為了提高競爭力，業界傾向於利用效率更高、成本更低的智慧型工廠，其中數位工廠為不可或缺的角色。即使現代的生產系統已有足夠的技術達到高度自動化，但仍少不了人員的參與，過去傳統的數位工廠著重生產的模擬，常將關於人的部分理想化，然而新的數位模擬開始重視人的分析，也就是人的動作產生與預測方法漸漸受到重視。而實現人的動作產生與預測，需要以動作擷取系統來建立動作資料庫，因此動作擷取系統的發展關係著智慧型工廠的完備性。
現今市面上的各類動作擷取系統雖然有良好的準確性，但是除了系統本身存在的限制外，成本或使用難易度上仍不夠理想；降低動作擷取系統的成本及操作上的複雜度即為本研究努力的方向，因此本研究主要是探討如何利用少數的感知器重建全身動作的問題。在方法上，首先評估現有的系統與技術，選定適合的動作擷取系統與動作資料標準格式；接著利用主成份分析萃取真正重要的關鍵特徵資訊，將這些資訊做為輸入訓練類神經網路模型，也就是重建全身動作的模型，以利於未來用少量感知器記錄的關鍵特徵部位資訊預測其餘資料；最後利用程式自動化的方法，將繁複的操作過程再簡化。
在結果方面，過去相關的研究多將各種不同的動作分別分析，單一種類的動作重建模型需要6個左右的關節資訊，重建的關節角度誤差平均約為1度，有的研究利用相似動作的搜尋將模型推廣到多種動作；而本研究提出的方法在利用6個感知器的情況下，單一種類的動作重建誤差平均也在1度左右。與其他研究最大的不同在於本研究的模型可以應用於更多種動作，僅需要10個感知器即可重建不同種動作的資料，不必先將動作類型的分類或搜尋，重建的誤差仍在1度左右；並且整合了不同的外部資料庫、動作擷取與重建系統，能夠簡單、快速地產生動畫，可以彈性地增加更多種類的動作資料，達到降低成本與操作的複雜度。

In digital factory simulation and computer animation, the issues of human motion are complex and become more and more important. To make the process of human motion generation efficient and cost effective, this paper proposes a method to reconstruct the whole-body motion with fewer sensors in motion capture system.
The main part is to construct the human motion reconstruction model by using a motion database. The first step is to select the key data of joints by PCA (principal component analysis). Then the selected data are taken as the input to train the artificial neural network model. The trained model can predict the data of the remaining joints with the fewer sensors on the subjects.
The results show that we can use the trained model to reconstruct the human motion well by using partial joint data with fewer sensors. The average reconstruction error of the model for single motion type with information of 6 features is about 1 degree per joint angle. It is similar to the previous works. The main difference is that the method can be easily applied to various motion types and have good performances. The average reconstruction error of the model for various motion types with 10 sensors is also about 1 degree per joint angle.
Additionally, this paper provides a simple and fast approach to integrate motion capture system, motion reconstruction model and different motion databases. All the exported motion data can be easily used to animate the digital human model in virtual environment.

1. Visual Components網站。www.visualcomponents.com/
2. Xsens網站。www.xsens.com/
3. Awad, C., N. Courty, K. Duarte, T. Le Naour, S. Gibet, 2009. “A Combined Semantic and Motion Capture Database for Real-time Sign Language Synthesis.” Proceedings of the 9th International Conference on Intelligent Virtual Agents (IVA’09), Amsterdam, volume 5773 of Lecture Notes in Artificial Intelligence, pages 432-438. Springer.
4. Barton, G., A. Lees, P. Lisboa, and S. Attfield, 2006. “Visualisation of gait data with Kohonen self-organising neural maps.” Gait & Posture 24(1): 46-53.
5. Çetiner, B. G. and M. Sar, 2010. “Tibial Rotation Assessment Using Artificial Neural Networks.” Mathematical and Computational Applications 15(1): 34-44.
6. Chai, J. and J. K. Hodgins, 2005. “Performance Animation from Low-dimensional Control Signals.” ACM Trans Graph 24(3): 686–696.
7. Chang, L. Y., N. S. Pollard, T. M. Mitchell, and E. P. Xing, 2007. “Feature Selection for Grasp Recognition from Optical Markers.” Proceedings of the 2007 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2007), pages 2944–2950.
8. Chen, H., 2003. “The Correlation between Energy Absorption Ratio and Joint Loading of the Upper Extremity under Different Fall Heights.”
9. Cho, M., 2005. “Effects of Materials of Wrist Guard and Arrest Strategies on Impact Force during Forward Falls.”
10. Chung, H. S. and Y. Lee, 2004. “MCML: motion capture markup language for integration of heterogeneous motion capture data.” Computer Standards & Interfaces 26(2): 113-130.
11. Cope, E., 2009. “Estimating Human Movement Using a Three Axis Accelerometer.” PhD Thesis, Arizona State University.
12. Corrales, J. A., F. A. Candelas, F. Torres, 2010. “Sensor data integration for indoor human tracking.” Robotics and Autonomous Systems 58(8): 931-939.
13. Duffy, V., 2007. “Digital Human Modeling.” Springer-Verlag Berlin Heidelberg.
14. Etou, H., Y. Okada, and K. Niijima, 2004. “Feature preserving motion compression based on hierarchical curve simplification.”
15. Giansanti, D., V. Macellari, G. Maccioni, and V. Macellari, 2005. “The Development and Test of a Device for the Reconstruction of 3-D Position and Orientation by Means of a Kinematic Sensor Assembly With Rate Gyroscopes and Accelerometers.” IEEE Transactions on Biomedical Engineering 52(7): 1271–1277.
16. Guerra-Filho, G. B., 2005. “Optical motion capture: theory and implementation.” Journal of Theoretical and Applied Informatics 12(2): 61–89.
17. JHA, P., 2009. "Novel Artificial Neural Network Application for Prediction of Inverse Kinematics of Manipulator." Thesis, National Institute of Technology.
18. Karduna, A. R., P. W. McClure, L. A. Michener, 2000. “Scapular kinematics: effects of altering the Euler angle sequence of rotations.” Journal of Biomechanics 33: 1063–1068.
19. Li, S. and M. Okuda, 2010. “Iterative frame decimation and watermarking for human motion animation.” ICGST International Journal on Graphics, Vision and Image Processing,Special Issue on Watermarking 7: 41-48.
20. Liebowitz, D. and S. Carlsson, 2003. “Uncalibrated motion capture exploiting articulated structure constraints.” International Journal of Computer Vision 51(3): 171-187.

21. Lind, S., B. Krassi, J. Viitaniemi, S. Kiviranta, J. Heilala, and C. Berlin, 2008. ” Linking Ergonomics Simulation to Production Process Development.” Proceedings of the 2008 Winter Simulation Conference.
22. Liu, G., J. Zhang, W. Wang, L. McMillan, 2006. “Human Motion Estimation from a Reduced Marker Set.” Proceedings of ACM SIGGRAPH Symposium on Interactive 3D Graphics (I3D), 2006: 35–42.
23. Liu, S., Y. Wang, Q. Zhu, 2008. “Development of a new EDRNN procedure in control of human arm trajectories.” Neurocomputing 72(1-3): 490-499.
24. Luciani, A., M. Evrard, D. Couroussé, N. Castagné, C. Cadoz, and J. L. Florens, 2006. “A basic gesture and motion format for virtual reality multisensory application.” Proceedings of the 1st international Conference on Computer Graphics Theory and Applications, Setubal, Portugal, March 2006.
25. Miller, N., O. C. Jenkins, M. Kallmann, and M. J. Matri'C, 2004. “Motion capture from inertial sensing for untethered humanoid teleoperation.” International Conference of Humanoid Robotics: 547-565.
26. Paliwal M. and U. A. Kumar, 2009. “Neural networks and statistical techniques: A review of applications.” Expert Systems with Applications 36(1): 2-17.
27. Perez, M. A., 2005. “Prediction of whole-body lifting kinematics using artificial neural networks.” Ph.D. dissertation, Virginia Tech, Blacksburg, VA, 2005.
28. Perez, M. A. and M. Nussbaum, 2008. “A neural network model for predicting postures during non-repetitive manual materials handling tasks.” Ergonomics 51(10): 1549-1564.
29. Ram, S. S. and H. Ling, 2008. “Simulation of Human MicroDopplers Using Computer Animation Data.” Proceedings of IEEE Radar Conference: 1-6.
30. Rezzoug, N. and P. Gorce, 2008. “Prediction of fingers posture using artificial neural networks.” Journal of Biomechanics 41(12): 2743-2749.
31. Rigotti, C., P. Cerveri, G. Andreoni, A. Pedotti, G. Ferrigno, 2001. “Modeling and driving a reduced human mannequin through motioncaptured data: a neural network approach.” IEEE Transactions on Systems, Man and Cybernetics, Part A 31(3): 187-193.
32. Roetenberg, D., 2006. “Inertial and magnetic sensing of human motion,” PhD Thesis, University of Twente.
33. Roetenberg, D., P. Slycke, and P. Veltink, 2007. “Ambulatory Position and Orientation Tracking Fusing Magnetic and Inertial Sensing.” IEEE Transactions on Biomedical Engineering 54: 883–890.
34. Saikko, V. and O. Calonius, 2002. “Slide track analysis of the relative motion between femoral head and acetabular cup in walking and in hip simulators.” Journal of Biomechanics 35(4): 455-464.
35. Schepers, H. M., Roetenberg, D., Veltink, P.H., 2010. “Ambulatory human motion tracking by fusion of inertial and magnetic sensing with adaptive actuation.” Medical and Biological Engineering and Computing 48: 27–37.
36. Siebers, P. O., 2004. “The Impact of Human Performance Variation on The Accuracy of Manufacturing System Simulation Models.” Cranfield University, School of Industrial and Manufacturing Science. PhD Thesis.
37. Siebers, P. O., 2006. “Worker Performance Modeling in Manufacturing Systems Simulation.” Chapter in J-P. Rennard (Eds.) Handbook of Research on Nature Inspired Computing for Economy and Management. Pennsylvania: Idea Group Publishing.
38. Simmons, J., 2010. “A self-contained motion capture platform for e-textiles.” Dissertation, Virginia Polytechnic Institute and State University, America.
39. Tautges, J., B. Kr¨uger, A. Zinke, A. Weber, 2008. “Tracking of Human Body Motions Using Very Few Inertial Sensors.”
40. Tenorth, M., J. Bandouch, M. Beetz, 2009. “The TUM Kitchen Data Set of Everyday Manipulation Activities for Motion Tracking and Action Recognition.” In IEEE International Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS) at ICCV, 2009.
41. Wu, G., S. Siegler, P. Allard, C. Kirtley, A. Leardini, D. Rosenbaum, M. Whittle, D. D'Lima, L. Cristofolini, H. Witte, O. Schmid, I. Stokes, 2002. ”ISB recommendation on definition of joint coordinate systems of various joints for the reporting of human joint motion-part I: ankle, hip and spine.” Journal of Biomechanics 35(4): 543-548.
42. Wu, G., F. van der Helm, H. E. J. Veeger, M. Makhsous, P. Van Roy, C. Anglin, J. Nagels, A. Karduna, K. McQuade, X. Wang, F. Werner, B. Bucholz, 2005. “ISB recommendation on definitions of joint coordinate systems of various joints for the reporting of human joint motion—Part II: shoulder, elbow, wrist and hand.“ Journal of Biomechanics 38: 981-992.
43. Xie, L., M. Kumar, Y. Cao, D. Gracanin, and F. Quek, 2008. “Data-driven Motion Estimation with Low-cost Sensors.” The 5th IET Visual Information Engineering 2008 Conference (VIE’08).
44. Zhang, K., M. Sum, D. K. Lester, F. X. Sunyer, C. N. Boozer, and R. W. Longman, 2005. “Assessment of human locomotion by using an insole measurement system and artificial neural networks.” Journal of Biomechanics 38(11): 2276–2287.
45. Zhou, H. and H. Hu, 2008. “Human motion tracking for rehabilitation–A survey.” Biomedical Signal Processing and Control 3(1): 1–18.
46. 許佑綸，2007。使用遞迴型神經網路之肌電圖動態動作預測機制。國立交通大學碩士論文。
47. 羅華強，2005。類神經網路－MATLAB的應用。高立圖書有限公司。
48. 蘇晨豪，2010。即時動作及生理負荷評估系統建立。國立清華大學碩士論文。