Abstract
In order to improve the image fire detection rate in spacious buildings, regression analysis is used to find the inherent relationship between flame features. Then support vector machines (SVM) are used to finish recognition. First, suspected fire regions are detected depending on improved fire-colored pixel detection and hierarchical clustering method. Then, features are extracted and analyzed with regression method. Finally, features are applied to a two-class SVM classifier for fire region verification. The experimental results show that the new feature, area overlap, is efficient and the proposed algorithm has a lower positive false rate than the previous algorithm.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Michael Wirth RZ (2010) Flame region detection based on histogram backprojection. In: 2010 Canadian conference computer and robot vision
Phillips W, Shah M, Lobo NV (2000) Flame recognition in video. In: Proceedings of the fifth IEEE workshop on applications of computer vision, pp 224–229
Chen T-H, Wu P-H, Chiou Y-C (2004) An early fire-detection method based on image processing. In: 2004 international conference on image processing
Yang N-J, Wang H-Q, Ma Z-F (2010) Image fire detection algorithm based on support vector machine. J Comput Appl 30(4):1787–1791
Liang J-S, Wang H-Q, Hu Y, Zou T, Wu M (2012) Image fire detection based on fuzzy cluster. Comput Eng 38(04):196–198
Tung TX, Kim J-M (2011) An effective four-stage smoke-detection algorithm using video images for early fire-alarm systems. Fire Saf J 46:276–282
Ko BC, Cheong KH, Nam JY (2009) Fire detection based on vision sensor and support vector machines. Fire Safety 44(3):322–329
Acknowledgments
This research is supported by grants from Specialized Research Fund for the Doctoral Program of Higher Education of China (SRFDP) (20126120110008), Natural Science Basic Research Plan in Shaanxi Province of China (2012JQ8021), Industrialization Program Funded by Shaanxi Provincial Education Department (2011JG12), and Scientific Research Program Funded by Shaanxi Provincial Education Department (11JK1048).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jia, Y., Wang, H. (2014). Image Fire Detection System Based on Feature Regression Analysis and Support Vector Machine. In: Wen, Z., Li, T. (eds) Practical Applications of Intelligent Systems. Advances in Intelligent Systems and Computing, vol 279. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54927-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-54927-4_14
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54926-7
Online ISBN: 978-3-642-54927-4
eBook Packages: EngineeringEngineering (R0)