基于改进FREAK的图像匹配算法

doi:10.19678/j.issn.1000-3428.0055349

摘要/Abstract

摘要： 为提升图像匹配算法的实时性和鲁棒性，提出一种基于改进FREAK的特征点匹配算法。将经典FREAK算法的8层视网膜模型简化为5层，根据贪婪搜索算法选取64组感受野点对，以在减少运算开销的同时尽量保留有效的点对信息。在此基础上，设计一种具有方向不变性的LBP算法对每个感受野进行编码，从而提高描述符的区分度。实验结果表明，与FREAK、BRISK等算法相比，该算法具有最小的描述符尺寸，且在多数场景下，其运算更快，精度更高，更适合光照变化复杂的环境。

关键词: 图像匹配, FREAK算法, 局部二值模式, 特征点匹配, 描述符

Abstract: To improve the real-time performance and robustness of image matching algorithms,this paper proposes a feature point matching algorithm based on improved FREAK.The algorithm simplifies the 8-layer retina model of the classical FREAK algorithm to a 5-layer one,and uses a greedy search algorithm to select 64 groups of receptive field pairs,so as to reduce the overhead of calculation and keep as much useful point pair information as possible.On this basis,a rotation-invariant Local Binary Patterns(LBP) algorithm is designed to encode every receptive field in order to increase the discriminative power of the descriptor.Experimental results show that compared with FREAK,BRISK and other algorithms,the proposed algorithm has the smallest descriptor size,and in most scenes has a higher calculation speed and accuracy,which means it is more suitable for environments with complex light changes.

Key words: image matching, FREAK algorithm, Local Binary Patterns(LBP), feature point matching, descriptor

中图分类号:

TP391

黄坤, 钱军浩, 王江文. 基于改进FREAK的图像匹配算法[J]. 计算机工程, 2020, 46(8): 250-257.

HUANG Kun, QIAN Junhao, WANG Jiangwen. Image Matching Algorithm Based on Improved FREAK[J]. Computer Engineering, 2020, 46(8): 250-257.

https://www.ecice06.com/CN/Y2020/V46/I8/250

图/表 16

20200819140709

20200819140713

20200819140716

20200819140719

20200819140722

20200819140726

20200819140729

20200819140733

20200819140736

20200819140738

20200819140747

20200819140750

20200819140753

20200819140758

20200819140801

20200819140806

参考文献

[1] XIE Yunxuan.A summary of research on target recognition based on matching[J].Science and Technology Innovation Herald,2017,14(3):110-112.(in Chinese)谢云璇.基于匹配的目标识别研究综述[J].科技创新导报,2017,14(3):110-112.
[2] XIAO Ming,BAO Yongliang,YAN Zhongxin.Overview of image registration methods based on point features[J].Acta Armamentarii Acta Armam,2015,36(S2):326-340.(in Chinese)肖明,鲍永亮,颜仲新.基于点特征的图像配准方法综述[J].兵工学报,2015,36(S2):326-340.
[3] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:2564-2571.
[4] LEUTENEGGER S,CHLI M,SIEGWART R Y.BRISK:binary robust invariant scalable keypoints[C]//Proceedings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2011:2548-2555.
[5] ALAHI A,ORTIZ R,VANDERGHEYNST P.Freak:fast retina keypoint[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2012:510-517.
[6] LIU Yu,CUI Jianjun,LI Xue.FREAK and improved RANSAC algorithm in photography matching[J].Beijing Surveying and Mapping,2018,32(7):835-841.(in Chinese)刘宇,崔建军,李雪.FREAK和改进的RANSAC算法在影像匹配中的应用[J].北京测绘,2018,32(7):835-841.
[7] CHEN Yantong,XU Wei,PIAO Yongjie,et al.Remote sensing image target recognition based on fast retina key point local invariant feature[J].Chinese Journal of Scientific Instrument,2016,37(4):852-859.(in Chinese)陈彦彤,徐伟,朴永杰,等.基于快速视网膜局部特征的遥感图像目标识别[J].仪器仪表学报,2016,37(4):852-859.
[8] WANG Canjin,SUN Tao,CHEN Juan.Rapid scene matching based on FREAK descriptor[J].Journal of Electronic Measurement and Instrumentation,2015,29(2):204-212.(in Chinese)王灿进,孙涛,陈娟.基于FREAK特征的快速景象匹配[J].电子测量与仪器学报,2015,29(2):204-212.
[9] WANG Jianyong,WANG Xuemei,YANG Xiaogang,et al.CS-FREAK:an improved binary descriptor[C]//Proceedings of the 8th Computer and Information Science Conference on Image and Graphics Technologies and Applications.Berlin,Germany:Springer,2014:129-136.
[10] WANG Qiang,LI Bailin,LUO Jianqiao,et al.Local binary pattern image feature point matching algorithm[J].Application Research of Computers,2019,36(1):268-272.(in Chinese)王强,李柏林,罗建桥,等.局部二值模式图像特征点匹配算法[J].计算机应用研究,2019,36(1):268-272.
[11] HUANG Bihui,WU Yong,ZHENG Senyuan.Study on the applicability of image matching algorithm for mobile equipment[J].Journal of Hainan Normal University(Natural Science),2017,30(4):407-413.(in Chinese)黄碧辉,吴勇,郑森源.面向移动设备的图像匹配算法适用性研究[J].海南师范大学学报(自然科学版),2017,30(4):407-413.
[12] EVERINGHAM M,VAN GOOL L,WILLIAMS C K I,et al.The PASCAL visual object classes challenge 2012 results[EB/OL].[2019-06-01].http://www.pascalnetwork.org/challenges/VOC/voc2012/workshop/index.html.
[13] LI Jingjiao,ZHAO Yue,WANG Aixia,et al.Real-time registration algorithm of augmented reality based on improved FREAK[J].Journal of Chinese Computer Systems,2016,37(1):173-177.(in Chinese)李晶皎,赵越,王爱侠,等.基于改进FREAK的增强现实实时注册算法[J].小型微型计算机系统,2016,37(1):173-177.
[14] OJALA T,PIETIKAINEN M,MAENPAA T.Multire-solution grayscale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[15] OJALA T,PIETIKAINEN M,HARWOOD D.A comparative study of texture measures with classification based on featured distributions[J].Pattern Recognition,1996,29(1):51-59.
[16] GAO Pan,LIU Guangshuai,MA Ziheng,et al.Enhanced pairwise rotation-invariant co-occurrence extended local binary pattern[J].Journal of Image and Graphics,2018,23(7):1024-1032.(in Chinese)高攀,刘光帅,马子恒,等.增强成对旋转不变的共生扩展局部二值模式[J].中国图象图形学报,2018,23(7):1024-1032.
[17] YU Qiang,NIE Hongyu,ZHANG Jingjing.Feature descriptor based on local binary pattern with equidistant ring[J].Computer Engineering,2017,43(1):274-279,286.(in Chinese)喻强,聂洪玉,张晶晶.基于等距环局部二值模式的特征描述子[J].计算机工程,2017,43(1):274-279,286.
[18] KANG Jie,LI Zhen,WANG Xiaodong,et al.Research on the AdaBoost face detection algorithm based on the rotation invariant features of MB_LBP[J].Journal of Shaanxi University of Science and Technology(Natural Science Edition),2017,35(4):164-167.(in Chinese)亢洁,李珍,王晓东,等.基于MB_LBP旋转不变特征的AdaBoost人脸检测算法研究[J].陕西科技大学学报(自然科学版),2017,35(4):164-167.
[19] MIKOLAJCZYE K,SCHMID C.A performance evaluation of local descriptors[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(10):1615-1630.
[20] ZHOU H,SATTLER T,JACOBS D W.Evaluating local features for day-night matching[C]//Proceedings of Computer Vision ECCV'16.Berlin,Germany:Springer,2016:724-736.
[21] MIKOLAJCZYK K,TUYTELAARS T,SCHMID C,et al.A comparison of affine region detectors[J].International Journal of Computer Vision,2005,65(1/2):43-72.

选择文件类型/文献管理软件名称

选择包含的内容