臺灣博碩士論文加值系統

智慧型的影片物件搜尋系統提供使用者一個快速瀏覽許多影片內容的方法，擷取、濃縮、配對是這個系統最主要的三個部分。在擷取部分，我們擷取影片中的連續物件並且分析他們視覺特徵值以便未來配對使用，此步驟系統會將物件視覺資訊儲存至伺服器中就像是一個分散式系統。在濃縮部分，將擷取到的物件都安排在同一背景上形成濃縮影片。在配對部分，我們將以內容為基礎的影像檢索概念製作物件配對規則，幫助使用者快速找到相似的物件而且不會遇到語意上的問題，使用這個系統，後端人員觀看大量的監視影片將不再費時耗力。

A smart video object search system is proposed, which provides a high e fficient condensing method for quickly browsing through many hours of video content. Capture, Condensation and Matching are the three main system components. The capture component extracts objects and forms a sequence of video stream that provides objects visual features for matching. The proposed system saves these visual features from different IP cameras into one database as a distributed system. In the condensation part, these extracted objects were used to constitute a condensed video. We arrange the appearing time of the objects and make sure all the objects have been arranged into the condensed video. In the matching procedure, the concept of content-based image retrieval was integrated into the proposed system. The user can then easily nd the object of interest through the condensed video using the proposed matching rules without any semantic problem. With the proposed system, it is not time-consuming anymore for the observers to nd clues from numerous videos.

1 Introduction 1
1.1 Motivation . . . 1
1.2 Objective . . . 2
1.3 Thesis Overview . . . 3
2 Literature Survey 4
2.1 Survey of Abstraction Video . . . 4
2.2 Survey of Video Object Retrieval System . . . 5
3 The Proposed Video Condensation and Object Searching System 7
3.1 System Architecture . . . 7
3.2 Video Condensation Algorithm . . . 8
3.3 Management of Visual Features
and Object Matching . . . 14
3.3.1 Management of Visual Features . . . 14
3.3.2 Object Matching . . . 18
4 Experimental Results 21
5 Conclusion and Future Work 25

[1] R. Ford. Beware rise of big brother state, warns data watchdog. 2004.
[2] These glimpses of a possible future are taken from section c of the full report, which also includes a full week in the life of a typical family. 2006.
[3] M. McCahill and C. Norris. Estimating the extent, sophistication and legality of cctv
in london. 2003.
[4] Norris C. and Armstrong G. The maximum surveillance society: The rise of closed circuit television. page 42, 1999.
[5] G. Welch and G. Bishop. An introduction to the kalman lter. University of North Carolina at Chapel Hill, Chapel Hill, NC, 7(1), 1995.
[6] Q. Fu and M. Santello. Tracking whole hand kinematics using extended kalman Filter. In Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE, pages 4606{4609. IEEE, 2010.
[7] D. Comaniciu, V. Ramesh, and P. Meer. Real-time tracking of non-rigid objects using mean shift. In Computer Vision and Pattern Recognition, 2000. Proceedings. IEEE Conference on, volume 2, pages 142{149. IEEE, 2000.
[8] A. Rav-Acha, Y. Pritch, and S. Peleg. Making a long video short: Dynamic video synopsis. In Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on, volume 1, pages 435{441. IEEE, 2006.
[9] Y. Pritch, S. Ratovitch, A. Hendel, and S. Peleg. Clustered synopsis of surveillance video. In Advanced Video and Signal Based Surveillance, 2009. AVSS'09. Sixth IEEE
International Conference on, pages 195{200. IEEE, 2009.
[10] Y. Pritch, A. Rav-Acha, A. Gutman, and S. Peleg. Webcam synopsis: Peeking around the world. In Computer Vision,2007. ICCV 2007. IEEE 11th International Conference on, pages 1{8. IEEE, 2007.
[11] Y. Pritch, A. Rav-Acha, and S. Peleg. Nonchronological video synopsis and indexing. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 30(11):1971{1984,2008.
[12] A. Van de Sande. Figure from: http://en.wikipedia.org/wiki/image:color cons.png ,
conversion from: http://en.wikipedia.org/wiki/hsl color space, 2005.
[13] L.M. Brown. Color retrieval for video surveillance. In Advanced Video and Signal Based Surveillance, 2008. AVSS'08. IEEE Fifth International Conference on, pages 283{290.
IEEE, 2008.
[14] D.C. Tseng and C.H. Chang. Color segmentation using perceptual attributes. In Pattern Recognition, 1992. Vol. III. Conference C: Image, Speech and Signal Analysis,
Proceedings., 11th IAPR International Conference on, pages 228{231. IEEE, 1992.
[15] J.L. Shih and C.H. Chen. Video object retrieval using color features. Proc. International MultiConference of Engineers and Computer Scientists (IMECS, pages 568{573, 2006.
[16] J. Lee, W. Tong, A. Jain, et al. Image retrieval in forensics: Application to tattoo image database. Multimedia, IEEE, (99):1{1, 2012.
[17] W. Hai-long and D. Jun-li. Research on clothing image retrieval technology and system. In Computer Network and Multimedia Technology, 2009. CNMT 2009. International
Symposium on, pages 1{3. IEEE, 2009.
[18] G. Paschos, I. Radev, and N. Prabakar. Image content-based retrieval using chromaticity moments. Knowledge and Data Engineering, IEEE Transactions on, 15(5):1069{1072,
2003.
[19] K. Vu, K.A. Hua, and W. Tavanapong. Image retrieval based on regions of interest. Knowledge and Data Engineering, IEEE Transactions on, 15(4):1045{1049, 2003.
[20] J.F. Omhover and M. Detyniecki. Strict: an image retrieval platform for queries based on regional content. Image and Video Retrieval, pages 2034{2035, 2004.
[21] C. Taskiran, J.Y. Chen, A. Albiol, L. Torres, C.A. Bouman, and E.J. Delp. Vibe: A compressed video database structured for active browsing and search. Multimedia,
IEEE Transactions on, 6(1):103{118, 2004.
[22] I. Decker. A picture-based document retrieval service for the electronic visualization library. Technical report, Technical Report, 1998.
[23] V. Mezaris, I. Kompatsiaris, N.V. Boulgouris, and M.G. Strintzis. Real-time compressed-domain spatiotemporal segmentation and ontologies for video indexing and retrieval. Circuits and Systems for Video Technology, IEEE Transactions on, 14(5):606{621, 2004.
[24] V. Mezaris and M. Strintzis. Object segmentation and ontologies for mpeg-2 video indexing and retrieval. Image and Video Retrieval, pages 643{643, 2004.
[25] M. Ramesh Naphade, I.V. Kozintsev, and T.S. Huang. Factor graph framework for semantic video indexing. Circuits and Systems for Video Technology, IEEE Transactions on, 12(1):40{52, 2002.
[26] M.R. Naphade, S. Basu, J.R. Smith, C.Y. Lin, and B. Tseng. Modeling semantic concepts to support query by keywords in video. In Image Processing. 2002. Proceedings.
2002 International Conference on, volume 1, pages I{145. IEEE, 2002.
[27] M.R. Naphade, T. Kristjansson, B. Frey, and T.S. Huang. Probabilistic multimedia objects (multijects): A novel approach to video indexing and retrieval in multimedia
systems. In Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on, pages 536{540. IEEE, 1998.
[28] S.F. Cheng, W. Chen, and H. Sundaram. Semantic visual templates: linking visual features to semantics. In Image Processing, 1998. ICIP 98. Proceedings. 1998 International
Conference on, pages 531{535. IEEE, 1998.
[29] R. Qian, N. Haering, and I. Sezan. A computational approach to semantic event detection. In Computer Vision and Pattern Recognition, 1999. IEEE Computer Society
Conference on., volume 1. IEEE, 1999.
[30] B. Erol and F. Kossentini. Shape-based retrieval of video objects. Multimedia, IEEE Transactions on, 7(1):179{182, 2005.
[31] E. Oomoto and K. Tanaka. Ovid: Design and implementation of a video-object database system. Knowledge and Data Engineering, IEEE Transactions on, 5(4):629{643, 1993.
[32] D. Zhong and S.F. Chang. An integrated approach for content-based video object segmentation and retrieval. Circuits and Systems for Video Technology, IEEE Transactions
on, 9(8):1259{1268, 1999.
[33] J. Sivic and A. Zisserman. Video google: A text retrieval approach to object matching in videos. In Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, pages 1470{1477. Ieee, 2003.
[34] J. Sivic, F. Scha alitzky, and A. Zisserman. E cient object retrieval from videos.In Proc. of the 12th European Signal Processing Conference EUSIPCO 04, Vienna,Austria, 2004.
[35] M.M. Deza and E. Deza. Encyclopedia of distances. Springer Verlag, 2009.