立體視覺似人類雙眼系統，藉由對應點比對而得物體深度資訊，但會因遮蔽、影像不連續性、特徵不明顯、光照影響等，造成尋找對應點的錯誤。本論文以可信度傳遞為基礎，利用多次信息傳遞的方式，改進同質區域的視差圖的準確率。由於同質區域內，像素點相似，將導致信息傳遞錯誤，因此，我們提出改良式可信度傳遞於同質區域之立體視覺匹配演算法，第一，我們利用影像梯度結合SAD（sum of absolute differences）資訊判斷以增加可信賴之對應點數目，再使用可信賴對應點傳遞信息，改善信息無法快速從同質區域外部傳遞至內部的問題。第二，我們提出改良式信息傳遞，只需少數的疊代，即能更新出較佳的信息。第三，我們利用加重信息傳遞的權重，加速影像中大範圍同質區域的信息傳遞，達到視差圖快速收斂的程度，以獲得對應準確度較高的視差圖。實驗結果顯示，我們所提出的演算法，在無特徵之平滑區域，時間複雜度較快速可信度傳遞演算法增加了22％，但錯誤率降低了12.2％。

Stereo vision uses two images from different viewpoints to reconstruct the depth of objects. However, stereo correspondence errors may occur due to the object occlusions, depth discontinuities, homogeneous regions and light effects. In this paper, we adopt the belief propagation based algorithm using the message propagation to obtain the disparity map. Due to the similarity of pixels in homogeneous regions, the inaccurate messages may result in the incorrect disparity map. Motivated by this, we further improve the stereo matching algorithm using belief propagation for homogeneous regions. First, we increase the reliable correspondence using the combination of SAD and gradients, and propagate the message from reliable correspondence for homogeneous regions. This improves message propagation from boundary to inside for homogeneous regions. Second, we propose improve message propagation to update optimal message in less iteration. Third, we further accelerate message propagation by increasing the weight of message propagation in larger homogeneous regions. Compared with efficient BP, our experimental results show that our proposed method reduce the inaccurate rate in textureless regions is 12.2％, but increase computation complexity is 22％.

[1] D. Lowe “Distinctive image features from scale-invariant keypoints.” International Journal of Computer Vision. Vol. 60, No. 2, pp. 91-110, 2004.
[2] Y. Ohta and T. Kanade “Stereo by intra- and inter-scanline search using dynamic programming.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 7, Issue 2, pp. 139-154, March, 1985.
[3] Loop C. and Zhengyou Zhang “Computing rectifying homographies for stereo vision.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 1, pp. 23-25, June, 1999.
[4] D. Scharstein and R. Szeliski “A taxonomy and evaluation of dense two-frame stereo correspondence algorithms.” IEEE Workshop on Stereo and Multi-Baseline Vision. pp. 131-140, Dec., 2001.
[5] J. Matas, O. Chum, M. Urban, and T. Pajdla “Robust wide baseline stereo from maximally stable extremal regions.” British Machine Vision Conference. pp.384-393, 2002.
[6] Andrea Vedaldi “An Implementation of Multi-dimensional maximally stable extremal regions.” Citeseer. February 7, 2007.
[7] Lars Kunze “Visual features to help close the loop in 6D-SLAM.” Citeseer. October, 2006.
[8] Jian Sun, Nan-Ning Zheng and Heung-Yeung Shum “Stereo matching using belief propagation.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 25, issue 7, pp. 787-800, July, 2003.
[9] Pedro Felzenszwalb and Daniel Huttenlocher “Efficient belief propagation for early vision.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Vol. 1, pp. 261-268, June, 2004.
[10] Pedro Felzenszwalb and Daniel Huttenlocher “Efficient belief propagation for early vision.” International Journal of Computer Vision. Vol. 70, No. 1, pp.41-54, Oct. 2006.
[11] Andreas Klaus, Mario Sormann and Konrad Karner “Segment-based stereo matching using belief propagation and a self-adapting dissimilarity measure.” International Conference on Pattern Recognition. Vol. 3, pp. 15-18, 2006.
[12] Qingxiong Yang, Liang Wang, Ruigang Yang, Henrik Stewenius and David Nister “Stereo matching with color-weighed correlation, hierarchical belief propagation and occlusion handling.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2006.
[13] Qingxiong Yang, Liang Wang, Ruigang Yang, Henrik Stewenius and David Nister “Stereo matching with color-weighed correlation, hierarchical belief propagation and occlusion handling.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 31, Issue 3, pp. 492-504, March, 2009.
[14] Zeng-Fu Wang and Zhi-Gang Zheng “A region based stereo matching algorithm using cooperative optimization.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2008.
[15] Qingxiong Yang, Liang Wang, Ruigang Yang, Shengnan Wang, Miao Liao and David Nister “Real-time global stereo matching using hierarchical belief propagation.” The British Machine Vision Conference. 2006.
[16] Erik B. Sudderth, Alexander T. Ihler, William T. Freeman and Alan S. Willsky “Nonparametric belief propagation.” IEEE Conference on Computer Vision and Pattern Recognition. Vol. 1, pp. 605-612, June, 2003.
[17] Tianli Yu, Ruei-Sung Lin, Boaz Super and Bei Tang “Efficient message representations for belief propagation.” International Conference on Computer Vision. Oct. 2007.
[18] Yu-Cheng Tseng, Nelson Chang and Tian-Sheuan Chang “Low memory cost block-based belief propagation for stereo correspondence.” International Conference on Multimedia and Expo. July, 2007.
[19] Chao-Chung Cheng, Chia-Kai Liang, Yen-Chieh Lai, Homer H. Chen and Liang-Gee Chen “Analysis of belief propagation for hardware realization.” IEEE Workshop on Signal Processing System. 2008.
[20] William T. Freeman and Egon C. Pasztor “Learning low-level vision.” International Conference on Computer Vision. Vol. 2, pp. 1182-1189, Sept. 1999.
[21] Sang-Beom Lee, Kwan-Jung Oh and Yo-Sung Ho “Segment-based multi-view depth map estimation using belief propagation from dense multi-view video.” 3DTV Conference. May, 2008.
[22] Jonathan S. Yedidia, William T. Freeman and Yair Weiss “Understanding belief propagation and its generalizations.” Mitsubishi Electric Research Laboratories. Jan. 2002.
[23] Marshall F. Tappen and William T. Freeman “Comparison graph cuts with belief propagation for stereo, using identical MRF parameters.” International Conference on Computer Vision. 2003.
[24] Brendan J. Frey and Nebojsa Jojic “A comparison of algorithms for inference and learning in probabilistic graphical models.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 27, No. 9, pp. 1392-1416, September, 2005.
[25] Richard Szeliski, Ramin Zabih, Daniel Scharstein, Olga Veksler, Vladimir Kolmogorov, Aseem Agarwala, Marshall Tappen and Carsten Rother “A comparative study of energy minimization methods for markov random fields.” Lecture Notes in Computer Science. pp. 16-29, 2006.
[26] David A. Forsyth and Jean Ponce “Computer vision：a modern approach” Cambridge University Press. London, England, 2000.
[27] Rafael C. Gonzalez and R. E. Woods “Digital image processing, Third Edition.” Prentice Hall. 2007.
[28] Milan Sonka, Vaclav Hlavac and Roger Boyle “Image processing, analysis, and machine vision.” International Thomson. 2007.
[29] Chih-I Cheng and Tsu-Tian Lee “Obstacle detection and distance estimation by computer vision for indoor corridor environment.” Department of Electrical and Control Engineering, National Chiao-Tung University. 2002.
[30] Daniel Scharstein and Richard Szeliski “High-accuracy stereo depth maps using structured light.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition. June, 2003.
[31] Dorin Comaniciu and Peter Meer “Mean Shift: a robust approach toward feature space analysis.” IEEE Transactions on Pattern Analysis and Machine Intelligence. Vol. 24, No. 5, pp. 603-619, May, 2002.
[32] http://vision.middlebury.edu/stereo