Abstract To overcome the uncertainty of smoke characteristics caused by the environment background, inhibit the redundancy between video smoke features, and improve the recognition rate simultaneously, a MI-Simba algorithm combining mutual information and simbafor recognizing cigarette smoke in indoor videos is proposed. Firstly, the statistic feature, color layout feature and dynamic feature of cigarette smoke are obtained by the method of video feature extraction, and then the initial feature vector is established. Secondly, the feature vector is updated automatically by MI-Simba, and the optimal feature combination in this environment is established. Then a transductive support vector machine(TSVM) is used for classification and recognition. Finally, the recognition rate and sensitivity are computed on the self-built video sequence database by 5-fold cross validation. The experimental results demonstrate the validity and superiority of the proposed algorithm compared with other algorithms.
[1] Odetallah A D, Agaian S S. Human Visual System-Based Smoking Event Detection // Proc of SPIE 8406: The Mobile Multimedia /Image Processing, Security, and Applications. Baltimore, USA, 2012: 4344-4347 [2] Bien T L, Lin C H. Detection and Recognition of Indoor Smoking Events//Proc of the 15th International Conference on Machine Vision. Wuhan, China, 2012. DOI:10.1117/12.2020967 [3] Inoue H, Tanake T. Image-Based Smoke Detection with k-Subspaces Clustering//Proc of RISP International Workshop on Nonlinear Circuits and Signal Processing. Hawaii, USA, 2009:321-324 [4] Wu P, Hsieh J W, Cheng J C, et al. Human Smoking Event Detection Using Visual Interaction Clues // Proc of the 20th International Conference on Pattern Recognition. Istanbul, Turkey, 2010: 4344-4347 [5] Chang S F, Sikora T, Purl A. Overview of the MPEG-7 Standard. IEEE Trans on Circuits and Systems for Video Technology, 2001, 11(6): 688-695 [6] Sikora T. The MPEG-7 Visual Standard for Content Description-An Overview. IEEE Trans on Circuits and Systems for Video Technology, 2001, 11(6): 696-702 [7] Wang T, Liu Y, Xie Z P. Flutter Analysis Based Video Smoke Detection. Journal of Electronics & Information Technology, 2011, 33(5): 1024-1029 (in Chinese) (王 涛,刘 渊,谢振平.一种基于飘动性分析的视频烟雾检测新方法.电子与信息学报, 2011, 33(5): 1024-1029) [8] Yuan F N. A Fast Accumulative Motion Orientation Model Based on Integral Image for Video Smoke Detection. Pattern Recognition Lett-ers, 2008, 29(7): 925-932 [9] Kira K, Rendell L A. A Practical Approach to Feature Selection // Proc of the 9th International Workshop on Machine Learning. Aberdeen, UK, 1992: 249-256 [10] Zhang X, Deng Z H, Wang S T, et al. Maximum Entropy Relief Feature Weighting. Journal of Computer Research and Development, 2011, 48(6): 1038-1048 (in Chinese) (张 翔,邓赵红,王士同,等.极大熵Relief特征加权.计算机研究与发展, 2011, 48(6): 1038-1048) [11] Battiti R. Using Mutual Information for Selecting Features in Supervised Neural Net Learning. IEEE Trans on Neural Networks, 1994, 5(4): 537-550 [12] Kwak N, Choi C H. Input Feature Selections for Classification Problems. IEEE Trans on Neural Networks, 2002, 13(1): 143-159 [13] Peng X J, Wang Y F. A Bi-Fuzzy Progressive Transductive Support Vector Machine Algorithm. Pattern Recognition and Artificial Intelligence, 2009, 22(4): 560-566 (in Chinese) (彭新俊,王翼飞.双模糊渐进直推式支持向量机算法. 模式识别与人工智能, 2009, 22(4): 560-566)
2015, Vol. 28 
