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...

融合特征的快速SURF配准算法

DOI: 10.11834/jig.20150110

Keywords: SURF特征点,颜色不变量边缘(CIM),CS-LBP纹理特征,RANSAC算法,最小二乘法

Full-Text   Cite this paper   Add to My Lib

Abstract:

目的针对基于SURF特征点的图像配准算法对颜色单一的彩色图像提取的特征点较少及配准时间复杂度高等问题,提出一种基于融合特征的快速SURF(speeduprobustfeatures)配准算法。方法该算法首先提取图像的颜色不变量边缘特征和CS-LBP(centralsymmetry-localbinarypatterns)纹理特征形成融合特征灰度图,并利用颜色直方图的方差自适应调节融合特征间的权重。其次,在融合特征灰度图上提取SURF(speeduprobustfeatures)特征点及描述子。再次,用最近邻匹配法形成粗匹配对,结合改进的快速RANSAC(randomsampleconsensus)算法得到精匹配对。最后,使用最小二乘法求出映射关系用于配准图像。结果本文算法能够在融合特征上提取更稳定的SURF特征点,用该特征点进行配准能提高配准5%精度,且减少时间复杂度15%,实现了对普通场景下图像的快速配准。结论本文算法能提取稳定数量的特征点,提高了精确度与鲁棒性,并通过改进的RANSAC算法提高了执行效率,降低了迭代次数。

References

[1]  Zitova B, Flusser J. Image registration methods: a survey[J]. Image and vision computing, 2003, 21(11): 977-1000.
[2]  Liu X J, Yang J, Sun J W, et al. Image registration based on SIFT key-points[J].Infrared and Laser Engineering, 2008, 37(1):156-160.[刘小军,杨杰,孙坚伟,等. 基于 SIFT 的图像配准方法 [J]. 红外与激光工程, 2008, 37(1): 156-160.]
[3]  Brown L G. A survey of image registration techniques[J]. ACM computing surveys, 1992, 24(4): 325-376.
[4]  Lowe D G. Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision. IEEE, 1999, 2: 1150-1157.
[5]  Bay H, Tuytelaars T, Van Gool L. Surf: speeded up robust features[M]//Computer Vision-ECCV 2006. Berlin Heidelberg: Springer, 2006: 404-417.
[6]  Zhang R J, Zhang J Q, Yang C, et al. Image registration of colored image based on CSIFT key-points[J].Journal of Optics,2009,28(11):2079-2103.[张锐娟, 张建奇, 杨翠, 等. 基于 CSIFT 的彩色图像配准技术研究[J]. 光学学报, 2009, 28(11): 2097-2103.]
[7]  Shi Y S. Image registration research for improved SURF key-points[D]. Xidian: Xidian University,2008[石雅笋. 改进的 SURF 图像配准算法研究[D]. 西安:西安电子科技大学, 2008.]
[8]  Shi Y S, Liu X Y, Chen F. Registration of colored image based on SURF key-points[J].Infrared Technique,2011,32(7):415-419.[石雅笋, 刘晓云, 陈奋. 基于 SURF 的彩色图像配准[J]. 红外技术, 2011, 32(7): 415-419.]
[9]  Wu Z. Image registration resarch based on fearture[D]. Hang zhou:Zhengjiang University, 2006.[吴铮. 基于特征的图像配准算法研究[D]. 杭州:浙江大学, 2006.]
[10]  Geusebroek J M, Van den Boomgaard R, Smeulders A W M, et al. Color invariance[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(12): 1338-1350.
[11]  Kubelka P, Munk F, Kubelka P. Ein beitrag ztlr optik der farbanstriche[J]. Z. Teeh. Physik, 193l, 12: 593-601.
[12]  Abdel-Hakim A E, Farag A A. CSIFT: a SIFT descriptor with color invariant characteristics[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington DC, USA: IEEE, 2006, 2: 1978-1983.
[13]  Heikkil? M, Pietik?inen M, Schmid C. Description of interest regions with center-symmetric local binary patterns[M]//Computer Vision, Graphics and Image Processing. Berlin Heidelberg: Springer, 2006: 58-69.
[14]  Yianilos P N. Data structures and algorithms for nearest neighbor search in general metric spaces[C]//The 4th annual ACM-SIAM Symposium on Discrete algorithms. Philadelphia PA, USA: Society for Industrial and Applied Mathematics, 1993: 311-321.
[15]  Fischler M A, Bolles R C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133