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...

三维物体抗仿射变换特征匹配方法

Keywords: 三维物体,图像匹配,mASIFT,多平面约束,Mransac

Full-Text   Cite this paper   Add to My Lib

Abstract:

为解决三维物体视角变化下的图像匹配问题,提出一种实现三维物体任意仿射变换间的图像匹配方法.在抗仿射变换的Affine-SIFT算法基础上,提出了多变换矩阵mASIFT(multiAffineSIFT)算法.使用多平面随机抽样一致性(multi-planeRANSAC,mRANSAC)几何变换约束方法,从描述子粗匹配结果中提取正确匹配对.比单一变换矩阵方法更加符合目标物体的立体多平面特性,匹配对数普遍是ASIFT的5~9倍.降低每个单应矩阵的误差阈值,使内点提取中双向变换误差阈值小于3个像素(或2个像素),更有效地剔除误匹配,可计算出更精确的变换矩阵,实现更加准确的匹配.

References

[1]  Brown M, Lowe D G. Invariant features from interest point groups[C]//Proceedings of British Machine Vision Conference. Cardiff, Wales:[s.n.], 2002:253-262.
[2]  Lowe D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[3]  吴刚, 武春风, 侯晴宇, 等.基于不变矩特征匹配的目标定位方法[J].光学精密工程, 2009, 17(2):460-468. Wu Gang, Wu Chunfeng, Hou Qingyu. Target location method based on invariable moment feature matching[J]. Optics and Precision Engineering, 2009, 17(2):460-468.(in Chinese)
[4]  曾峦, 王元钦, 谭久彬.改进的SIFT特征提取和匹配算法[J].光学精密工程, 2011, 19(6):1391-1397. Zeng Yuan, Wang Yuanqin, Tan Jiubin. Improved algorithm for SIFT feature extraction and matching[J]. Optics and Precision Engineering, 2011, 19(6):1391-1397. (in Chinese)
[5]  贺柏根, 朱明.改进的抗全反射尺度不变特征变换图像匹配算法[J].光学精密工程, 2011, 19(10):2472-2477. He Bogen, Zhu Ming. Improved fully affine invariant SIFT-based image matching algorithm[J]. Optics and Precision Engineering, 2011, 19(10):2472-2477. (in Chinese)
[6]  Morel J M, Yu Guoshen. ASIFT: a new framework for fully affine invariant image comparison[J]. SIAM Journal on Imaging Sciences, 2009, 2(2):438-469.
[7]  冯嘉.SIFT算法的研究和改进[D].长春:吉林大学, 2010. Feng Jia. The research and improve of the SIFT[D]. Changchun: Jilin University, 2010. (in Chinese)
[8]  Harris C, Stephens M. A combined corner and edge detector[C]//Proceedings of the 4th Alvey Vision Conference. Manchester: the University of Sheffield Printing Unit, 1988:147-151.
[9]  Lindeberg T. Scale-space theory: a basic tool for analyzing structures at different scales[J]. Journal of Applied Statistics, 1994, 21(2):224-270.
[10]  David G, Lowe D G. Object recognition from local scale-invariant features[J]. International Conference on Computer Vision. Corfu, Greece, 1999:1150-1157.
[11]  Morel J M, Yu Guoshen. On the consistency of the SIFT method. CMLA, ENS Cachan, France: Technical Report CMLA 2008-26, 2008.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133