全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

垂直交叉双向搜索策略的自适应窗口匹配算法

DOI: 10.11834/jig.20150111

Keywords: 视差图,垂直交叉双向搜索,自适应窗口,米字投票,双边滤波器

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的基于区域的局部匹配算法是一种简单高效的立体匹配方法。针对局部算法中窗口的抉择问题,提出了基于垂直交叉双向搜索的自适应窗口匹配算法。方法该算法考虑到局部区域内灰度值与视差值的相关性,通过垂直交叉双向搜索策略自适应地调节窗口的形状和大小,并获得相应掩码窗口;再利用积分图像计算掩码窗口的匹配代价,获取视差图;最后采用米字投票和双边滤波器两个步骤对视差图进行修复。结果针对不同图像采用提出的自适应窗口算法,得到了适用于各种图像结构的匹配窗口,相较于原始垂直交叉算法的匹配精度提高了约30%(Teddy),同时两步骤视差后处理较好地保持了图像边缘。结论实验结果表明,该算法改善了规则窗口产生的视差边缘扩充问题,在提高视差精度的同时提高了算法鲁棒性。

References

[1]  Wang Z F, Zheng Z G. A region based stereo matching algorithm using cooperative optimization[C]//Proceedings of Computer Vision and Pattern Recognition.Anchorage, Alaska: IEEE Computer Society Press, 2008: 1-8. [DOI: 10.1109/CVPR. 2008. 4587456]
[2]  Di Stefano L, Marchionni M, Mattoccia S. A fast area-based stereo matching algorithm [J]. Image Vision Computer, 2004, 22(12): 983-1005. [10.1016/j.imavis.2004.03.009]
[3]  Zhou D X, Cai X P, Sun M Y. A feature-constrained stereo matching algorithm [J]. Journal of Image and Graphics, 2001, 6(7): 653-656.[周东翔,蔡宣平,孙茂印. 一种基于特征约束的立体匹配算法[J].中国图象图形学报,2001, 6(7): 653-656][DOI:10.11834/jig200107144]
[4]  Scharstein D. Matching images by comparing their gradient fields [C]//Proceedings of IEEE Pattern Recognition. Jerusalem, Israel: IEEE Computer Society Press, 1994, 1:572-575. [DOI: 10.1109/ICPR.1994.576363]
[5]  Huang X F. Cooperative optimization for energy minimization: a case study of stereo matching[EB/OL]. [2013-06-11]. http://front.math.ucdavis.edu/author/X.Huang cs.
[6]  Verksler 0. Stereo correspondence by dynamic programming on a tree[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego, CA USA: IEEE Computer Society Press, 2005,2: 384-390. [DOI: 10.1109/CVPR.2005.334]
[7]  Vladimir K, Pascal M, Pauline T. Kolmogorov and Zabih\'s graph cuts stereo matching algorithm[EB/OL]. [2013-06-11].http://dev.ipol.im/monasse/ipol_demo/kmt_stereo_with_graph_cuts/.
[8]  Zhu Q B, Wang H Y. Handling occlusions method for stereo correspondence using graph cuts [J]. Journal of Huazhong University of Science and Technology, 2010, 38(1): 81-84.[朱清波,王宏远. 使用图像分割的遮挡恢复立体匹配算法[J]. 华中科技大学学报,2010,38(1): 81-84]
[9]  He F, Da F P. Stereo matching using belief propagation and local edge construction-based cost aggregation [J]. Journal of Image and Graphics, 2011, 16(11): 2060-2066. [何?,达飞鹏. 置信度传播和区域边缘构建的立体匹配算法[J].中国图象图形学报, 2011, 16(11): 2060-2066][DOI:10.11834/jig.20111116]
[10]  Kanade T, Okutomi M. A stereo matching algorithm with an adaptive window-theory and experiment[J]. IEEE Tran. on Pattern Anal., 1994, 16(9): 920-32. [DOI: 10.1109/ROBOT.1991. 131738]
[11]  Yoon K J, Kweon I S. Locally adaptive support-weight approach for visual correspondence search[C]//Proceedings of IEEE Computer Society Conference on the Computer Vision and Pattern Recognition. San Diego, CA, USA: IEEE Computer Society Press, 2005: 20-26 .[DOI: 10.1109/CVPR.2005.218]
[12]  Zhang K, Lu J, Lafruit G. Cross-based local stereo matching using orthogonal integral images [J]. IEEE Trans. on Circuits Syst. Video Technol., 2009, 19(7): 1073-1079. [DOI: 10.1109/TCSVT.2009.2020478]
[13]  Scharstein D, Szeliski R. Middlebury Stereo Benchmark[EB/OL].[2013-06-11]. http://vision.middlebury.edu/stereo.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133