深度攝影機倚賴其三維資訊的擷取能力以及較低的售價，已廣泛應用於許多領域，舉凡消費、遊戲、教育、機器人及醫療復健領域皆有其相關研究。其中醫療復健項目受到相當多矚目，已有公司推出以深度攝影機進行復健活動的產品。根據世界衛生組織的調查指出全世界應復健人口數超過十億人，約占總人口數之百分之十五，因此需要一個有效率的復健流程來因應如此龐大的人數。若能讓病人無論在家或在醫院皆能自行正確地完成復建，並且自動化記錄其復健情形，病人便不需在住所與醫院間來回奔波，亦可減少醫院負擔。為此本論文建置一套輔助人體復健之3D虛擬導引系統，結合3D 虛擬人物與深度攝影機資訊協助病人檢視自身動作，其復健模式包含一般復健與增添趣味性之復健活動，在一般復健模式中，病人動作若出現錯誤，螢幕上便會出現導引指示，因此可協助病人自行修正錯誤，減少復健動作錯誤的情形：而趣味復健活動則是有助於提高病人的復健意願。實驗結果顯示此系統獲得受試者之高度好評，為一實用性與可用性頗高之系統。

Depth camera relies on its three-dimensional information capture capabilities and low prices, has been widely used in many areas, such as consumer, gaming, education, robotics and medical rehabilitation. The medical rehabilitation project has attracted attention, and some company has launched the products with depth cameras for rehabilitation activities. According to the World Health Organization (WHO) survey, more than a billion people, about 15 percent of the population, should rehabilitate worldwide. An effective rehabilitation process is needed to cope with such a great number of people. In this thesis, a 3D virtual guidance system is designed to assist human to accomplish rehabilitation. It integrates the 3D virtual characters and depth camera information so patients can view their own movements. The rehabilitation mode includes general rehabilitation and recreational activities. In the General Rehabilitation mode, if the patient moves to the wrong direction, the guidance will appear on the screen. It can help patients to correct errors. And recreational activities enhance the patient’s rehabilitation will. The experimental results show that the system has been highly praised by the subjects. It is a practical system with high availability.

論文審定書 i
論文審定書(英文版) ii
致謝 iii
中文摘要 iv
Abstract v
Contents vi
List of Figures viii
List of Tables vx
Chapter 1 Introduction 1
1.1 Overview 1
1.2 Motivation 3
1.3 Organization 4
Chapter 2 Background Review 5
2.1 Depth Camera 5
2.1.1 Kinect 6
Chapter 3 System Development 10
3.1 Development Tools 10
3.2 3D Virtual Character 11
3.3 Guidance Rule 13
Chapter 4 System Operations 15
4.1 User Interface 16
4.2 Clinic Interface 24
Chapter 5 Experimental Results and Conclusions 27
5.1 Experimental Results 27
5.2 Conclusions 29
Reference 30

[1] Andres Traumann, Gholamreza Anbarjafari, Sergio Escalera, “A New Retexturing Method for Virtual Fitting Room Using Kinect 2 Camera,” in Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 75-79, 2015.

[2] Yin Chen, Zhi-Quan Cheng, Chao Lai, Ralph R. Martin, Gang Dang, “Realtime Reconstruction of an Animating Human Body from a Single Depth Camera,” IEEE Transactions on Visualization and Computer Graphics, vol. 22, no. 8, pp. 2000-2011, 2016.

[3] Jing Zhang, Qian Huang, Xiang Peng, “3D Reconstruction of Indoor Environment Using the Kinect Sensor,” in Proceedings of 2015 Fifth International Conference on Instrumentation and Measurement, Computer, Communication and Control, pp. 538-541, 2015.

[4] WHO, “Children and Young People with Disabilities Fact Sheet,” Available: http://www.unicef.org/disabilities/files/ Factsheet_A5_Web_NEW.pdf.

[5] Q. Wang, G. Kurillo, F. Ofli and R. Bajcsy, “Evaluation of pose tracking accuracy in the first and second generations of Microsoft Kinect,” in Proceedings of IEEE International Conference of Healthcare Informatics, pp. 380-389, 2015.

[6] Hachaj, T., Ogiela, M.R., Koptyra, K., “Effectiveness comparison of Kinect and Kinect 2 for recognition of Oyama karate techniques,” in Proceedings of the 18-th International Conference on Network-Based Information Systems, pp. 332–337, 2015.

[7] Chuong V. Nguyen , Shahram Izadi , David Lovell, “Modeling Kinect Sensor Noise for Improved 3D Reconstruction and Tracking,” in Proceedings of the 2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, pp. 524-530, 2012.

[8] D. Alexiadis, D. Zarpalas and P. Daras, “Real-time, full 3-D reconstruction of movingforeground objects from multiple consumer depth cameras", IEEE Trans. Multimedia, vol. 15, no. 2, pp. 339-358, 2013.

[9] P. Jagodzi ski, ans R. Wolski, “Assessment of Application Technology of Natural User Interfaces in the Creation of a Virtual Chemical Laboratory,” Journal of Science Education and Technology, vol. 24, no. 1, pp. 16-28, 2015.

[10] T. Hachaj, and D. Baraniewicz, “Knowledge Bricks—Educational immersive reality environment,” International Journal of Information Management, vol. 35, no. 3, pp. 396-406, 2015.

[11] B. Wang, Z. Li, W. Ye, and Q. Xie, “Development of Human-Machine Interface for Teleoperation of a Mobile Manipulator,” International Journal of Control, Automation, and Systems, vol. 10, no. 6, pp. 225-1231, 2012.

[12] “Jintronix.” [Online]. Available: http://www.jintronix.com/

[13] “Reflexion.” [Online]. Available: http://reflexionhealth.com/

[14] “Virtualrehab.” [Online]. Available: http://www.virtualrehab.info/

[15] “Seeme.” [Online]. Available:
http://www.virtual-realityrehabilitation.com/products/seeme/what-is-seeme

[16] Y. J. Chang, S. F. Chen, J. D. Huang, “A Kinect-based system for physical rehabilitation: A pilot study for young adults with motor disabilities” Research in Developmental Disabilities, vol. 32, no. 6, pp. 2566-2570, 2011.

[17] W. Zhao, D. D. Espy, M. Reinthal, and H. Feng, “A feasibility study of using a single kinect sensor for rehabilitation exercises monitoring: A rule based approach,” in Computational Intelligence in Healthcare and e-health (CICARE), 2014 IEEE Symposium on. IEEE, pp. 1–8, 2014.

[18] W. Zhao, H. Feng, R. Lun, D. D. Espy, and M. Reinthal, “A kinect-based
rehabilitation exercise monitoring and guidance systems,” in Proceedings of the 5th IEEE International Conference on Software Engineering and Service Science. IEEE, pp. 762–765, 2014.

[19] B. Bonnechere, B. Jansen, P. Salvia, H. Bouzahouene, L. Omelina, F. Moiseev, V. Sholukha, J. Cornelis, M. Rooze, and S. Van Sint Jan, “Validity and reliability of the kinect within functional assessment activities: Comparison with standard stereophotogrammetry,” Gait &posture, vol. 39, no. 1, pp. 593-598, 2014

[20] C. L. Lai, Y.L. Huang, T.K. Kiao, C. M. Tseng, Y. F. Chen, D. Erdenetsogt, “A Microsoft Kinect-Based Virtual Rehabilitation System to Train Balance Ability for Stroke Patients,” in Proceedings of 2015 International Conference on Cyberworlds, pp. 54–60, 2015.

[21] ADa Gama, T. Chavez, L. Figueiredo, V. Teichrieb, “Poster improving motor rehabilitation process through a natural interaction based system using Kinect sensor,” in Proceedings of IEEE Symposium on 3D User Interfaces 2012, pp. 145-146, 2012.