火災防範是很重要的安全議題之一。一套有效的火災預警系統能夠及早偵測出火源並發出警告。早期發現火災便可及時撲滅，避免火災擴大，免除許多不必要的傷亡。傳統偵測火源的感測器偵測系統以偵測煙霧及溫度為主，而煙霧以及溫度擴散的速度較慢，便存在偵測時間延遲且感測距離較短等問題。視覺式火源偵測系統，則可改善這些缺點，但其精確度仍有改善的空間。因此，在本論文中提出一套有效的視覺式火焰偵測方法，搭配由高斯運算產生的適應性背景，以摘取出前景資訊。並利用資料探勘相關技術分析前景影像，藉由火焰顏色的特性來探勘其中的像素關連，進而找出火焰像素，以達到即早發現火災避免擴大的目的。實驗結果顯示，本論文所提出的方法可有效偵測靜態圖片中火焰並可有效支援即時偵測火焰。在靜態及動態的火焰偵測中，本論文所提的方法在偵測準確率上勝過Çelik等人分別於2007年及2009年所提的方法，並且有較低的誤判率。

摘 要 iv
Abstract v
誌 謝 vi
目 次 vii
表目錄 ix
圖目錄 x
第一章 緒論 1
1.1 研究背景 1
1.2 研究動機 2
1.3 本論文內容架構 3
第二章 文獻探討 4
2.1 火焰偵測技術 4
2.1.1 Chen等人所提出的方法 5
2.1.2 Çelik等人所提出的方法 8
2.1.3 Ko等人所提出的方法 9
2.2 基礎資料探勘理論 11
2.2.1 關聯法則探勘 11
2.2.2 循序樣式探勘 12
第三章 提出的視覺式火焰偵測方法 16
3.1 火焰介紹 16
3.1.1 什麼是火焰 16
3.1.2 火焰顏色特徵 17
3.2 產生火焰區域法則 19
3.2.1 火焰圖像收集及前置處理 20
3.2.2 分段量化處理並產生序列 21
3.2.3 運用循序樣式探勘 24
3.3色彩模型結合循序樣式探勘之靜態圖片火焰偵測 26
3.4 動態（即時）火焰偵測 28
3.4.1適應性背景與前景偵測 28
3.4.2 前景偵測結合循序樣式探勘之即時火焰偵測 32
第四章 實驗結果與討論 34
4.1實驗環境與設備 34
4.2 實驗結果與比較 36
4.2.1 靜態圖片火焰偵測之實驗 36
4.2.2 即時火焰偵測之實驗 39
第五章 結論與未來方向 66
5.1 結論 66
5.2 未來方向 66
參考文獻 67

[內政部10]內政部消防署(2010)，全國火災次數、起火原因及火災損失統計表，內政部消防署全球資訊網之統計資料， http://www.nfa.gov.tw/Show.aspx?MID=129&UID=131&PID=97 (Jul. 10, 20010讀取).
[AIS93]R. Agrawal, T. Imielinski, and A. Swami (May 1993), “Mining association rules between sets of items in large databases,” in Proc. 1993 ACM SIGMOD Intl. Conf. on Management of Data, Washington, D.C., pp. 207-216.
[AS94]R. Agrawal and R. Srikant (Sep. 1994), “Fast algorithms for mining association rules,” in Proc. 20th Intl. Conf. on Very Large Data Bases, Santiago, Chile, pp. 487-499.
[AS95]R. Agrawal and R. Srikant (Mar. 1995), “Mining sequential patterns,” in Proc. 11th Intl. Conf. on Data Engineering, Taipei, Taiwan, pp. 3-14.
[BZM08]M. Barnathan, J. Zhang, and V. Megalooikonomou (May 2008), “A web-accessible framework for the automated storage and texture analysis of biomedical images,” in Proc. 5th IEEE Intl. Symposium on Biomedical Imaging: From Nano to Macro (ISBI 2008), Philadelphia, PA, pp. 257-259.
[BCMS01]F. Berzal, J. C. Cubero, N. Marín, and J. M. Serrano (2001), “TBAR: An efficient method for association rule mining in relational databases,” Data & Knowledge Engineering, 37(1):47-64.
[BMUT97]S. Brin, R. Motwani, J. D. Ullman, and S. Tsur (May 1997), “Dynamic itemset counting and implication rules for market basket data,” in Proc. 1997 ACM SIGMOD Intl. Conf. on Management of Data, Tucson, AZ, pp. 255-264.
[CD09]T. Çelik and H. Demirel (2009), “Fire detection in video sequences using a generic color model,” Fire Safety Journal, 44(2):147-158.
[CDOU07]T. Çelik, H. Demirel, H. Ozkaramanli, and M. Uyguroglu (2007), “Fire detection using statistical color model in video sequences,” Journal of Visual Communication & Image Representation, 18(2):176-185.
[Che09]C.-H. Chen (2009), “A real time fire detection and query surveillance system on java open source platform,” Master Thesis, CSIE, National Chi Nan University, Taiwan.
[CKC03]T.-H. Chen, C.-L. Kao and S.-M. Chang (Oct. 2003), “An intelligent real-time fire-detection method based on video processing,” in Proc. of the IEEE 37th Intl. Carnahan Conf. on Security Technology, Taiwan, pp. 104-111.
[CWC04]T.-H. Chen, P.-H. Wu, and Y.-C. Chiou (Oct. 2004), “An early fire-detection method based on image processing,” in Proc. Intl. Conf. on Image Processing, Singapore, pp. 1707-1710.
[CBJ08]B.-H. Cho, J.-W. Bae, and S.-H. Jung (Jul. 2008), “Image processing-based fire detection system using statistic color model,” in Proc. Intl. Conf. on Advanced Language Processing and Web Information Technology (ALPIT 2008), Dalian, Liaoning, China, pp. 245-250.
[CG99]T. Cleary, W. Grosshandler (1999), “Survey of fire detection technologies and system evaluation/certification methodologies and their suitability foraircraft cargo compartments,” Tech. Report: NISTIR 6356, US, Department of Commerce, Technology Administration, National Institute of Standards and Technology.
[DN99]W. Davis, K. Notarianni (1999), “NASA fire detection study,” Tech. Report: NISTIR 5798, US, Department of Commerce, Technology Administration, National Institute of Standards and Technology.
[Gao02]J.-L. Gao (2002), “Digital video recorder with moving object tracking and fire detection,” Master Thesis, EECS, Southern Taiwna University, Taiwan.
[GW02]R. C. Gonzalez, Richard E. Woods (2002), “Digital image processing,” 2nd Ed., Prentice Hall, New Jersey.
[GZ03]G. Grahne and J. Zhu (Dec. 2003), “Efficient using prefix-tree in mining frequent itemsets,” in Proc. IEEE ICDM Workshop on Frequent Itemset Mining Implementations, Melbourne, FL.
[HL09]D. Han and B. Lee (2009), “Flame and smoke detection method for early real-time detection of a tunnel fire,” Fire Safety Journal, 44(7):951-961.
[HPYM04]J. Han, J. Pei, Y. Yin, and R. Mao (2004), “Mining frequent patterns without candidate generation: a frequent pattern tree approach,” Data Mining and Knowledge Discovery, 8(1):53-87.
[KCN09]B. C. Ko, K.-H. Cheong, and J.-Y. Nam (2009), “Fire detection based on vision sensor and support vector machines,” Fire Safety Journal, 44(3):322-329.
[LC04]Y.-C. Li and C.-C. Chang (2004), “A new FP-tree algorithm for mining frequent itemsets,” Lecture Notes in Computer Science 3309 --- Advanced Workshop on Content Computing, C. H. Chi, and K. Y. Lam (Eds.), Springer-Verlag, Berlin, pp. 266-277.
[LA04]C.-B. Liu and N. Ahuja (Aug. 2004), “Vision based fire detection,” in Proc. of the 17th Intl. Conf. on Pattern Recognition, vol. 4, Cambridge, UK, pp. 134-137.
[MK02]A. Mazurkiewicz and H. Krawczyk (Sep. 2002), “A parallel environment for image data mining,” in Proc. Intl. Conf. on Parallel Computing in Electrical Engineering, Warsaw, Poland, pp. 429-434.
[OIK+06]T. Ono, H. Ishii, K. Kawamura, H. Miura, E. Momma, T. Fujisawa, and J. Hozumi (2006), “Application of neural network to analyses of CCD colour TV-camera image for the detection of car fires in expressway tunnels,” Fire Safety Journal, 41(4):279-284.
[PCY95]J. S. Park, M.-S. Chen, and P. S. Yu (May 1995), “An effective hash-based algorithm for mining association rules,” in Proc. 1995 ACM-SIGMOD Intl. Conf. on Management of Data, San Jose, CA, pp. 175-186.
[PHM+01]J. Pei, J. Han, B. Mortazavi-Asl, H. Pinto, Q. Chen, U. Dayal, and M. C. Hsu (Apr. 2001), “PrefixSpan: Mining sequential patterns efficiently by prefix-projected pattern growth,” in Proc. of IEEE Intl. Conf. on Data Engineering, pp. 215-224.
[PHM+04]J. Pei, J. Han, B. Mortazavi-Asl, J. Wang, H. Pinto, Q. Chen, U. Dayal, and M. C. Hsu (2004), “Mining sequential patterns by pattern-growth: The prefixspan approach,” IEEE Trans. on Knowledge and Data Engineering, 16(11):1424-1440.
[PSL03]W. Phillips III, M. Shah, and N. V. Lobo (2003), “Flame recognition in video,” Pattern Recognition Letters, vol. 23, pp. 319–327.
[Qui97]J. G.. Quintiere (1997), “Principles of Fire Behavior,” Delmar Publishers, New York.
[RRHG01]J. A. Rushing, H. S. Ranganath, T. H. Hinke, and S. J. Graves (2001), “Using association rules as texture features,” IEEE Trans. on Pattern Analysis and Machine Intelligence, 23(8):845-858.
[SON95]A. Savasere, E. Omiecinski, and S. Navathe (Sep. 1995), “An efficient algorithm for mining association rules in large databases,” in Proc. 21th Intl. Conf. on Very Large Data Bases, Zurich, Switzerland, pp. 432-444.
[SA96]R. Srikant and R. Agrawal (Mar. 1996), “Mining sequential patterns: Generalizations and performance improvements,” in Proc. 5th Intl. Conf. on Extending Database Technology, Avignon, France, pp.3-17.
[TDGC06]B. U. Toreyin, Y. Deleoglu, U. Gudukbay, and A. E. Cetin (2006), “Computer vision based method for real-time fire detection,” Pattern Recognition Letter, 27(1):49-58.
[WJT09]S.-J. Wang, D.-L. Jeng, and M.-T. Tsai (2009), “Early fire detection method in video for vessels,” Journal of Systems and Software, 82(4):656-667.
[YY99]H. Yamagishi, J. Yamaguchi (Nov. 1999), “Fire flame detection algorithm using a color camera,” in Proc. of 1999 Intl. Symposium on Micromechatronics and Human Science, Tokyo, pp. 255–260.
[Zak01]M. J. Zaki (2001), “SPADE: An efficient algorithm for mining frequent sequences,” Machine Learning, 42(1-2):31-60.