近來，有越來越多的動作擷取資料應用於各式不同的方面，像是電腦遊戲，動畫及虛擬環境的建構。因此當我們想要了解動作資料庫時，動作之概觀介紹是一個非常重要的議題。到目前為止，關於單人的動作概觀介紹已有被探討過，但是多人動作瀏覽的研究仍然非常稀少。如何去分析多人動畫是一件困難的任務。

與以往的研究不同，我們藉由人際距離學，社會力以及社群網絡分析，去模組化人與人的動態關係。分析人與人的關係，可以在一段動畫期間當中發現重要的時刻。藉由分析出的結果，由攝影機去追蹤重要的人物，產生多人動畫之運鏡規劃；或是利用人物的重要性挑出關鍵影格製作分鏡腳本，是本篇研究主要的兩個應用。除此之外還可衍生出動作萃取，動作修改等等有用的工具。

In these days, there is more and more motion capture data has been used in various applications, such as computer games, animations and virtual environment. The motion overview is an important issue when we want to see into the motion data base. So far, the motion overview of single character problem has been addressed, but the works about motion overview of multi-character animations are still very few. How to analysis multi-character animation is a difficult mission.

Different from previous study, we borrow the knowledge in Proxemics, social force and social network analysis to model the dynamic relation between the participators. By analyzing the variation of relation among the participators, we can discover importance moment in the motion period. According to analysis result, we generate camera path planning by focus on importance character. We can also choose keyframe to produce a storyboard. The work can be extended to various applications, such as motion extraction and motion editing tools.

[1] ASSA, J., CASPI, Y., AND COHEN-OR, D. Action synopsis: Pose selection and illustration. In SIGGRAPH 2005 Conference Proceedings, vol. 24, 667–676. 2005.
[2] ASSA, J., COHEN-OR, D., YEH, I.-C., AND LEE, T.-Y. Motion overview of human actions. In ACM SIGGRAPH Asia 2008, 1–10. 2008.
[3] ASSA, J., WOLF, L., AND COHEN-OR, D. The virtual director: A correlation based online viewing of human motion. In Eurographics. 2010.
[4] BARES, W. H., THAINIMIT, S., AND MCDERMOTT, S. A model for constraint based camera planning. In Smart Graphics, Papers from the 2000 AAAI Spring Symposium, AAAI Press, vol. 4, 84–91. 2000.
[5] BONACICH, P. Technique for analyzing overlapping membership. In H. L. Costner, (ed.), Sociological Methodology (pp. 176–185). San Francisco: Jossey-Bass. 1972.
[6] CHRISTIE, M., AND OLIVIER, P. Camera control in computer graphics: models, techniques and applications. In ACM SIGGRAPH ASIA 2009 Courses, 1–197. 2009.
[7] CORREA, C. D., MA, K-L. Dynamic Video Narratives. ACM Trans. on Graphics, Volume 29, Number 3 – 2010. 2010.
[8] DRUCKER, S. M., AND ZELTZER, D. Intelligent camera control in a virtual environment. In Proceedings of Graphics Interface ’94, 190–199. 1994.
[9] FREEMAN, L. The Development of Social Network Analysis. Empirical Press, Vancouver. 2004.
[10] FREEMAN, W. T., AND ZHANG, H. Shape-time photography. In Proc. Computer Vision and Pattern Recognition, 151–157. 2003.
[11] Grassi, R., Stefani, S., Torriero, A.. Some newresults on the eigenvector centrality. Journal of Mathematical Sociology. 31, 237–248 .2007.
[12] GOLDMAN, D.B., CURLESS, B., SALESIN, D., SEITZ, S.M. Schematic storyboarding for video visualization and editing. ACM Trans. Graph. 25, 3, 862–871. 2006.
[13] HALL, E. T. The Hidden Dimension. Anchor Book. 1966.
[14] HALPER, N., HELBING, R., AND STROTHOTTE, T. A camera engine for computer games: Managing the trade-off between constraint satisfaction and frame coherence. In Eurographics 2001, vol. 20(3), 174–183. 2001.
[15] Hanneman, R. A. & Riddle M. Introduction to Social Networks Methods. Riverside, CA: University of Carolina, Riverside. 2005.
[16] HART, J. The art of the storyboard: storyboarding for film, TV and animation. Focal Press. 1999
[17] HE, L.-W., COHEN, M. F., AND SALESIN, D. H. The virtual cinematographer: a paradigm for automatic real-time camera control and directing. In SIGGRAPH 1996 Conference Proceedings, ACM, 217–224. 1996.
[18] HELBING, D., AND MOLNAR, P. Social force model for pedestrian dynamics. Physical Review E 51, 4282-4286. 1995.
[19] JOHANSSON, A., HELBING, D., AND SHUKLA, P., K.. Specification of the social force pedestrian model by evolutionary adjustment to video tracking data. Advances in Complex Systems 2008.
[20] KATZ, S. D. Film Directing Shot by Shot: Visualizing from Concept to Screen. Michael Wiese Productions. 1991.
[21] KIM, M., HYUN, K., KIM, J., AND LEE, J. Synchronized multi-character
motion editing. ACM Trans. Graph. 28, 3, 1–9. 2009.
[22] King, A.J., Cowlishaw, G., Leaders, followers, and group decision-making. Communicative and Integrative Biology, 2. 2009.
[23] KWON, J.-Y., AND LEE, I.-K. Detemination of camera parameters for character motions using motion area. The Visual Computer 24, 475–483. 2008.
[24] LEWIN, K. Field Theory in Social Science. Harper and Brothers, New York. 1951.
[25] MCCABE, H., AND KNEAFSEY, J. A virtual cinematography system for first person shooter games. In Proceedings of International Digital Games Conference, 25–35. 2006.
[26] MEHRAN, R., OYAMA, A., AND SHAH, M. Abnormal crowd behavior detection using social force model. In CVPR09, 935–942. 2009.
[27] Sueur C, Petit O. Organization of group members at departure is driven by social structure in Macaca. Int J Primatol 29:1085–1098. 2008.
[28] TURKAY, C., KOC, E., AND BALCISOY, S. An information theoretic approach to camera control for crowded scenes. Vis. Comput. 25, 5-7, 451–459. 2009.
[29] VIEIRA, T., BORDIGNON, A., PEIXOTO, A., TAVARES, G., LOPES, H., VELHO, L. AND LEWINER, T. Learning good views through intelligent galleries. In Eurographics, 717–726. 2009.
[30] VLACHOS, M., KOLLIOS, G., AND GUNOPULOS, D. Discovering similar multidimensional trajectories. In International Conference on Data Engineering, 673–684. 2002.
[31] WANG, J., XU, Y., SHUM, H.-Y., AND COHEN, M. F. Video tooning. In SIGGRAPH ’04: ACM SIGGRAPH 2004 Papers, 574–583. 2004.
[32] WEXLER, Y., AND SIMAKOV, D. Space-time scene manifolds. In Proc. ICCV, 858–863. 2005.