移動物件的偵測是許多智慧型影像監控系統中佔有舉足輕重地位的步驟，系統後續處理諸如動作分析或移動物件之追蹤均十分仰賴偵測之結果。本論文提出一個以貝氏定理為基礎之背景相減方法達到偵測移動物件的目的，並且提出遞迴式的背景模型更新公式，得到較佳的背景影像模型，此背景影像機率模型之更新速度可隨著場景光線變化自動改變。本論文提出之方法與先前已發表之數個演算法進行模擬與實際的影像結果之比較，本方法擁有較穩定且快速的結果。

Moving objects detection is a crucial step for video surveillance. Succeeding processes such as motion object tracking and recognition highly depend on the results of detection. This paper proposes a Bayesian-based background subtraction approach for the detection of moving object. The approach devises recursive formula to better estimate the probabilistic model of background. The update rate of the probabilistic background model is adaptive to light change of environments. The proposed approach is compared to several methods in experiments of simulated and real-world videos. Fast and stable experimental results show the feasibility of our approach.

Abstract（in Chinese） i

Abstract ii

Acknowledgement（in Chinese） iii

Contents iv

List of tables vi

List of figures vii

Chapter 1 Introduction 1
1.1. Motivation 1
1.2. System overview 1
1.2.1. Background subtraction by Bayesian decision 2
1.2.2. Improved Gaussian mixture background modeling 2
1.3. Thesis organization 2
Chapter 2 Related works 5

Chapter 3 Background 14

Chapter 4 Background subtraction by Bayesian decision 21

Chapter 5 Improved Gaussian mixture background modeling 25
5.1. Parameters estimation 25
5.2. Lighting change analyzer 28
Chapter 6 Experimental results 32
6.1. Synthetic data simulations 32
6.2. Comparison of detection results 39
6.3. Image sequences tests 43
6.3.1. Introduction to image sequences 44
6.3.2. The results 45
Chapter 7 Conclusions 52

References 53

[1]R. Cucchiara, C. Grana, M. Piccardi, and A. Prati, “Detecting moving objects, ghosts, and shadows in video streams,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, pp. 1337-1342, 2003.
[2]B. Shoushtarian and H. E. Bez, “A practical adaptive approach for dynamic background subtraction using an invariant colour model and object tracking,” Pattern Recognition Letters, vol. 26, no. 1, pp. 5-26, 2005.
[3]C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “Pfinder: Real-time tracking of the human body,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 780-785, 1997.
[4]C. Stauffer and W. E. L. Grimson, “Adaptive background mixture models for real-time tracking,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, 1999, pp. 246-252.
[5]P. KaewTraKulPong and R. Bowden, “An improved background mixture model for real-time tracking with shadow detection,” in Proc. of 2nd European Workshop on Advanced Video Based Surveillance Systems, vol. 25, 2001.
[6]Z. Zivkovic, “Improved adaptive Gaussian mixture model for background subtraction,” in Proc. of IEEE International Conference on Pattern Recognition, vol. 2, 2004, pp. 28-31.
[7]A. Elgammal, R. Duraiswami, D. Harwood, and L. S. Davis, “Background and foreground modeling using nonparametric kernel density estimation for visual surveillance,” in Proc. IEEE, vol. 90, no. 7, 2002, pp. 1151-1163.
[8]I. Haritaoglu, D. Harwood, and L. S. Davis, “ : Real-time surveillance of people and their activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 809-830, 2000.
[9]S. Kang, J. Paik, A. Koschan, B. Abidi, and M. A. Abidi, “Real-time video tracking using PTZ cameras,” in Proc. of SPIE 6th International Conference on Quality Control by Artificial Vision, vol. 5132, 2003, pp. 103-111.
[10]Y. Ivanov, A. Bobick, and J. Liu, “Fast lighting independent background subtraction,” International Journal of Computer Vision, vol. 37, no. 2, pp. 199-207, 2000.
[11]P. W. Power and J. A. Schoonees, “Understanding background mixture models for foreground segmentation,” in Proc. of Image and Vision Computing New Zealand, 2002, pp. 267-271.
[12]D. S. Lee, J. Hull, and B. Erol, “A Bayesian framework for Gaussian mixture background modeling,” in Proc. of IEEE International Conference on Image Processing, vol. 3, 2003, pp. 14-17.
[13]W. E. L. Grimson, C. Stauffer, R. Romano, and L. Lee, “Using adaptive tracking to classify and monitor activities in a site,” in Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 1998, pp. 22-29.
[14]M. Cristani, M. Bicego, and V. Murino, “Integrated region- and pixel-based approach to background modelling,” in Proc. of IEEE Computer Society Conference on Motion and Video Computing, 2002, pp. 3-8.
[15]D. S. Lee, “Effective Gaussian mixture learning for video background subtraction,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 5, pp. 827-832, 2005.
[16]S. E. Chen, “QuickTime VR – An image based approach to virtual environment navigation,” in Proc. of SIGGRAPH 95, 1995, pp. 29-38.
[17]Y. Ren, C. S. Chua, and Y. K. Ho, “Statistical background modeling for non-stationary camera,” Pattern Recognition Letters, vol. 24, pp. 183-196, 2003.