使用HSV色彩空間的多模演算法(Multimodal)可能遇到二個常見的狀況：1.)使用HSV色彩空間時可能需要二次轉換影響演算效能；HSV是電腦視覺(computer vision)領域常見的色彩空間，然而HSV轉換也存在色相回歸以及色相不存在時其色相值為0的兩個淺在問題，此外，色差計算時必需將色相及色度作二次轉換成為平面座標，這些特性間接影響演算法的效率。在色彩空間的部份本篇研究將RGB轉換為色座標空間(Color Coordination Space簡稱CCS)，CCS是基於HSV概念的空間轉換，它解決了HSV存在的問題並且保留它應有的特性，應用在背景偵測技術中可減少系統的運算負擔。2.)當背景為靜止的狀態下演算法效率遠低於單模演算法；本篇基於自組織背景濾除法(SOBS)加入了靜態指標(Static Model Index簡稱SMI)，輸入向量經由SMI取得靜態背景模型，在理想的靜態背景狀態下，演算時間大約是SOBS的百分之二十並且能維持SOBS應有的特性。

The effectiveness of algorithm and color space connected with a strong bond between each other. HSV is the common color space in computer vision field. However, the return of hue characteristics of HSV in some applications will indirectly affect the efficiency of the algorithm. In this paper, RGB space is converted into color coordinates space (CCS) and this method can simplify the color difference calculation and reduce the impact of the luminance change. The proposed algorithm, based on self-organizing background subtraction (SOBS) and add a static model index (SMI), can effectively reduce the system in the background to detect 80% of static time and maintenance proper characteristics SOBS achieve rapid calculation purposes.

[1] Gonzalez, Digital Image Processing. Upper Saddle River, New Jersey: Prentice Hall, 2001.
[2] C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, "Pfinder: real-time tracking of the human body," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 19, pp. 780-785, 1997.
[3] C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real-time tracking," in Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., 1999, p. 252 Vol. 2.
[4] H. D. Elgammal A, Davis L.S, "Non-Parametric Model for Background Subtraction," presented at the Computer Vision, European Conference, 2000.
[5] T. H. C. Kyungnam Kim, David Harwood, Larry Davis, "Real-Time Foreground-Background Segmentation Using Codebook Model," Real-Time Imaging, vol. 11, p. 127, 2006.
[6] C. S. Hsu, "Hierarchical Method for Background Subtracction Using Codebook Model," Electrical Engineering, NTUST, Taiwan, 2010.
[7] J. A. Freeman and D. M. Skapura, "Neural Networks Algorithms, Applications, and Programming Techniques," in 1992 ed. Boston: Addison-Wesley, 1992.
[8] 林俊良, 智慧型控制-分析與設計. Tawian: 全華科技圖書股份有限公司, 2005.
[9] T.Kohonen, Self-Organization and Associative Memory, 2 ed. Finland: Springer Verlag, 1988.
[10] L. Maddalena and A. Petrosino, "A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications," Image Processing, IEEE Transactions on, vol. 17, pp. 1168-1177, 2008.
[11] L. Maddalena and A. Petrosino, "The SOBS algorithm: What are the limits?," in Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on, Providence, RI, 2012, pp. 21-26.
[12] D. M. Rashed, M. S. Sayed, and M. I. Abdalla, "Improved moving object detection algorithm based on adaptive background subtraction," in Electronics, Communications and Computers (JEC-ECC), 2013 Japan-Egypt International Conference on, 6th of October City, 2013, pp. 29-33.
[13] Y. J. Chang, "A Foreground Regions Selection Algorithm to Detect Moving Objects in Dynamic Backgroung," Electrical Engineering, NTUST, Taiwan, 2010.
[14] R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, "Detecting moving objects, ghosts, and shadows in video streams," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 25, pp. 1337-1342, 2003.
[15] C. Benedek and T. Szirányi, "Study on color space selection for detecting cast shadows in video surveillance," International Journal of Imaging Systems and Technology, vol. 17, pp. 190-201, 2007.