具有抗仿射性的局部特征点匹配方法

doi:10.11772/j.issn.1001-9081.2019091588

计算机应用 ›› 2020, Vol. 40 ›› Issue (4): 1133-1137.DOI: 10.11772/j.issn.1001-9081.2019091588

• 虚拟现实与多媒体计算 • 上一篇下一篇

具有抗仿射性的局部特征点匹配方法

邱云飞, 刘兴

辽宁工程技术大学软件学院, 辽宁葫芦岛 125105

收稿日期:2019-09-18 修回日期:2019-10-18 出版日期:2020-04-10 发布日期:2019-10-28
通讯作者: 刘兴
作者简介:邱云飞(1976-),男,辽宁阜新人,教授,博士,CCF会员,主要研究方向:数据挖掘、情感分析;刘兴(1995-),男,辽宁沈阳人,硕士研究生,主要研究方向:数据挖掘、图像处理。
基金资助:
国家自然科学基金资助项目（71771111）。

Local feature point matching algorithm with anti-affine property

QIU Yunfei, LIU Xing

School of Software Engineering, Liaoning Technical University, Huludao Liaoning 125105, China

Received:2019-09-18 Revised:2019-10-18 Online:2020-04-10 Published:2019-10-28
Supported by:
This work is partially supported by the National Natural Science Foundation of China(71771111).

摘要/Abstract

摘要： 针对现有局部特征匹配算法对具有仿射性的图像匹配效果欠佳、耗时较长，以及随机采样一致性（RANSAC）算法对仿射性图像匹配得不到较好的参数模型等问题，提出一种具有抗仿射性的A-AKAZE（Affine Accelerated KAZE）算法，并用向量场一致性来筛选内点。首先利用非线性函数构建尺度空间，然后借助Hessian矩阵检测特征点，并以特征点为中心选取合适的区域作为特征采样窗口；再把特征采样窗口在经纬度上进行投影以模拟不同角度对图像的影响，随后在投影区域中提取具有抗仿射性的A-MLDB（Affine Modified-Local Difference Binary）描述符；最后利用向量场一致性算法提取内点。实验结果表明：A-AKAZE算法的正确匹配率相较于AKAZE算法提高了20%以上，与AKAZE+RANSAC算法相较提升了15%左右，与ASIFT（Affine Scale-Invariant Feature Transform）算法相比提高了10%左右，相比ASIFT+RANSAC算法提高了5%；而且该算法的匹配速度远高于AKAZE+RANSAC、ASIFT和ASIFT+RANSAC算法。

关键词: 仿射不变, AKZAE算法, 向量场一致性, MLDB描述符, 图像匹配

Abstract: In order to solve the problems that the existing local feature matching algorithm has poor matching effect and high time cost on affine images,and RANdom SAmple Consensus(RANSAC)algorithm cannot obtain a good parameter model on affine image matching,Affine Accelerated KAZE(A-AKAZE)algorithm with anti-affine property was proposed and the vector field consistency was used to screen interior points. Firstly,the scale space was constructed by using the nonlinear function,then the feature points were detected by Hessian matrix,and the appropriate areas were selected as the feature sampling windows with the feature points as the centers. Secondly,the feature sampling windows were projected on longitude and latitude to simulate the influence of different angles on the image,and then the Affine Modified-Local Difference Binary(A-MLDB)descriptors with anti-affine property were extracted from the projection region. Finally,the interior points were extracted by the vector field consistency algorithm. Experimental results show that the correct matching rate of A-AKAZE algorithm is more than 20% higher than that of AKAZE algorithm,is about 15% higher than that of AKAZE+RANSAC algorithm,is about 10% higher than that of Affine Scale-Invariant Feature Transform(ASIFT)algorithm, and is 5% higher than that of ASIFT+RANSAC algorithm;at the same time,A-AKAZE algorithm has the matching speed much higher than AKAZE+RANSAC,ASIFT and ASIFT+RANSAC algorithms.

Key words: affine invariant, Accelerated KAZE (AKAZE) algorithm, vector field consistency, Modified-Local Difference Binary (MLDB) descriptor, image matching

中图分类号:

TP391.41

邱云飞, 刘兴. 具有抗仿射性的局部特征点匹配方法[J]. 计算机应用, 2020, 40(4): 1133-1137.

QIU Yunfei, LIU Xing. Local feature point matching algorithm with anti-affine property[J]. Journal of Computer Applications, 2020, 40(4): 1133-1137.

参考文献

[1] MATAS J,CHUM O,URBAN M,et al. Robust wide-baseline stereo from maximally stable extremal regions[J]. Image and Vision Computing,2004,22(10):761-767.
[2] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2):91-110.
[3] MOREL J M,YU G. ASIFT:a new framework for fully affine invariant image comparison[J]. SIAM Journal on Imaging Sciences,2009,2(2):438-469.
[4] 侯毅, 周石琳, 雷琳, 等. 基于ORB的快速完全仿射不变图像匹配[J]. 计算机工程与科学,2014,36(2):303-310.(HOU Y, ZHOU S L,LEI L,et al. Fast fully affine invariant image matching based on ORB[J]. Computer Engineering and Science,2014,36(2):303-310.)
[5] RUBLEE E,RABAUD V,KONOLIGE K,et al. ORB:an efficient alternative to SIFT or SURF[C]//Proceeding of the 2011 International Conference on Computer Vision. Piscataway:IEEE, 2011:2564-2571.
[6] LEUTENEGGER S,CHLI M,SIEGWART R. BRISK:binary robust invariant scalable keypoints[C]//Proceedings of the 2011 International Conference on Computer Vision. Piscataway:IEEE, 2011:2548-2555.
[7] 黄友文, 黄雅兰, 袁春经. 具有仿射不变性的彩色图像配准方法研究[J]. 小型微型计算机系统,2015,36(2):338-342. (HUANG Y W,HUANG Y L,YUAN C J. A method of affine invariant for color image registration[J]. Journal of Chinese Computer Systems,2015,36(2):338-342.)
[8] BAY H,ESS A,TUYTELAARS T,et al. Speeded-Up Robust Features(SURF)[J]. Computer Vision and Image Understanding, 2008,110(3):346-359.
[9] WEICKERT J. Efficient image segmentation using partial differential equations and morphology[J]. Pattern Recognition, 2001,34(9):1813-1824.
[10] MA J,ZHAO J,TIAN J,et al. Robust point matching via vector field consensus[J]. IEEE Transactions on Image Processing, 2014,23(4):1706-1721.
[11] MA J,ZHAO J,TIAN J,et al. Regularized vector field learning with sparse approximation for mismatch removal[J]. Pattern Recognition,2013,46(12):3519-3532.
[12] OUYANG P,YIN S,LIU L,et al. A FAST extreme illumination robust feature in affine space[C]//Proceedings of the 22nd International Conference on Pattern Recognition. Piscataway:IEEE,2014:2365-2370.
[13] YANG X,CHENG K T T. Local difference binary for ultrafast and distinctive feature description[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(1):188-194.
[14] YANG X,CHENG K T T. LDB:an ultra-fast feature for scalable augmented reality on mobile devices[C]//Proceedings of the 2012 IEEE International Symposium on Mixed and Augmented Reality. Piscataway:IEEE,2012:49-57.
[15] MICCHELLI C A, PONTIL M. On learning vector-valued functions[J]. Neural Computation,2005,17(1):177-204.
[16] MYRONENKO A,SONG X. Point set registration:coherent point drift[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(12):2262-2275.
[17] 薄单, 李宗春, 王晓南, 等. 适用于倾斜影像的加速KAZE-SIFT特征提取算法[J]. 计算机应用,2019,39(7):2093-2097.(BO D,LI Z C,WANG X N,et al. Accelerated KAZE-SIFT feature extraction algorithm for oblique images[J]. Journal of Computer Applications,2019,39(7):2093-2097.)

具有抗仿射性的局部特征点匹配方法

Local feature point matching algorithm with anti-affine property

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	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.
[2]	王焱, 吕猛, 孟祥福, 李宇浩. 具有光照鲁棒的图像匹配方法[J]. 计算机应用, 2019, 39(1): 262-266.
[3]	李为, 李为相, 张璠, 揭伟. 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.
[4]	陈虹, 肖越, 肖成龙, 宋好. 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.
[5]	方智文, 曹治国, 朱磊. 基于梯度角度的直方图局部特征描述子的图像匹配算法[J]. 计算机应用, 2015, 35(4): 1079-1083.
[6]	张旭, 高佼, 王万国, 刘俍, 张晶晶. 基于显著图的输电线路杆塔图像拼接方法[J]. 计算机应用, 2015, 35(4): 1133-1136.
[7]	王琳, 赵健康, 夏轩, 龙海辉. 基于双目立体视觉技术的桥梁裂缝测量系统[J]. 计算机应用, 2015, 35(3): 901-904.
[8]	刘欢朱平肖蓉唐卫东. 基于立体视觉的新组合不变矩腹部体型重建[J]. 计算机应用, 2013, 33(11): 3183-3186.
[9]	汤培楷陈玮麦毅成. 图像局部映射二进制串描述符[J]. 计算机应用, 2013, 33(04): 1096-1099.
[10]	李威史泽林尹健. 立体目标的宽基线图像匹配[J]. 计算机应用, 2013, 33(03): 635-639.
[11]	章薇陈和平杨玲贤. 基于向量长度的Hausdorff距离图像匹配方法[J]. 计算机应用, 2012, 32(11): 3161-3167.
[12]	薛振华王萍张楚涵蔡思佳. 图像匹配中去除误配的对抗性优化方法的改进[J]. 计算机应用, 2012, 32(11): 3157-3160.
[13]	卫津津李素梅刘文娟臧艳军. 基于可控金字塔的立体图像质量评价方法[J]. 计算机应用, 2012, 32(03): 710-714.
[14]	吴庆双付仲良. 一种鲁棒的序列图像自动拼接方法[J]. 计算机应用, 2012, 32(02): 499-503.
[15]	马伟陈家新潘维薇. 基于体素相似度的医学图像层间插值方法[J]. 计算机应用, 2012, 32(02): 538-553.