Flame and smoke detection method for early real-time detection of a tunnel fire

This paper presents an image-processing technique for automatic real-time flame and smoke detection in a tunnel environment. To avoid the large-scale damage caused by fire occurring in different environments, there are many studies about discovering and minimizing an incident as fast as possible. However, we need an original algorithm specialized for a tunnel fire, because this environment is quite different and it is difficult to apply existing fire detection algorithms to a tunnel environment. Therefore, this paper proposes an original algorithm that applies to a tunnel environment. Color and motion information are used to minimize false detections in tunnels, and this information enables us to detect the exact position of an event at an early stage, by detection, test, and verification procedures. The experimental results show the validity and efficiency of the proposed algorithms by a comparison of the characteristics of each algorithm.

[1]  Alexander G. Mamistvalov n-Dimensional Moment Invariants and Conceptual Mathematical Theory of Recognition n-Dimensional Solids , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  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.

[3]  K. Koga,et al.  Integrated traffic flow monitoring system in a large-scale tunnel , 1997, Proceedings of Conference on Intelligent Transportation Systems.

[4]  Turgay Çelik,et al.  Fire detection using statistical color model in video sequences , 2007, J. Vis. Commun. Image Represent..

[5]  Thou-Ho Chen,et al.  An intelligent real-time fire-detection method based on video processing , 2003, IEEE 37th Annual 2003 International Carnahan Conference onSecurity Technology, 2003. Proceedings..

[6]  Hiromitsu Ishii,et al.  Application of neural network to analyses of CCD colour TV-camera image for the detection of car fires in expressway tunnels , 2006 .

[7]  Vito Cappellini,et al.  An intelligent system for automatic fire detection in forests , 1989, Recent Issues in Pattern Analysis and Recognition.

[8]  Chao-Ho Chen,et al.  The smoke detection for early fire-alarming system base on video processing , 2006, 2006 International Conference on Intelligent Information Hiding and Multimedia.

[9]  Markus Loepfe,et al.  An image processing technique for fire detection in video images , 2006 .

[10]  A. Cigada,et al.  Road and railway tunnel fire hazard: a new measurement method for risk assessment and improvement of transit safety , 2005, Proceedings of the 2005 IEEE International Workshop on Measurement Systems for Homeland Security, Contraband Detection and Personal Safety Workshop, 2005. (IMS 2005).