Flame Recognition in Video Images with Color and Dynamic Features of Flames

Journal: Journal of Autonomous Intelligence DOI: 10.32629/jai.v2i1.35

Jiaqing Chen1, Xiaohui Mu1, Yinglei Song2, Menghong Yu1, Bing Zhang1

2. Department of Electronics and Information Science, Jiangsu University of Science and Technology, Professor


Recently, video based flame detection has become an important approach for early detection of fire under complex circumstances. However, the detection accuracy of most existing methods remains unsatisfactory. In this paper, we develop a new algorithm that can significantly improve the accuracy of flame detection in video images. The algorithm segments a video image and obtains areas that may contain flames by combining a two-step clustering based approach with the RGB color model. A few new dynamic and hierarchical features associated with the suspected regions, including the flicker frequency of flames, are then extracted and analyzed. The algorithm determines whether a suspected region contains flames or not by processing the color and dynamic features of the area altogether with a BP neural network. Testing results show that this algorithm is robust and efficient, and is able to significantly reduce the probability of false alarms.


Fire Detection; RGB Color Model; Dynamic Features; Hierarchical Features; Feature Fusion


[1] G. Zang, C. Huang, Y. Wang et al., “Multi-criterion indentification technology of fire with video and its application,” Computer Applications and Software, vol. 30, no. 2, pp. 65-67, February 2013.
[2] T. Chen, P Wu, and Y Chiou, “An early fire-detection method based on image processing,” in Proceedings of International Conference on Image Processing, Singapore, October 2004, pp. 1707-1710.
[3] T. Celik et al., “Fire detection using statistical color model in video sequences,” Visual Communication & Image Representation, vol. 18, no. 2, pp. 176-185, January 2007.
[4] P. Gomes, P. Santana, and J. Barata, “A vision-based approach to fire detection,” International Journal of Advanced Robotic Systems, vol. 11, no. 149, pp. 1-12, 2014.
[5] T. Celik, H. Demirel, “Fire detection in video sequences using a generic color model,” Fire Safety Journal, vol. 44, no. 2, pp. 147-158, 2009.
[6] L. Chen, W. Huang, “Fire detection using spatial-temporal analysis,” in Proceedings of the world Congress on Engineering, London, U.K., July 2013, pp. 1-4.
[7] W. Horng, J. Peng, and C. Chen, “A new image-based real-time flame detection method using color analysis,” in Proceedings of IEEE Networking, Sensing and Control, March 2005, pp. 100-105.
[8] G. Marbach, M. Loepfe, and T. Brupbacher, “An image processing technique for fire detection in video images,” Fire Safety Journal, vol. 41, no. 4, pp. 285-289, 2006.
[9] T. Truong, Y. Kim, and J. Kim, “Fire detection in video using genetic-based neural networks,” IEEE International Conference on Information Science and Applications, April 2011, pp. 445-449.
[10] B. Toreyin, Y. Dedeoglu, and A. Cetin, “Flame detection in video using hidden markov models,” in Proceedings of International Conference on Image Processing, Genoa, Italy, September 2005, pp. 1230-1233.
[11] T. Celik, “Fast and efficient method for fire detection using image processing,” ETRI Journal, vol. 32, no. 6, pp. 881-890, December 2010.
[12] Y. Wang, D. Xu Dafang, X. Chen et al., “Fire detection method based on flame dynamic features,” Measurement & Control Technology, vol. 26, no. 5, pp. 7-9, 2007.
[13] J. Zhao, Z. Zhang, S. Han et al., “SVM based forest fire detection using statistic and dynamic features,” Computer Science and Information Systems, vol. 8, no. 3, pp. 821-840, June 2011.
[14] S. Rinsurongkawong, M. Ekpanyapong, and M. N. Dailey, “Fire detection for early fire alarm based on optical flow video processing,” IEEE International Conference on ECTI-CON, May 2012, pp. 1-4.
[15] B. Toreyin, Y. Dedeoglu, and A.E. Cetin, “Computer vision based method for real-time fire and flame detection,” Pattern Recognition Letters, vol. 27, no. 1, pp. 49-58, 2006.
[16] F. Yuan, G. Liao, Y. Zhang, “Feature extraction for computer vision based fire detection,” Journal of University of Science and Technology of China, vol. 36, no. 1, pp. 39-43, January 2006.
[17] X. Wu, Y. Yan, J. Du et al., “Fire detection based on fusion of multiple features,” CAAI Transactions on Intelligent Systems, vol. 10, no. 2, pp. 240-247, April 2015.
[18] Y. Yang, J. Du, S. Gao et al., “Video flame detection based on fusion of multi-feature,” Journal of Computer-Aided Design & Computer Graphics, vol. 27, no. 3, pp. 433-440, March 2015.
[19] G. Yadav, V. Gupta, V. Gaur et al., “Optimized flame detection using image processing based techniques,” Indian Journal of Computer Science and Engineering, vol. 3, no. 2, pp. 202-211, April 2012.
[20] M. Kandil, M. Salama, “A new hybrid algorithm for fire-vision recognition,” in IEEE Eurocon, May 2009, pp. 1460-1466.
[21] L. Wang, A. Li, C. Hao, “A fire detection method using the flame image jumping feature,” in Proceedings of the 33rd Chinese Control Conference, Nanjing, China, July 2014, pp. 7421-7425.

Copyright © 2019 Jiaqing Chen, Xiaohui Mu, Yinglei Song, Menghong Yu, Bing Zhang

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License