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...

基于自适应迭代松弛的立体点对匹配鲁棒算法

DOI: 10.11834/jig.20090722

Keywords: 立体匹配,极线约束,松弛法,双目立体测量,3维重建

Full-Text   Cite this paper   Add to My Lib

Abstract:

图像匹配是立体视觉的重要部分,也是双目立体测量系统必须解决和最难解决的问题。为了对图像进行鲁棒性匹配,提出了一种基于自适应迭代松弛的立体点对匹配方法。该方法首先利用视差梯度约束来构造匹配支持度函数;然后通过松弛方法优化该函数来完成立体点对的匹配。由于利用了动态更新松弛匹配过程参数的方法,因此有效地降低了误匹配率和误剔除率。在此基础上还提出了对松弛过程结束后的匹配结果,再次使用视差梯度约束来进行进一步检验的策略,该策略能够以一定幅度的误剔除率提升为代价,大幅度降低了误匹配率,从而可满足许多要求严格限制误匹配率的应用。实验结果证明,该新算法是有效的,并已经用于一个双目立体测量原型系统当中。

References

[1]  Trucco E,Verri A,Introductory Techniques for 3D Computer Vision,Upper Saddle River New Jersey USA:Prentice Hall,1998.
[2]  Scharatoin D,Sseliski R,A taxonomy and evaluation of dense twoframe stereo correspondence algorithms,International Journal of Computer Vision,2002(1/2/3).
[3]  Macial J,Coateira J P,A global solution to sparse correspondence problems,IEEE Transactions on Pattern Analysis and Machine Intelligence,2003(2).
[4]  Kolmogorov V,Zabih R,Computing visual correspondence with occlusions using graph cuts,Vancouver,BC,Canada,2001.
[5]  Lowe D O,Distinctive image features from seale-invariant keypoints,International Journal of Computer Vision,2004(2).
[6]  Ke Y,Sukthankar R,PCA-SIFT:A more distinctive representation for Iconl image descriptors,Washington,DC USA,2004.
[7]  Pollard S B,The PMF stereo algorithm:theory and implementation,Parallel Architectures and Computer Vision,1988.
[8]  Zhang Z,Deriche R,Faugerau O,A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry,Artificial Intelligence,1995(1-2).
[9]  Galo M,Tozzi C L,Feature-point based matching:a sequential approach based on relaxation labeling and relative orientation,Journal of WSCG(the Winter School Computer Graphics),2004(1-3).
[10]  Zhang W,Gao X,Sung E,A feature-baood matching scheme:MPCD and robust matching strategy,Pattern Recognition Letters,2007(10).
[11]  Yoon K J,Kweon I S,Adaptive support-weight approach for correspondence search,IEEE Transactions on Pattern Analysis and Machine Intelligence,2006(4).
[12]  Chen Y S,Hung Y F,Fuh C S,Fast block matching algorithm based on the winner-update strategy,IEEE Transactinns on Image Processing,2001(8).
[13]  周玲.张丽艳.郑建冬.张维中 近景摄影测量中标记点的自动检测 [J].-应用科学学报2007(3)
[14]  张辉.张丽艳.陈江.赵转萍 基于平面模板自由拍摄的双目立体测量系统的现场标定 [J].-航空学报2007(3)

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133