Video-based Recognition of Early Fire Flame in Road Tunnel

WANG Lin, YAO Xin, LEI Dan

China Journal of Highway and Transport ›› 2018, Vol. 31 ›› Issue (11) : 121-129.

PDF Full Text Download(1979 KB)
PDF Full Text Download(1979 KB)
China Journal of Highway and Transport ›› 2018, Vol. 31 ›› Issue (11) : 121-129.

Video-based Recognition of Early Fire Flame in Road Tunnel

  • WANG Lin, YAO Xin, LEI Dan
Author information +
History +

Abstract

Effective detection and warning of early fires in road tunnels are important. Owing to the slow response of the traditional temperature-sensitive fire flame detectors in large-space environments such as road tunnels, both static and dynamic features in the uncontrolled flame image were investigated. An early fire flame recognition method based on the flame image features and AdaBoost algorithm was proposed. A frame differential algorithm was used to extract the moving target. The suspicious region was segmented by the color statistical model of flame in RGB and Lab spaces. Further, the feature vector, which was formed by combining the first order moment of H component, circularity, and the feature value of LBP's first order moment, was used as input to the AdaBoost static feature model. The normalized feature value of centroid beating frequency was extracted from the suspicious region in a detection period. Then, the ratio of the number of flame frames in the recognition result of the AdaBoost static feature model was derived. Both the normalized feature value and the ratio were input to the AdaBoost synthesized feature model. Further, the parameters of AdaBoost model were selected and optimized. The classifiers of the AdaBoost static feature model and the AdaBoost synthesized feature model were tested using analog and public videos. The experimental results revealed that the proposed method can effectively recognize early fire flame in road tunnels and exclude false alarms resulting from interferences such as false flame and car lights.

Key words

tunnel engineering / fire flame detection / AdaBoost algorithm / multi-feature fusion

Cite this article

Download Citations
WANG Lin, YAO Xin, LEI Dan. Video-based Recognition of Early Fire Flame in Road Tunnel[J]. China Journal of Highway and Transport, 2018, 31(11): 121-129

References

[1] 《中国公路学报》编辑部.中国隧道工程学术研究综述·2015[J].中国公路学报,2015,28(5):1-65. Editorial Department of China Journal of Highway and Transport.Review on China Tunnel Engineering Research:2015[J]. China Journal of Highway and Transport, 2015, 28(5):1-65.
[2] 王少飞,林志,余顺.公路隧道火灾事故特性及危害[J].消防科学与技术,2011,30(4):337-340.WANG Shao-fei, LIN Zhi, YU Shun. The Characteristic and Damage of Fire Accidents in Road Tunnel[J]. Fire Science and Technology, 2011, 30(4):337-340.
[3] 王华牢,刘学增,马小君.长大公路隧道火灾安全疏散研究[J].公路交通科技,2010,27(11):83-87. WANG Hua-lao, LIU Xue-zeng, MA Xiao-jun. Research on Safe Evacuation in Long Road Tunnel During Fire[J]. Journal of Highway and Transportation Research and Development, 2010, 27(11):83-87.
[4] SCHULTZE T, KEMPKA T, WIlLMS I. Audio-video Fire-detection of Open Fires[J]. Fire Safety Journal, 2006, 41(4):311-314.
[5] 孙庆翔,秦刚,丁国锋.高速公路隧道害事件检测新方法及应用研究[J].公路交通科技,2010,27(11),94-99.SUN Qing-xiang, QIN Gang, DING Guo-feng. A New Detection Method and Application for Expressway Tunnel Accidents and Disasters[J]. Journal of Highway and Transportation Research and Development, 2010, 27(11):94-99.
[6] NODA S, UEDA K. Fire Detection in Tunnels Using an Image Processing Method[C]//IEEE. Proceedings of Vehicle Navigation and Information Systems Conference. New York:IEEE, 1994:57-62.
[7] HAN D, LEE B. Flame and Smoke Detection Method for Early Real-time Detection of a Tunnel Fire[J]. Fire Safety Journal, 2009, 44(7):951-961.
[8] 陈建新,刘青,陈佳.基于视频数据的公路隧道火灾预警算法[J].北京理工大学学报,2012,32(6):596-601.CHEN Jian-xin, LIU Qing, CHEN Jia.Algorithm to Predict Highway Tunnel Fire Based on Video Data[J]. Transactions of Beijing Institute of Technology, 2012, 36(6):596-601.
[9] WONG A K K, FONG N K. Experimental Study of Video Fire Detection and Its Applications[J]. Procedia Engineering, 2014, 71:316-327.
[10] HABIBOGLU Y H, GVNAY O, ÇETIN A E. Covariance Matrix-based Fire and Flame Detection Method in Video[J]. Machine Visio and Applications, 2011, 25(2):339-351.
[11] DIMITROPOULOS K, BARMPOUTIS P, GRAMMALIDIS N. Spatio-temporal Flame Modeling and Dynamic Texture Analysis for Automatic Video-based Fire Detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2015, 25(2):339-351.
[12] 王琳,郭晨,李爱国,等.基于多特征的公路隧道早期火灾火焰视频探测[J].公路交通科技,2015,32(6):103-108.WANG Lin, GUO Chen, LI Ai-guo, et al. An Early Fire Flame Detection Method for Road Tunnel Based on Video Multi Features[J]. Journal of Highway and Transportation Research and Development, 2015, 32(6):103-108.
[13] WANG Hai-feng, REN Hong-e. Research on the Segmentation and Pick-up Algorithm of Bamboo Wood Cross-section Based on Lab Color Space[J].International Journal of Signal Processing, Image Processing and Pattern Recognition, 2015, 8(5):161-168.
[14] CHEN Li, WANG Dong-yi, LIU Yi-qin, et al. A Novel Automatic Tongue Image Segmentation Algorithm:Color Enhancement Method Based on Lab Color Space[C]//IEEE. Proceedings of 2015 IEEE International Conference on Bioinformatics and Biomedicine. New York:IEEE, 2015:990-993.
[15] STRICKER M A, ORENGO M. Similarity of Color Images[J]. Proceedings of SPIE, 1995, 2420:381-392.
[16] OJALA T, P IETIKÄINEN M, MÄENPÄÄ T. Multi Resolution Gray Scale and Rotation Invariant Texture Classification with Local Binary Patterns[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7):971-987.
[17] 严云洋,唐岩岩,刘以安,等.使用多尺度LBP特征和SVM的火焰识别算法[J].山东大学学报:工学版,2012,42(5):47-52,58. YAN Yun-yang, TANG Yan-yan, LIU Yi-an, et al. Flame Detection Based on LBP Features with Multi-scales and SVM[J]. Journal of Shandong University:Engineering Science, 2012, 42(5):47-52, 58.
[18] 安志伟,袁宏永,屈玉贵. 数据采集在火焰闪烁频率的测量研究及分析中的应用[J].火灾科学,2000,9(2):43-47. AN Zhi-wei, YUAN Hong-yong, QU Yu-gui. Data Collection on the Research of Fire Flash Frequency[J]. Fire Safety Science, 2000, 9(2):43-47.
[19] 王琳,李爱国,郝春雨.基于火焰图像跳动特征的火灾识别算法[C]//徐胜元,赵千川.第33届中国控制会议论文集. 上海:上海系统科学出版社,2014:7421-7425.WANG Lin, LI Ai-guo, HAO Chun-yu. A Fire Detection Method Using the Flame Image Jumping Feature[C]//XU Sheng-yuan, ZHAO Qian-chuan. Proceedings of the 33rd Chinese Control Conference. Shanghai:Shanghai Systems Science Publisher, 2014:7421-7425.
[20] FREUND Y, SCHAPIRE, R. A Decision Theoretic Generalization of on Line Learning and an Application to Boosting[J]. Journal of Compute and System Sciences, 1997, 55(1):119-139.
[21] 崔华,张骁,郭璐,等.多特征多阈值级联AdaBoost行人检测器[J].交通运输工程学报,2015,15(2):109-117.CHI Hua, ZHANG Xiao, GUO Lu, et al. Cascade AdaBoost Pedestrian Detector with Multi-features and Multi-thresholds[J]. Journal of Traffic and Transportation Engineering, 2015, 15(2):109-117.
[22] 文学志,方巍,郑钰辉.一种基于类Haar特征和改进AdaBoost分类器的车辆识别算法[J].电子学报,2011,39(5):1121-1126.WEN Xue-zhi, FANG Wei, ZHENG Yu-hui. An Algorithm Based on Haar-like Features and Improved AdaBoost Classifier for Vehicle Recognition[J]. Acta Electronica Sinica, 2011, 39(5):1121-1126.
[23] WANG L W, SUGIYAMA M, YANG C, et al. On the Margin Explanation of Boosting Algorithms[C]//COLT. Proceedings of the 21st Annual Conference on Learning Theory. Madison:Omni Press, 2008:479-490.
[24] MASON L, BARTLETT P L, BAXTER J. Direct Optimization of Margins Improves Generalization in Combined Classifiers[C]//NIPS. Proceedings of the 1998 Conference on Advances in Neural Information Processing Systems. Cambridge:The MIT Press, 1999:288-294.
[25] 曹莹,苗启广,刘家辰,等.AdaBoost算法研究进展与展望[J].自动化学报,2013,39(6):745-758.CAO Ying, MIAO Qi-guang, LIU Jia-chen, et al. Advance and Prospects of AdaBoost Algorithm[J]. Acta Automatica Sinica, 2013, 39(6):745-758.
PDF Full Text Download(1979 KB)

1385

Accesses

0

Citation

Detail

Sections
Recommended

/