隨著科技的進步，電器產品在人類的生活中隨處可見，根據統計大部分火災的發生都是由於電器使用不慎走火而產生，因此如何快速且有效的偵測出火災的發生，並適時的提醒人民逃離現場且通報消防隊是非常重要的一件事。在本論文中，我們提出一個使用固定式攝影機來做煙霧及火焰偵測的系統，以防範火災發生所造成的金錢損失及人員的傷亡，且此偵測系統可使用於戶外背景會些許變動的環境。系統主要分為三大部分，第一個部分我們使用非參數化的模型 (Non-parametric Model)來做移動物體的偵測，此模型具有可快速適應背景些許變化的優點，第二個部分為將偵測出的移動物體利用一些門檻值或是機率值去做煙霧及火焰像素的判斷，在此我們用HSV及YUV兩不同色彩空間的色彩直方圖資訊 (Color Histogram)來做偵測並且比較使用不同色彩空間的優缺點，第三部分為去除類似於煙霧及火焰像素的誤判我們將會利用一些煙霧或火焰的特性去實做，例如: 火焰具有閃爍及大小變動的特性，依據這個特性固定不動的路燈將會被去除，最後得到偵測的結果。

Due to the development of technology, electrical products are everywhere in our life and it make our life more convenient. Most fire accidents are caused by human careless using electricity. And it may burn to fire. So it is an important thing that how to detect fire in time. And let human to escape soon.
In this thesis, we present a fixed camera system to detect smoke and flame. This system can reduce the loss of money and human casualties. And this system can adaptive quickly with the little change background. We have three steps in this smoke and flame detection system. First, we use non-parametric background model to do motion detection and we can detect the moving pixels and we also can call it foreground pixel. This model has the advantage that it can adaptive quickly with little change background and we can set our camera outside. Second, we use HSV and YUV color histogram information to do smoke and flame detection. We use some thresholds and probabilities to detect whether the moving pixel is smoke or flame pixel. And we will compare different color space to know which space is better. In the end, we use some methods to eliminate the false positive smoke and flame pixel, for example car light or street light.

[1] J. Barron, D. Fleet, and S. Beauchemin, “Performance of Optical Flow Techniques,” International Journal of Computer Vision, Vol. 12, No. 1, pp. 43–77, 1994.
[2] J. Chen, Y. He, and J. Wang, “Multi-Feature Fusion Based Fast Video Flame Detection,” Building and Environment, 2009.
[3] T. Celik and H. Demirel, “Fire Detection in Video Sequences using a Generic Color Model,” Fire Safety Journal, pp. 147-158, 2009.
[4] T. Celik, H. Demirel, H. Ozkaramanli, and M. Uyguroglu, “Fire Detection Using Statistical Color Model in Video Sequences,” Journal of Visual Communication and Image Representation, pp. 176-185, 2007.
[5] T. H. Chen, C. L. Kao, and S. M. Chang, “An Intelligent Real-Time Fire-Detection Method Based on Video Processing,” IEEE International Carnahan Conference on Security Technology, pp. 104-111, 2003.
[6] T. Celik, H. Ozkaramanli, and H. Demirel, “Fire and Smoke Detection without Sensors: Image Processing Based Approach,” European Signal Processing Conference, pp. 1794-1798, 2007.
[7] T. H. Chen, P. Wu, and Y. Chiou, “An Early Fire-detection Method based on Image Processing,” International Conference on Image Processing, pp. 1707-1710, 2004.
[8] T. H. Chen, Y. H. Yin, S. F. Huang, and Y. T. Ye, “The Smoke Detection for Early Fire-Alarming System Base on Video Processing,” IEEE Intelligent Information Hiding and Multimedia Signal Processing, pp. 427-430, 2006.
[9] A. Elgammal, D. Harwood, and L. S. Davis, “Non-parametric Model for Background Subtraction,” Proceedings of the European Conference on Computer Vision, pp.751-767, 2000.
[10] R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd edition, Prentice-Hall, Upper Saddle River, 2002.
[11] D. Han and B. Lee, “Flame and Smoke Detection for Early Real-Time Detection of a Tunnel Fire,” Fire Safety Journal, pp. 147-158, 2009.
[12] B. C. Ko, K. H. Cheong, and J. Y. Nam, “Fire Detection based on Vision Sensor and Support Vector Machines,” Fire Safety Journal, pp. 322-329, 2009.
[13] B. P. L. Lo and S. A. Velastin, “Automatic Congestion Detection System for Underground Platforms,” Proceedings of International Symposium on Intelligent Multimedia, Video, and Speech Processing, pp. 158-161, 2001.
[14] G. Marbach, M. Loepfe, and T. Brupbacher, ” An Image Processing Technique for Fire Detection in Video Images,” Fire Safety Journal, pp. 285-289, 2006.
[15] Water Philips III, Mubarak Shah, and Niels da Vitoria Lobo, “Flame Recognition in Video,” Pattern Recognition Letters, pp. 319-327, 2002.
[16] C. Ridder, O. Munkelt, and H. Kirchner, “Adaptive Background Estimation and Foreground Detection using Kalman-Filtering,” Proceedings of International Conference on Recent Advances in Mechatronics, pp. 193–199, 1995.
[17] C. Stauffer and W.E.L. Grimson, “Adaptive Background Mixture Models for Real-Time Tracking,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 246-252, 1999.
[18] B. U. Toreyin, Y. Dedeoglu, and A. E. Cetin, “Flame Detection in Video using Hidden Markov Models,” Procedings of IEEE International Conference on Image
Processing, pp. 1230-1233, 2005.
[19] B. U. Toreyin, Y. Dedeoglu, U.Gudukbay, and A. E. Cetin, “Computer Vision Based Method for Real-Time Fire and Flame Detection,” Pattern Recognition Letter, pp. 49-58, 2006.
[20] B. U. Toreyin, Y. Dedeoglu, U.Gudukbay, and A. E. Cetin, “Contour based Smoke Detection in Video using Wavelets,” European Signal Processing Conference, 2006.
[21] J. Vicente and P. Guillement, “An Image Processing Technique for Automatically Detecting Forest Fire,” International Journal of Thermal Science, pp. 1113-1120, 2002.
[22] C. Wren, A. Azarbayejani, T. Darrell, and A. Pentland, “Pfinder: Real-Time Tracking of the Human Body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 780-785, 1997.
[23] Z. Xu and J. Xu, “Automatic Fire smoke Detection Based on Image Visual Features,” International Conference on Computational Intelligence and Security Workshops, pp. 316-319, 2007.
[24] F. Yuan, “A Fast Accumulative Motion Orientation Model Based on Integral Image for Video Smoke Detection,” Pattern Recognition Letters, pp. 925-932, 2008.
[25] H. Yamagishi and J. Yamaguchi, “Fire Flame Detection Algorithm using a Color Camera,” International Symposium on Micromechatronics and Human Science, pp. 255–260, 1999.