Recursive Bayesian fire recognition using greedy margin-maximizing clustering

详细信息    查看全文

• 作者：Sujung Bae (1)
  Sungeun Hong (1)
  Yeongjae Choi (1)
  Hyun S. Yang (1)
  
• 关键词：Fire recognition ; Recursive Bayesian estimation ; Data clustering ; Mixture of Gaussians
• 刊名：Machine Vision and Applications
• 出版年：2013
• 出版时间：November 2013
• 年：2013
• 卷：24
• 期：8
• 页码：1605-1621
• 全文大小：1591KB
• 参考文献：1. Borges, P., Izquierdo, E.: A probabilistic approach for vision-based fire detection in videos. IEEE Trans. Circuits Syst. Video Technol. 20(5), 721鈥?31 (2010) CrossRef
  2. 脟elik, T., Demirel, H.: Fire detection in video sequences using a generic color model. Fire Saf. J. 44(2), 147鈥?58 (2009) CrossRef
  3. Cetin, A.E.: Computer vision based fire detection software. (2007) http://signal.ee.bilkent.edu.tr/VisiFire/
  4. Cetin, A.E., Porikli, F.: Special issue on dynamic textures in video. Mach. Vis. Appl. 22(5), 739鈥?40 (2011) CrossRef
  5. Chen, T., Wu, P., Chiou, Y.: An early fire-detection method based on image processing. In: International Conference on Image Processing (ICIP), vol. 3, pp. 1707鈥?710 (2004)
  6. Chetverikov, D., Fazekas, S., Haindl, M.: Dynamic texture as foreground and background. Mach. Vis. Appl. 22(5), 741鈥?50 (2011)
  7. Choi, J., Cho, Y., Cho, K., Bae, S., Yang, H.S.: A view-based multiple objects tracking and human action recognition for interactive virtual environments. Int. J. Virtual Real. 7(3), 71鈥?6 (2008)
  8. Collins, R.T., Lipton, A.J., Kanade, T., et al.: A system for video surveillance and monitoring. Technical Report. CMU-RI-TR-00-12, The Robotics Institute, Carnegie Mellon University (2000)
  9. Dasgupta, S.: Learning mixtures of gaussians. In: Symposium on Foundations of Computer Science, pp. 634鈥?44 (1999)
  10. Dedeoglu, Y., T枚reyin, B., G眉d眉kbay, U., 脟etin, A.E.: Real-time fire and flame detection in video. In: International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 669鈥?73 (2005)
  11. Doretto, G., Chiuso, A., Wu, Y.N., Soatto, S.: Dynamic textures. Int. J. Comput. Vis. 51(2), 91鈥?09 (2003) CrossRef
  12. Gunay, O., Toreyin, B.U., Kose, K., Cetin, A.E.: Entropy-functional-based online adaptive decision fusion framework with application to wildfire detection in video. IEEE Trans. Image Process. 21(5), 2853鈥?865 (2012) CrossRef
  13. Habibo臒lu, Y.H., G眉nay, O., 脟etin, A.E.: Covariance matrix-based fire and flame detection method in video. Mach. Vis. Appl. 23(6), 1103鈥?113 (2012) CrossRef
  14. Healey, G., Slater, D., Lin, T., Drda, B., Goedeke, A.: A system for real-time fire detection. In: International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 605鈥?06 (1993)
  15. Ho, C.C.: Machine vision-based real-time early flame and smoke detection. Meas. Sci. Technol. 20(4), 1鈥?3 (2009) CrossRef
  16. Ko, B., Cheong, K., Nam, J.: Fire detection based on vision sensor and support vector machines. Fire Saf. J. 44(3), 322鈥?29 (2009)
  17. Ko, B., Cheong, K.H., Nam, J.Y.: Early fire detection algorithm based on irregular patterns of flames and hierarchical bayesian networks. Fire Saf. J. 45(4), 262鈥?70 (2010) CrossRef
  18. Ko, B.C., Ham, S.J., Nam, J.Y.: Modeling and formalization of fuzzy finite automata for detection of irregular fire flames. IEEE Trans. Circuits Syst. Video Technol. 21(12), 1903鈥?912 (2011)
  19. Liu, C., Ahuja, N.: Vision based fire detection. In: International Conference on Pattern Recognition (ICPR), vol. 4, pp. 134鈥?37 (2004)
  20. Matthews, S., Sullivan, A., Gould, J., Hurley, R., Ellis, P., Larmour, J.: Field evaluation of two image-based wildland fire detection systems. Fire Saf. J. 47, 54鈥?1 (2012) CrossRef
  21. Orchard, M., Bouman, C.: Color quantization of images. IEEE Trans. Signal Process. 39(12), 2677鈥?690 (1991) CrossRef
  22. P茅teri, R., Fazekas, S., Huiskes, M.J.: DynTex : a comprehensive database of dynamic textures. Pattern Recognit. Lett. 31(12), 1627鈥?632 (2010). http://projects.cwi.nl/dyntex/
  23. Phillips III, W., Shah, M., da Vitoria Lobo, N.: Flame recognition in video. Pattern Recognit. Lett. 23, 319鈥?27 (2002)
  24. T枚reyin, B.U., 脟etin, A.E.: Online detection of fire in video. In: International Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1鈥? (2007)
  25. T枚reyin, B.U., Dedeo臒lu, Y., G眉d眉kbay, U., 脟etin, A.E.: Computer vision based method for real-time fire and flame detection. Pattern Recognit. Lett. 27(1), 49鈥?8 (2006) CrossRef
  26. Verstockt, S., Poppe, C., Hoecke, S.V., Hollemeersch, C., Merci, B., Sette, B., Lambert, P., de Walle, R.V.: Silhouette-based multi-sensor smoke detection: Coverage analysis of moving object silhouettes in thermal and visual registered images. Mach. Vis. Appl. 23(6), 1243鈥?262 (2012)
  27. Warhade, K.K., Merchant, S.N., Desai, U.B.: Shot boundary detection in the presence of fire flicker and explosion using stationary wavelet transform. Signal Image Video Process. 5(4), 507鈥?15 (2011) CrossRef
  28. Yuan, F.: An integrated fire detection and suppression system based on widely available video surveillance. Mach. Vis. Appl. 21(6), 941鈥?48 (2010)
  
• 作者单位：Sujung Bae (1)
  Sungeun Hong (1)
  Yeongjae Choi (1)
  Hyun S. Yang (1)
  
  1. Department of Computer Science, Korea Advanced Institute of Science and Technology, 291 Daehak-ro, Yuseong-gu, Daejeon, 305-701, Republic of Korea
  
• ISSN：1432-1769

文摘

Vision-based fire detection is a challenging research area, since the visual features of fire dynamically change due to several factors such as weather conditions. In this paper, we propose a novel fire detection approach in which detected fire-candidate blobs are categorized as fire or non-fire under recursive Bayesian estimation. By employing the recursive estimation, we attempt to deal with fire characteristics that are dynamic as well as spatiotemporally continuous in a hidden Markov process. More specifically, for each detected fire-candidate blob, future beliefs about hidden classes are predicted and corrected by the most recent beliefs and observations of the blob. This is repeated during the lifetime of the blob. In this framework, to reduce the Bayes error in classification, we devised the greedy margin-maximizing clustering algorithm. This algorithm learns color clusters to model the feature space while attempting to maximize the in-cluster margins within a class and between classes. To further improve the detection accuracy, we developed two methods, $\epsilon $ -time delayed decision and on-line learning of transition probability. These were invented to suppress false alarms caused by temporary fire-like instances and to determine the current class by considering the majority of previous classification results. Experiments and comparative analyses with two contemporary approaches are conducted for various fire situations. The results show that the proposed approach is superior to the previous approaches in detecting fire and reducing false alarms. Furthermore, the proposed approach is shown to be competitive in applications to real environments.