隨著近年來炸彈恐怖攻擊的增加，而且恐怖攻擊大部分都發生在人潮密集的公共場所，所以如何設計一個偵測靜止可疑(遺棄)物體的監視系統是非常重要的；在本篇論文提出了一個監視系統的技術，希望能在前景(foreground)較複雜的公共場合裡，儘快且不失準確性地找尋出靜止不動的可疑物體。
有一些研究也是在討論這類的問題。他們大部分都是利用靜止不動的可疑物體的兩個特性來設計其監視系統： a)靜止可疑物體不屬於背景。b)以及在監視的影片中，靜止可疑物體出現在頻率會比其他的前景出現的頻率高，或是靜止的可疑物體在某個時間內會連續的出現在影片中。
上述的監視系統在人潮並沒有十分擁擠的環境中，可以得到不錯的監視效果，但是當系統用來監視人潮非常擁擠場所時(如在捷運台北車站)，由於靜止物體可能大部分時間都被行人給擋住了，導致上述的靜止物體的第二特性就不明顯，這些方法就不適用。所以此篇論文主要是設計一個動態過濾器(motion filter)，先將每張frame中極有可能是動態物體的點先移除掉後，紀錄剩下可能為靜態物體的點。倘若某個點，在video sequence中出現靜態物體的點的次數累積足夠多，且顏色均相似，我們才宣告此點為可疑物體上的點。而我們套用現在model background很熱門的方法之一-Mixture of Gaussian，來紀錄的每個點顏色的歷史紀錄。
最後，我們針對三種人潮量不同的video sequences來做實驗。我們發現在人潮量最少以及人潮量普通的環境裡，沒有使用我們設計的動態過濾器，也可以找出影片中的靜止物體；但是當人潮非常眾多的時候，倘若沒有使用我們的動態過濾器，會出現許多的錯誤警告。如果加上我們的動態過濾器，就可以移除掉這些來自於人潮造成的干擾(和其他方法比較，約減少70%的錯誤警告)。

As the increasing of the bomb attacks in recent years and these attacks are repeatedly concentrated on the public places, such as MRT stations. Establishing a surveillance system with high-tech appliances to against terrorism becomes a critical issue nowadays. In this thesis, an algorithm of finding the abandoned objects in the environment of crowded public places is proposed.
There exist some approaches to discover the abandoned objects under the circumstance of two scenarios: 1) The pixels in the scenes of abandoned objects do not intermixed with background pixels; 2) The abandoned objects emerge more often than other moving objects (pedestrians, commuters, etc.) in a surveillance video segment. These approaches work well in the phenomena of occasionally few pedestrians, but may fail in case there are crowded in rush hours; the system would issue many false alarms then.
In this study a motion filter is proposed to filter out the partial scenes caused by irrelevant motion objects, together with accumulate the remaining useful pixel information. If we have enough evidence of abandoned objects according to cumulated records, an alarm is issued. We use the Mixture of Gaussian (MoG), which is the most popular background modeling tool, to record the useful history of each pixel.
Finally, we use three scenarios to examine the performance of our approach, they are: few, normal and rush hours. The detection accuracy of the system without our motion filter is still satisfying in the environment with casual or normal cases, however it issued numerous false alarms in the environment that is highly crowded. While on the contrary the system with the help of our motion filter will issue the proper alarm for abandoned objects or some few unfavorable alarms for some specific background noises.

[1] http://www.cs.cmu.edu/~vsam/vsamhome.html
[2] Ts Yang; Quan Pan; Li, S.Z.; Jing Li ,“Multiple Layer Based Background Maintenance In Complex Environment,” Image and Graphics, 2004. Proceedings. Third International Conference on, 18-20, Dec. 2004, pp.112 – 115
[3] Alsaqre, F.E., Yuan Baozong,”Multiple Moving Objects Tracking for Video Surveillance Systems,” Signal Processing, 2004. Proceedings. ICSP '04. 2004 7th International Conference on, Volume 2, 31 Aug.-4 Sept. 2004 Page(s):1301 - 1305 vol.2.
[4] Stringa, E., Soldatini, F., RegazzoniJoint, “Video-Shot and Layer Indexing in Video-Surveillance Application,” Image Processing, 1999. ICIP 99. Proceedings. 1999 International Conference on, Volume 3, 24-28 Oct. 1999 Page(s):274 - 278 vol.3
[5] Liyuan Li, Leung, M.K.H., “Fusion of Two Different Motion Cues for Intelligent Video Surveillance,” Electrical and Electronic Technology, 2001. TENCON. Proceedings of IEEE Region 10 International Conference on, Volume 1, 19-22 Aug. 2001 Page(s):341 - 344 vol.1
[6] Bhandarkar, S.M.; Xingzhi Luo, “Fast and Robust Background Updating for Real-time Traffic Surveillance and Monitoring,” Computer Vision and Pattern Recognition, 2005 IEEE Computer Society Conference on, vol. 3, June 2005,pp. 55 – 55
[7] Zivkovic, Z ., ”Improved Adaptive Gaussian Mixture Model for Background,” Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on, Volume 2, 23-26 Aug. 2004 Page(s):28 - 31 Vol.2
[8] Sangho Park, Aggarwal, J.K., “Segmentation and Tracking of Interacting Human Body Parts Under Occlusion and Shadowing,” Motion and Video Computing, 2002. Proceedings. Workshop on, 5-6 Dec. 2002 Page(s):105 - 111
[9] Lim Hock Wyi Aloysius, Guo Dong; Huang Zhiyong, Tele Tan, “Human Posture Recognition in Video Sequence Using Pseudo 2-D Hidden Markov Models,” Control, Automation, Robotics and Vision Conference, 2004. ICARCV 2004 8th, Volume 1, 6-9 Dec. 2004 Page(s):712 - 716 Vol. 1
[10] Gibbins, D., Newsam, G.N., Brooks, M.J.Detecting, “Suspicious Background Changes in Video Surveillance of Busy Scenes,” Applications of Computer Vision, 1996. WACV '96., Proceedings 3rd IEEE Workshop on, 2-4 Dec. 1996 Page(s):22 - 26
[11] Sacchi, C., Regazzoni, C.S., “A Distributed Surveillance System for Detection of Abandoned Objects in Unmanned Railway Environments,” Vehicular Technology, IEEE Transactions on, Volume 49, Issue 5, Sept. 2000 Page(s):2013 - 2026
[12] Ts Yang, Quan Pan, Li, S.Z., Jing Li, “Multiple Layer Based Background Maintenance in Complex Environment,” Image and Graphics, 2004. Proceedings. Third International Conference on, 18-20 Dec. 2004 Page(s):112 - 115
[13] Stauffer, C., Grimson, W.E.L., “Adaptive Background Mixture Models for Real-Time Tracking,” Computer Vision and Pattern Recognition, 1999. IEEE Computer Society Conference on., Volume 2, 23-25 June 1999 Page(s):
[14] P.Wayne Power, Johann.A. Schoonees, ”Understanding Background Mixture Models for Foreground Segmentation,” Proceedings Image and Vision Computing New Zealand 2002, 26-28th November 2002
[15] Bailo, G., Bariani, M.; Ijas, P., Raggio, M.,”Background Estimation with Gaussian Distribution for Image Segmentation, a Fast Approach,” Measurement Systems for Homeland Security, Contraband Detection and Personal Safety Workshop, 2005. (IMS 2005) Proceedings of the 2005 IEEE International Workshop on, 29-30 March 2005 Page(s):2 - 5
[16] Qi Zang and Reinhard Klette, “Evaluation of an Adaptive Composite Gaussian Model in Video Surveillance,” CITR at Tamaki Campus, Aug 2002