根據台北市交通局的統計資料顯示，目前市內現有停車位和登記車輛數有著相當大的差距，要如何在此條件之下，提高停車空位的使用效率，已經成為現今解決停車問題的首要課題。本研究提出的系統架構可分為三大部分，分別是環境地圖建立、車輛偵測以及車輛追蹤。車輛偵測的部份主要是找出攝影機畫面中移動的物體，車輛追蹤則是針對上個步驟所偵測出的前景物進行追蹤，最後再將追蹤所得到的資訊，透過環境地圖建立過程中所得到的座標轉換公式將最終結果呈獻給使用者。
在車輛偵測的部份這邊是採用連續影像相減法，並且透過邊緣偵測以及注意力區域取得移動中的物件邊緣資訊，再利用水平集方法得到完整的物件邊緣，最後得到追蹤所需要的前景物資訊。透過此過程進行車輛偵測，除了可以避免環境中光影對前景物擷取產生的影響，也可以降低物件區塊碎裂和物件邊緣不完整情形發生的可能性，得到的結果也比一般的連續影像相減法及背景影像相減法來得完整。
接著在追蹤的部份，本研究使用聯合粒子濾波器的技術來對前一個步驟得到的前景物進行追蹤，聯合粒子濾波器的特性就是可以同時考慮到影像畫面中所有移動車輛的狀態，並且對所有的車輛建立出各個相聯關係事件，透過對每一個事件的重要性計算，可以預測出這些車輛在下一個影像畫面中可能出現的位置，與傳統粒子濾波器相比其結構更為嚴謹，獲得的結果也較為準確。
最後再利用是已計算出的座標轉換公式將追蹤得到的結果，先透過座標轉換以及平面對應兩個步驟，將最終的位置傳送到使用者介面，讓使用者在監控停車場時可以清楚明瞭的知道停車場中所有車輛的情況。

The temporal difference method is used for vehicle detection in this paper. We can obtain the current edge image and background edge image by canny edge detection, and to generate the region of attention (ROA) can be used to find object edge. Final, to obtain the complete object edge by level set method. These processing can avoid the incomplete object edge information. A technique, joint particle filter (JPF), is proposed for multi vehicles tracking in image sequences. To use JPF have to consider all states of vehicles in this frame at the same time and to construct the joint association events (JAE). The weights of these joint association events are used to predict some locations which maybe appear vehicles in next frame. The final result of vehicle tracking will send to administrator after coordinate translation and floor-plane mapping.

[Als 04] F.E. Alsaqre, Yuan Baozong, ”Multiple moving objects tracking for video surveillance systems,” IEEE 2004 7th International Conference on Signal Processing, Page(s): 1301-1305 vol.2, 2004.

[Bla 02] J. Black, T. Ellis, P. Rosin, “Multi View Image Surveillance and Tracking,” IEEE Workshop on Motion and Video Computing, Page(s):169–174, 2002.

[Boe 07]Y. Boers, H. Driessen, “The Mixed Labeling Problem in Multi Target Particle,” IEEE 10th International Conference on Information Fusion, Page(s):1–7, 2007.

[Che 08] Ai-hua Chen, Ming Zhu, Yan-hua Wang, Chen Xue, “Mean shift tracking combining SIFT,” 9th IEEE International Conference on Signal Processing, Page(s):1532–1535, 2008.

[Com 99] D. Comaniciu, P. Meer, “Mean shift analysis and applications,” The Proceedings of the Seventh IEEE International Conference on Computer Vision, Volume 2, Page(s):1197–1203, 1999.

[Com 02] D. Comaniciu, V. Ramesh, P. Meer, “Real-time tracking of non-rigid objects using mean shift,” IEEE Conference on Computer Vision and Pattern Recognition, Volume 2, Page(s):142–149, 2000.

[Ekm 07] M. Ekman, E. Sviestins, L. Sjoberg, “Particle Filters for Tracking Closely Spaced Targets,” IEEE 10th International Conference on Information Fusion, Page(s):1-8, 2007.

[Kim 08] Zu-Whan Kim, ”Real time object tracking based on dynamic feature grouping with background subtraction,” IEEE Conference on Computer Vision and Pattern Recognition, Page(s): 1–8, 2008.

[Kuh 06] A. Kuh, D. Mandic, ”Sequential Detection Using Least Squares Temporal Difference Methods,” International Conference on Acoustics, Speech and Signal Processing, Volume 5, Page(s):V-V, 2006.

[Lip 98] A.J. Lipton, H. Fujiyoshi, R.S. Patil, ”Moving target classification and tracking from real-time video,” IEEE Workshop on Applications of Computer Vision, Page(s):8-14, 1998.

[Mas 01] O. Masoud, N.P. Papanikolopoulos, “A novel method for tracking and counting pedestrians in real-time using a single camera,” IEEE Transactions on Vehicular Technology, Volume 50, Issue 5, Page(s): 1267–1278, 2001.

[Sha 04] Caifeng Shan, Yucheng Wei, Tieniu Tan, F. Ojardias, “Real time hand tracking by combining particle filtering and mean shift,” Sixth IEEE International Conference on Automatic Face and Gesture Recognition, Page(s):669 – 674, 2004.

[Unn 07] H. Unno, K. Ojima, K. Hayashibe, H. Saji, ”Vehicle Motion Tracking Using Symmetry of Vehicle and Background Subtraction” IEEE Workshop on Intelligent Vehicles Symposium, Page(s):1127-1131, 2007.

[Wan 06] Jung-Ming Wang, Ching-Ting Tsai, Shen Cherng, Sei-Wang Chen, “Omni-Directional Camera Networks and Data Fusion for Vehicle Tracking in an Indoor Parking Lot,” IEEE International Conference on Video and Signal Based Surveillance, Page(s): 45–45, 2006.

[Wan 07] Tiesheng Wang, I.Y.H. Gu, A. Backhouse, Pengfei Shi, “Moving Object Tracking from Videos Based on Enhanced Space-Time-Range Mean Shift and Motion Consistency,” IEEE International Conference on Multimedia and Expo, Page(s):2002 – 2005, 2007.

[Wu 06] Wu Qiying, Cui Huali, Du Xiaofeng, Wang Mingfen, Jin Taisong, “Real-time Moving Maritime Objects Segmentation and Tracking for Video Communication,” IEEE International Conference Communication Technology, Page(s):1–4, 2006.

[Xu 08] Fang Xu, Jun Cheng, Chao Wang, “Real time face tracking using particle filtering and mean shift,” IEEE International Conference on Automation and Logistics, Page(s):2252-2255, 2008.

[林 02] 林仲璋, “Application of Complex Kalman Filter for Dynamic State Estimation of Power System Harmonics,” 國立成功大學 電機工程學系, 2002.

[凌 04] 凌啟銘, “以適應性背景相減法偵測及追蹤移動物體,” 國立中央大學 資訊工程研究所, 2004

[羅 08] 羅安鈞, “A People Counting Using Top-view Video Sequences,” 國立台灣師範大學 資訊工程研究所, 2008.

[黃 05] 黃仲誼, “Intelligent Parking Management System,” 國立台灣師範大學 資訊工程研究所, 2005.

[張 05] 張厥煒、張傑閔, “A Dynamic Object Searching and Tracking Approach in Sports Video Scenes,” 國立台北科技大學 資訊工程系, 台北科技大學學報第四十之ㄧ期, 2005.

[張 06] 張日菁, “Guidance System of an Intelligent Parking Lot,” 國立台灣師範大學 資訊工程研究所, 2006.

[姚 08] 姚國鵬, “An In-Vehicle Vision-Based Driver’s Drowsiness Detection System,” 國立台灣師範大學 資訊工程研究所, 2008.

[王 05] 王政雄, “Wide Area Security Surveillance Using an Integrated Omni-Directional Camera and PTZ Camera,” 國立台灣師範大學 資訊工程研究所, 2005.