Image matching algorithm based on improved RANSAC-GMS

doi:10.11772/j.issn.1001-9081.2018122590

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 Chengde^1,2, LI Zhiwei¹, WANG Kai¹, GAO Yan¹, GUO Hengchang²

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).

基于改进网格运动统计特征的图像匹配算法

朱成德^1,2, 李志伟¹, 王凯¹, 高燕¹, 郭亨长²

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:
国家自然科学基金资助项目（61705127）；上海市经济和信息化委员会产业转型升级发展专项资金产研合作专题（沪CXY-2016-009）。

Abstract

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:

TP391.41

ZHU Chengde, LI Zhiwei, WANG Kai, GAO Yan, GUO Hengchang. Image matching algorithm based on improved RANSAC-GMS[J]. Journal of Computer Applications, 2019, 39(8): 2396-2401.

朱成德, 李志伟, 王凯, 高燕, 郭亨长. 基于改进网格运动统计特征的图像匹配算法[J]. 计算机应用, 2019, 39(8): 2396-2401.

References

[1] ABATE A F, NAPPI M, RICCIO D, et al. 2D and 3D face recognition:a survey[J]. Pattern Recognition Letters, 2007, 28(14):1885-1906.
[2] JIA K, CHAN T H, ZENG Z, et al. ROML:a robust feature correspondence approach for matching objects in a set of images[J]. International Journal of Computer Vision, 2016, 117(2):173-197.
[3] LU Y, SONG D. Visual navigation using heterogeneous landmarks and unsupervised geometric constraints[J]. IEEE Transactions on Robotics, 2015, 31(3):736-749.
[4] 侯一民,隋文秀,孙晓雪. SIFT特征降维方法及其在图像检索中的应用[J].中国激光, 2015,42(s1):s108002. (HOU Y M, SUI W X, SUN X X. SIFT feature dimension reduction method and its application in image retrieval[J]. Chinese Journal of Lasers, 2015, 42(s1):108002.)
[5] 王凯,李志伟,朱成德,等.基于二次引导滤波的局部立体匹配算法[J]. 激光与光电子学进展, 2019,56(8):081004. (WANG K, LI Z W, ZHU C D, et al. Local stereo matching algorithm based on twice guided filtering[J]. Laser & Optoelectronics Progress, 2019, 56(8):081004.)
[6] 吴强,侯树艳,李旭雯.融合图像灰度信息与边缘特征的快速匹配算法[J]. 信号处理, 2013,29(2):268-273. (WU Q, HOU S Y, LI X W. Fast image matching algorithm based on gray and edge features[J]. Journal of Signal Processing, 2013, 29(2):268-273.)
[7] 贾雯晓,张贵仓,汪亮亮,等.基于SIFT和改进的RANSAC图像配准算法[J].计算机工程与应用,2018,54(2):203-207. (JIA W X, ZHANG G C, WANG L L, et al. Image registration algorithm based on SIFT and improved RANSAC[J]. Computer Engineering and Applications, 2018, 54(2):203-207.)
[8] 陈虹,肖越,肖成龙,等.基于SIFT算子融合最大相异系数的自适应图像匹配算法[J].计算机应用,2018,38(5):1410-1414. (CHEN H, XIAO Y, XIAO C L, et al. Adaptive image matching algorithm based on SIFT operator fused with maximum dissimilarity coefficient[J]. Journal of Computer Applications, 2018, 38(5):1410-1414.)
[9] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[10] BAY H, ESS A, TUYTELAARS T, et al. Speeded-up robust features[J]. Computer Vision & Image Understanding, 2008, 110(3):346-359.
[11] BRADSKI G, RUBLEE E, KONOLIGE K, RABAUD V, et al. ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of the 13th IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2011:2564-2571.
[12] TRAN Q, CHIN T, CARNEIRO G, et al. In defence of RANSAC for outlier rejection in deformable registration[C]//Proceedings of the 2012 European Conference on Computer Vision, LNCS 7575. Berlin:Springer, 2012:274-287.
[13] 冯文斌,刘宝华.改进的SIFT算法图像匹配研究[J].计算机工程与应用,2018,54(3):200-205. (FENG W B, LIU B H. Research on image matching based on improved SIFT algorithm[J]. Computer Engineering and Applications, 2018, 54(3):200-205.)
[14] 孙雪强,黄旻,张桂峰,等.改进RANSAC算法在多光谱图像匹配中的应用[J].半导体光电,2018,39(4):563-568. (SUN X Q, HUANG M, ZHANG G F, et al. Application of improved RANSAC algorithm to multi-spectral image matching[J]. Semiconductor Optoelectronics, 2018, 39(4):563-568.)
[15] 陈树,杨天,孙顺远.融合彩色不变量和SURB检测的特征点匹配算法[J]. 激光与光电子学进展,2018,55(5):138-145. (CHEN S, YANG T, SUN S Y. Feature point matching algorithm for fusion of color invariants and SURB detection[J]. Laser & Optoelectronics Progress, 2018, 55(5):138-145.)
[16] 秦晓飞,皮军强,李峰.基于极线约束的ORB特征匹配算法[J].计算机应用研究,2018,35(8):2865-2868. (QIN X F,PI J Q, LI F.ORB feature matching based on epipolar constraint[J]. Application Research of Computers, 2018, 35(8):2865-2868.)
[17] BIAN J, LIN W, MATSUSHITA Y, et al. GMS:Grid-based motion statistics for fast, ultra-robust feature correspondence[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2017:2828-2837.
[18] 陈方杰,韩军,王祖武,等.基于改进GMS和加权投影变换的图像配准算法[J].激光与光电子学进展,2018,55(11):174-180. (CHEN F J, HAN J, WANG Z W, et al. Image registration algorithm based on improved GMS and weighted projection transformation[J]. Laser & Optoelectronics Progress, 2018, 55(11):174-180.)
[19] YAN K, HAN M. Aerial image stitching algorithm based on improved GMS[C]//Proceedings of the 2018 Eighth International Conference on Information Science and Technology. Washington, DC:IEEE Computer Society, 2018:351-357.
[20] 赵明富,陈海军,宋涛,等.改进RANSAC-SIFT算法在图像匹配中的研究[J].激光杂志,2018,39(1):114-118. (ZHAO M F, CHEN H J, SONG T, et al. Research on image matching based on improved RANSAC-SIFT algorithm[J]. Laesr Journal, 2018, 39(1):114-118.)
[21] 李倩,江泽涛.二值化的SIFT特征描述子及图像拼接优化[J].中国图象图形学报,2016,21(12):1593-1601. (LI Q, JIANG Z T. Binary quantized SIFT feature descriptors for optimized image stitching[J]. Journal of Image and Graphics, 2016, 21(12):1593-1601.)
[22] 李为,李为相,张璠,等.基于运动平滑约束项的快速误匹配剔除算法[J].计算机应用,2018,38(9):2678-2682. (LI W, LI W X, ZHANG F, et al. Rapid mismatching elimination algorithm based on motion smoothing constraints[J]. Journal of Computer Applications, 2018, 38(9):2678-2682.)

Image matching algorithm based on improved RANSAC-GMS

基于改进网格运动统计特征的图像匹配算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	QIU Yunfei, LIU Xing. Local feature point matching algorithm with anti-affine property [J]. Journal of Computer Applications, 2020, 40(4): 1133-1137.
[2]	DING Hui, LI Lihong, YUAN Gang. Image registration algorithm combining GMS and VCS+GC-RANSAC [J]. Journal of Computer Applications, 2020, 40(4): 1138-1143.
[3]	MU Qi, TANG Yang, LI Zhanli, LI Hong'an. Fast stitching method for dense repetitive structure images based on grid-based motion statistics algorithm and optimal seam [J]. Journal of Computer Applications, 2020, 40(1): 239-244.
[4]	XIU Chunbo, MA Yunfei, PAN Xiaonan. Image feature point matching method based on distance fusion [J]. Journal of Computer Applications, 2019, 39(11): 3158-3162.
[5]	WANG Yan, LYU Meng, MENG Xiangfu, LI Yuhao. Image matching method with illumination robustness [J]. Journal of Computer Applications, 2019, 39(1): 262-266.
[6]	LI Wei, LI Weixiang, ZHANG Fan, JIE Wei. Rapid mismatching elimination algorithm based on motion smoothing constraints [J]. Journal of Computer Applications, 2018, 38(9): 2678-2682.
[7]	CHEN Hong, XIAO Yue, XIAO Chenglong, SONG Hao. Adaptive image matching algorithm based on SIFT operator fused with maximum dissimilarity coefficient [J]. Journal of Computer Applications, 2018, 38(5): 1410-1414.
[8]	SUN Zengyou, DUAN Yushuai, LI Ya. Image feature point matching algorithm based on center surround filter detection [J]. Journal of Computer Applications, 2017, 37(12): 3547-3553.
[9]	BAI Xuebing, CHE Jin, MU Xiaokai, ZHANG Ying. Improved feature points matching algorithm based on speed-up robust feature and oriented fast and rotated brief [J]. Journal of Computer Applications, 2016, 36(7): 1923-1926.
[10]	LIN Tao, HUANG Guorong, HAO Shunyi, SHEN Fei. Application of scale-invariant feature transform algorithm in image feature extraction [J]. Journal of Computer Applications, 2016, 36(6): 1688-1691.
[11]	HOU Yifan, WANG Dong, XING Shuai, XU Qing, GE Zhongxiao. Design and implementation of online real-time mapping system based on image stereo vision [J]. Journal of Computer Applications, 2016, 36(5): 1450-1454.
[12]	ZHANG Xu, GAO Jiao, WANG Wanguo, LIU Liang, ZHANG Jingjing. Image mosaic approach of transmission tower based on saliency map [J]. Journal of Computer Applications, 2015, 35(4): 1133-1136.
[13]	FANG Zhiwen, CAO Zhiguo, ZHU Lei. Image matching algorithm based on histogram of gradient angle local feature descriptor [J]. Journal of Computer Applications, 2015, 35(4): 1079-1083.
[14]	WANG Lin, ZHAO Jiankang, XIA Xuan, LONG Haihui. Bridge crack measurement system based on binocular stereo vision technology [J]. Journal of Computer Applications, 2015, 35(3): 901-904.
[15]	LIU Huan ZHU Ping XIAO Rong TANG Weidong. Belly shape modeling with new combined invariant moment based on stereo vision [J]. Journal of Computer Applications, 2013, 33(11): 3183-3186.