基于改进局部敏感散列算法的图像配准

龚卫国; 张旋; 李正浩

doi:10.3788/OPE.20111906.1375

您当前的位置：

首页 >

文章列表页 >

基于改进局部敏感散列算法的图像配准

信息科学 | 更新时间：2020-08-12

- 基于改进局部敏感散列算法的图像配准
- Image registration based on extended LSH
- 光学精密工程 2011年19卷第6期页码：1375-1383
- 作者机构：
  
  重庆大学光电技术及系统教育部重点实验室重庆,400044
- 作者简介：
- 基金信息：
  
  国家863高技术研究发展计划资助项目(No.2007AA01Z423)();公安部应用创新项目(No.2010YYCXCQSJ074)();重庆市科技攻关重点项目(No
- DOI：10.3788/OPE.20111906.1375
  中图分类号： TP391.41
- 收稿日期：2010-10-08，
  
  修回日期：2010-11-29，
  
  网络出版日期：2011-06-25，
  
  纸质出版日期：2011-06-25
- 稿件说明：
移动端阅览
龚卫国, 张旋, 李正浩. 基于改进局部敏感散列算法的图像配准[J]. 光学精密工程, 2011,19(6): 1375-1383

GONG Wei-guo, Zhang Xuan, LI Zheng-hao. Image registration based on extended LSH[J]. Editorial Office of Optics and Precision Engineering, 2011,19(6): 1375-1383
龚卫国, 张旋, 李正浩. 基于改进局部敏感散列算法的图像配准[J]. 光学精密工程, 2011,19(6): 1375-1383 DOI： 10.3788/OPE.20111906.1375.

GONG Wei-guo, Zhang Xuan, LI Zheng-hao. Image registration based on extended LSH[J]. Editorial Office of Optics and Precision Engineering, 2011,19(6): 1375-1383 DOI： 10.3788/OPE.20111906.1375.

摘要

为实现图像间的快速准确配准

在局部敏感散列(LSH)算法基础上

提出一种高效的高维特征向量检索算法改进的LSH(ELSH)算法用以图像特征间的检索配对

从而实现图像间的配准。该配准算法首先采用尺度不变特征变换(SIFT)算法提取图像的特征点并进行描述

得到图像的高维特征向量。然后

根据随机选择的若干子向量构建哈希索引结构

以缩减构建索引数据的维数和搜索的范围

从而缩短建立索引的时间。最后

根据数据随机取样一致性(RANSAC)剔除错误点。实验结果表明

与BBF (Best-Bin-First)和LSH算法相比

ELSH算法不但提高了匹配点对的准确性同时也缩短了匹配时间

其特征匹配时间分别减少了49.9%和37.9%。实验表明该算法可以快速、精确地实现图像间的配准。

Abstract

In order to realize quickly and accurately matching between the image features

an efficient high-dimensional feature vector retrieval algorithm

Extended Locality Sensitive Hashing(ELSH)

was proposed based on LSH(Locality Sensitive Hashing). Firstly

the Scale Invariant Feature Transform (SIFT) algorithm was used to get the special point of an image and its features. Then

according to the sub-vectors selected randomly from the SIFT features

a hash index structure was built to reduce the indexing dimension and the searching scope. Thus

it can significantly reduce the time cost of indexing. Finally

the Random Sample Consensus (RANSAC) algorithm was used to select the right feature point pairs. Experimental results indicate that compared with the Best-Bin-First(BBF) and the LSH algorithm

ELSH algorithm not only ensures the accuracy of matching points

but also reduces the matching time. The time cost of ELSH only takes 50.1% of that of the BBF

and 62.1% of that of the LSH. In conclusion

the proposed algorithm can quickly and precisely achieve the registration between images.

关键词

Keywords

references

ZITOVA B,FLUSSER J. Image registration methods: a survey [J]. Image and Vision Computing, 2003(21):977-1000.[2] 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, 2008,28(11):2097-2103. ZHANG R J, ZHANG J Q, YANG C, et al.. Study on color image registration technique Based on CSIFT [J]. Acta Photonica Sinca, 2008,28(11):2097-2103.(in Chinese)[3] GEORGE L, MARIA P. Image registration using the Walsh transforms .IEEE Transactions on Image Processing, 2006,15(8):2343-2357.[4] 魏雪云,李景文,徐华平. 基于融合处理的遥感图像快速配准方法[J]. 电波科学学报, 2009,24(6):1055-1059. WEI X Y, LI J W, XU H P. Fast registration method for remote-sense images based on fusion result [J]. Chinese Journal of Radio Science, 2009,24(6):1055-1059.[5] LI Z H, GONG W G,NEE A Y C,ONG S K. The effectiveness of detector combinations [J].Optics Express, 2009,17(9):7407-7418.[6] 刘松涛,王学伟,周晓东,等. 基于传感器参数和目标轮廓中心的自动配准算法研究[J]. 光学精密工程, 2005,13(3):354-363. LIU S T, WANG X W, ZHOU X D, et al.. Automatic registration algorithm based on sensor parameters and target's contour centroid [J]. Opt. Precision Eng., 2005,13(3):354-363.(in Chinese)[7] JEFFREY S B, DAVID G L. Shape indexing using approximate nearest neighbors search in high dimensional spaces .Proceedings of the IEEE 1997, 16 Computer Society Conference on Computer Vision and Pattern Recognition, 1997:1000-1006.[8] BROWN M, LOWE D G. Recognizing panoramas . Proceedings of the 9th IEEE International Conference on Computer Vision. Washington D.C., USA: IEEE, 2003:1218-1225.[9] NENE S A, NAYAR S K. A simple algorithm for nearest neighbor search in high dimensions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997,19(9):989-100.[10] INDYK P, MOTWANI R. Approximate nearest neighbors: Towards removing the curse of dimensionality .Jeffrey V, ed. Proc.of the 30th Annual ACM Symp. On Theory of Computing. New York: ACM Press, 1998:604-613.[11] AUCLAIR A,COHEN L D, VINCENT N. How to use SIFT vectors to analyze an image with database templates . Proceedings of 5th International Workshop on Adaptive Multimedia Retrieval(AMR),2007:224-236.[12] KULIS B,GRAUMAN K. Kernelized locality sensitive hashing for scalable image search . Proc12th International Conference on Computer Vision (ICCV), 2009:1-8.[13] YU C,OOI B C,TAN K L,et al.. Indexing the Distance: An Efficient Method to KNN Processing . Proceedings of the 27th VLDB Conference, 2001:421-430.[14] LI Z H,GONG W G,NEE A Y C,et al.. Region-restricted rapid keypoint registration[J]. Optics Express, 2009,17(24):22096-22101.[15] 杨晓敏, 吴炜, 卿粼波,等. 图像特征点提取及匹配技术[J]. 光学精密工程, 2009,17(9):2276-2282. YANG X M,WU W,QING L B, et al.. Image feature extraction and matching technology [J].Opt. Precision Eng., 2009,17(9):2276-2282.(in Chinese)[16] 龚卫国,童玉娟,李正浩. 各向异性非刚性形变局部不变特征研究[J]. 仪器仪表学报,2010,31(1):99-104. GONG W G,TONG Y J , LI ZH H.Research on local invariant features for anisotropic non-rigid deformation [J]. Chinese Journal of Scientific Instrument, 2010,31(1):99-104.(in Chinese)[17] 纪华,吴元昊,孙宏海,等. 结合全局信息的SIFT特征匹配算法[J]. 光学精密工程, 2009,17(2):439-444. JI H, WU Y H,SUN H H, et al.. SIFT feature matching algorithm with global information [J]. Opt. Precision Eng., 2009,17(2):439-444.(in Chinese)[18] LOWE D G. Distinctive image features from scale-invariant keypoints [J]. International Journal of Computer Vision, 2004,2(60):91-110.[19] FISCHLER M A,BOLLES R C. Random sample consensus:a paradigm for model fitting with application to image analysis and automated cartography [J]. ACM Communications, 1981,24(6):381-395.[20] 牛津大学仿射协变特征图像测试库 .http://www.robots.ox.ac.uk/-vgg/research/affine/, Jul 2007. Affine Covariant Features Database of Oxford University. .http://www.robots.ox.ac.uk/-vgg/research/affine/, Jul 2007.[21] 狄红卫,刘显峰. 基于结构相似度的图像融合质量评价[J]. 光子学报,2006,35(5):766-771. DI H W, LIU X F. Image Fusion Quality Assessment Based on Structural Similarity [J]. Acta Photonica Sinca, 2006,35(5):766-771.(in Chinese)

浏览量

951

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

弱纹理环境下融合点线特征的双目视觉同步定位与建图

针对目标遮挡的自适应特征匹配网络

基于自适应惯导辅助特征匹配的视觉SLAM算法

融合二维图像和三维点云的相机位姿估计

采用轮廓特征匹配的红外-可见光视频自动配准