臺灣博碩士論文加值系統

傳統的保全監控系統，在災害或犯罪事件發生後想要找出可疑人物，必須經由人工調閱並監看事件發生時所錄下的視訊影像，如此一來將花費過多的人力、時間，而延誤案情。本論文提出一個運用於保全監控系統的視訊檢索系統架構，使用背景相減方法(Background Subtraction Method)偵測異常物體，找出監控畫面中的異常事件段落，並藉由關鍵異常畫面擷取(Key Frame Extraction)演算法，找出可明顯表現出異常物體特徵之關鍵異常畫面，再建立畫面中異常物體的以顏色為基礎之物體模型(Object Model)，並將相關資訊紀錄於資料庫中。使用者可以時間或攝影地點等條件查詢異常事件，並可框選出感興趣的異常物體，與資料庫中的紀錄進行比對，完成監控系統視訊資料庫中異常物體搜尋動作。

In the traditional surveillance system, the search of suspects in the video tapes has to be monitored by human and is always time consuming. In this thesis, we propose a new video indexing and retrieval mechanism for surveillance video database. This mechanism detects abnormal events by using background subtraction method, extracts representative images of abnormal objects by our key frame extraction method, and stores these information into the surveillance video database. When searching for the abnormal suspects in the database, user can select an object by specifying a region of interesting in an image. The Select object can be compared with these abnormal objects in the database by the color-based similarity measure method.

摘 要 i
ABSTRACT ii
誌 謝 iii
目 錄 iv
表目錄 vii
圖目錄 viii

第1章 緒論 1
1.1 研究動機 1
1.2 研究目的 2
1.3 研究範圍與限制 3
1.4 論文架構 3
第2章 相關研究與文獻討論 5
2.1 異常物體偵測 5
2.2 以內容為基礎之檢索技術 6
第3章 系統架構與說明 9
3.1 系統概要 9
3.2 系統架構說明 11
3.2.1 資料庫管理模組 12
3.2.2 異常偵測模組 12
3.2.3 關鍵異常畫面擷取模組 13
3.2.4 特徵擷取模組 14
3.2.5 系統設定模組 14
3.2.6 視訊瀏覽模組 14
3.2.7 查詢處理模組 15
第4章 異常事件偵測 17
4.1 異常事件偵測 17
第5章 關鍵異常畫面擷取 21
5.1 關鍵畫面擷取相關技術 21
5.2 關鍵異常畫面考慮因素 22
5.2.1 異常物體面積 23
5.2.2 異常物體密度 23
5.2.3 異常物體寬高比 24
5.2.4 畫面變動量 24
5.2.5 畫面清晰度 27
5.2.6 畫面明亮度特徵 28
5.3 關鍵異常畫面擷取演算法 29
第6章 異常物體特徵擷取與相似度比對 31
6.1 顏色特徵相關技術 31
6.2 異常物體特徵擷取 32
6.2.1 物體模型與核心函數 32
6.3 相似度比對 34
第7章 實驗結果與分析 37
7.1 系統環境 37
7.2 實驗結果 37
7.2.1 異常事件偵測 38
7.2.2 關鍵異常畫面擷取 40
7.2.3 異常事件查詢 42
7.2.4 異常物體查詢 44
7.2.5 相似度比對 45
第8章 結論 47
8.1 結論 47
8.2 未來展望 47
參考文獻 49

[1]S. Antani, R. Kasturi, and R. Jain, “A survey on the use of pattern recognition methods for abstraction, indexing, and retrieval of images and video,” Pattern Recognit., vol. 35, no. 4, pp. 945-965, 2002.
[2]D. Makris and T. Ellis, “Path Dectection in Video Surveillance,” Image and Vision Computin., vol. 20, pp. 895-903, 2002.
[3]W. Hu, T. Tan, L. Wang, and S. Maybank, “A Survey on Visual Surveillance of Object Motion and Behaviors,” IEEE Transaction on System, Man, and Cybernetics—Part C: Applications and Reviews, vol. 34, no. 3, Aug., 2004.
[4]A. Elgammal, D. Harwood, and L. Davis, “Non-Parametric Model for Background Subtraction,” Proc. IEEE Frame Rate Workshop, 1999.
[5]S. Jabri, and et al., “Detection and Location of People in Video Images Using Adaptive Fusion of Color and Edge Information,” Proceedings International Conference on Pattern Recognition, vol. 4, pp. 627-630., 2000.
[6]Lipton, A. J., Fujiyoshi, H., and Patil, R. S. “Moving Target Classification and Tracking from Real-time Video,” Proceedings of the 4th IEEE Workshop on Applications of Computer Vision, pp. 8-14, 1998.
[7]D. Meyer, J. Denzler, and H. Niemann, “Model based extraction of articulated objects in image sequencesfor gait analysis,” Proc. IEEE Int. Conf. Image Processing, pp. 78-81, 1998.
[8]Liyuan Li , Weimin Huang , Irene Y. H. Gu , Qi Tian, “Foreground object detection from videos containing complex background,” Proceedings of the eleventh ACM international conference on Multimedi., p. 2-10, 2003.
[9]D. Comaniciu, V. Ramesh, and P. Meer, “Kernel Based Object Tracking,” IEEE Trans. Pattern Anal. Machine Intel., Vol. 25, No.5, pp. 564-557, May 2003.
[10]D Comaniciu, V Ramesh, P Meer, "Real-Time Tracking of Non-Rigid Objects Using Mean Shift" In Proceedings Conference on Computer Vision and Pattern Recoginition, vol.2, pp. 142-149, 2000.
[11]T. Sikora, “The MPEG-7 Visual Standard for Content Description – An Overview,” IEEE Trans. Circuits and Sysetem for Video Technology, vol. 11, pp. 696-702, Jun. 2001.
[12]SF Chang, W Chen, HJ Meng, H Sundaram, “A fully automated content-based video search engine supporting spatiotemporal queries,” IEEE Transactions on Circuits and Systems for Video Technology, vol.8, no. 5, Sep. 1998.
[13]H. S. Chang, S. Sull, S. U. Lee, “Efficient Video Indexing Scheme for Content-Based Retrieval,” IEEE Trans Circuits Syst Video Technol., vol. 9, no. 8, pp. 1269-1279, 1999.
[14]H. J. Zhang, J. Wu, D. Zhong, and S. W. Smoliar, “An Integrated System for Content-based Video Retrieval and Browsing,” pattern Recognit., vol. 30, no. 4, pp. 643-658, 1997.
[15]B. Gunsel and A. M. Tekalp, “Content-based Video Abstraction,” in Proc. IEEE Int. Conf. Image Processing, Chicago, IL, pp. 128-132, 1998.
[16]A Dorado, J Calic, E Izquierdo, “A Rule-Based Video Annotation System,” IEEE Trans Circuits Syst Video Technol., vol. 14, no. 5, pp. 622-633, 2004.
[17]ME Dönderler, E Saykol, Ö Ulusoy, U Güdükbay, “BilVideo: A Video Database Management System,” IEEE MultiMedia, 2003, vol.10, pp. 66-70, Jan. 2003.
[18]R. Zabih, J. Miller,and K. Mai. ,“A Feature Based Algorithm for Detecting and Classifying Scene Breaks,” Proc. of ACM Multimedia 95, San Francisco, CA, pp. 189-200, Nov. 1995.
[19]M. S. Kankanhalli, B. M. Mehtre and J. K. Wu, “Cluster Based Color Matching for Image Retrieval,” Pattern Recognition, vol. 19, no. 4, pp.701-708, 1996.
[20]M. J. Swain and D. H. Ballard, “Color Indexing,” International Journal of Computer Vision, vol. 7, no. 1, pp 11-32, 1991.
[21]Y. Chahir and L. Chen, “Efficient Content-Based Image Retrieval based on Color Homogeneous Objects Segmentation and Their Spatial Relationship Characterization,” IEEE International Conference on Multimedia Computing Systems, vol. 2, pp. 705-709, 1999.
[22]L. Devroye, L. Gyorfi and G. Lugosi, “A Probabilistic Theory of Pattern Recognition, ” Applications of Mathematics. Springer-Verlag Inc., Vol. 31, New York, N.Y., pp. 25-32, 1996.
[23]李冠穎、張厥煒，「視訊片段之代表性圖片選擇法」，國立台北科技大學資訊工程所論文，民國93年
[24]林堯弘、韓欽銓、李建興，「利用軌跡特徵應用於視訊監控資料檢索」，中華大學資訊工程所論文，民國94年
[25]郭文傑、李錫堅，「從影片序列中建立以人為基礎的影像資料」，國立交通大學資訊工程所論文，民國94年
[26]黃一哲、李錫堅，「影帶中特定人物的搜尋」，國立交通大學資訊工程所論文，民國95年