許多的應用都需要由影片來抽取基本的資訊，進一步執行處理、分析和資訊擷取等後續動作。而整體運動的估測在不同的影片應用上是被廣泛應用的，例如全景影像合成、視訊穩定化、移動物體分割和視訊擷取等。
在這篇論文中，我們提出了二個全新且強固的整體運動估測演算法；也就是trimmed least-squares整體運動估算演算法及長期性最短路徑主要運動估測演算法。在第一個演算法中，我們利用trimmed least-squares的方法從已求得的光流場向量來估測一組affine移動參數，再來，當我們把位移向量套入這組affine移動參數，把產生較大偏差值的光流場向量去除。在第二個演算法中，我們首先套用RANSAC方法在二張連續的影片中求得數個主要運動，再利用Dijkstra的演算法來解決最短路徑問題以求得這些主要運動在整段影片中的軌跡。
視訊穩定化和照相機移動型式辨別是應用我們提出的主要運動估測演算法所聚焦的兩個應用。在視訊穩定化方面，我們使用trimmed least-squares整體運動估測演算法來計算simplified affine移動參數，再把regularization-based smoothing方法套用在這些參數上。實驗結果顯示我們可在即時的速度上得到視訊穩定的結果。而在照相機移動型式辨別方面，首先我們利用長期性最短路徑主要運動估測演算法來估測出最主要的移動軌跡，再利用前饋式類神經網路來分辨照相機的移動形式。經由實驗得知我們可以精確的分辨不同型式的照相機移動。

Many applications require the extraction of some basic information from a video for processing, analysis or retrieval. Global motion estimation is popularly demanded in various video applications, including video mosaicing, video stabilization, moving object segmentation and video retrieval.

In this thesis, we propose two new and robust global motion estimation algorithms; namely the trimmed least-squares global motion estimation algorithm and the long-term shortest-path dominant motion estimation algorithm. For the first algorithm, we apply trimmed least-squares estimation to fit the computed optical flow vectors to an affine motion model and reject outliers by discarding the optical flow vectors that contain large model fitting errors. For the second algorithm, we first apply the RANSAC method to find multiple dominant motions for every two adjacent frames in the video and then find the long-term dominant motion trajectories by solving the shortest-path problems with Dijkstra’s algorithm.

Video stabilization and camera motion classification are the two focused applications based on the proposed two global motion estimation algorithms. For video stabilization, we employ the proposed trimmed least-squares affine motion estimation algorithm to compute the simplified affine motion parameters and then apply the regularization-based smoothing method to these parameters. Experimental results show that we can obtain a stabilized video in real-time speed. For the camera motion type classification, we first estimate the most dominant motion trajectory by the proposed long-term shortest-path dominant motion estimation algorithm and then classify the camera motion type by using a feedforward neural network. Experimental results show accurate classification results on various types of camera motions.

References
[1] Krishna Ratakonda, “Real time digital video stabilization for multimedia applications”, Circuits and Systems, 1998. ISCAS '98. Proceedings of the 1998 IEEE International Symposium on , Volume: 4 , 31 May-3 June 1998. pp. 69 - 72 vol.4.
[2] Yeping Su, Ming-Ting Sun, Vincent Hsu, “Global motion estimation from coarsely sampled motion vector field and the applications”, Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on, Volume: 2 , 25-28 May 2003 pp. II-628 - II-631 vol.2.
[3] S. Etrurk, “Digital image stabilization with sub-image phase correlation based global motion estimation”, Consumer Electronics, IEEE Transactions on , Volume: 49 , Issue: 4 , Nov. 2003. pp. 1320 - 1325.
[4] Jyh-Yeong Chang, Wen-Feng Hu, Mu-Huo Chen, Bo-Sen Chang, “Digital image translational and rotational motion stabilization using optical flow technique”, Consumer Electronics, IEEE Transactions on , Volume: 48 , Issue: 1 , Feb. 2002. pp. 108 – 115.
[5] Yossi Keller, Amir Averbuch, ”Fast gradient methods based on global motion estimation for video compression”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, No. 4, April 2003.
[6] Carlos Morimoto, Rama Chellappa, ”Automatic digital image stabilization”, IEEE International Conference on Pattern Recognition, pp. 660-665, 1997.
[7] Carlos Morimoto, Rama Chellappa, “Fast electronic digital image stabilization for off-road navigation”, IEEE International Conference on Pattern Recognition, Vol. 3, pp. 284-288, August, 1996.
[8] Zhigang Zhu, Guangyou Xu, Yudong Yang, Jesse S. Jin, ”Camera stabilization based on 2.5D motion estimation and inertial motion filtering”, IEEE International Conference on Intelligent Vehicles 1998. pp. 329 – 334.
[9] Aljoscha Smolic, Thomas Sikora, Jens-Rainer Ohm, ”Long term global motion estimation and its application for sprite coding, content description, and segmentation”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 8, December, 1999.
[10] Demin Wang, Limin Wang, “Global motion parameters estimation using a fast and robust algorithm”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 7, No. 5, October, 1997.
[11] Ming Fai Fu, Oscar Au, Wing Cheong Chan, ”Fast global motion estimation based on local motion segmentation”, IEEE International Conference on Image Processing, Vol. 2, pp. 367-370, September, 2003.
[12] Yap Pen Tan, Drew D. Saur, Sanjeev R. Kulkarni, Peter J. Ramadge, ”Rapid estimation of camera motion from compressed video with application to video annotation”, IEEE Transactions on Circuits and Systems for Video Technology, Vol. 10, No. 1, February, 2000.
[13] Fang Zhu, Ping Xue, Eeping Ong, “Low complexity global motion estimation based on content analysis”, ISCAS, Vol. 2, pp. II624--II627, May, 2003.
[14] Q. Tian, H. J. Zhang, “Video shot detection and analysis: Content-based approaches”, in: C.W. Chen, Y. Q. Zhang, Visual information representation, communication, and image processing, pp.227~253, Marcel Dekker, 1999.
[15] B. S. Manjunath, P. Salembier, and T. Sikora, ”Introduction to MPEG-7”, John Wiley & Sons, 2002.
[16] P. Bouthemy, M. Gelgon, and F. Ganansia, “A unified approach to shot change detection and camera motion characterization,” IEEE Transactions on Circuits and Systems for Video Technology, Vol. 9, No. 7, October, 1999.
[17] J. H. Kuo and J. L. Wu, “An efficient algorithm for scene change detection and camera motion characterization using the approach of heterogeneous video transcoding on MPEG compressed videos,” Proc. SPIE: storage and retrieval for media databases, Vol. 4676, pp.168~176, 2002.
[18] N. V. Patel and I. K. Sethi, “Video shot detection and characterization for video databases,” Pattern Recognition, Vol. 30, No. 4, pp. 607~625, April, 1997.
[19] J. G. Kim, H. S. Chang, J. W. Kim, and H. M. Kim, “Efficient camera motion characterization for mpeg video indexing,” IEEE International Conference on Multimedia, New York, July, 2000.
[20] T. Chen, “Video stabilization algorithm using a block-based parametric motion model”, EE392J Project Report, Winter 2000.
[21] A. Litvin, J. Konrad, W. C. Karl, ”Probabilistic video stabilization using Kalman filtering and mosaicking”, In IS&T/SPIE Symposium on Electronic Imaging, Image and Video Communications and Proc., Jan. 20-24, 2003.
[22] B. D. Lucas and T. Kanade, “An Iterative Image Registration Technique with an Application to Stereo Vision”, Proc. IJCAI81, pp. 674-679, 1981.
[23] A. Nomura, “Spatio-temporal optimization method for determining motion vector fields under non-stationary illumination”, Image and Vision Computing 18, pp. 939-950, 2000.
[24] S.-H. Lai□□and W.-K. Li, “New video shot change detection algorithm based on accurate motion, and illumination estimation”, Proc. SPIE: storage and retrieval for media databases, vol. 4676, pp. 148-157, 2002
[25] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2000.
[26] N. V. Patel and I. K. Sethi, “Video shot detection and characterization for video databases”, Pattern Recognition, vol. 30, no. 4, pp. 607~625, April 1997.
[27] T. H. Cormen, C. E. Leiserson and R. L. Rivest, and C. Stein, Introduction to Algorithms, 2nd Edition, MIT Press, 2001.
[28] T. M. Mitchell, Machine Learning, chapter 4, McGraw-Hill, 1997.
[29] Z. Duric and A. Rosenfeld, “Image sequence stabilization in real time”, Real-Time Imaging 2, pp. 271-284, 1996.
[30] J. H. Kuo and J. L. Wu, “An efficient algorithm for scene change detection and camera motion characterization using the approach of heterogeneous video transcoding on MPEG compressed videos,” Proc. SPIE: storage and retrieval for media databases, vol. 4676, pp.168-176, 2002.