進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-0908201120192500
論文名稱(中文) 於多感測器3D行動重建系統中使用動作基元之資料減縮技術
論文名稱(英文) Data Reducing with Motion Primitives for A Multi-Sensors 3D Action Reconstruction System
校院名稱 成功大學
系所名稱(中) 工程科學系專班
系所名稱(英) Department of Engineering Science (on the job class)
學年度 99
學期 2
出版年 100
研究生(中文) 王禎溶
研究生(英文) Chen-Jung Wang
學號 N97981037
學位類別 碩士
語文別 中文
論文頁數 48頁
口試委員 指導教授-黃悅民
口試委員-林志敏
口試委員-黃宗傳
口試委員-曾紹崟
口試委員-陳俊良
中文關鍵字 跌倒偵測  感測器  動作片段  高斯混合模型 
英文關鍵字 Fall Detection  Sensor  Motion Primitives  GMM 
學科別分類
中文摘要 跌倒偵測是感測器常見的應用之一,透過多個三軸加速度感測器偵測身體行為模式與跌倒意外的發生,以運動學公式計算人體骨架的運動,於電腦重現3D跌倒過程姿態,在跌倒意外發生時除了發出警告,更能重現當時身體的姿態、重要部位是否受到撞擊等等,提供更多資訊給予醫療人員做精準的判斷。然而影響感測器的能源消耗最顯著的原因來自於大量數據通訊,本研究利用連續語音識別的靈感,以高斯混合模型動作片段分類訊號技術,有效以少量參數趨近原始大量數據,並最佳化參數個數,藉此可改善還原跌倒3D影像重建時資料傳送所造成的能源損耗。
英文摘要 Fall detection is one of the most common applications in sensors. Through a number of three-axis acceleration sensors, we can reproduce the process of 3D falling posture by computing movement of human skeleton using kinematics equations in computer. After falling accident, it will not only alarm but also represent the posture and whether major part is struck. Therefore, it provides more information to medical care personnel for more precise judgment. However, the most significant energy consumption of sensor comes from data communications. In this research, we use GMM motion primitives to classify data inspire from continuous speech recognition. It is valid to approach the original large amount of data in few parameters. We also optimize the number of parameters to ameliorate the energy consumption in 3D falling reconstruction.
論文目次 第一章 緒論................................................1
1.1.研究動機...............................................1
1.2.相關研究...............................................2
1.3.研究目的...............................................3
1.4.論文架構...............................................4
第二章 背景知識介紹........................................5
2.1感測器..................................................5
2.2正向運動與反向運動.....................................12
2.3高斯混合模型(Gaussian Mixture Model, GMM)..............16
第三章 動作片段擷取方法...................................20
3.1限制與系統架構簡介.....................................20
3.2高斯混合模型參數.......................................22
3.3模型選擇(Model Selection)..............................26
3.4跌倒3D重建系統.........................................31
3.5測試動作與方法.........................................36
第四章 效能評估與實作結果.................................37
4.1動作片段優化...........................................37
4.2效能評估...............................................41
4.3優化跌倒3D重建結果.....................................44
第五章 結論與未來展望.....................................45
參考文獻..................................................46
參考文獻 [1]「民國99年重要人口指標」,內政部戶政司,100年4月。
[2]Kun-Je Lin, “Design and Implementation of Multi-Sensors Based 3D Reconstruction System for Elderly Falling”, 國立成功大學工程科學研究所碩士論文, July 2010.
[3]A Sixsmith and N Johnson., “Smart sensor to detect the falls of the elderly". IEEE Pervasive Computing, 3(2):42–47, April-June, 2004.
[4]Thome, N.; Miguet, S.; Ambellouis, S.; , "A Real-Time, Multiview Fall Detection System: A LHMM-Based Approach," IEEE Transactions on Circuits and Systems for Video Technology, vol.18, no.11, pp.1522-1532, Nov. 2008
[5]C. F. Lai, Y. M. Huang, J. H. Park and H. C. Chao, “Adaptive Body Posture Analysis Using Collaborative Multi-Sensors for Elderly Falling Detection,” IEEE Journal on Intelligent System, Vol. 25, No. 2, pp.20-30, March 2010.
[6]Y. M. Huang, M. Y. Hsieh, H. C. Chao, S. H. Hung and J. H. Park, “Pervasive, Secure Access to a Hierarchical Sensor-Based Healthcare Monitoring Architecture in Wireless Heterogeneous Networks,” IEEE Journal on Selected Area in Communications, Vol. 27, No. 4, pp.400-302, May 2009.
[7]M. Y. Hsieh, Y. M. Huang and H. C. Chao, “Adaptive security design with malicious node detection in cluster-based sensor networks,” Journal on Computer Communications, Vol. 30, no. 11-12, pp. 2385-2400, September 2007.
[8]Chin-Feng Lai; Sung-Yen Chang; Han-Chieh Chao; Yueh-Min Huang; , "Detection of Cognitive Injured Body Region Using Multiple Triaxial Accelerometers for Elderly Falling," Sensors Journal, IEEE , vol.11, no.3, pp.763-770, March 2011.
[9]Ghasemzadeh, H.; Loseu, V.; Jafari, R.; , “Structural Action Recognition in Body Sensor Networks: Distributed Classification Based on String Matching”, IEEE Transactions on Information Technology in Biomedicine, vol.14, no.2, pp.425-435, March 2010.
[10]L. Hyman, Phonology, ”Theory and Analysis. Heinle & Heinle Publishers”, 1975.
[11]I. Akyildiz, W. Su, Y. Sankarasubramaniam, and E. Cayirci, “Wireless sensor networks: a survey,” Computer Networks, vol. 38, no. 4, pp. 393–422, 2002.
[12]H. C. Huang, Y. M. Huang and J. W. Ding, “An implementation of battery-aware wireless sensor network using ZigBee for multimedia service,” Proceedings of the IEEE International Conference on Consumer and Electronics, pp. 369-370, February 2006.
[13]Wei-Ting Cho, Chin-Feng Lai, Yueh-Min Huang1, Wei-Tsong Lee, Sing-Wei Huang, “Home Energy Management System for Interconnecting and Sensing of Electric Appliances”, KSII Transactions on Internet and Information Systems, 2010.
[14]Ming-Yi Liao, Chu-Sing Yang, Chun-Wei Tsai Ming-Chao Chiang, Chin-Feng Lai, Energy Efficiency Based on High Performance Particle Swarm Optimization: A Case Study, Spinger Telecommunication Systems, 2011.
[15]Kai Lin, Chin-Feng Lai, Xin Guan, “Energy Efficiency Routing with Node compromised Resistance in Wireless Sensor Networks”, ACM/Springer Mobile Networks & Applications (MONET), 2010.
[16]R. Musaloiu and A. Terzis, “Minimising the effect of wifi interference in 802.15.4wireless sensor networks,” Int. J. Sen. Netw., vol. 3, no. 1, pp. 43–54, 2007.
[17]G. Guerra-Filho, C. Ferm¨uller, and Y. Aloimonos, “Discovering a language for human activity,” in FS’05: Proc. AAAI 2005 Fall Symp. Anticipatory Cogn. Embodied Syst., pp. 70–77, 2005.
[18]陳永霖,”CMOS MEMS Design Platform and Applications”, CICeNews Vol.75, January 2007.
[19]台灣任天堂http://www.nintendo.tw/
[20]Apple iPhone4 http://www.apple.com/tw/iphone/
[21]Mertzios, B.G.; Grigoriadis, G.K.; , "Fast Implementation of forward robot kinematics of position with distributed arithmetic architecture," Systems, Man and Cybernetics, Part A: Systems and Humans, IEEE Transactions on , vol.29, no.3, pp.325-332, May 1999.
[22]S. R. BUSS, “Introduction to inverse kinematics with Jacobian transpose, pseudoinverse, and damped least squares methods.", Typeset manuscript, available from http://math.ucsd.edu/~sbuss/ResearchWeb , July 2010.
[23]Foulley JL, Jaffrezic F, Robert-Granié C, 2000, EM-REML estimation of covariance parameters in Gaussian mixed models for longitudinal data analysis, Genet Sel Evol 32, 129-141.
[24]M. Marolt, “Gaussian mixture models for extraction of melodiclines from audio recordings,” in Proc. ISMIR, pp.80–83, 2004
[25]Johnson, S.,” Hierarchical clustering schemes”, Psychometrika 32(3), 241–254, 1967.
[26]Hartigan, J., Wong, M.,” A K-means clustering algorithm”, JR Stat. Soc. Ser. CAppl.Stat. 28, 100–108, 1979.
[27]Fraley, C., Raftery, A., ”How Many Clusters? Which Clustering Method? Answers Via Model-Based Cluster Analysis.” The Computer Journal 41(8), pp.578–588, 1998.
[28]Figueiredo, M., Jain, A, ”Unsupervised Learning of Finite Mixture Models”, IEEE Transactions on Pattern Analysis and Machine Intelligence, pp.381–396, 2002.
[29]Y. Weiss., ”Motion segmentation using EM – a short tutorial.”, http://www.cs.huji.ac.il/˜yweiss/emTutorial.pdf, 1997.
[30]T. Needham, ”A Visual Explanation of Jensen's Inequality”, American Math. Monthly 100, 768-771, 1993.
[31]G. Schwarz, “Estimating the dimension of a model,” The annals of statistics, vol.6, pp.461-464, 1978.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2021-12-31起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2021-12-31起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw