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...

一种利用动态规划和左右一致性的立体匹配算法

DOI: 10.11834/jig.20080426

Keywords: 立体匹配,动态规划,左右一致性,视差搜索策略

Full-Text   Cite this paper   Add to My Lib

Abstract:

立体匹配是计算机视觉领域研究的一个重要课题,为了得到准确、稠密的视差图,提出了一种利用动态规划和左右一致性的立体匹配算法。该算法首先分别以左、右图像为基元图像,计算各自的视差空间图像,在视差空间图像上利用动态规划,计算得到左视差图和右视差图;然后通过使用左右视差图之间的一致性关系,消除误匹配点,得到较为准确的部分视差图;最后利用视差图的顺序约束关系,给出未匹配视差点的搜索空间计算方法,并利用一种简单有效的方法来计算这些点的视差值。在一些标准立体图像对上所做的实验结果表明,该算法效果良好。

References

[1]  Seharstein D,Sseliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithm[J].Internafional Journal of Computer Vision,2002,47(1/2/3):7~42.
[2]  Sun C.A fast stereo matching method[A].In:Proeecdinss of Digital Image Computing:Techniques and Applications[C],Auckland,New Zealand,1997:95~100.
[3]  Randriamnsy S,Gagalowcz A.Region baaed stereo matching oriented image processing[A].In:Preceedin8s of Computer Vision and Pattern Recognition[C],Mani,HI,USA,1991:736~737.
[4]  Birchfield S,Tomssi C.Depth discontinuities by pixal-te-pixel stereo[J].International Journal of Computer Vision,1999,35(3):269~293.
[5]  Sun J,Zheng N,Shum H.Stereo matching using belief propagation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):1~14.
[6]  Brown Z,Burschka D,Hager G.Advance in computational stereo[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,2S(8):993~1008.
[7]  Bahat D,Nayar S.Ordinal measure for image eorrespendenee[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(4):415~423.
[8]  Kluth V,Kunkel G,Ranhala U.Global least squares matching[A].In:Proceedings of International Geoseiences and Remote Sensing Symposium[C],San Diego,CA,USA,1992:1615~1618.
[9]  Birehfield S,Tomasi C.A pixel dissimilarity measure that is insensitive to image sampling[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,20(4):401~406.
[10]  Bobick A,Intille S.Large occlusion stereo[J].International Journal of Computer Vision,1999,33(3):181~200.
[11]  Boykov Y,Kolmogorov V.An experimental comparison of min-cnt/max-flow algorithms for energy minimization in vision[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(9):1124~1137.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133