臺灣博碩士論文加值系統

本論文研製之監控影像資料庫中針對前景物的搜尋方法，以蒙恬公司所提供的監控影像追蹤技術為基礎，分析物體在不同情況下的移動狀態並做相關處理，將代表前景物的外接矩形(Bounding Box)依時間順序建構出移動軌跡，作為監控影像資料庫的索引。而在搜尋介面上，由於傳統文字介面的查詢對於使用者而言，比較無法直觀找出所需要的資訊，因此我們採用友善的圖形化搜尋介面，讓使用者直接就可在畫面上輸入所欲搜尋物體之移動軌跡，經過與已建構的資料庫索引比對後，即可找到最相似的所需內容，讓使用者操作非常方便而更容易上手。

The thesis focuses on a searching method of foreground in a surveillance video database. We base on the tracking technology of PanPower Corp. and analyze moving states of objects to set up their trajectories which become the indexes of the surveillance video database. The trajectories are composed of a lot of bounding boxes which are arranged in a time sequence. The interface of the surveillance video database provides users to enter a trajectory of target object and compares it with indexes which have been set up before to find the most precise result. The design of interface is friendly to users and better than a traditional text interface.

第一章 緒論. 1
1.1. 研究動機與目的 1
1.2. 相關研究 2
1.3. 系統流程 3
1.4. 本論文各章節介紹 4
第二章 監控影像資料庫系統介紹. 5
2.1. 硬體設備 5
2.2. 軟體架構與操作介面 6
2.3. 資料庫內容 9
2.3.1. 影片名稱編碼規則 9
2.3.2. 視訊特徵 10
2.3.3. 各場景視訊檔內容 11
第三章 以蒙恬TRACKIN 前景物偵測功能為基礎建構軌跡式索引. 13
3.1. 蒙恬“TRACKIN 智慧型全域追蹤監控系統”簡介 13
3.2. 使用代表前景物體的外接矩形進行軌跡的追蹤 15
3.2.1. 分析區塊重疊來追蹤 15
3.2.2. 利用顏色直方圖來輔助追蹤 18
3.2.3. 單一物體移動 19
3.2.4. 多個物體移動 21
3.3. 雜訊偵測與附加軌跡屬性 24
3.3.1. 雜訊偵測（Detecting Noise） 25
3.3.2. 對實際物體的移動軌跡附加屬性 26
3.4. 圖形化使用者搜尋介面 28
第四章 實驗結果與討論 . 31
4.1. 物體各移動型態之追蹤結果 31
4.1.1. 單一物體移動 31
4.1.2. 多個物體移動 32
4.2. 追蹤失誤原因 38
4.3. 雜訊偵測問題 39
第五章 結論與未來工作 . 41
參考文獻 . 42

參考文獻

[1] S. Deb and Y. Zhang, “An Overview of Content-based Image Retrieval Techniques, ” Proceedings of International Conference on Advanced Information Networking and Applications, vol. 01, no. 1, p. 59, 2004.
[2] F. Arman, A. Hsu, and M. Chiu, “Image Processing on Compressed Data for Large Video Databases,” Proceedings of ACM Multimedia ’93, pp. 267-272, 1993.
[3] D. Makris and T. Ellis, “Path Detection in Video Surveillance,” Image and Vision Computing Journal, vol.20, no. 12, pp. 895-903, 2002.
[4] I. Junejo, O. Javed, and M. Shah, “Multi feature path modeling for video surveillance,” in International Conference on Pattern Recognition, 2004.
[5] Z. Fu, W. Hu, and T. Tan, “Similarity Based Vehicle Trajectory Clustering and Anomaly Detection,” Proceedings of the International Conference in Image Processing, vol. 2, pp. 602-605, 2005.
[6] J. Black, T. Ellis, and D. Makris, “A hierarchical database for visual surveillance
Applications,” in Proc. IEEE International Conference on Multimedia and expo, pp. 1571-1574, 2004.
[7] E. Sahouria and A. Zakhor, “A trajectory Based Video Indexing System for Street Surveillance,” IEEE International Conference on Image Processing, pp. 24-28, 1999.
[8] S. McKenna, S. Jabri, Z. Duric, and A. Rosenfeld, “Tracking groups of people,” Computer Vision and Image Understanding, no. 80, pp. 42-56, 2000.
[9] M. Swain and D. Ballard, “Colour indexing,” International Journal of Computer Vision, vol. 7, no. 1, pp. 11-32, 1991.
[10] C. Jaynes, S. Webb, R. Steele, and Q. Xiong, “An open development environment for evaluation of video surveillance systems, ” Proceedings of the Third International Workshop on Performance Evaluation of Tracking and Surveillance, 2002.
[11] C. Needham and R. Boyle, “Performance evaluation metrics and statistics for positional tracker evaluation,” Proceedings of the Computer Vision Systems: Third International Conference, vol. 2626, pp. 278-289, 2003.
[12] F. Porikli, “Trajectory distance metric using hidden markov model based representation,” In IEEE European Conference on Computer Vision, PETS Workshop, 2004.
[13] A. Nghiem, F. Bremond, M. Thonnat, and V. Valentin, “ETISEO, performance evaluation for video surveillance systems,” In IEEE International Conference on Advanced Video and Signal based Surveillance, 2007.