改进的SURF算法在特征匹配中的应用

赵立荣1; 朱玮2; 曹永刚2; 柳玉晗2; 孙俊喜1

doi:10.3788/OPE.20132112.3263

您当前的位置：

首页 >

文章列表页 >

改进的SURF算法在特征匹配中的应用

信息科学 | 更新时间：2020-08-12

- 改进的SURF算法在特征匹配中的应用
- Application of improved SURF algorithm to feature matching
- 光学精密工程 2013年21卷第12期页码：3263-3271
- 作者机构：
  
  1. 中国科学院长春光学精密机械与物理研究所，吉林长春 130033,中国
  2. 长春理工大学通讯与信息学院，吉林长春 130031
- 作者简介：
- 基金信息：
  
  国家863高科技研究发展计划资助项目(2011AAXXX2035)
- DOI：10.3788/OPE.20132112.3263
  中图分类号： TP391.4
- 收稿日期：2013-01-08，
  
  修回日期：2013-07-23，
  
  网络出版日期：2013-12-25，
  
  纸质出版日期：2013-12-25
- 稿件说明：
移动端阅览
赵立荣, 朱玮, 曹永刚, 柳玉晗, 孙俊喜. 改进的SURF算法在特征匹配中的应用[J]. 光学精密工程, 2013,21(12): 3263-3271

DIAO Li-Rong, SHU Wei, CAO Yong-Gang, LIU Yu-Han, SUN Jun-xi. Application of improved SURF algorithm to feature matching[J]. Editorial Office of Optics and Precision Engineering, 2013,21(12): 3263-3271
赵立荣, 朱玮, 曹永刚, 柳玉晗, 孙俊喜. 改进的SURF算法在特征匹配中的应用[J]. 光学精密工程, 2013,21(12): 3263-3271 DOI： 10.3788/OPE.20132112.3263.

DIAO Li-Rong, SHU Wei, CAO Yong-Gang, LIU Yu-Han, SUN Jun-xi. Application of improved SURF algorithm to feature matching[J]. Editorial Office of Optics and Precision Engineering, 2013,21(12): 3263-3271 DOI： 10.3788/OPE.20132112.3263.

摘要

提出一种新的多尺度改进加速鲁棒特征（SURF)分块特征匹配算法，定义为Modified-SURF(M-SURF)。此方法在运用图像积分技术的SURF基础上进行分块特征匹配，使计算速度进一步加快；同时使用了基于二阶多尺度模板生成的特征描述子，提高了特征点匹配的鲁棒性。文中首先推导了M-SURF算法二阶多尺度模板公式；然后，介绍了分块匹配的方法，解决了匹配计算速度与精度不能兼得的矛盾，通过实验获得了分块模板的最佳参数；最后，采用欧氏空间最近距离比次近距离的方法衡量匹配的优劣度，利用LMedS方法剔除误匹配点，使匹配精度有较大的提高。对多组图像进行了匹配实验，结果表明：与SURF和尺度不变特征变换（SIFT）算法比较，M-SURF的计算速度提高了28％，匹配精度提高了3％。该算法能够很好地实现特征点的正确匹配，具有很高的使用价值。

Abstract

A new improved method

Speed Up Robust Features(SURF) matching by image partition

is propoed

which is defined as Modified-SURF(M-SURF). The method uses the feature matching adopting an image integral based on SURF to speed up the computing speed

meanwhile

it takes the second-order feature descriptors derived by the second-order multi-scale gauge to improve the feature matching robustness. The paper firstly deduces the formula of the second-order multi-scale gauge. Then

it introduces the image partition algorithm to resolve the inconsistency between the computing speed and the precision of matching. With an experiment

it obtains the optimal parameters of image partition matching. At last

it weighs the quality of matching by the algorithm of the ratio of the shortest distance and shorter distance in Euclid space

and improves the matching precision by eliminating the false matching dot with the LMedS. The result shows that the computing speed of M-SURF has raised more than 28％ and the matching precision of M-SURF increases by 3％ as comparing with those of SURF and Scale Invariance Feature Transfer(SIFT) by matching tests for several series of images. This algorithm can achieve a better matching of feature points and has a practical value.

关键词

Keywords

references

［1］赵立荣，柳玉晗，朱玮，等.光电经纬仪单站空间余弦及多站面面交汇的飞机姿态测量［J］.光学精密工程，2009,17(11):2786-2793.ZHAO L R,LIU Y H, ZHU W, et al.. Measurement of aircraft attitude by spatial cosine relationship in single-station and planes to intersection in multi-station of electro-optical theodolite ［J］. Opt. Precision Eng., 2009,17(11):2786-2793. (in Chinese)［2］赵立荣，朱玮，曹永刚，等.基于构建最优函数提高飞机姿态测量精度［J］.光学精密工程，2012,20(6):1325-1333.ZHAO L R, ZHU W,CAO Y G, et al.. Improvement of measurement precision of plane attitude by constructing optimization functions ［J］. Opt. Precision Eng., 2012, 20(6):1325-1333. (in Chinese)［3］LOWE D. Object recognition from local scale-invariant features［C］.Proc. of the International Conference on Computer Vision (ICCV), Corfu, Greece, 1999,1150-1157.［4］CSURKA G,DANCE C R,FAN L X,et al.. Visual categorization with bags of keypoints ［C］. In Workshop on Statistical Learning in Computer Vision, ECCV, 2004, 1-22.［5］AGARWAL S,SNAVELY N,SIMON I,et al.. Building Rome in a Day ［C］.Internation Conference on Computer Vison, 2009.［6］TOLA E,LEPETIT V,DAISY P. An efficient dense descriptor applied to wide-baseline stereo］［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(5):815-830.［7］FERGUS R,PERONA P, ZISSERMAN A. Object class recognition by unsupervised scale-invariant learning ［C］.2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition,2003,2:264-271.［8］RUBLEE E,RABAUD V,KONOLIGE K,et al.. ORB: an efficient alternative to SIFT or SURF［C］.2011 IEEE International Conference on Computer Vison(ICCV),2011,2564-2571. ［9］WERNER K, MARTIN K. Interest point based tracking ［C］. 20th International Conference on Pattern Recognition(ICPR), 2010:3549-3552. ［10］HE W, YAMASHITA T,LU H T, et al.. SURF Tracking ［C］.2009 IEEE 12th International Conference on Computer Vision, Kyoto, Japan, September, 2009:1586-1592.［11］TA D N, CHEN W CH, NATASHA G, et al.. SURFTrac: Efficient tracking and continuous object recognition using local feature descriptors ［C］.IEEE Conference on Computer Vision and Pattern Recognition,2009:2937-2944.［12］LINDEBERG T. Feature detection with automatic scale selection ［J］.Internation Journal of Computer Vision,1998,30(2):77-116. ［13］BAY H,ESS A,TUYTELAARS T. Gool, SURF: Speeded up robust 826 features, Computer Vision and Image Understanding,2008,110(3):346-827 359.［14］DAMON J. Local Morse theory for solutions to the heat equation and Gaussian blurring ［J］. Journal of Differential Equations,1995,115(2):368-401. ［15］ROUSSEEUW P J. Least median of squares regression ［J］. Journal of the American Statistical Association,1984,79(388):871-880.［16］闫辉，许廷发，吴青青，等.多特征融合匹配的多目标跟踪［J］.中国光学，2013，6（2）：163-170. YAN H, XU T F,WU Q Q,et al.. Multi-object tracking based on multi-feature joint matching ［J］. Chinese Optics, 2013，6（2）：163-170. (in Chinese)［17］陶李, 王珏, 邹永宁，等. 改进的Zernike矩工业CT图像边缘检测［J］.中国光学, 2012,5(1):48-56. TAO L, WANG J, ZOU Y N,et al.. Improved Zernike moment method for industrial CT image edge detection ［J］.Chinese Optics, 2012,5(1):48-56. (in Chinese)［18］韩广良. 高频信息矢量匹配实现异源图像配准［J］.中国光学, 2011,4(5):468-473.HAN G L. Alignment between different source images by high frequency vector matching［J］. Chinese Optics, 2011,4(5):468-473. (in Chinese)［19］孙辉, 李志强, 孙丽娜,等. 一种空域和频域相结合的运动图像亚像素配准技术［J］.中国光学, 2011,4(2):154-160. SUN H, LI ZH Q, SUN L N，et al.. Sub-pixel registration of special and frequency domains for video sequences ［J］. Chinese Optics, 2011,4(2)：154-160. (in Chinese) ［20］王希军. 激光散斑的亚像素位移法计算及比较［J］.中国光学, 2012,5(6):652-657. WANG X J. Computation and comparison of laser speckle with sub-pixel measurement methods［J］. Chinese Optics, 2012,5(6):652-657. (in Chinese)［21］ZHANG Z. Flexible camera calibration by viewing a plane from unknown orientations ［C］.The Proceedings of the 7th IEEE International Conference on Computer Vision,1999, 666-673.［22］丘文涛，赵建，刘杰. 结合区域分割的SIFT图像匹配方法［J］. 液晶与显示，2012，27（6）：827-831.QIU W T，ZHAO J，LIU J. Image matching algorithm combining SIFT with region segmentation ［J］. Chinese Journal of Liquid Crystals and Displays,2012，27（6）：827-831. (in Chinese)［23］李英，李静宇，徐正平. 结合SURF与聚类分析方法实现运动目标的快速跟踪［J］.液晶与显示，2011, 26（4）：544-550.LI Y，LI J Y，XU ZH P. Moving target fast tracking using SURF and cluster analysis method ［J］. Chinese Journal of Liquid Crystals and Displays,2011,26（4）：544-550. (in Chinese)［24］王思珺，赵建，韩希珍. 基于仿射变换的快速全局运动估计算法［J］. 液晶与显示,2012,27(2):263-266.WANG S J, ZHAO J, HAN X ZH. Fast global motion estimation algorithm based on affine transformation ［J］. Chinese Journal of Liquid Crystals and Displays,2012, 27(2):263-266. (in Chinese)

浏览量

602

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

自适应变尺度特征点提取方法

强环境噪声下的双目视觉受电弓轨旁异常检测

弱纹理环境下融合点线特征的双目视觉同步定位与建图

空洞卷积和双边格网的立体匹配网络

针对目标遮挡的自适应特征匹配网络