This paper presents a computer vision-based approach for automatically detecting the presence of fire and smoke in video sequences. Since the fire causes serious disasters, fire detection has been an important study to protect human life. In this paper, the system proposed the fire- smoke detection algorithm in video sequence. The system focuses on optimizing the flame detection by identifying gray cycle pixels nearby the flame, which is generated because of smoke and of spreading of fire pixel and the area spread of flame. The model uses different color model for both fire and smoke and also the model use fuzzy logic or fuzzy inference system (FIS) to detect fire pixels. These techniques can be used to reduce false alarm by giving the accurate result of fire occurrence along with fire detection methods. The color models are extracted using statistical analysis of samples extracted from different type of video sequence and images. The extracted models can be used in complete fire/smoke detection system which combines color information with motion analysis. The strength of using video in flame detection is the ability to monitor large and open spaces. The system also give the opportunity to adjust the system by applying different combination of fire detecting techniques which will help in implementation of system according to different sensitive area requirement.

Fire detection, Smoke detection video precessing, Fuzzy Inference System (FIS), Mamdani Model, RGB, YCbCr

[1] TurgayÇelik, HüseyinÖzkaramanlı and HasanDemirel, “Fire and Smoke Detection without Sensors: Image Processing Based Approach”, 15th European Signal Processing Conference (EUSIPCO 2007), Poznan, Poland, September-3-7, 2007.
[2] GauravYadav,Vikas Gupta, Vinod Gaur and Dr. MahuaBhattacharya, “Optimized Flame Detection Using Image Processing Based Techniques”, ISSN: 0976-5166, Vol. 3 No. 2, April-May, 2012.
[3] VipinVenu, “Image Processing Based Forest Fire Detection”, ISSN 2250-2459, Volume 2, Issue 2, February 2012.
[4] Surya T.S, Suchithra M.S, P.G. Student, “Survey on Different Smoke Detection Techniques Using Image Processing”, ISSN (O): 2278-5841, 2014.
[5] Chen, T., Wu, P., Chiou, Y., “An early fire-detection method based on image processing”, Proc. IEEE Internat. Conf. on Image Processing, ICIP’04, pp. 1707-1710, 2004.
[6] Klir, G. J., Yuan B., “Fuzzy Sets and Fuzzy Logic”, Prentice Hall, 1995.
[7] Mathews, J.H., Fink, K.D., “Numerical Methods using matlab”, Prentice Hall, 1999.
[8] Turgay Celik, Huseyin Ozkaramanli, Hasan Demirel, “Fire Pixel Classification Using Fuzzy Logic and Statistical Color Model”, ICASSP 2007.
[9] T. Chen, P. Wu, and Y. Chiou (2004): “An early fire-detection method based on image processing”, in ICIP ’04, pp.1707–1710.

[10] C.-B. Liu, N. Ahuja (2004): “Vision based fire detection”, Proceedings of the 17th International Conference on Pattern Recognition (ICPR’ 04), Vol.4, pp. 134-137.
[11] S. Noda, K. Ueda (1994): “Fire detection in tunnels using an image processing method”, in Vehicle Navigation & Information Systems Conference Proceedings, pp. 57-62.
[12] TurgayCelik (2010): “Fast and Efficient Method for Fire Detection Using Image Processing”, ETRI Journal, Volume 32, Number 6.