一种基于SURF和BRIEF的图像配准算法

尚明姝; 王克朝

Chinese

您当前的位置：

首页 >

文章列表页 >

一种基于SURF和BRIEF的图像配准算法

更新时间：2026-09-04

- 一种基于SURF和BRIEF的图像配准算法
- A image registration method based on SURF and BRIEF
- 微电子学与计算机 2020年37卷第10期页码：59-63
- 作者机构：
  
  1. 哈尔滨学院信息工程学院,黑龙江,哈尔滨,150080
  2. 哈尔滨工业大学计算机科学与技术学院,黑龙江,哈尔滨,150001
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61977020黑龙江省自然科学基金 LH2019F046
- DOI：
  中图分类号：
- 纸质出版：2020
- 稿件说明：
移动端阅览
尚明姝, 王克朝. 一种基于SURF和BRIEF的图像配准算法[J]. 微电子学与计算机, 2020, 37(10): 59-63.

SHANG Ming-shu, WANG Ke-chao. A image registration method based on SURF and BRIEF[J]. 2020, 37(10): 59-63.
尚明姝, 王克朝. 一种基于SURF和BRIEF的图像配准算法[J]. 微电子学与计算机, 2020, 37(10): 59-63. DOI：

SHANG Ming-shu, WANG Ke-chao. A image registration method based on SURF and BRIEF[J]. 2020, 37(10): 59-63. DOI：

摘要

针对SURF算法特征描述复杂和匹配精确度不高的问题，提出先用SURF算法提取特征点，再计算其Harris响应值，剔除质量较差的特征点，使用BRIEF算法描述特征点，再用最近邻汉明距离匹配特征点.采用改进的K-means算法对数据分类，将数量较多的类里的匹配点作为正确匹配点保留.最后应用改进的RANSAC算法求变换矩阵.实验验证了算法性能.

Abstract

Considering SURF feature description having great computational complexity and feature matching not having high accuracy

an advanced image registration method is proposed. At first it uses SURF to extract the feature points from two images

then calculates Harris response values of every feature points. The feature points of low quality are canceled. Then BRIEF descriptor is utilized to characterize those feature points. Lastly the improved K-means algorithm is used to classify the data

and the classes with more matching points are reserved. The advanced RANSAC algorithm is used to compute the transform matrix between the two images. The experiments verify the algorithms efficiency.

关键词

Keywords

references

TU M L, GUO T L. Improved RANSAC matching point purification algorithm based on ORB characteristics[J].Cable TV Technology, 2018(8):18-22. DOI: 18

STEINLEY D.K-means clustering:A half-century synthesis[J].BritishJournal of Mathematical and Statistical Psychology, 2006:59:1-34. DOI: 1

HARRIS C, STEPHENS M. A combined corner and edgedetector [C].Proceedings of the 4th Alvey Vision Conference, Manchester, 1988: 147-151.

RICHARD SZELISKI. Video mosaics for virtual environments[J]. IEEE Computer Graphics and Applications, 1996, 16(2): 22-30. DOI: 22

Cambridge RICHARD HARTLEY, ANDREW ZISSERMAN. Multiple View Geometry inComputer Vision [M]. Cambridge : Cambridge University Press, 2003:23-150 DOI: 23

HERBERT BAY, TINNE TUYTELAARS, LUCVANGOOL. SURF: Speeded up robust features[C].ECCV'06 Proceedings of the 9th European conference on Computer Vision, 2006: 404-417.

MA L W, ZHU G H. Research on image mosaics based on improved SURF Algorithm[J].Microcomputers and applications, 2014, 33(24):45-47. DOI: 45

QIN X J, HONG X Y. Improved SURF feature matching algorithm for remote sensing image[J]. Minicomputer system, ,2016, 37(2):327-331. DOI: 327

ZHUANG Z G, SUN H J. Image matching algorithm based on corner detection and its application in image mosaic[J].Journal of the Xiamen University, 2007, 46(4):501-505. DOI: 501

MENG H Y, WANG H P. UAV remote sensing image mosaic method based on improved SURF algorithm[J].Journal of Naval Institute of Aeronautical Engineering, 2018, 33(2):181-200. DOI: 181

CHEN T H, WANG F L. Image feature point matching based on improved ORB and symmetric matching[J]. Application of computer system, 2016, 25(5):147-152. DOI: 147

WANG H L, ZHANG L. SURF feature point matching based on correlation region constraint[J]. Communication Technology, 2012, 45(2):135-137. DOI: 135

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于改进蝙蝠算法的云计算任务调度研究

混合细菌觅食和粒子群的k-means聚类算法

基于改进K-means算法的海量数据分析技术研究

基于距离阈值及样本加权的K-means聚类算法

一种基于权重的核k-means聚类算法