室內抽菸於近幾年漸漸受到各國政府關注並禁止，在現今菸害防制法中，室內三人以上工作場所及室內公共場合全面禁菸。然而，此稽查的效果卻有限，因人力限制難以無時無刻監看是否有室內抽菸行為的發生。因此本論文提出一新穎之方法，利用已裝設在室內之監視器達成自動化偵測及辨識抽菸事件。主要想法為偵測人在抽煙時的重覆性動作來達成偵測與辨識抽菸事件。在我們所提出的方法中，利用背景去除(Background Subtraction)與人體姿態估測(Human Pose Estimation)取得人的頭與雙手之位置與大小資訊。然而，人體姿態估測主要利用膚色偵測(Skin Color Detection)資訊，其資訊會因為光線變化的情況使得偵測效果不佳。因此，我們加入光線補償(Lighting Compensation)演算法，減少影像顏色受光線變化的影響，由實驗結果顯示，此方法可使膚色偵測更加精確。然而，仍有光線補償所無法解決的問題，因光線照射的角度所產生之陰影，使頭、手之顏色偏向非膚色。因此，我們利用卡爾曼濾波器(Kalman filter)追蹤並找出偵測失敗的物件資訊。最後，利用頭與雙手之位置資訊計算出手接近頭的機率特徵。支持向量機器(Support Vector Machine)利用機率特徵達成偵測與辨識抽菸事件。為了分析我們所提出方法的辨識率，測試資料建立在室內，並以監視器畫面角度拍攝。實驗結果顯示準確率達到82.5%。

Smoking in public indoor spaces has become prohibited in many countries since it not only affects the health of the people around you, but also increases the risk of fire outbreaks. This thesis proposes a novel scheme to automatically detect and recognize smoking events by using existing surveillance cameras. The main idea of our proposed method is to detect human smoking events by recognizing their actions. In this scheme, the human pose estimation is introduced to analyze human actions from their poses. The human pose estimation method segments head and both hands from human body parts by using a skin color detection method. However, the skin color methods may fail in insufficient light conditions. Therefore, the lighting compensation is applied to help the skin color detection method become more accurate. Due to the human body parts may be covered by shadows, which may cause the human pose estimation to fail, the Kalman filter is applied to track the missed body parts. After that, we evaluate the probability features of hands approaching the head. The support vector machine (SVM) is applied to learn and recognize the smoking events by the probability features. To analysis the performance of proposed method, the datasets established in the surveillance camera view under indoor environment are tested. The experimental results show the effectiveness of our proposed method with accuracy rate 82.5%.

[1] Wren, C. R., Azarbayejani, A., Darrell, T., and Pentland, A. P., "Pfinder: real-time tracking of the human body," the 2nd International Conference on Automatic Face and Gesture Recognition, pp. 51-56 (1996).
[2] Fujiyoshi, H., Lipton, A. J., and Kanade, T., "Real-time human motion analysis by image skeletonization," the 4th IEEE Workshop on Applications of Computer Vision, pp. 15-21 (1998).
[3] Porle, R. R., Chekima, A., Wong, F., and Sainarayanan, G., "2D upper human body pose modelling using windowing and template matching techniques," International Conference on Man-Machine Systems, pp. 2A7 1-2A7 6 (2009).
[4] Micilotta, A., and Bowden, R., "View-based Location and Tracking of Body Parts for Visual Interaction," British Machine Vision Conference, pp. 849-858 (2004).
[5] Noorit, N., Suvonvorn, N., and Karnchanadecha, M., "Model-based human action recognition," Proceedings of SPIE - The International Society for Optical Engineering (2010).
[6] Chen, H. S., Chen, H. T., Chen, Y. W., and Lee, S. Y., "Human action recognition using star skeleton," the 4th ACM International Workshop on Video Surveillance and Sensor nNetworks, pp. 171-178 (2006).
[7] Chang, C.-Y., “Trajectory-Based Event Detection and Discovery for Surveillance Videos,” Master Thesis, National Tsing Hua University, Hsinchu, Taiwan (2008).
[8] Chen, H.-L., “A Vision Approach for Recognizing Swimmer's Behaviors in Swimming Pool,” Master Thesis, National Taiwan University of Science and Technology, Taipei, Taiwan (2009).
[9] Iwamoto, K., Inoue, H., Matsubara, T., and Tanaka, T., "Cigarette smoke detection from captured image sequences," Proceedings of SPIE - The International Society for Optical Engineering (2010).
[10] Ying, N.-T., “The Vision-Based Recognition and Detection for Indoor Smoking Behavior,” Master Thesis, National Taipei University of Technology, Taipei, Taiwan (2008).
[11] Yeh, H.-Y., “Vision-based Detection System of Smoking Event,” Master Thesis, Yuan Ze University, Taoyuan, Taiwan (2009).
[12] Wu, P., Hsieh, J. W., Cheng, J. C., Cheng, S. C., and Tseng, S. Y., "Human Smoking Event Detection Using Visual Interaction Clues," International Conference on Pattern Recognition, pp. 4344-4347 (2010).
[13] Zhang, W., Zhu, P., Wang, X., and Tian, W., "Feature fusion and prototype learning algorithm based smoking shot recognition," Lecture Notes in Electrical Engineering, pp. 533-540 (2011).
[14] Chai, D., and Ngan, K. N., “Face segmentation using skin-color map in videophone applications,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9(4), pp. 551-564 (1999).
[15] Chen, L., and Grecos, C., "Fast skin color detector for face extraction," Proceedings of SPIE - The International Society for Optical Engineering, pp. 93-101 (2005).
[16] Lin, W.-C., “Skin Color Detection and Face Location in Different sceneries,” Master Thesis, National Central University, Taoyuan, Taiwan (2009).
[17] Phung, S. L., Bouzerdoum, A., and Chai, D., "A novel skin color model in YCbCr color space and its application to human face detection," International Conference on Image Processing, pp. I-289-I-292 (2002).
[18] Soriano, M., Martinkauppi, B., Huovinen, S., and Laaksonen, M., "Using the skin Locus to cope with Changing Illumination Conditions in Color-Based Face Tracking," Proceedings of IEEE Nordic Signal Processing Symposium, pp. 383-386 (2000).
[19] Kalman, R. E., “A New Approach to Linear Filtering and Prediction Problems,” Transactions of the ASME-Journal of Basic Engineering, Vol. 82, pp. 35-45 (1960).
[20] Suliman, C., Cruceru, C., and Moldoveanu, F., “Kalman filter based tracking in an video surveillance system,” Advances in Electrical and Computer Engineering, Vol. 10, pp. 30-34 (2010).
[21] Menezes, P., Barreto, J. C., and Dias, J., "Face Tracking Based On Haar-Like Features And Eigenfaces," the 5th IFAC Syposium on Intelligent Autonomous Vehicles, pp. 5-7 (2004).
[22] Cjang, C. C., and Lin, C. J., “LIBSVM: A library for support vector machines,” ACM Transactions on Intelligent Systems and Technology, Vol. 2, pp. 27:1-27:27 (2011).
[23] Cutler, R., and Davis, L., "View-based detection and analysis of periodic motion," the 14th International Conference on Pattern Recognition, pp. 495-500 (1998).
[24] Funt, B., Barnard, K., and Martin, L., "Is Machine Colour Constancy Good Enough?," the 5th European Conference on Computer Vision, pp. 445-459 (1998).
[25] Pai, Y. T., Ruan, S. J., Shie, M. C., and Liu, Y. C., "A Simple and Accurate Color Face Detection Algorithm in Complex Background," International Conference on Multimedia and Expo, pp. 1545-1548 (2006).
[26] Carletta, J., “Assessing agreement on classification tasks: the kappa statistic,” Computational Linguistics, Vol. 22(2), pp. 249-254 (1996).
[27] Fleiss, J. L., Levin, B., and Paik, M. C., Statistical Methods for Rates & Proportions (3rd ed.) Wiley-Interscience (2003).