在本篇論文中，我們提出了一個從校正好的一組影像得到視差圖的新演算法。我們首先使用影像過度分割來建立以內容為基礎的階層式馬可夫隨機場。這種影像表示方式包含了兩個利於做視覺應用的優點。第一個是階層式馬可夫隨機場的建立，而另一個是正規的圖形結構。前者已經被廣泛地應用於電腦視覺的問題來改進最佳化馬可夫隨機場的效率。後者可以簡化最佳化馬可夫隨機場技術其訊息的傳遞和硬體的實作。在建立完以內容為基礎的階層式馬可夫隨機場後，我們使用階層式可信度傳遞於對稱的立體匹配與遮蔽處理在提出的圖形模型上。最後，引進一個精煉視差圖的方法(例如平面擬合或雙向濾波器)來減少因遮蔽、無紋理區域或是影像上雜訊等等導致視差的錯誤估計。我們的實驗結果展現出我們可以有效率地獲得媲美大部分全局立體匹配演算法的準確度之視差圖。對於真實的影像序列，我們可以先使用強健的自身影像校正前處理來準確地估計出每張影格的深度資訊。

In this thesis, we present a novel algorithm to infer disparity map from given a pair of rectified images. We first employ image over-segmentation to construct a Content-based Hierarchical Markov Random Field (CHMRF). This image representation contains two advantages for vision applications. One is the hierarchical MRF construction, and the other is the regular graph structure. The former has been widely applied to computer vision problems to improve the efficiency in MRF optimization. The latter can simplify the message passing and hardware implementation of MRF optimization techniques. After the construction of CHMRF, we perform symmetric stereo matching and occlusion handing using Hierarchical Belief Propagation (HBP) based on the proposed graphical model. Finally, a refinement process for the disparity map is introduced (e.g. plane fitting or bilateral filtering) to reduce the disparity errors caused by occlusion, textureless region or image noise, etc. Our experimental results show that we can efficiently obtain disparity maps of comparable accuracy when compared to most global stereo algorithms. For real stereo video sequences, we are able to accurately estimate the depth information for each frame with the pre-processing of robust self image rectification.

[1] D. Scharstein and R. Szeliski. “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms”. In IJCV, vol. 47, no. 1, pp. 7-42, 2002.
[2] http://vision.middlebury.edu/stereo/.
[3] J. Sun, H. Y. Shum, and N. N. Zheng. “Stereo matching using belief propagation”. In A. Heyden, G. Sparr, M. Nielsen, and P. Johansen, editors, Computer Vision - ECCV 2002, number 2351 in Lecture Notes in Computer Science, pages 510–524, 2002.
[4] Y. Boykov, O. Veksler, and R. Zabih. “Fast Approximate Energy Minimization via Graph Cuts”. In IEEE Trans. PAMI, 23(11), Nov. 2001.
[5] A. Klaus, M. Sormann and K. Karner. “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure”. In ICPR 2006.
[6] Z. Wang and Z. Zheng. “A region based stereo matching algorithm using cooperative optimization”. In CVPR 2008.
[7] Q. Yang, L. Wang, R. Yang, H. Stewnius, and D. Nist□r. “Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling”. In TPAMI, 31(3):492–504, 2009.
[8] Y. Taguchi, B. Wilburn and C. L. Zitnick. “Stereo Reconstruction with Mixed Pixels Using Adaptive Over-Segmentation”. In CVPR 2008.
[9] J. Sun, Y. Li, S. B. Kang and H.-Y. Shum. “Symmetric stereo matching for occlusion handling”, In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. II:399-406, 2005.
[10] L. Zitnick and S.B. Kang. “Stereo for image-based rendering using image over-segmentation”. In IJCV 2007.
[11] S. Mattoccia. “A locally global approach to stereo correspondence”. In 3DIM 2009.
[12] K.-J. Yoon and I.-S. Kweon. “Adaptive support-weight approach for correspondence search”. In PAMI 28(4):650-656, 2006.
[13] H. Hirschm□ller. “Accurate and efficient stereo processing by semi-global matching and mutual information”. In PAMI 30(2):328-341, 2008.
[14] S. Kosov, T. Thorm□hlen, and H.-P. Seidel. “Accurate real-time disparity estimation with variational methods”. In ISVC 2009.
[15] K. Zhang, J. Lu, and G. Lafruit. “Cross-based local stereo matching using orthogonal integral images”. In IEEE TCSVT 2009.
[16] V. Kolmogorov and R. Zabih. “Computing visual correspondence with occlusions using graph cuts”. In ICCV 2001.
[17] T. kanade and M. Okutomi. “A stereo matching algorithm with an adaptive window: Theory and experiment”. In IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, P. 920 September 1994.
[18] H. Tao, H. S. Sawhney, and R. Kumar. “A global matching framework for stereo computation”. In ICCV, Vol I:532–539, 2001.
[19] L. Hong and G. Chen. “Segment-based stereo matching using graph cuts”. In CVPR, Vol I:74–81, 2004.
[20] M. Bleyer and M. Gelautz. “A layered stereo matching algorithm using image segmentation and global visibility constraints”. In ISPRS Journal, 59(3):128–150, 2005.
[21] A. Klaus, M. Sormann, and K. Karner. “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure”. In ICPR, pages 15–18, 2006.
[22] L. Xu and J. Jia. “Stereo matching: An outlier confidence approach". In ECCV, 2008.
[23] C. Christoudias, B. Georgescu, and P. Meer. ”Synergism in low-level vision”. In ICPR, volume 4, pages 150–155, 2002.
[24] P. Felzenszwalb and D. Huttenlocher. “Efficient belief propagation for early vision”. In IJCV, 70(1):41–54, 2006.
[25] T. Yu, R. S. Lin, B. J. Super, and B. Tang, “Efficient message representations for belief propagation”. In ICCV, 2007, pp. 1–8.
[26] Q. Yang, L. Wang, R. Yang, S. Wang, M. Liao and D. Nist□r. “Real-time global stereo matching using hierarchical belief propagation”. In BMCV 2006.
[27] C. Liang, C. Cheng, Y. Lai, L. Chen and H. Chen. “Hardware-efficient belief propagation”. In CVPR 2009.
[28] Q. Yang, L. Wang and N. Ahuja. “A constant-space belief propagation algorithm for stereo matching”. In CVPR 2010.
[29] G. Borgefors. “Distance transformations in digital images”. In Computer Vision, Graphics and Image Processing, 34(3):344–371, 1986.
[30] A. Criminisi, T. Sharp, and A. Blake. “Geos: Geodesic image segmentation”. In ECCV, pages 99–112, 2008.
[31] S. Birchfield and C. Tomasi. “A pixel dissimilarity measure that is insensitive to image sampling”. In IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 20, No. 4, April 1998.
[32] C.-M. Cheng, S.-H. Lai, and S.-H. Su. “Self Image Rectification for Un-calibrated Stereo Video with Varying Camera Motions and Zooming Effects”. In MVA09, Japan, May 20-22, 2009.