臺灣博碩士論文加值系統

在本篇論文中，提出了一套新的視訊索引及擷取的技術。此套技術的比對方法是以物體移動軌跡為主。我們用三個表示法去描述一個物體的移動軌跡，分別是：此移動物體水平方向以及垂直方向相對於時間軸的移動位址，以及在不包含時間座標系下，空間座標系中物體因移動所留下的移動路徑，而每個表示法皆以多項式函式作逼近，之後拿這些多項式的係數來作索引。為了估測相似性，我們合併不同空間時間上的特性去提供較為彈性的擷取方式。此外我們還提供多重解析度的方式來增進擷取的效率。因此，整個架構設計成可處理三種搜尋方式：以範例搜尋、以手繪軌跡搜尋、以及以輸入的變數搜尋。我們做很多實驗證明方法的效率和效能。實驗結果顯示了滿意的成果。

This thesis presents a technique to efficiently index and retrieve video clips in terms of motion-trajectory-based similarity. We describe a motion trajectory in three representations: the horizontal and vertical movements of the trajectory, and the motion trail that indicates shape of the trajectory. Each representation is approximated by a polynomial function, and the polynomial coefficients are then indexed for retrieval. To measure the matching distance, we combine different spatio-temporal characteristics to provide flexible retrieval processes. In addition, we also proposed a multiscale mode to improve the retrieval efficiency. A unified framework is developed to deal with various query types: query-by-example, query-by-sketch, and query-by-specification. We have performed many experiments to confirm the effectiveness and efficiency of our method. Experimental results indicate satisfactory performance of our work.

1. INTRODUCTION 1
2. SURVEY OF RELATED WORK 3
2.1. Motion Description by Manual Symbolic Representation 3
2.2. Motion Description with Chain Coding Representation 4
2.3. Motion Description Using Exact Positions 5
2.4. Motion Description of Exact Positions Using Wavelet Transform 7
2.5. Motion Description by Motion Trail 7
2.6. Motion Description by Curve Fitting 8
3. TRAJECTORY DESCRIPTION 13
3.1. Proposed Descriptor 13
3.2. Multiscale Trajectory Descriptor 16
4. TRACKING AND INDEXING THE TRAJECTORY 18
4.1. Shot-Change Detection 18
4.2. Global Motion Detection 20
4.3. Semi-Automatic Moving Object Tracking 22
4.4. Indexing the Trajectory 23
5. TRAJECTORY MATCHING 26
5.1. Temporal Exact Retrieval 26
5.1.1. Spatial exact retrieval 27
5.1.2. Spatial shift invariant retrieval 28
5.1.3. Spatial shift-and-scale invariant retrieval 28
5.2. Temporal Shift Invariant Retrieval 30
5.2.1. Spatial exact retrieval 30
5.2.2. Spatial shift invariant retrieval 30
5.2.3. Spatial shift-and-scale invariant retrieval 30
5.3. Temporal Shift-and-Scale Invariant Retrieval 34
5.3.1. Spatial exact retrieval 34
5.3.2. Spatial shift invariant retrieval 34
5.3.3. Spatial shift-and-scale-invariant retrieval 34
5.4. Motion Trail Retrieval 37
5.4.1. Spatial exact retrieval 39
5.4.2. Spatial shift-invariant retrieval 40
5.4.3. Spatial shift-and-scale-invariant retrieval 40
5.4.4. Spatial shift-and-rotation invariant retrieval 41
5.4.5. Spatial shift-and-scale-and-transform invariant retrieval 41
5.5. Multiscale Trajectory Matching 44
6. QUERY TYPES AND EXPERIMENTS 46
6.1. Query by Example 46
6.2. Query by Sketch 58
6.3. Query by specification 59
7. FUTURE WORK AND CONCLUSION 60
7.1. Future work 60
7.2 Conclusion 61
8. REFERENCES 62

[1] S. Jeannin, and A. Divakaran, “MPEG-7 Visual Motion Descriptors,” IEEE Trans. Circuit Syst. Video Technol., vol. 11, no. 6, pp.720-724, June 2001.
[2] S. Jeannin and B. Mory, “Video Motion Representation for Improved Content Access,” IEEE Trans. Consumer Electron., vol. 46, no. 3, pp. 645-655, Aug. 2000.
[3] M. Nabil, A.H.H Ngu, J. Shepherd, “Modeling and Retrieval of Moving Objects,” Multimedia Tools and Applications, 13, pp. 35-71, 2001.
[4] S.F. Chang et al., “A Fully Automated Content-Based Video Search Engine Supporting Spatiotemporal Queries,” IEEE Trans. Circuits Syst. Video Technol., vol. 8, no. 5, pp. 602-615, Sep. 1998.
[5] S. Dagtas et al., “Models for Motion-Based Video Indexing and Retrieval,” IEEE Trans. Image Processing, vol. 9, no. 1, pp. 88-101, Jan. 2000.
[6] N. Dimitrova, F. Golshani, “Motion recovery for video content classification,” ACM Trans. Information Systems, vol. 13, no. 14, pp. 408-439, Oct. 1995.
[7] K.W. Lee, W.S. You, and J. Kim, “Video Retrieval based on the Object’s Motion Trajectory,” Proc. VCIP, vol. SPIE-4067, pp. 114-124, 2000.
[8] A.D. Bimbo, Visual Information Retrieval, Morgan Kaufmann, 1999.
[9] W. Li and E. Salari, “Successive Elimination Algorithm for Motion Estimation,” IEEE Trans. Image Processing, vol.4, no.1, pp. 105-107, Jan. 1995.
[10] W. H. Press et al., Numerical Recipes in C: the Art of Scientific Computing, Cambridge University Press, 1992.
[11] A.D. Bimbo, E, Vicario and D. Zingoni, “Symbolic description and visual querying of image sequences using spatio temporal logic,” IEEE Trans. Knowledge and Data Engineering., vol. 7, pp. 609-622, Aug. 1995.
[12] E. Sahouria, “Video Indexing Based on Object motion,” M.S. thesis, Dept. of EECS, UC Berkeley, Berkeley, CA.
[13] T. Arndt and S.K. Chang, “Image Sequence Compression by Iconic Indexing,” Proc. IEEE VL ’89 Workshop on Visual Languages, Roma Italy, pp. 177-182, September, 1989.
[14] J. J. Little, Z. Gu, “Video Retrieval by Spatial and Temporal Structure of Trajectories,” SPIE Storage and Retrieval for Media Databases 2001, San Jose.
[15] S. Zhu, and K-K. Ma, “A New Diamond Search Algorithm for Fast Block-Matching Motion Estimation,” IEEE Trans. Image Processing, vol. 9, no. 2, pp. 287-290, Feb. 2000.
[16] A. M. Tourapis, G. Shen, M. L. Liou, O. C. Au, I. Ahmad, “A New Predictive Diamond Search Algorithm for Block Based Motion Estimation,” Proc. of Visual Comm. and Image Proc. 2000 (VCIP-2000), Perth, Australia, Jun. 2000.
[17] G. Strang, and T. Nguyen, Wavelets and Filter Banks, Wellesley-Cambridge Press, 1996.
[18] R. Jain, R. Kasturi, and B.G. Schunck, Machine Vision, McGRAW-Hill, 1995.
[19] C.L. Huang, and B.Y. Liao, “A Robust Scene-Change Detection Method for Video Segmentation,” IEEE Trans. Circuit and Systems for Video Technology, vol. 11, no. 12, December 2001.
[20] J. Lee and B.W. Dickinson, “Hierarchical Video Indexing and Retrieval for Subband-coded Video,” IEEE Trans. Circuit and Systems for Video Technology, vol. 10, no. 5, pp.824-829, 2000.
[21] M.G. Chung, H. Kim, and S.M. Song, “A Scene Boundary Detection Method,” Proc. ICIP, 2000.
[22] Zhang, H.j., A. Kankanhalli, and S. Amoliar, “Automatic partitioning of video,” Multimedia Systems, 1(1): 10-28, 1993.
[23] Y. Wang, J. Ostermann, and Y.Q. Zhang, Video Processing and Communications, Prentice Hall, 2002.
[24] D. Zhong, and S.F. Chang, “An Integrated Approach for Content-Based Video Object Segmentation and Retrieval,” IEEE Trans. Circuit and Systems for Video Technology, vol. 9, no.8, pp. 1259-1268, December 1999.
[25] S. Jeannin and R. Jasinschi et al., “Motion descriptors for content-based video representation,” SPIC. vol. 16, no. 1-2, pp. 59-85, Sept. 2000.
[26] MPEG-7 FCD [Online]. Available: http://www.cselt.it/mpeg/
[27] T.Y. Wai and L.P. Chen, “Retrieving Video Data via Motion Tracks of Content Symbols,” Proc. ACM 6th Int’l. Conf. on Information and Knowledge Management, 2000.