Vision-based flame analysis using motion and Edge Detection

Fire can lead to major financial losses to industries. Consequently, it is very crucial to develop a reliable method to detect an occurrence of fire. In this research, the algorithms for flame detection using video processing will be proposed. System identification will be used to obtain a process model of the flame. This paper stresses on the flame detection algorithm. The results show that detection of flame using motion & shape features can be achieved by using Background Subtraction and Edge Detection approach.

[1]  ByoungChul Ko,et al.  Fire detection based on vision sensor and support vector machines , 2009 .

[2]  Magy Kandil,et al.  A new hybrid algorithm for fire vision recognition , 2009, IEEE EUROCON 2009.

[3]  Lennart Ljung,et al.  System identification toolbox for use with MATLAB , 1988 .

[4]  Narendra Ahuja,et al.  Vision based fire detection , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[5]  Nixon,et al.  Feature Extraction & Image Processing , 2008 .

[6]  S. Noda,et al.  Fire detection in tunnels using an image processing method , 1994, Proceedings of VNIS'94 - 1994 Vehicle Navigation and Information Systems Conference.

[7]  Chin-Lun Lai,et al.  Advanced real time fire detection in video surveillance system , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[8]  Nicholas True,et al.  Computer Vision Based Fire Detection , 2009 .

[9]  Dongil Han,et al.  Flame and smoke detection method for early real-time detection of a tunnel fire , 2009 .