and a model for its analysis. Perception psychophysics, 14(2):201–211, 1973. [41] Kensho Hara, Hirokatsu Kataoka, and Yutaka Satoh. Learning spatiotemporal features with 3d residual networks for action recognition. In Proceedings of the IEEE International Conference on Computer Vision Workshops, pages 3154–3160, 2017. [42] Chunhui Gu, Chen Sun, David A Ross, Carl Vondrick, Caroline Pantofaru, Yeqing Li, Sudheendra Vijayanarasimhan, George Toderici, Susanna Ricco, Rahul Sukthankar, et al. Ava: A video dataset of spatiotemporally localized atomic visual actions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 6047–6056, 2018. [43] Agnieszka Mikołajczyk and Michał Grochowski. Data augmentation for improving deep learning in image classification problem. In 2018 international interdisciplinary PhD workshop (IIPhDW), pages 117–122. IEEE, 2018. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/80993 | - |
| dc.description.abstract | 近幾十年來，隨著人口老齡化，台灣已進入高齡社會。根據衛生福利部資料指出，跌倒意外已成為長者意外傷害死亡的第二大原因，且跌傷後就醫比例僅8%，長者發生跌倒意外事件已成為不可忽視的議題。因此為了改善低就醫比例之問題，本論文提出一種監控式影像居家跌倒偵測系統，其透過重新訓練後之物件辨識模型偵測畫面中人物，之後進行動作判斷，並且依照判斷的方式分為二種演算法，分別為使用SVM進行動作特徵分類的SVM跌倒偵測演算法(SVMFDA)，以及使用深度學習法的SlowFast跌倒偵測演算法(SFFDA)，並且二種演算法皆可辨識出除跌倒外其他四種日常行為動作。經由多種跌倒資料集之實驗結果，此二種跌倒偵測方法皆能成功辨識出長者的跌倒事件，其正確率分別達到93% 與95%。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T03:25:16Z (GMT). No. of bitstreams: 1 U0001-0209202114242700.pdf: 29688910 bytes, checksum: 0121348d4d0d9b4c8cee323d736094e7 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | 口試委員審定書i 致謝ii 摘要iii Abstract iv 目錄vi 圖目錄ix 表目錄xii 第一章緒論 1 1-1 研究背景 1 1-2 論文架構 3 第二章相關研究 5 2-1 跌倒資料集 5 2-1-1 Le2i fall dataset 5 2-1-2 UR fall dataset 6 2-1-3 Multiple cameras fall dataset 7 2-2 相關研究 8 2-2-1 穿戴式裝置偵測跌倒之方法 8 2-2-2 環境感測器偵測跌倒之方法 9 2-2-3 影像偵測跌倒之方法 9 第三章影像人物偵測與跌倒偵測演算法 11 3-1人物偵測 12 3-1-1 影像形態學偵測法 12 3-1-2 深度學習偵測法 13 3-1-3 偵測方法之比較 14 3-2 深度學習網路 15 3-2-1 預訓練模型之測試 17 3-2-2 模型訓練之資料集 18 3-2-3 重新訓練模型 19 3-2-4 模型準確度優化與比較 21 3-2-5 人物遮罩輸出 23 3-3 SVM跌倒偵測演算法(SVMFDA) 25 3-3-1 長寬比特徵與人物遮罩投影 25 3-3-2 中心點距離特徵 29 3-3-3 AR值與CPED分析 31 3-3-4 決策樹分類法 37 3-3-5 SVM跌倒偵測演算法 39 3-4 SlowFast跌倒偵測演算法(SFFDA) 44 3-4-1 網路架構 44 3-4-2 訓練資料集 46 3-4-3 SlowFast 跌倒偵測 48 第四章實驗結果與討論 50 4-1 實驗環境與設備規格 50 4-2 人物偵測模型 50 4-3 SVM跌倒偵測演算法(SVMFDA) 55 4-4 SlowFast跌倒偵測演算法（SFFDA） 63 4-5 跌倒與日常動作辨識準確率測試 71 第五章結論 76 參考文獻 78 | |
| dc.language.iso | zh-TW | |
| dc.subject | 影像辨識 | zh_TW |
| dc.subject | 機器學習 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 動作辨識 | zh_TW |
| dc.subject | 物件偵測 | zh_TW |
| dc.subject | 跌倒偵測 | zh_TW |
| dc.subject | Machine Learning | en |
| dc.subject | Fall Detection | en |
| dc.subject | ObjectDetection | en |
| dc.subject | Action Recognition | en |
| dc.subject | Image Recognition | en |
| dc.subject | Deep Learning | en |
| dc.title | 使用深度學習物件辨識與動作識別進行居家跌倒偵測之研究 | zh_TW |
| dc.title | Home Fall Down Detection: using Deep Learning Object Detection and Action Recognition | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 張瑞益(Hsin-Tsai Liu),黃乾綱(Chih-Yang Tseng),張恆華 | |
| dc.subject.keyword | 機器學習,深度學習,影像辨識,動作辨識,物件偵測,跌倒偵測, | zh_TW |
| dc.subject.keyword | Machine Learning,Deep Learning,Image Recognition,Action Recognition,ObjectDetection,Fall Detection, | en |
| dc.relation.page | 84 | |
| dc.identifier.doi | 10.6342/NTU202102955 | |
| dc.rights.note | 同意授權(限校園內公開) | |
| dc.date.accepted | 2021-09-07 | |
| dc.contributor.author-college | 工學院 | zh_TW |
| dc.contributor.author-dept | 工程科學及海洋工程學研究所 | zh_TW |
| 顯示於系所單位： | 工程科學及海洋工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-0209202114242700.pdf 授權僅限NTU校內IP使用（校園外請利用VPN校外連線服務） | 28.99 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。