由於傳統的自然模擬方式往往透過物理方程式或是程序式設計來達成，但在實際視覺感受和科學計算上往往不能產生直接的連結。另一方面，影像重建領域的文獻對於其產生的結果缺乏互動性以及無法產生連續性的動畫結果。針對這些問題，本論文提出一個新的基於視覺特徵學習方式搭配程序式方法來改善火焰模擬的效果。
首先透過影像二值化和邊緣偵測，尋找出火焰輪廓的變化情形，再加上原始影像集合成一個火焰檔案。為了能夠從簡短的火焰短片進而產生長時間的動畫，我們提出兩個影像學習機制去利用它們：第一個是透過火焰檔案可將不同搖曳程度之火焰輪廓個別進行角度分析並手動分類出各角度的影像區塊並另存，再搭配針對火焰搖曳動態所設計的有限狀態機讓使用者可對火焰輸入不同程度的外力以其產生的狀態及角度得到相應的火焰搖曳結果；另一個是將圖像中的火焰部份以其長寬正規化後按照比例分割出多個區塊並統計各區塊之平均RGB色值，以建構出一顏色查詢表達到快速變更火焰粒子顏色參數的目的。在繪製階段，我們也提出利用Cubic Spline曲線方程式搭配不同面向的特徵點產生各切面之間的三維空間關係並同時擴展出立體效果。因此我們提出的方法能夠不僅能夠提升火焰模擬的視覺真實度，另外和其它文獻相比也具有更高的互動性。

The natural phenomena simulation in computer graphics is commonly achieved by the procedural methods or the physics model. However, these approaches are hard to directly approach the visual experience. On the other hand, the image reconstruction works can provide the outcome based on real images but lack of interactivity and efficiency on using image resource. For solving these drawbacks, we propose a novel method that enhances the fire simulation effect using the visual learning of image features and generates continuous animations by integrating with procedural methods.
We first obtain the dynamics of fire contour by binarization and edge detection. The information extracted from images is gathered into a set of feature data called fire profile. To generate a long sequence of fire animation from a short clip of fire video, we propose two approaches of visual learning to utilize fire profile to produce continuous animation. One is to use the fire image to setup a color value lookup table which contains the average color value of the fire spatial divisions; the other is to design a state machine for describing fire wiggling movement that can generate effects based on user’s input. During the rendering stage of 3D visualization, we set up the fire volume which connecting the feature points of two cross-views by the cubic spline. Then the edge points found on the fire volume can be used as the contour points of the supplementing slices and generate these supplements inside the planned fire volume to formulate a complete fire effect. The proposed method can raise not only the visual reality but also the interactive ability compared with the existing work.

Chapter 1 Introduction 1
1.1. Overview 1
1.2. Problem Definition 2
1.3 Organization of This Thesis 3
Chapter 2 Related Work 4
2.1. Modeling Methods 4
2.1.1 Procedural Method 4
2.1.2. Physics Models 7
2.1.3. Other Modeling Methods 8
2.2. Rendering Methods 9
2.2.1. Scientific Visualization 9
2.2.2. Direct Volume Rendering 10
2.2.3. Hardware Acceleration Techniques 12
2.2.4. Illumination from Fire 13
2.3. Motivation 13
Chapter 3 Proposed Method 15
3.1. Preprocessing Stage 16
3.1.1. Finding Fire Contour 17
3.1.2. Feature Point Extraction 18
3.1.3. Motion Vector Extraction 21
3.2. Feature Statistics Learner 23
3.2.1. Shape 24
3.2.2. Color 29
3.3. Rendering with a Particle System 31
3.3.1. Region Detector 33
3.3.2. Path Builder 35
3.3.3. Expanding to Three Dimensional 39
Chapter 4 Implementation 42
4.1. User Interface 43
4.2. Details of Implementation 45
4.3. Rendering Result 51
4.4. Discussion 54
Chapter 5 Conclusions 56
References 57

[1] S. Hasinoff and K. Kutulakos, “Photo-consistent reconstruction of semi-transparent scenes by density sheet decomposition.” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, No. 5, pages 870–885, 2007.
[2] I. Ihrke and M. Magnor, “Adaptive grid optical tomography,” Graphical Models, Vol. 68, No. 5, pages 484–495, 2006.
[3] N. Chiba, K. Muraoka, H. Takahashi, and M. Miura, “Two-dimensional visual simulation of flames, smoke and the spread of fire,” The Journal of Visualization and Computer Animation, Vol. 5, No. 1, pages 37–54, Jan.–Mar, 1994.
[4] A. Lamorlette and N. Foster, “Structural modeling of flames for a production environment,” In Proc. ACM SIGGRAPH 2002, Vol. 21, No. 3, pages 729–735, 2002.
[5] W. T. Reeves, “Particle Systems – A technique for modeling a class of fuzzy objects,” ACM Transactions on Graphics, Vol. 2, No. 2, pages 91-108, April 1983.
[6] X. Wei, W. Li, K. Mueller, and A. Kaufman, ”Simulating fire with texture splats,” In Proc. IEEE Visualization, pages 227-237, Nov. 2002.
[7] A. R. Fuller, H. Krishnan, K. Mahrous, B. Hamann, and K. I. Joy, “Real-time procedural volumetric fire,” In Proceedings of the 2007 symposium on Interactive 3D graphics and games , pages: 175 – 180, 2007.
[8] Y. Takai, K. Ecchu, and N. K. Takai, “A cellular automaton model of particle motions and its applications,” The Visual Computer, Vol. 11, No. 5, pages 240–252, 1995.
[9] Y. Dobashi, K. Kaneda, H. Yamashita, T. Okita, and T. Nishita, “A simple, efficient method for realistic animation of clouds,” In Proc. ACM SIGGRAPH 2000, pages 19–28, 2000.
[10] M. Balci, M. Alnasser, and H. Foroosh, "Image-based simulation of gaseous material," Image Processing, 2006 IEEE International Conference on, pages 489-492, Oct. 2006.
[11] D. Nguyen, R. Fedkiw, and H. Jensen, “Physically based modeling and animation of fire,” In Proc. ACM SIGGRAPH 2002, pages 721–728, 2002.
[12] J. Hong, T. Shinar, R. Fedkiw, “Wrinkled flames and cellular patterns,” ACM Transactions on Graphics, Vol. 26, No. 3, Article 47, July 2007.
[13] J. Stam and E. Fiume, “Depicting fire and other gaseous phenomena using diffusion processes,” In Proc. ACM SIGGRAPH 1995, pages 129–136, 1995.
[14] G. Yngve, J. O’Brien, and J. Hodgins, “Animating explosions,” In Proc. SIGGRAPH 2000, vol. 19, pages 29–36, 2000.
[15] B. Feldman, J. O’Brien, and O. Arikan, “Animating suspended particle explosions,” In Proc. SIGGRAPH 2003, Vol. 22, No. 3, pages 708–715, 2003.
[16] P. S. McCormick and J. P. Ahrens, “Visualization of wildfire simulations,” IEEE Computer Graphics and Applications, Vol. 18, No. 2, pages 17–19, Mar.–Apr. 1998.
[17] R. W. Bukowski and C. H. Séquin, “Interactive simulation of fire in virtual building environments,” In Proc. ACM SIGGRAPH 1997, pages 35–44, 1997.
[18] H. Rushmeier, A. Hamins, and M. Y. Choi, “Volume rendering of pool fire data,” IEEE Computer Graphics and Applications, Vol. 15, No. 4, pages 62–66, July 1995.
[19] D. Laur and P. Hanarahan, “Hierarchical splatting: a progressive refinement algorithm for volume rendering,” In Proc. ACM SIGGRAPH 1991, pages 285–288, 1991.
[20] L. Westover, “Footprint evaluation for volume rendering,” In Proc. ACM SIGGRAPH 1990, pages 367–376, 1990.
[21] J. Stam, “Stochastic rendering of density fields,” In Proc. Graphics Interface 1994, pages 51–58, 1994.
[22] T. McReynolds and D. Blythe, “Advanced Graphics Programming Techniques Using OpenGL,” Course presented at ACM SIGGRAPH 1999, available at http://www.opengl.org/developers/code/sig99.
[23] S. A. King, R. A. Crawfis, and W. Reid, “Fast volume rendering and animation of amorphous phenomena,” In Proc. International Workshop on Volume Graphics 1999, pages 229–242, 1999.
[24] C. Horvath and W. Geiger, “Directable, high-resolution simulation of fire on the GPU,” ACM Trans. Graph, Vol. 28, No. 3, pages 1–8, August 2009.
[25] J. Takahashi, H. Takahashi, and N. Chiba, “Image synthesis of flickering scenes including simulated flames,” IEICE Transactions on Information and Systems, E80- D(11):1102–1108, Nov. 1997.
[26] R. Fedkiw, J. Stam, and H. W. Jensen, “Visual simulation of smoke,” In Proc. ACM SIGGRAPH 2001, pages 15–22, 2001.
[27] G. Cox and R. Chitty, “Some source-dependent effects of unbounded fires,” Combustion and Flame, Vol. 60, No. 3, pages 219-232, 1985.
[28] BJ. McCaffrey, “Purely buoyant diffusion flames: some experimental results,” National Bureau of Standards, NBSIR 79-1910, 1979.
[29] P. P. K. Raj, A. N. Moussa, and K. Aravamudan, “Experiments involving pool and vapour fires from spills of liquefied natural gas on water,” US Coast Guard Report, No. CG-D-55-79, 1979.
[30] D. Drysdale, “An introduction to fire dynamics,” John Wiley and Sons, Chichester, second edition, 1998.
[31] C. B. Liu and N. Ahuja, “Vision Based Fire Detection,” In Proc. of Int. Conf. on Pattern Recognition, Vol. 4, 2004.
[32] S. J. Wang, D. L. Jeng, and M. T. Tsai, “Early fire detection method in video for vessels,” Journal of Systems and Software, Vol. 82, No. 4, pages 656–667, 2009.
[33] Edward Angel, “Interactive Computer Graphics: A Top-Down Approach Using OpenGL,” Addison-Wesley, Fifth Edition, 2009.
[34] F. Bridault-Louchez, M. Leblond, F. Rouselle, and C. Renaud, “Real-time rendering and animation of plentiful flames,” In Proc. of the 3rd Eurographics Workshop on Natural Phenomena, 2007.
[35] ALGLIB, available at http://www.alglib.net/