[1]曹云云,达飞鹏,邵静.一种具有选择性的置信度传播立体匹配算法[J].东南大学学报(自然科学版),2011,41(5):1013-1018.[doi:10.3969/j.issn.1001-0505.2011.05.023]
 Cao Yunyun,Da Feipeng,Shao Jing.A stereo matching algorithm based on selective belief propagation[J].Journal of Southeast University (Natural Science Edition),2011,41(5):1013-1018.[doi:10.3969/j.issn.1001-0505.2011.05.023]
点击复制

一种具有选择性的置信度传播立体匹配算法()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
41
期数:
2011年第5期
页码:
1013-1018
栏目:
计算机科学与工程
出版日期:
2011-09-20

文章信息/Info

Title:
A stereo matching algorithm based on selective belief propagation
作者:
曹云云达飞鹏邵静
(东南大学复杂工程系统测量与控制教育部重点实验室,南京 210096)
Author(s):
Cao YunyunDa FeipengShao Jing
(Key Laboratory of Measurement and Control for Complex Systems of Engineering of Ministry of Education,
Southeast University, Nanjing 210096, China)
关键词:
自适应权重图像分割置信度传播立体匹配
Keywords:
adaptive support-weight image segmentation belief propagation stereo matching
分类号:
TP391.41
DOI:
10.3969/j.issn.1001-0505.2011.05.023
摘要:
为了改善立体匹配算法在低纹理和深度跳变区域的匹配性能,提出了一种改进的置信度传播立体匹配算法.首先利用均值漂移算法对图像进行彩色分割,然后通过自适应权重算法计算匹配代价并获取初始视差图,再利用匹配代价可信度检测和左右一致性校验将初始匹配结果按照可靠度分类,最后在全局优化的过程中分别通过可靠度分类和图像分割结果来指导置信度传播方向和范围的选择,从而优化传播路径,提高匹配性能.将该算法应用于标准库图像中可以提高低纹理和深度跳变区域的匹配精度,得到边界清晰、稠密光滑的视差图,同时,将其应用于实拍图像的三维重建系统中能够得到生动逼真的立体模型,证明了该算法的有效性和实用性.
Abstract:
In order to improve the matching performance in low-texture and depth-discontinuous regions, an improved belief propagation-based stereo matching algorithm is proposed. First, the mean-shift algorithm is applied in the color image segmentation. Secondly, the adaptive support-weight approach is used to calculate the matching cost and initialize the disparity map. Then, the pixels are classified by different reliabilities according to matching cost confidence measure and mutual consistency check. The results of image segmentation and pixel classification are used to select the direction and range of the improved belief propagation in the global optimization. Using the new technique, a better path of propagation is established and the matching performance is improved. Experimental results show that the method is efficient and can produce dense disparity maps with high accuracy even in low-texture and depth-discontinuous regions when applied in Middlebury standard images matching, and the method can also generate vivid stereo models when applied in the 3D reconstruction of the image capture in the real world.

参考文献/References:

[1] Scharstein D,Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J].Computer Vision,2002,47(1):7-42.
[2] Bleyer M,Gelautz M.Graph-cut based stereo matching using image segmentation with symmetrical treatment of occlusions[J].Signal Processing:Image Communication,2007,22(2):127-143.
[3] Sun J,Zheng N N,Shum H Y.Stereo matching using belief propagation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):787-800.
[4] Kim J C,Lee K M,Choi B T,et al.A dense stereo matching using two-pass dynamic programming with generalized ground control points[C]// Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition.San Diego,CA,USA,2005,2:1075-1082.
[5] Hirschmuller H.Accurate and efficient stereo processing by semi-global matching and mutual information[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(2):328-341.
[6] Bleyer M,Gelautz M.A layered stereo algorithm using image segmentation and global visibility constraints[C]//Proceedings of International Conference on Image Processing.Singapore,2004,2:2997-3000.
[7] Yang Q C,Wang L,Yang R Q,et al.Stereo matching with color-weighted correlation,hierarchical belief propagation and occlusion handling[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2009,31(3):492-504.
[8] Comaniciu D,Meer P.Mean shift:a robust approach toward feature space analysis[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(5):603-619.
[9] Yoon K J,Kweon I S.Adaptive support-weight approach for correspondence search[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(4):650-656.
[10] Birchfield S,Tomasi C.Depth discontinuities by pixel-to-pixel stereo[C]//Proceedings of the IEEE International Conference on Computer Vision.Bombay,India,1998:1073-1080.
[11] Scharstein D.Middlebury stereo evaluation[EB/OL].(2011-03-10)[2011-03-15].http://vision.middlebury.edu/stereo/.
[12] Yang Q,Engels C,Akbarzadeh A.Near real-time stereo for weakly-textured scenes[C]//British Machine Vision Conference.Leeds,UK,2008:80-87.
[13] Hosni A,Bleyer M,Gelautz M,et al.Local stereo matching using geodesic support weights[C]//Proceedings of International Conference on Image Processing.Cairo,Egypt,2009:2093-2096.
[14] Larsen E S,Mordohai P,Pollefeys M,et al.Temporally consistent reconstruction from multiple video streams using enhanced belief propagation[C]//Proceedings of the IEEE International Conference on Computer Vision.Rio de Janeiro,Brazil,2007:4409013.
[15] Yu T L,Lin R S,Super B,et al.Efficient message representations for belief propagation[C]//Proceedings of the IEEE International Conference on Computer Vision.Rio de Janeiro,Brazil,2007:4408905.
[16] Kolmogorov V,Zabih R.Computing visual correspondence with occlusions using graph cuts[C]// Proceedings of the IEEE International Conference on Computer Vision.Vancouver,BC,Canada,2001,2:508-515.
[17] Zhang Zhengyou.A flexible new technique for camera calibration[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334.
[18] Fusiello A,Trucco E,Verri A.A compact algorithm for rectification of stereo pairs[J].Machine Vision and Applications,2000,12(1):16-22.

相似文献/References:

[1]张煜东,吴乐南.基于二维Tsallis熵的改进PCNN图像分割[J].东南大学学报(自然科学版),2008,38(4):579.[doi:10.3969/j.issn.1001-0505.2008.04.007]
 Zhang Yudong,Wu Lenan.Image segmentation based on 2D Tsallis entropy with improved pulse coupled neural networks[J].Journal of Southeast University (Natural Science Edition),2008,38(5):579.[doi:10.3969/j.issn.1001-0505.2008.04.007]
[2]王培珍,陈维南.基于模糊聚类与二维阈值的图像分割[J].东南大学学报(自然科学版),1998,28(6):74.[doi:10.3969/j.issn.1001-0505.1998.06.015]
 Wang Peizhen,Image Segmentation Based on Fuzzy Clustering and Two Dimensional Thresholding[J].Journal of Southeast University (Natural Science Edition),1998,28(5):74.[doi:10.3969/j.issn.1001-0505.1998.06.015]

备注/Memo

备注/Memo:
作者简介:曹云云(1986—),女,博士生;达飞鹏(联系人),男,博士,教授,博士生导师,dafp@seu.edu.cn.
基金项目:国家自然科学基金资助项目(60775025)、江苏省自然科学基金资助项目(BK2010116).
引文格式: 曹云云,达飞鹏,邵静.一种具有选择性的置信度传播立体匹配算法[J].东南大学学报:自然科学版,2011,41(5):1013-1018.[doi:10.3969/j.issn.1001-0505.2011.05.023]
更新日期/Last Update: 2011-09-20