本研究利用RGB-D深度感測裝置來建立一套適用於運動教學訓練的軟體工具，並以醫療教育用途為主要考量。此工具包括以下幾種功能：第一為參考姿勢影片錄製功能，用以錄製教學者所示範的動作。第二是比對資料錄製的功能，工具集擷取從RGB-D感測器所感測到的人體骨架資料並且將資料儲存為XML格式檔案，並可和事先錄製的參考姿勢比對。第三則是分辨受訓者追蹤骨架資訊的功能，當RGB-D感測器同一時間有兩個人存在於感測範圍，身體又很接近時，RGB-D的感測功能容易被混淆而造成骨架資訊混亂，不易區分兩者骨架。我們利用感測器所擷取到的深度資料來判斷分辨受訓者的骨架資訊，以解決此問題。

This research introduces commodity RGB-D sensors to build a software tool for comparing human body motions, especially for people to learn new exercises. The goal of the tool is an exercise training tool for medical education. With this toolkit, a user can training oneself at any time and any place. First, a trainer (or an expert) would build a sample video for the target exercise. The trainer would mark the important posture on the recorded video. Secondly, the trainee would perform the same exercise. The trainee’s video is also recorded. The tool illustrates a comparison between the important posture made by the trainer and the trainee. The differences are highlighted. In this way, the trainee is ex-pected to have better training performance. The technology improvements over the com-modity available package are that the display of the trainee’s and trainer’s skeletons is smoothed. And the problem that when two persons are too close their skeletons would confuse the RGB-D is also solved. A model is developed to trace the motion of the target person.

[1] S. de Ribaupierre, B. Kapralos, F. Haji, E. Stroulia, A. Dubrowski, and R. Eagleson, "Healthcare Training Enhancement Through Virtual Reality and Serious Games," in Virtual, Augmented Reality and Serious Games for Healthcare 1. vol. 68, M. Ma, L. C. Jain, and P. Anderson, Eds., ed: Springer Berlin Heidelberg, 2014, pp. 9-27.
[2] Y. Yang, P. Fang, L. Yan, L. Shuyu, F. Yubo, and L. Deyu, "Reliability and Validity of Kinect RGB-D Sensor for Assessing Standing Balance," IEEE Sensors Journal, , vol. 14, pp. 1633-1638, 2014.
[3] B. Mentiplay, R. Clark, A. Mullins, A. Bryant, S. Bartold, and K. Paterson, "Reliability and validity of the Microsoft Kinect for evaluating static foot posture," Journal of Foot and Ankle Research, vol. 6, p. 14, 2013.
[4] Y. Fouda and K. Ragab, "An efficient implementation of normalized cross-correlation image matching based on pyramid," in 2013 International Joint Conference on Awareness Science and Technology and Ubi-Media Computing (iCAST-UMEDIA), , 2013, pp. 98-103.
[5] M. Raptis, D. Kirovski, and H. Hoppe, "Real-time classification of dance gestures from skeleton animation," presented at the Proceedings of the 2011 ACM SIGGRAPH/Eurographics Symposium on Computer Animation, Vancouver, British Columbia, Canada, 2011.
[6] L. Miranda, T. Vieira, D. M. Morera, T. Lewiner, A. W. Vieira, and M. F. M. Campos, "Real-Time Gesture Recognition from Depth Data through Key Poses Learning and Decision Forests," presented at the SIBGRAPI, 2012.
[7] R. Vemulapalli, F. Arrate, and R. Chellappa, "Human Action Recognition by Representing 3D Skeletons as Points in a Lie Group," in 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), , 2014, pp. 588-595.
[8] F. Vetere, K. O'Hara, J. Paay, B. Ploderer, R. Harper, and A. Sellen, "Social NUI: social perspectives in natural user interfaces," presented at the Proceedings of the 2014 companion publication on Designing interactive systems, Vancouver, BC, Canada, 2014.
[9] K. Berger, "A State of the Art Report on Multiple RGB-D Sensor Research and on Publicly Available RGB-D Datasets," in Computer Vision and Machine Learning with RGB-D Sensors, L. Shao, J. Han, P. Kohli, and Z. Zhang, Eds., ed: Springer International Publishing, 2014, pp. 27-44.
[10] I. Culjak, D. Abram, T. Pribanic, H. Dzapo, and M. Cifrek, "A brief introduction to OpenCV," in 2012 Proceedings of the 35th International Convention MIPRO, , 2012, pp. 1725-1730.
[11] 許孟勤, "使用消費型無標記動作擷取裝置之人體姿勢比對工具集," 碩士論文, 工程科學系, 國立成功大學, 台南市, 2012.
[12] W.-G. Teng, M.-C. Hsu, Y.-Y. Hsu, and T.-W. Hou, "Posture Identification with Markerless Commodity Devices," Advanced Science Letters, vol. 9, pp. 399-405, 2012.
[13] A. P. Gritti, O. Tarabini, J. Guzzi, G. A. Di Caro, V. Caglioti, L. M. Gambardella, et al., "Kinect-based people detection and tracking from small-footprint ground robots," in 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2014), , 2014, pp. 4096-4103.
[14] X. Chen and M. Koskela, "Classification of RGB-D and Motion Capture Sequences Using Extreme Learning Machine," in Image Analysis. vol. 7944, J.-K. Kämäräinen and M. Koskela, Eds., ed: Springer Berlin Heidelberg, 2013, pp. 640-651.
[15] H. Jungong, S. Ling, X. Dong, and J. Shotton, "Enhanced Computer Vision With Microsoft Kinect Sensor: A Review," IEEE Transactions on Cybernetics, , vol. 43, pp. 1318-1334, 2013.
[16] G. T. Papadopoulos, A. Axenopoulos, and P. Daras, "Real-Time Skeleton-Tracking-Based Human Action Recognition Using Kinect Data," presented at the MMM 1, 2014.
[17] O. Patsadu, C. Nukoolkit, and B. Watanapa, "Human gesture recognition using Kinect camera," in 2012 International Joint Conference on Computer Science and Software Engineering (JCSSE), 2012, pp. 28-32.
[18] R. R. Bond, D. D. Finlay, C. D. Nugent, and G. Moore, "An XML Format for storing Body Surface Potential Map recordings," in Computers in Cardiology, 2009, 2009, pp. 233-236.
[19] A. Jana, Kinect for Windows SDK Programming Guide: Packt Publishing, 2012.
[20] E. J. Almazan and G. A. Jones, "Tracking People across Multiple Non-overlapping RGB-D Sensors," in 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), , 2013, pp. 831-837.
[21] H. S. Koppula, R. Gupta, and A. Saxena, "Learning human activities and object affordances from RGB-D videos," The International Journal of Robotics Research, vol. 32, pp. 951-970, July 1, 2013 2013.
[22] K. Adistambha, C. H. Ritz, and I. S. Burnett, "Motion classification using Dynamic Time Warping," in IEEE 10th Workshop on Multimedia Signal Processing, 2008, 2008, pp. 622-627.
[23] M. Raptis, I. Kokkinos, and S. Soatto, "Discovering discriminative action parts from mid-level video representations," in 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), , 2012, pp. 1242-1249.
[24] R. Poppe, "A survey on vision-based human action recognition," Image and Vision Computing, vol. 28, pp. 976-990, 6// 2010.
[25] Z. Wenbing, F. Hai, R. Lun, D. D. Espy, and M. A. Reinthal, "A Kinect-based rehabilitation exercise monitoring and guidance system," in 2014 5th IEEE International Conference on Software Engineering and Service Science (ICSESS), , 2014, pp. 762-765.
[26] L. Jiann-der, H. Chung-Hung, and L. Ting-Yang, "A Kinect-based Tai Chi exercises evaluation system for physical rehabilitation," in 2014 IEEE International Conference on Consumer Electronics (ICCE), , 2014, pp. 177-178.
[27] C.-Y. Su, F.-A. Huang, C.-Y. Shih, and Y.-T. Chen, "Kinect-based midair handwritten number recognition system for dialing numbers and setting a timer," in 2014 IEEE International Conference on Systems, Man and Cybernetics (SMC), , 2014, pp. 2127-2130.
[28] A. Kadambi, A. Bhandari, and R. Raskar, "3D Depth Cameras in Vision: Benefits and Limitations of the Hardware," in Computer Vision and Machine Learning with RGB-D Sensors, L. Shao, J. Han, P. Kohli, and Z. Zhang, Eds., ed: Springer International Publishing, 2014, pp. 3-26.
[29] S. Ju, W. Xiao, Y. Shuicheng, C. Loong-Fah, C. Tat-Seng, and L. Jintao, "Hierarchical spatio-temporal context modeling for action recognition," in IEEE Conference on, 2009 Computer Vision and Pattern Recognition, 2009. CVPR 2009., pp. 2004-2011.
[30] C. Chen, K. Liu, and N. Kehtarnavaz, "Real-time human action recognition based on depth motion maps," Journal of Real-Time Image Processing, pp. 1-9, 2013/08/11 2013.
[31] S. Choppin and J. Wheat, "The potential of the Microsoft Kinect in sports analysis and biomechanics," Sports Technology, vol. 6, pp. 78-85, 2013/05/01 2013.
[32] H. Fuchs, A. State, and J. C. Bazin, "Immersive 3D Telepresence," Computer, vol. 47, pp. 46-52, 2014.
[33] A. Maimone and H. Fuchs, "Real-time volumetric 3D capture of room-sized scenes for telepresence," in 3DTV-Conference: The True Vision - Capture, Transmission and Display of 3D Video (3DTV-CON), 2012, 2012, pp. 1-4.
[34] S. X. M. Yang, M. S. Christiansen, P. K. Larsen, T. Alkjær, T. B. Moeslund, E. B. Simonsen, et al., "Markerless motion capture systems for tracking of persons in forensic biomechanics: an overview," Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 2, pp. 46-65, 2014/01/02 2013.