從雙眼立體影像系統中，估測出精準且邊界貼齊物體的視差圖一直都是研究人員致力研究的主題。傳統估測視差的做法多從左右兩張影像中，先經過立體影像校正，再透過立體匹配演算法估測準確度高的視差圖，許多研究專注於立體匹配演算法並且在準確的估測視差圖中有相當巨大的進步。
在本篇論文中，我們提出一個在雙眼鏡頭影片中，視差圖估測的系統，此系統不需事先立體影像校正，僅透過簡單的前處理，再由光流法基準的方法估測精準、邊緣保留且貼齊物體的視差圖。在本篇方法中，我們改善TV-L1光流法。我們的系統結合邊界偵測、遮蔽區域偵測、紋理少的區域偵測，與導向濾波器，解決視差圖和彩色圖中，物體邊界的不一致性。此外，我們提出了時域濾波器，改善從雙眼立體影片中，每張視差圖中時域上的不連續性，使得影片跳動的情況可以避免。
在真實影像的實驗結果中，我們所提出的系統不只在深度圖的精確度上較原本的TV-L1光流法準確，且在失焦合成的影片中，讓使用者有更佳舒適的觀感和品質。

A number of researches have focused on estimating accurate and edge-preserve disparity map from stereo videos for many years. From left and right images, most previous works apply stereo rectification in the pre-processing step and then estimate the disparity map with stereo matching methods. Many previous works on stereo matching made considerable progress to compute accurate disparity maps in the past few years.
In this thesis, we propose a disparity map estimation system for stereo videos. In this work, we develop a novel optical flow based method to estimate accurate, edge-preserving and edge-aligned disparity map. The proposed algorithm improves the TV-L1 optical flow approach by incorporating edge detection, occlusion area detection, textureless region detection and guided filtering to alleviate the problem of inconsistency between the disparity map and color image around object boundary. Furthermore, we propose a temporal filter to improve the temporal consistency of the disparity maps computed from the stereo videos.
Experimental results on various real videos are shown to demonstrate that the proposed system effectively improves the accuracy of the disparity maps estimation compared with the TV-L1 optical flow approach.

[1] B.K.P. Horn and B.G. Schunck. Determining optical flow. Artificial Intelligence, 1981.
[2] Lukas, B., Kanade, T. An iterative image registration technique with an application to stereo vision. In: Image Understanding Workshop, 1981.
[3] C. Zach, T. Pock, and H. Bischof. A duality based approach for realtime TV-L1 Optical Flow. In: 29th DAGM Symposium on Pattern Recognition, 2007.
[4] A. Bruhn, J. Weickert, and C. Schnorr, Combining the advantages of local and global optic flow methods, in Pattern Recognition, Luc Van Gool, ed., vol. 2449 of Lecture Notes in Computer Science, 2002.
[5] M. Drulea. Total variation regularization of local-global optical flow. ITSC, 2011.
[6] M. A. Mohamed and B. Mertsching, “TV-L1 optical flow estimation with image details recovering based on the modified census transform,” ISVC, 2012.
[7] L. Bao, Q. Yang, and H. Jin. Fast edge-preserving patchmatch for large displacement optical flow. IEEE Trans. Image Processing, 2014.
[8] M. Drulea and S. Nedevschi. Motion estimation using the correlation transform, IEEE Trans. Image Processing, 2013.
[9] D. Sun, S. Roth, and M. Black. Secrets of optical flow estimation and their principles. CVPR, 2010.
[10] C. Rhemann, A. Hosni, M. Bleyer, C. Rother, and M. Gelautz. Fast cost-volume filtering for visual correspondence and beyond. CVPR, 2011
[11] Q. Yang. A non-local cost aggregation method for stereo matching. CVPR, 2012.
[12] S. Mattoccia, S. Giardino, and A. Gambini. Accurate and efficient cost aggregation strategy for stereo correspondence based on approximated joint bilateral filtering. In Asian Conf. Computer Vision, 2009
[13] J. T. Barron, A. Adams, Y.C Shih, C. Hernandez. Fast Bilateral-Space Stereo for Synthetic Defocus. CVPR, 2015.
[14] J. Jiao, R. Wang, and W. Wang. Local stereo matching with improved matching cost and disparity refinement. IEEE Int. J. Multimedia, 2014.
[15] X. Mei et al., “On Building an Accurate Stereo Matching System on Graphics Hardware,” Proc. IEEE Int’l Conf. Computer Vision Workshops, 2011.
[16] K. Zhang, J. Lu, and G. Lafruit. Cross-based local stereo matching using orthogonal integral images. IEEE TCSVT, 2009.
[17] HTC. Htc one-m8. www.htc.com/us/smartphones/ htc-one-m8/camera
[18] L. I. Rudin, S. Osher, and E. Fatemi. Nonlinear total variation based noise removal algorithms. Physica D, 1992.
[19] Antonin Chambolle. An Algorithm for Total Variation Minimization and Applications. Journal of Mathematical Imaging and Vision, 2004.
[20] P. Dollár and C. Zitnick. Structured Forests for Fast Edge Detection. ICCV, 2013.
[21] K. He, J. Sun, and X. Tang. Guided Image Filtering. ECCV, 2010.
[22] P. Sand and S. Teller. Particle Video: Long-Range Motion Estimation using Point Trajectories. IJCV, 2008
[23] A. Geiger, M. Roser, and R. Urtasun. Efficient large-scale stereo matching. ACCV, 2010.
[24] K. Yamaguchi, D. A. McAllester, and R. Urtasun. Efficient joint segmentation, occlusion labeling, stereo and flow estimation. ECCV, 2014.
[25] K. Zhang, Y. Fang. Cross-Scale Cost Aggregation for Stereo Matching. CVPR, 2014.
[26] Z. Wang, A. C. Bovik, H. R. Sheikh and E. P. Simoncelli, "Image quality assessment: From error visibility to structural similarity," IEEE Transactions on Image Processing, 2004.