Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (8): 2396-2401.DOI: 10.11772/j.issn.1001-9081.2018122590

• Virtual reality and multimedia computing • Previous Articles     Next Articles

Image matching algorithm based on improved RANSAC-GMS

ZHU Chengde1,2, LI Zhiwei1, WANG Kai1, GAO Yan1, GUO Hengchang2   

  1. 1. School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China;
    2. Shanghai M & G Stationery Incorporation, Shanghai 201406, China
  • Received:2019-01-02 Revised:2019-04-02 Online:2019-08-10 Published:2019-04-24
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61705127), the Special Funds for Industrial Transformation, the Upgrading and Development of Shanghai Economic and Information Commission (HU CXY-2016-009).


朱成德1,2, 李志伟1, 王凯1, 高燕1, 郭亨长2   

  1. 1. 上海工程技术大学 电子电气工程学院, 上海 201620;
    2. 上海晨光文具股份有限公司, 上海 201406
  • 通讯作者: 李志伟
  • 作者简介:朱成德(1993-),男,河南项城人,硕士研究生,主要研究方向:图像处理、目标识别;李志伟(1982-),男,河南沈丘人,讲师,博士,主要研究方向:光学、模式识别;王凯(1994-),男,江苏扬州人,硕士研究生,主要研究方向:图像处理、立体匹配;高燕(1985-),女,甘肃武威人,讲师,博士,主要研究方向:智能控制、目标识别;郭亨长(1977-),男,广东潮汕人,研究员,博士,主要研究方向:光学、图像处理。
  • 基金资助:

Abstract: In order to solve the problem that Scale Invariant Feature Transform (SIFT) algorithm has low matching accuracy and long time consuming in image matching, an improved image matching algorithm based on grid motion statistical feature, namely RANSAC-GMS, was proposed. Firstly, the image was pre-matched by Oriented FAST and Rotated BRIEF (ORB) algorithm and Grid-based Motion Statistics (GMS) was used to support the estimator to distinguish the correct matching points from the wrong matching points. Then, an improved RANdom SAmple Consensus (RANSAC) algorithm was used to filter the feature points according to the distance similarity between the matching points, and an evaluation function was used to reorganize the filtered new datasets to eliminate the mismatching points. The experiments were carried out on Oxford standard image library and images taken in reality. Experimental results show that the average matching accuracy of the proposed algorithm in image matching is over 91%. Compared with algorithms such as GMS, SIFT and ORB, the near-scene matching accuracy and the far-scene matching accuracy of the proposed algorithm are improved by 16.15 percentage points and 3.56 percentage points respectively. The proposed algorithm can effectively eliminate mismatching points and achieve further improvement of image matching accuracy.

Key words: image matching, feature point matching, distance similarity, wrong matching, Grid-based Motion Statistics (GMS)

摘要: 为了解决尺度不变特征变换(SIFT)算法在图像匹配中匹配正确率低、耗时长等问题,提出一种基于改进网格运动统计特征RANSAC-GMS的图像匹配算法。首先,利用快速旋转不变性特征(ORB)算法对图像进行预匹配,对预匹配的特征点采用网格运动统计(GMS)来支持估计量以实现正确匹配点与错误匹配点的区分;然后,采用改进的随机抽样一致性(RANSAC)算法通过匹配点间的距离相似性对特征点进行筛选,并采用评价函数对筛选后的新数据集进行重新整理,进而实现对误匹配点的剔除。采用Oxford标准图库和现实中拍摄的图像对图像匹配算法进行测试对比,实验结果表明,所提算法在图像匹配中的平均匹配正确率达到91%以上;与GMS、SIFT、ORB等算法相比,该改进算法的近景匹配正确率和远景匹配正确率分别最少提高了16.15个百分点和3.56个百分点,说明它能有效剔除误匹配点,进一步提高图像匹配精度。

关键词: 图像匹配, 特征点匹配, 距离相似性, 误匹配, 网格运动统计

CLC Number: