Computer Science ›› 2015, Vol. 42 ›› Issue (3): 301-306.doi: 10.11896/j.issn.1002-137X.2015.03.062

Previous Articles     Next Articles

Video Smoke Detection Using Two-level Classification Algorithm

TONG Bo-bing and WANG Shi-tong   

  • Online:2018-11-14 Published:2018-11-14

Abstract: In order to improve the accuracy of video smoke detection,a probability-based two-level nearest neighbor classification algorithm (PTLNN) was proposed to detect smoke in video.Aiming at minimizing the mean absolute error of principle,combining the advantages of AdaBoost and KNN algorithm,and fully considering local and global sample distribution,the proposed algorithm can significantly improve the classification accuracy.The proposed algorithm adopts the discrete cosine transform (DCT) and discrete wavelet transform (DWT) two ways to extract smoke characteristics.By comparing with the traditional algorithms,the proposed PTLNN algorithm with the discrete cosine transform has better effectiveness on video smoke detection which not only meets the real-time requirements but also improves the detection accuracy.

Key words: Two-level classification,Mean absolute error,Probability-based,Smoke detection,Discrete cosine transform

[1] Fang Lu-ming,Xu Ai-jun,Tang Li-hua.Study of the key technology of forest fire prevention based on a cooperation of video monitor and GIS[J].Natural Computation,2008,5:391-396
[2] Huang Fu-zhen,Wu Hai-tao.Video flame detection basedon color and contour features[C]∥Proceeding of the 31st Chinese Control Conference(CCC).Hefei,China,2012:3668-3671
[3] Chen Juan,He Ya-ping,Wang Jian.Multi-feature fusion basedfast video flame detection[J].Building and Environment,2010,45(5):1113-1122
[4] Toreyin B U,Dedeoglu Y,Cetin A E.Flame detection in video using hidden markov models[C]∥Proc of IEEE International Conference on Image Processing.IEEE Press,2005,2:1230-1233
[5] Habiboglu Y,Gunay O,Cetin A E.Flame detection method invideo using covariance descriptors[C]∥2011 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP).2011:1817-1820
[6] Li Ma,Wu Kai-hua,Zhu L.Fire smoke detection in video imagesusing Kalman filter and Gaussian mixture color model[C]∥IEEE Conputer Press Artificial Intelligence and Computational Intelligence.Las Vegas,USA,2010:484-487
[7] Ko B C,Kwak J,Nam J.Wildfire smoke detection using temporal-spatial features and random forest classifiers[J].Optical Engineering,2012,1(1):1-10
[8] 袁非牛,张永明,刘士兴,等.基于累积量和主运动方向的视频烟雾检测方法[J].中国图象图形学报,2008,13(4):808-813
[9] Yang Jing,Cheng Feng,Zhang Wei-dong.Visual-based smokedetection using support vector machine[C] ∥Fourth International Conference on Natural Computation.Jinan,China,2008:301-305
[10] 吴梦宇,罗琴娟,韩摇宁.基于多运动特征的森林火灾烟雾图像识别算法[J].北京林业大学学报,2013,35(3):154-158
[11] Gubbi J,Marusic S,Palaniswami M.Smoke detection in videousing wavelets and support vector machines[J].Fire Safety Journal,2009,44(8):1110-1115
[12] Wang Zhi-jie,Salah B,Zhang Hong.Discrete wavelet transform based steam detection with Adaboost[C]∥International Confe-rence on Information and Automation (ICIA).Shenyang,China,2012:542-547
[13] 盛家川.基于小波变换的国画特征提取及分类[J].计算机科学,2014,41(2),317-319
[14] Gao Y,Pan J,Ji G,et al.A novel two-level nearest neighbor classification algorithm using an adaptive distance metric[J].Knowledge-Based Systems,2012,26:103-110
[15] 边肇祺,张学工.模式识别[M].北京:清华大学出版社,2000
[16] Duda R O,Hart P E,Stork D G.Pattern classification [M].John Wiley & Sons,2012
[17] XU Zeng-lin,Huang Kai-zhu,Zhu Jian-ke,et al.A novel kernel-based maximum a posteriori classification method[J].Neural Networks,2009,22(7):977-987
[18] Liu Z,Xue Y,Shen L,et al.Nonparametric saliency detectionusing kernel density estimation[C]∥International Conference on Image Processing (ICIP).HongKong,2010:253-256

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!