視差是造成立體感的主要因素，此視差亦即水平位移，透過左右二張影像的合成可重建深度資訊。本論文利用光流求得兩張圖片間的位移資訊，透過區域成長的方式及光流的特性，將物體移動所包含的區域找出，並以水平位移的方式附予其擬真立體效果。
HORN&SCHUNCK 所提出的光流，原本應用於電腦視覺中影像移動的偵測。我們根據其方法求得每個圖素的位移資訊，且利用向量分割方式，讓求得的位移資訊更具群體性，並將所得結果做一連串修正，便可得一製作立體效果區域的影像。搭配原影像可得右眼視差影像，最後將此二張影像重合即可得一擬真立體影像。

The depth information is a fundamental factor in stereo imaging. The depth information of an object can be associated to the horizontal shift (with respect to the location in the parallax image) in a simple linear relation. Therefore, we can generate a stereo video by combining a regular monoscopic video with an artificial parallax video implemented with a designed horizontal shift. In this research, the manmade
horizontal shift is designed according to the pixel translations of the monoscopic
video obtained by the optical flow computation algorithm.
Optical flow proposed by Horn and Schunck was originally developed in the field of computer vision for the application of moving detection. Following this flow computation algorithm, a vector segmentation algorithm is applied to the flow field for grouping effects associated to the foreground. Finally, some merging procedures are applied to get a better foreground mask. With this foreground mask,the parallax video is then generated for creating our artificial stereo video.

第一章 引言............................................1

第二章 MPEG動態影像壓縮的原理..........................5
2-1 MPEG簡介...........................................5
2-2 MPEG的視訊壓縮原理.................................6

第三章 光流與分割之基本定理...........................11
3-1 簡介..............................................11
3-2 光流之基本定理....................................11
3-3 區域成長之基本定理................................23

第四章 立體成像原理介紹...............................28
4-1 簡介..............................................28
4-2 透視轉換立體成像的原理............................29
4-3 立體參數的計算....................................33

第五章 系統實作.......................................34
5-1 簡介..............................................34
5-2 光流計算..........................................36
5-3 向量分割..........................................37
5-4 修正向量分割結果..................................39
5-5 製作右眼視差影像..................................43
5-6 製作立體影像......................................44

第六章 實驗結果與分析.................................45
6-1 簡介..............................................45
6-2 各序列立體圖製作與討論............................46
6-3 各序列執行時間結果與討論..........................55
6-4 其它製作方法結果與討論............................56
6-5 總結..............................................70

第七章 結論...........................................72

[1].S. Birchfield and C. Tomasi. Depth discontinuities by pixel-to-pixel stereo. IEEE International Conference on Computer Vision, Bombay,India 1998
[2].G. Van Meerbergen, M. Vergauwen, M. Pollefeys and L. Van Gool “A hierarchical stereo algorithm using dynamic programming,”
[3].Sabine Randriamasy-Andre Gagalowicz”Direct cooperation between region-based stereo matching and top-down segmentation”
[4].Luo Yan, Zhang Zhaoyang, and An Ping “Stereo Video Coding Based on Frame Estimation and Interpolation” IEEE TRANSACTIONS ON BROADCASTING, VOL. 49, NO. 1, MARCH 2003
[5].B.G. Schunck，〝Image flow : Fundamentals and algorithm〞，in motion Understanding : Robot and Human Vision，W.N.Martin and J . K . Aggarwal ，Eds . Norwell ，MA : Kluwer Academic Publishers ，1988 。
[6].J . K . Aggarwel ，L .S .Davis ， and W. N. Martin ，〝Correspondence processes in dynamic scence analysis，〞 Proc.IEEE，vol.69，no.6，pp.562-572，May 1981。
[7].J. Q. Fang and T. s. Huang ，〝Some exeperiments on estimating the 3-D motion parameters of a rigid body from two consecutive image frames，〞IEEE Trans. Pattern Anal。 Machine Intell. Vol.PAMI-6 ，pp.545-554，Sept.1984。
[8].S. Ranade and A. Rosenfeld，〝Point pattern matching by relaxation，〞Pattern Recognition，vol. 12，pp. 269-275，1980。
[9].Gibson，J，J.，on the analysis of change in the optic array ， Scandinavian J.Psychol.18(1977)161-163。
[10].Nakayama，K.and Loomis，J.M.，Optical velocity patterns ， velocity-sensitive neurons and space perception，Perceptrion3(1974) 63-80。
[11].T.Pavlidis, Structure Pattern Recognition, Springer, New York , 1977。
[12].R.M.Haralick and Linda. G.Shapiro, Computer and Robot Vision , Vol.1,Addison-Wesley Pub.Co.,1992。
[13].S.L.Horowitz and Y.Pavlidis, ”Picture Segmentation by a Directed Split-and-Merge Procedure,” Proc. 2nd Int. Joint Conf. Pattern Recognition,pp.424-433,1974。
[14].S.W.Zucker, ”Region Growing : Childhood and adolescence,” Computer Graphics and Image Processing,5,pp.382-399, 1976。
[15].A low bit-rate video codec based on two-dimensional mesh motion compensation with adaptive interpolation Pohsiang Hsu; Liu, K.J.R.; Chen, T. Circuits and Systems for Video Technology, IEEE Transactions on , Volume: 11 Issue: 1 , Jan. 2001 Page(s): 111 –117
[16].Rafael C. Gonzalez&Richard E. Woods “Digital Image processing”,1992 Addision-Wesley Publishing Company.
[17].Ga-U Young, ”Investigation Of Compression Based Upon Optical Flow”, Master Thesis Advised by Ben-Shung Chow, Dept. of Electrical Engineering, San-Yet Sun University, 1995.