臺灣博碩士論文加值系統

為了更方便的建構包含人物之虛擬環境，一低成本並易於操作之動作擷取方法在先前的研究中被提出（張朝順, 1999）。先前的研究方法主要基於圓錐曲線理論的一重要特性：空間中一已知半徑之平面圓的3D旋轉與位移資訊可由其2D的橢圓投影來獲得。
本研究主要著重於強化先前系統中不足。第一，我們利用Java Media Framework（JMF）將攝影機與本動作追蹤系統作一整合。第二，（張朝順, 1999）的研究中對於相互覆蓋與不完整之投影橢圓無法很有效的從中正確的辨別橢圓邊緣點。本研究中我們建立了四個限制條件，以在連續的影像中正確的粹取出橢圓邊緣點。第三，利用正向運動學原理並配合Quaternion Transform來自動的設置3D虛擬人物模型的動作。最後我們並討論在影像經數位化後發生誤差的情形下本系統的準確性。

To facilitate the development of a human-popularized environment, a low-cost, easy-to-operate motion capture method has been developed in a previous work (Chang, 1999). This method is based on an important property of conics theory: the 3D rotation and translation of a planar circle with known radius could be derived from its 2D elliptic projection.
This work focus on the improvement of several drawbacks suffered by previous system. First, we employ the Java Media Framework (JMF) to integrate the video camera with our motion tracking system. Secondly, (Chang, 1999)’s approach has problems identifying boundary pixels when ellipse are broken or overlapping with each other. In this work, we develop four constraints to correctly extract boundary pixels of ellipses in consecutive images. Thirdly, a forward kinematics approach, together with the quaternion transform technique, is used to automatically specify the pose of the 3D computer graphic model of a virtual human. Finally, we discuss the accuracy evaluation of our motion tracking system under digitalization error.

目錄
中文摘要 …………………………………………………………………………….i
英文摘要 ……………………………………………………………………………ii
誌謝 ……………………………………………………………………………….iii
目錄 ……………………………………………………………………………….iv
圖目錄 ……………………………………………………………………………..vi
表目錄 ……………………………………………………………………………viii
第一章 緒論1
1.1 研究背景與動機1
1.2 研究目的4
第二章 文獻探討6
2.1 接觸式動作擷取技術6
2.1.1 電磁感應追蹤系統6
2.1.2 無線光學系統6
2.1.3 機械式感應系統7
2.2 非接觸式的動作擷取技術7
2.2.1 單台攝影機動作擷取技術8
2.2.2 多台攝影機動作擷取技術9
2.3 混和式動作擷取技術9
第三章 系統與硬體之整合11
3.1 系統與硬體之溝通橋樑 - JMF11
3.2 本系統與JMF之整合15
第四章 連續影像中的橢圓參數粹取與反推3D圓盤位移與旋轉量17
4.1 橢圓追蹤17
4.2 橢圓參數估算18
4.3 橢圓邊緣點選取19
4.4 反推3D圓盤位移與旋轉量25
第五章 虛擬人物身體各部之動作產生30
5.1 虛擬人物動作的產生30
5.1.1 由各關節點的推算位置估算各關節點的旋轉矩陣31
第六章 實驗結果36
6.1 系統架構36
6.2 實驗結果38
6.2.1 伸展運動38
6.2.2 原地踏步動作41
6.2.3 歡迎動作43
6.2.4 踢足球動作46
第七章 影像數位化失真對圓盤3D位置估算之影響48
7.1 投影橢圓形狀變化時影像數位化失真對圓盤3D位置重建的影響49
7.2 提高影像解析度對於3D位置重建時誤差改善的情況54
7.3 結果討論59
第八章 結論61
參考文獻63

參考文獻
Abbott, A. (1990), Dynamic Integration of depth Cues for Surface Reconstruction from Stereo Image, Ph.D. Thesis, Department of Electrical Engineering, University of Illinois at Urbana-Champaign, 1990.
Chen, Z. and Lee, H. j., “Knowledge-Guided Visual Perception of 3-D Human Gait form a single Image Sequence,” IEEE Transactions on Systems, Man, and Cyberntics, Vol. 22, No. 2, pp. 336-342, March/April 1992.
Foley, J. D., Van Dam, A., Feiner, S. K., Hughes, J. F. and Phillips, R. L., Introduction to Computer Graphics, 1994.
Gonzalez, R. C. and Woods, R. E., “Digital Image Processing,” ADDISION WESLEY, 1992.
Hienz, H., Grobel, K. and Offner, G., ”Real-time hand-arm motion analysis using a single video camera,” Proceedings of the Second International Conference on Automatic Face and Gesture Recognition, pp. 323-327, 1996.
Holt, R. J., Netravali, A. N., Huang, T. S. and Qian, R. J., “Determining articulated motion from perspective views: a decomposition approach,” Pattern Recognition, Vol. 30, No. 9, pp. 1435-1449, 1997.
Iwasawa, S., Ohya, J., Takahashi, K., Sakaguchi, T., Kawato, S., Ebihara, K. and Morishima, S., “Real-time, 3D Estimation of Human Body Postures Trinocular Images,” Proceedings of IEEE International Workshop on Modeling People, pp. 3-10, 1999.
Ken, S., “Quaternions and 4X4 Matrices,” in James Arvo, ed., Graphics Gems II, Academic Press, Inc, pp. 351-354, 1991.
Leung, M. K. and Yang, Y. H., “First Sight:A Human Body Outline Labeling System,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 17, No. 4, pp. 359-377, April 1995.
Ma, S. D., “Conics-Based Stereo, Motion Estimation, and Pose Determination,” International Journal of Computer Vision, 10:1, pp. 7-25, 1993.
Noma, T., Oishi, I., Futsuhara, H., Baba, H., Ohashi, T. and Ejima, T. “Motion Generator Approach to Translation Human Motion from Video to Animation,” Proceedings of Seventh Pacific Conference on Computer Graphics and Applications, pp. 50 -58, 318, 1999.
O’rourke J. and Norman I. B., “Model-Based Image Analysis of Human Motion Using Constraint Propagation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-2, No. 6, pp. 522-536, November 1980.
Shinagawa, Y., Nakajima, J., Kunii, T. L. and Hara, K., Computer Animation '97, pp. 48 —57, 1997.
Sun Microsystems, Inc., “JavaTM Media Framework API Guide,” Sun Microsystems, Inc., 1999.
Wang, L. L. and Tsai, W. H., “Camera Calibration by Vanishing Lines for 3-D Computer Vision,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, NO. 4, pp. 370-376, April 1991.
Wiley, D. J. and Hahn, J. K., “Interpolation Synthesis of Articulated Figure Motion,” IEEE Computer Graphics and Applications, Volume. 17, Issue. 6, pp. 39 —45, Nov.-Dec. 1997.
Wren, C. R. and Pentland, A. P., “Understanding Purposeful Human Motion,” Proceedings of IEEE International Workshop on Modeling People, pp. 19-25, 1999.
Wu, W. Y. and Wang, M. J., “Elliptical object detection by using its geometric properties,” Pattern Recognition, Vol. 26, No. 10, 1993, pp. 1499-1509.
Yuen, H. K., Illingworth, J. and Kittler, J., “Detecting partially occluded ellipse using the Hough transform,”Image and Computer Vision, vol. 7, no. 1, pp.31-37, February 1989.
張朝舜，『以單台攝影機配合圓錐曲線理論發展網路3D場景中人物動作擷取技術』，私立元智大學，碩士論文，民國88年6月（1999）。
蔡佩瑜，『電控聚焦鏡頭之相機校正及其在深度估計上之應用』，國立臺灣大學，碩士論文，民國84年6月（1995）。