應用機器視覺技術於室內火源偵測之研究

In Development of an Indoor Fire Detection System using Machine Vision

趙啟棟(Chi-Tung Chao)

指導教授 ： 吳明川

國立臺北科技大學/機電學院/自動化科技研究所/碩士(2010年)

摘要

在起火現場中，黃金時期逃生與救火是非常重要的，本研究將火災災害警報與機器視覺技術結合，建置一套智慧型且反應快速可即時監控之機器視覺室內火源偵測系統，用來保障生命與財產安全。
在本研究中利用火源高亮度特徵，採用色彩空間中的強度空間配合火源輪廓脈動特徵，使用累積差值法(Accumulative Difference Method)過濾出第一階段火源影像候選像素，在經由火源隨機顏色特徵由修正之權重式單一高斯模型(Weight Single Gaussian Model)過濾出第二階段火源影像候選像素，最後由YCrCb模糊邏輯分類器(YCrCb Fuzzy Logic Classifier)與修正之貝氏分類器(Bayesian Classifier)做分類，找出正確火源二值影像，作為判斷火源發生的依據。

關鍵字

累積差值法 ； 權重式單一高斯模型 ； YCrCb模糊邏輯分類器 ； 貝氏分類器

並列摘要

In breaking out a fire at the scene, gold period flees for people life and fire fighting it is very important. This research combines the fire alarm with the vision technology of the machine to construct an indoor fire detection system using machine vision which is intelligent, real-time monitoring, and can response immediately. The system is good to ensure the life and property safety.
In this research, we utilize the high light characteristic of fire, and adopt the intensity space in the color space to cooperate with the pulsating characteristic of outline of fire, use Accumulative Difference Method filter out the candidate for fire image of first stage. Weight Single Gaussian Model revised via the random color characteristic of fire filter out the candidate for fire image of second stage. In finally, using the YCrCb Fuzzy Logic Classified and Bayesian Classifier to find out the correct image of fire, as judging the basis that happens in the fire.

並列關鍵字

Accumulative Difference Method ； Weight Single Gaussian Model ； YCrCb Fuzzy Logic Classifier ； Bayesian Classifier

參考文獻

[2]B. U. Toreyin, Y. Dedeoglu, U. Gudukbay, and A. E. Cetin, “Computer vision based method for real-time fire and flame detection,” Pattern Recognition Letters, 2006, pp. 49-58.

[3]N. True, Y. Dedeoglu, U. Gudukbay and A.E. Cetin, “Computer vision based fire detection,” 2008.

[4]A. J. Lipton, H. Fujiyoshi, and R. S. Patil, “Moving target classification and tracking from real-time video,” IEEE Workshop Applications of Computer Vision, 1998, pp. 8-14.

[5]R. Cutler and L. S. Davis, “Robust real-time periodic motion detection, analysis, and applications,” IEEE Trans. Pattern Anal. Machine Intell., vol. 22, Aug. 2000, pp. 781-796.

[6]S. C. Cheung and C. Kamath, “Robust techniques for back ground subtraction in Urban Traffic Video,” Proceedings of SPIE, 2004.