北京航空航天大学学报 ›› 2021, Vol. 47 ›› Issue (10): 2149-2154.doi: 10.13700/j.bh.1001-5965.2020.0359

• 论文 • 上一篇    

一种改进的ORB特征匹配算法

廖泓真1, 王亮2, 孙宏伟2, 刘云清1   

  1. 1. 长春理工大学 电子信息工程学院, 长春 130022;
    2. 北京信息技术研究所, 北京 100094
  • 收稿日期:2020-07-24 发布日期:2021-11-08
  • 通讯作者: 刘云清 E-mail:mzliuyunqing@163.com
  • 基金资助:
    吉林省发改委重点研发项目(2018C035-3)

An improved ORB feature matching algorithm

LIAO Hongzhen1, WANG Liang2, SUN Hongwei2, LIU Yunqing1   

  1. 1. College of Electronic and Information Engineering, Changchun University of Science and Technology, Changchun 130022, China;
    2. Beijing Institute of Information Technology, Beijing 100094, China
  • Received:2020-07-24 Published:2021-11-08

摘要: 针对现有的ORB特征匹配算法在图像模糊、光照变化、图像压缩、噪声条件下,匹配准确率下降问题,提出了一种改进的ORB特征匹配算法。首先,在提取特征点过程中,对图像进行网格化处理,并引入四叉树结构,使提取的特征点在图像中均匀分布,解决传统的特征提取方法遇到的特征点集中问题。然后,利用暴力匹配进行初步匹配,并采用交叉验证的方式,剔除部分误匹配,改善暴力匹配的结果。最后,利用高斯核对网格运动统计的结果做加权处理,优化统计结果,进一步剔除误匹配,得到准确率更高的匹配集合。实验结果表明:改进后的算法在图像模糊、光照变化、图像压缩和噪声条件下,平均准确率分别提高了3.5%、4.2%、2.2%和6%。

关键词: 特征匹配, ORB特征, 网格运动统计, 特征提取, 高斯核

Abstract: An improved ORB feature matching algorithm is proposed to solve the problem of decreasing matching accuracy under the conditions of image blur, light change, image compression and noise. First, in the process of extracting feature points, the image is meshed and quad-tree structure is introduced to make the extracted feature points evenly distributed in the image, thus solving the problem of feature points concentration encountered by traditional feature extraction methods. Then, the brute-force matching is used for preliminary matching, and cross validation is adopted to eliminate some mismatches and improve the result of brute-force matching. Finally, Gaussian kernel is used to weight the results of grid-based motion statistics to optimize the statistical results and further eliminate the mismatches to obtain the matching set with higher accuracy. The experimental results show that this algorithm improves the average accuracy by 3.5%, 4.2%, 1.8% and 6% respectively under the conditions of image blur, light change, image compression and noise.

Key words: feature matching, ORB feature, grid-based motion statistics, feature extraction, Gaussian kernel

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发