臺灣博碩士論文加值系統

近年來，隨著智慧型安全監控系統的蓬勃發展，對於火焰偵測的研究也如雨後春筍般的萌芽，日漸受到重視。以往火災偵測系統皆是依靠裝置各種感應器於環境中，當火災發生時，發出警報再由人力親至現場確認。若是依靠視訊監控系統，不僅對於火災的反應時間較為快速，也不需由人力親自奔波至現場確認情況，並可記錄下感測器所無法提供的各種火災訊息。本論文提出一套在各種影像解析度視訊監控系統下，利用火焰特徵資訊自動地偵測出火焰前期的小型火苗與火焰燃燒旺盛時火焰之方法。研究中採用動量偵測與YCbCr色彩空間的搭配來萃取出前景物體，縮小偵測的範圍，在動量偵測中為避免影像解析度不同所造成的背景雜訊影響，因此以縮圖及建立區間背景邊緣模型的方法來取代形態學的處理。再搭配火焰各種特徵，角點閃爍頻率、緊緻度、增長率及填充率判斷出前景物體是否為火焰物件。本論文方法改善了火焰區域擷取的完整度，並且利用火焰各種特徵嚴謹的條件判斷，降低誤偵測的機率。本實驗環境設定在各種影像解析度的複雜環境當中，無論影像解析度高或低、室內室外、及干擾物體的存在，例如：室外汽機車的經過、紅色飄動的旗幟，利用本論文的方法，能夠準確地判斷出火災的發生，並且排除掉沒有危險性的人為控制火焰。

In current era, there are various kinds of sensor used to detect the occurrence of fire. When a fire disaster occurs, security needs to go to the place and assesses the situation. In contrast, video-based fire detection system not only gives a faster response time but also provides with some fire information. This information help security to verify the fire alarm. This study proposes a method to detect the little flame in the early stage of fire combustion. The foreground object was extracted by motion detection and YCbCr color clues. To avoid the noise of motion detection in different resolution videos, background edge is used to eliminate noise instead of morphology. Next, with the help of fire characteristics, the foreground object is identified. A fire object is determined by compactness, corner flicker rate, and growth rate. The experiment can be applied to any resolution video and complex scene, both indoors and outdoors, such as squares, where people walk around and vehicles pass by. The outcome of experiment, using this proposed method, can detect the fire object accurately and exclude the undangerous fire.

摘 要 i
ABSTRACT ii
致謝 iii
目錄 iv
表目錄 vi
圖目錄 vii
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 2
1.3 研究貢獻 3
1.4 章節編排 4
第二章 文獻探討 5
2.1 前景偵測 6
2.2 邊緣偵測 7
2.3 顏色及色彩空間 8
2.3.1 RGB色彩空間 9
2.3.2 HSV色彩空間 10
第三章 火焰偵測方法 13
3.1 影像前處理 13
3.1.1 縮圖 14
3.1.2 影像雜訊撫平 15
3.2 初期偵測與前景物件擷取 19
3.2.1 動量偵測 20
3.2.2 建立區間背景邊緣模型 23
3.2.3 YCbCr偵測 27
3.2.4 火焰遮罩匹配 29
3.3 火焰行為分析 30
3.3.1 建立火焰物件，分配物件編號 31
3.3.2 閃爍頻率 32
3.3.3 記算緊緻度 34
3.3.4 計算物件範圍內火焰遮罩的填充率 35
3.3.5 計算火焰增長速率 36
第四章 案例研究 38
4.1 問題描述 38
4.2 系統設計 38
4.2.1 系統流程 39
4.2.2 系統架構 41
4.3 實驗結果 43
4.3.1 影像解析度低之實驗影片 46
4.3.2 影像解析度高之實驗影片 47
4.4 相關研究比較 48
4.4.1 文獻[16]簡述 49
4.4.2 比較結果 49
第五章 結論與未來展望 52
5.1 結論 52
5.2 未來展望 52
參考文獻 53

[1]Hong Jin, and Rong-Biao Zhang," A Fire and Flame Detecting Method Based on Video," in International Conference on Machine Learning and Cybernetics, vol.4, pp. 2347-2352, 2009.
[2]Wen-Bing Horng, Jian-Wen Peng, and Chih-Yuan Chen," A New Image-Based Real-Time Flame Detection Method Using Color Analysis," in IEEE on Networking, Sensing and Control, pp. 100- 105, 2005.
[3]T. Celik, H. Demirel, H. Ozkaramanli, and M. Uyguroglu," Fire Detection in Video Sequences Using Statistical Color Mode," in IEEE International Conference on Speech and Signal Processing, pp. 14-19, vol.2, 2006.
[4]Dengyi Zhang, Jinming Zhao, Jianhui Zhao, Shizhong Han, Zhong Zhang, Chengzhang Qu, and Youwang Ke," A New Color-based Segmentation Method for Forest Fire from Video Image," in International Seminar on Future BioMedical Information Engineering, pp. 41-44, 2008.
[5]Thou-Ho Chen, Ping-Hsueh Wu, and Yung-Chuen Chiou," An Early Fire-Detection Method Based on Image Processing," in International Conference on Image Processing, vol. 3, pp. 1707- 1710, 2004.
[6]T. Celik, H. Ozkaramanli, and H. Demirel," Fire Pixel Classification using Fuzzy Logic and Statistical Color Model," in IEEE International Conference on Speech and Signal Processing, vol. 1, pp. 1205-1208, 2007.
[7]Dengyi Zhang, Yujie Rao, Jianhui Zhao, Jinming Zhao, Aike Hu, and Bo Cai," Feature Based Segmentation and Clustering on Forest Fire Video," in IEEE International Conference on Robotics and Biomimetics, pp. 1788-1792, 2007.
[8]W.T.A. Budi, and I.S. Suwardi," Fire Alarm System Based-on Video Processing," in International Conference on Electrical Engineering and Informatics, pp. 1-7, 2011.
[9]Jianning Chi, Chengdong Wu, and Yunzhou Zhang," Early Fire Disaster Features Research and Detection Method Design in Video Images," in Symposium on Photonics and Optoelectronics, pp. 1-4, 2011.
[10]Y. Habiboglu, O. Gunay, and A.E. Cetin," Flame Detection Method in Video Using Covariance Descriptors," in IEEE International Conference on Speech and Signal Processing, pp. 1817-1820, 2011.
[11]A. Chenebert, T.P. Breckon, and A. Gaszczak," A Non-Temporal Texture Driven Approach to Real-time Fire Detection," in IEEE International Conference on Image Processing , pp. 1741-1744, 2011.
[12]Huan Li, Shan Chang, Zhe Li, and Lipng Shao," Color Context Analysis Based Efficient Real-time Flame Detection Algorithm," in 3rd IEEE Conference on Industrial Electronics and Applications , pp. 1953-1957, 2008.
[13]Tian Qiu, Yong Yan, and Gang Lu," A New Edge Detection Algorithm for Flame Image Processing," in Instrumentation and Measurement Technology Conference, pp. 1-4, 2011.
[14]B.U. Toreyin, Y. Dedeoglu, and A.E. Cetin," Flame Detection in Video Using Hidden Markov Models," in IEEE International Conference on Image Processing, vol.2, pp. 1230-1233, 2005.
[15]Tianyang Chi, Huaibo Zhang, and Qingfeng Yu," A Method for Flame Flicker Frequency Calculation with the Empirical Mode Decomposition," in Third International Conference on Measuring Technology and Mechatronics Automation, pp. 104-106, 2011.
[16]Byoung Chul Ko, Sun Jae Ham, and Jae Yeal Nam," Modeling and Formalization of Fuzzy Finite Automata for Detection of Irregular Fire Flames," in IEEE Transactions on Circuits and Systems for Video Technology, vol.21, no.12, pp.1903-1912, 2011.
[17]S. Mohd Razmi, N. Saad, and V.S. Asirvadam," Vision-based Flame Detection: Motion Detection & Fire Analysis," in IEEE Student Conference on Research and Development, pp.187-191, 2010.
[18]Qin Jiang, and Qiang Wang," Large Space Fire Image Processing of Improving Canny Edge Detector based on Adaptive Smoothing," in International Conference on Innovative Computing and Communication, pp.264-267, 2010.
[19]Zhong Zhang, Jianhui Zhao, Zhiyong Yuan, Dengyi Zhang, Shizhong Han, and Chengzhang Qu," Color Based Segmentation and Shape Based Matching of Forest Flames from Monocular Images," in International Conference on Multimedia Information Networking and Security, vol.1, pp.625-628, 2009.
[20]Tongying Guo, Bin Ma, Jiejia Li, and Hongying He," Research on Flame Image Edge Detection Algorithm Based on Mobile Robot Platform," in International Conference on Artificial Intelligence and Computational Intelligence, vol. 2, pp. 78-81, 2010.
[21]P. Jenifer," Notice of Violation of IEEE Publication Principles Effective Visual Fire Detection in Video Sequences using Probabilistic Approach," in International Conference on Emerging Trends in Electrical and Computer Technology, pp.870-875, 2011.
[22]Qing Liu, Sun''an Wang, and XiaoHui Zhang, Yun Hou," Flame Recognition Algorithm Research under Complex Background," in International Conference on Computer and Information Technology, pp.503-510, 2010.
[23]M. Valera, and S.A. Velastin," Intelligent Distributed Surveillance Systems: A Review," in IEEE Proceedings on Vision Image Signal Process, vol.152, pp. 192-204, 2005.
[24]A. Torralba, R. Fergus, and W.T. Freeman," 80 Million Tiny Images: A Large Data Set for Nonparametric Object and Scene Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 30 (11), pp. 1958-1970, 2008.
[25]G. Marbach, M. Loepfe, and T. Brupbacher," An Image Processing Technique for Fre Detection in Video Images," Fire Safety J., vol. 41, no. 4, pp. 285–289, 2006.
[26]Jong Yih Kuo, Tai Yu Lai, Fu-Chu Huang, and Kevin Liu," The Color Recognition of Objects of Survey and Implementation on Real-Time Video Surveillance," IEEE International Conference on Systems, Man, and Cybernetics, pp.3741-3748, 2010.
[27]R.C. Gonzalez, and R.E. Wood, Digital Image Processing 2Ed. New Jersey: Prentice Hall, 2002.
[28]賴岱佑，數位影像處理技術手冊，台北：文魁資訊股份有限公司，2007。
[29]Jing Huang, Jianhui Zhao, Weiwei Gao, Chengjiang Long, Lu Xiong, Zhiyong Yuan, and Shizhong Han," Local Binary Pattern Based Texture Analysis for Visual Fire Recognition," 3rd International Congress on Image and Signal Processing, pp.3741-3748, 2010.