除了近年來影片拍攝器材的價格愈加平民化，YOUTUBE、優酷、土豆網等線上影片分享平台，亦鼓勵大眾拍攝影片上傳分享，成為了家家都有一台攝影機的催化劑，因此我們提出了影片抖動去除技術，希望能有效地幫助民眾消除手持拍攝時，容易因晃動而造成影片抖動的憂慮。
本論文以影片抖動移除後，其空間關係的維持為主要目的，透過串流方式的軌跡平滑化演算法，除了可移除高頻抖動外，亦可使平滑後的軌跡維持原軌跡之形狀，避免因抖動去除後，造成影片失真的後遺症；除了失真的問題外，剪裁後影片內容的減少，也是該技術的瓶頸之一，我們經由增加渲染時可信賴之特徵點的數目，減少因特徵點稀疏導致影片內容扭曲，而過度剪裁影片的問題。另外，本論文亦提出高準確度的前景特徵點移除技術，移除動向不可預測地前景軌跡，避免其他軌跡在平滑化時受到其影響產生扭曲。

The prices of video shooting devices are becoming more and more acceptable for common users. And recently in the Internet, new video-sharing websites suddenly burst out everywhere, such as YOUTUBE, YOUKU, and TUDOU. This phenomenon encouraged people to upload their homemade video to the websites. Therefore, we come out with a new video stabilization method, hoping to help hand-held video cameras to avoid shooting unstable footage.
In our paper, we focus on preserving the spatial relationship between video contents. Through our streaming trajectory smoothing method, we not only stable the high frequency shaking, but also preserved the shape of the original trajectory in our smoothed result, and prevent video from being distorted. Besides distortion, the coverage of the cropping region is always an unsolvable problem in this area. We samples features uniformly among frames, in order to maximize the coverage of control points, which would also help us to avoid boundary distortions and gain more coverage for our results. We also introduce a foreground removal algorithm, which could separate foreground from contents, and makes the smoothing method work properly.

[1] BHAT, P., ZITNICK, C. L., SNAVELY, N., AGARWALA, A., AGRAWALA, M., COHEN, M., CURLESS, B., AND KANG, S. B. 2007. Using photographs to enhance videos of a static scene. In Proceedings of the 18th Eurographics Workshop on Rendering, 327–338.
[2] BOYKOV, Y., AND KOLMOGOROV, V. 2004. An experimental comparison of min-cut/max- flow algorithms for energy minimization in vision. In IEEE Transaction on PAMI, 26, 9, 1124-1137.
[3] BUEHLER, C., BOSSE, M., AND MCMILLAN, L. 2001. Non-metric image-based rendering for video stabilization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 609–614.
[4] CHEN, P. 2008. Optimization algorithms on subspaces: Revisiting missing data problem in low-rank matrix. International Journal of Computer Vision, 80, 1, 125–142.
[5] FITZGIBBON, A.,WEXLER, Y., AND ZISSERMAN, A. 2005. Image-based rendering using image-based priors. International Journal of Computer Vision, 63, 2 (July), 141–151.
[6] GLEICHER, M. L. AND LIU, F. 2008. Re-cinematography: Improving the camerawork of casual video. ACM Transactions on Multimedia Computing, Communications and Applications, 5, 1, 1–28.
[7] ITTI, L., KOCH, C., AND NIEBUR, E. 1998. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20, 11, 1254–1259.
[8] KR¨AHENB¨U HL, P., LANG, M., HORNUNG, A., AND GROSS, M. 2009. A system for retargeting of streaming video. ACM Trans. Graph. 28, 5.
[9] LEE, K.-Y., CHUANG, Y.-Y., CHEN, B.-Y., AND OUHYOUNG, M. 2009. Video stabilization using robust feature trajectories. In Proceedings of the IEEE International Conference on Computer Vision. 1397–1404.
[10] LIU, F., GLEICHER, M., JIN, H., AND AGARWALA, A. 2009. Content-Preserving Warps for 3D Video Stabilization. ACM Trans. Graph. 28, 3.
[11] LIU, F., GLEICHER, M., WANG, J., JIN, H., AND AGARWALA, A. 2011. Subspace Video Stabilization. ACM Trans. Graph. 30, 1.
[12] MATSUSHITA, Y., OFEK, E.,GE, W.,TANG, X., AND SHUM, H.-Y. 2006. Full-frame video stabilization with motion inpainting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28, 7, 1150–1163.
[13] MORIMOTO, C., AND CHELLAPPA, R. 1997. Evaluation of image stabilization algorithms. In Proceedings of the ARPA Image Understanding Workshop, 295-302.
[14] SHEWCHUK, R., J. 1996. Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator. In “Applied Computation Geometry: Towards Geometric Engineering”, 1148, 203-222.
[15] SHEWCHUK, R., J. 2002. Delaunay Refinement Algorithms for Triangular Mesh Generation. In Computational Geometry: Theory and Application, 22, 21-74.
[16] WANG, Y.-S., LIN, H.-C., SORKINE, O., LEE, T.-Y. 2010. ACM Trans. Graph. 29, 4, 90.
[17] WERLBERGER, M., TROBIN, W., POCK, T., WEDEL, A., CREMERS, D., AND BISCHOF, H. 2009. Anisotropic Huber-L1 Optical Flow. In Proceedings of BMVC.
[18] WERLBERGER, M., POCK, T., AND BISCHOF, H. 2010. Motion Estimation with Non-Local Total Variation Regularization. In Proceedings of CVPR, 2464-2471.
[19] ZHANG, G.-X., CHENG, M.-M., HU, S.-M., AND MARTIN, R. R. 2009. A Shape-Preserving Approach to Image Resizing. In Computer Graphics Forum, 28, 7, 1897-1906.