在本論文中，我們提出一個背景濾除演算法於即時影像監控系統。採用混合高斯模型(GMM)的方法去建立動態背景的背景模型，並且結合背景模型中顏色在時間上資訊，階層式做前景與背景的判定，並利用連續影像空間上變化的程度，更新與重建背景模型，讓背景模型紀錄所有發生狀況的能力。另外我們利用連續影像間前景面積變化的程度與梯度上的資訊，即時的更新背景模型來解決劇烈光線變化的影響。在實驗過程中，我們將本篇論文所提出來的演算法與其他背景濾除演算法做比較，結果可以發現我們的演法在解決戶外場景如：相機晃動、樹葉搖晃、劇烈光線變化下等等，都有不錯的效果。

In this thesis, we present an adaptive background subtraction algorithm for real-time video surveillance. The proposed algorithm build a dynamic background image model on Gaussian mixture model methods. Then, we use color statistical information to segment background and foreground in a hierarchical scheme. The parameters of background are updated according to the results of segmentation and spatial variation of sequence image so all events happened are recorded in the background model. In addition, we update the background immediately by using region variation of foreground of sequence image and gradient information to resist light changes. In our experiment, we compare our algorithm with other algorithms. The results show that our algorithm can handle vibrating camera, waving trees, light changes and so forth in outdoor scene. The proposed background subtraction algorithm is robust against different types of sequence image.

參考文獻
[1] N. Friedman, S. Russel, “Image segmentation in video sequences: A
probabilistic approach,” in Proc. 13th Conf. Uncertainty Artificial
Intelligence, 1997
[2] I. Haritaoglu, D. Harwood, and L.S. Davis, “W4: Real-time surveillance of
people and their activities.” IEEE Transaction on Pattern Analysis and
Machine Intelligence, 22(8):809—830, 2000.
[3] R. Bourezak, G-A. Bilodeau, “Object detection and tracking using
iterative division and correlograms.” Proceedings of the 3rd Canadian
Conference on Computer and Robot Vision, art. no. 1640393, 2006.
[4] C. Stauffer, W.E.L. Grimson, “Adaptive background mixture models for real- time tracking,” Proceedings of the IEEE Computer Society Conference on
Computer Vision and Pattern Recognition 2, pp. 246-252, 1999.
[5] P. KaewTraKulPong, R. Bowden, “An Improved Adaptive Background Mixture
Model for Real-time Tracking with Shadow Detection,” in 2nd European
Workshop on Advanced Video-based Surveillance Systems.Kingston upon
Thames, 2001.
[6] P.W. Power, J.A. Schoonees, “Understanding background mixture models for
foreground segmentation,” Proc. Image and Vision Computing New Zealand,
pp. 267-271, Auckland, New Zealand, November 2002.
[7] K. Toyama, J. Krumm, B. Brumitt, B. Meyers, “Wallflower: principles and
practice of background maintenance,” Proceedings of the IEEE
International Conference on Computer Vision 1, pp. 255-261, 1999.
[8] W. Zhang, X. Fang, X. Yang, Q.M.J. Wu, “Spatiotemporal Gaussian mixture
model to detect moving objects in dynamic scenes,” Journal of Electronic
Imaging 16 (2), art. no. 023013, 2007.
[9] K. Kim, T.H. Chalidabhongse, D. Harwood, L. Davis, “Real-time foreground-
background segmentation using codebook model,” Real-Time Imaging 11 (3),
pp. 172-185, 2005.
[10] M. Heikkilä, M. Pietikäinen, “A Texture-Based Method for Modeling the
Background and Detecting Moving Objects,” IEEE Transactions on Pattern
Analysis and Machine Intelligence 28 (4), pp. 657-662, 2006.
[11] K. Huang, L. Wang, T. Tan, S. Maybank, “A real-time object detecting and
tracking system for outdoor night surveillance,” Pattern Recognition 41
(1), pp. 432-444, 2008.
[12] H.C. Zeng, S.H. Lai, “Adaptive foreground object extraction for real-
time video surveillance with lighting variations,” ICASSP, IEEE
International Conference on Acoustics, Speech and Signal Processing -
Proceedings 1, art. no. 4217301, pp. I1201-I1204, 2007.
[13] D. Hearn and M.P. Baker, Computer Graphics, 2nd Edition, Prentice Hall,
New York, pp. 49-81, 1994.
[14] M. Seul, L. O’Gorman, and M.J. Sammon, Practical Algorithms for Image
Analysis, Cambridge University, New York, pp. 51-55, 2000.
[15] 鍾國亮，“影像處理與電腦視覺”，台北，東華書局，民國九十三年。

[16] X. Lin, “Low bit rate image coding in the scale space, ” Data
Compression　Conference, DCC 2002, pp. 33-42, 2-4, April 2002.
[17] Y. Sun, B. Yuan, “Hierarchical GMM to handle sharp changes in moving
object detection,” Electronics Letters 40 (13), pp. 801-802, 2004.
[18] R. Cucchiara, C. Grana, M. Piccardi, A. Prati, “Detecting moving
objects, ghosts, and shadows in video streams,” IEEE Transactions on
Pattern Analysis and Machine Intelligence 25 (10), pp. 1337-1342, 2003.