人物動作的攝影機路徑規劃一直以來都是一個基礎的研究議題，許多實務應用都受益於這方面的技術發展。現有的透過全域最佳化來規劃攝影機路徑的方式，在效能尚無法適用於互動操作的應用上。即時計算的攝影機路徑產生器所得到的結果亦未能滿足使用者觀看上的需要。因此在這個研究中，我們首先提供了一個具有即時運算潛力的高效能攝影機路徑演算法。在著重於效能的同時，我們也同時將許多現有的攝影機規劃限制和評估方式整合到我們的系統，藉此產生媲美全域最佳化的結果。相對於解決一個高度複雜的攝影機在四維時空中的路徑優化問題，我們採用了一個基於貪婪搜尋的樹狀結構搜尋演算法來巧妙的推斷攝影機路徑。實驗的結果顯示，在這樣的架構之下可以有效地產生穩定且富含資訊的攝影機路徑，同時忠實地捕捉人物動作中相對重要的動作。透過使用者問卷調查，我們演算法和目前頂尖的研究成果以及專業動畫師所製作的結果對於使用者來說具有相似的觀看體驗。
再者，一連串的人物活動之間所產生的事件也是相當令感興趣的。在虛擬世界中，一群虛擬角色會相互交流互動(傳遞物品,握手)並隨著時間改變群組關係。在受到社會學研究的啟發後，我們提出一個新穎的方式來透過分析在群眾之間的社交事件以及群體運動。我們利用人際關係學、社會力以及社群網路分析的方式來評估社交事件之間的動態關係，以及身處相同事件中人物之間的交互運動。透過這樣的方式來分析事件中人物之間關係力的波動以及空間位置的相互關聯的改變量，藉此人群活動中挖掘出相對重要的社交事件。並且根據分析結果自動化的產生一個穩定的攝影機路徑來拍攝由系統分析出來的重要事件，或是由使用者決定的重要人物所引發的事件。如此系統可以利用退火演算法最佳化出一個穩定且包含最多資訊的攝影機運鏡結果。在本研究中，我們測試了許多不同的群眾運動動作資料，並且提供了兩類不同的使用者問卷來評估攝影機運鏡的順暢性以及可讀性。在這樣的評估中，我們的結果明顯的勝過沒有事件分析的攝影機運鏡結果，並同時達到可以跟專業製作的影片相比的可讀性。

Camera path planning for character motions is a fundamental and important research topic, benefiting many animation applications. Existing optimal-based approaches are generally computationally expensive and infeasible for interactive applications. Current human viewer still not satisfied with presented real-time camera control. In this work, we propose an efficient approach that can take many constraints of finding the camera path into account and can potentially enable interactive camera control. With these view point quality measurements and efficient camera path planning, we could generator high competent result efficiently.

Instead of solving a highly complicated camera optimization problem in a spatiotemporal four-dimensional space, we heuristically determine the camera path based on an efficient greedy-based tree traversal approach.
The experimental results show that the proposed approach can efficiently generate a smooth, informative, and aesthetic camera path that can reveal the significant features of character motions. Moreover, the conducted user study also shows that the generated camera paths are comparable to those of a state-of-the-art approach and those made by professional animators.

Furthermore, the interaction among individuals and groups often produces interesting events in a sequence of animation. In a virtual world, a group of virtual characters can interact with each other, (e.g., passing objects, shaking hands) and may dynamically form or dismiss from time to time. Here we propose a novel approach to discover social events involving mutual interactions or group activities in multi-character animations and automatically plan a smooth camera motion to view interesting events suggested by our system or relevant events specified by a user.

Inspired by sociology studies, we borrow the knowledge in proxemics, social force, and social network analysis to model the dynamic relation among social events and the relation among the participants within each event. By analyzing the variation of relation strength among participants and spatiotemporal correlation among events, we discover salient social events in a motion clip and generate an overview video of these events with smooth camera motion using a simulated annealing optimization method. We tested our approach on different motions performed by multiple characters and also conducted two user studies to evaluate the smoothness and comprehensibility of camera control in our results. This evaluation shows that our approach is clearly preferred over the camera control without event analysis and comparable with professional results by an artist.

[1] B. Apolloni, C. Carvalho, and D. de Falco. Quantum stochastic optimization. Stochastic Processes and their Applications, 33(2):233-244, 1989.
[2] D. Arijon. Grammar of the lm language. Silman-James Press, 1976.
[3] J. Assa, Y. Caspi, and D. Cohen-Or. Action synopsis: pose selection and illustration. ACM Transactions on Graphics, 24:667-676, July 2005.
[4] J. Assa, D. Cohen-Or, I.-C. Yeh, and T.-Y. Lee. Motion overview of human actions. ACM Transactions on Graphics, 27:115:1-115:10, 2008.
[5] J. Assa, L.Wolf, and D. Cohen-Or. The virtual director: a correlation-based online viewing of human motion. Computer Graphics Forum, 29(2):595-604, 2010.
[6] W. H. Bares, S. Thainimit, and S. McDermott. A model for constraint-based camera planning. In Proceeding of the 2000 AAAI Spring Symposium, volume 4, pages 84-91, 2000.
[7] F. Benhamou, F. Goualard, E. Langu enou, and M. Christie. Interval constraint solving for camera control and motion planning. ACM Transactions on Computer Logic, 5:732-767, 2004.
[8] V. Blanz, M. J. Tarr, and H. H. Bultho . What object attributes determine canonical views. Perception, 28(5):575-600, 1999.
[9] Y. G. Cheong, A. Jhala, B. C. Bae, and R. M. Young. Automatically generating summary visualizations from game logs. In C. Darken, M. Mateas, C. Darken, and M. Mateas, editors, AIIDE. The AAAI Press, The AAAI Press, 2008.
[10] M. Christie, R. Machap, J. marie Norm, P. Olivier, and J. Pickering. Virtual camera planning: A survey. In Proceedings of Smart Graphics, pages 40-52.
[11] M. Christie and P. Olivier. Camera control in computer graphics: models, techniques and applications. In ACM SIGGRAPH ASIA 2009 Courses, pages 1-197. ACM, 2009.
[12] T. Corrigan and P. White. The Film Experience, page 140. Bedford/St. Martin's, 2004.
[13] H. A. David. The Method of Paired Comparisons. Charles Gri n & Company Ltd, London, 1988.
[14] D. DeMenthon, V. Kobla, and D. Doermann. Video summarization by curve simpli cation. In MULTIMEDIA '98: Proceedings of the sixth ACM international conference on Multimedia, pages 211-218. ACM, 1998.
[15] S. M. Drucker and D. Zeltzer. Intelligent camera control in a virtual environment. In GI '94: Proceedings of Graphics Interface 1994, pages 190-199, 1994.
[16] S. M. Drucker and D. Zeltzer. Camdroid: A system for implementing intelligent camera control. In Proceedings of 1995 Symposium on Interactive 3D Graphics, pages 139-144, 1995.
[17] L. Freeman. The Development of Social Network Analysis. Empirical Press, Vancouver, 2006.
[18] R. Grassi, S. Stefani, and A. Torriero. Some new results on the eigenvector centrality. The Journal of Mathematical Sociology, 31(3):237-248, 2007.
[19] E. T. Hall. The Hidden Dimension. Anchor Book, 1966.
[20] N. Halper, R. Helbing, and T. Strothotte. A camera engine for computer games: Managing the trade-o between constraint satisfaction and frame coherence. In Eurographics 2001 Conference Proceedings, volume 20(3), pages 174-183, 2001.
[21] N. Halper and P. Olivier. Camplan: A camera planning agent. In Proceedings of the 2000 AAAI Spring Symposium on Smart Graphics, pages 92-100, 2000.
[22] L.-W. He, M. F. Cohen, and D. H. Salesin. The virtual cinematographer: a paradigm for automatic real-time camera control and directing. SIGGRAPH 1996 Conference Proceedings, pages 217-224, 1996.
[23] D. Helbing and P. Molnar. Social force model for pedestrian dynamics. Physical Review E, 51(5):4282-4286, May 1995.
[24] Y. Hu, S. Wu, S. Xia, J. Fu, and W. Chen. Motion track: Visualizing variations of human motion data. In Paci cVis '10: Proceedings of IEEE Paci c Visualization Symposium, pages 153-160, 2010.
[25] F. Jardillier and E. Langu enou. Screen-space constraints for camera movements: the virtual cameraman. Computer Graphics Forum, 17(3):175-186, 1998.
[26] A. Johansson, D. Helbing, and P. Shukla. Speci cation of the social force pedestrian model by evolutionary adjustment to video tracking data. Advances in Complex Systems, 10(2):271-288, 2007.
[27] K. Kardan and H. Casanova. Virtual cinematography of group scenes using hierarchical lines of actions. In Sandbox '08: Proceedings of the 2008 ACM SIGGRAPH symposium on Video games, pages 171-178, 2008.
[28] S. D. Katz. Film Directing Shot by Shot: Visualizing from Concept to Screen. Michael Wiese Productions, 1991.
[29] M. Kim, K. Hyun, J. Kim, and J. Lee. Synchronized multi-character motion editing. ACM Transactions on Graphics, 28(3):1-9, 2009.
[30] J.-Y. Kwon and I.-K. Lee. Determination of camera parameters for character motions using motion area. The Visual Computer, 24:475-483, 2008.
[31] K. Lewin. Field Theory in Social Science. Harper and Brothers, 1951.
[32] T.-C. Lin, Z.-C. Shih, and Y.-T. Tsai. Wscg. In Proceeding of Cinematic Camera Control in 3D Computer Games, pages 289-296, 2004.
[33] C. Lino, M. Christie, F. Lamarche, G. Scho eld, and P. Olivier. A real-time cinematography system for virtual 3d environments. In SCA '10: Proceedings of the 2010 ACM SIGGRAPH/Eurographics Symposium on Computer Animation,
2010.
[34] H. McCabe and J. Kneafsey. A virtual cinematography system first person shooter games. In Proceedings of International Digital Games Conference, pages 25-35, 2006.
[35] R. Mehran, A. Oyama, and M. Shah. Abnormal crowd behavior detection using social force model. In CVPR '09: Proceedings of Computer Vision and Pattern Recognition, pages 935-942, 2009.
[36] M. Mortara and M. Spagnuolo. Technical section: Semantics-driven best view of 3d shapes. Comput. Graph., 33:280-290, 2009.
[37] P. Olivier, J. Pickering, N. Halper, and P. Luna. Visual composition as optimisation. In AISB Workshop on AI and Creativity in Entertainment and Visual Art,
pages 22-30, 1999.
[38] J. H. Pickering. Intelligent Camera Planning for Computer Graphics. PhD thesis, University of York, 2002.
[39] O. Polonsky, G. Patan e, S. Biasotti, C. Gotsman, and M. Spagnuolo. What's in an image: Towards the computation of the "best" view of an object. The Visual Computer, 21(8-10):840-847, 2005.
[40] G. Shakhnarovich, T. Darrell, and P. Indyk, editors. Nearest-Neighbor Methods in Learning and Vision: Theory and Practice. MIT Press, March 2006.
[41] C. Turkay, E. Koc, and S. Balcisoy. An information theoretic approach to camera control for crowded scenes. The Visual Computer, 25(5-7):451-459, 2009.
[42] T. Vieira, A. Bordignon, A. Peixoto, G. Tavares, H. Lopes, L. Velho, and T. Lewiner. Learning good views through intelligent galleries. In Eurographics 2009 Conference Proceedings, pages 717-726, 2009.
[43] M. Vlachos, G. Kollios, and D. Gunopoulos. Discovering similar multidimensional trajectories. In Proceedings of the 18th International Conference on Data Engineering, ICDE '02, pages 673-, Washington, DC, USA, 2002. IEEE Computer
Society.
[44] S. Wasserman and K. Faust. Social Network Analysis: Methods and Applications. Cambridge University Press, Cambridge, UK, 1994.