薄单,李宗春,蓝朝桢,訾栓紧

• 1:信息工程大学地理空间信息学院

摘要(Abstract)：

针对基于最近邻距离比率约束和几何条件约束的影像特征匹配方法,在处理重复纹理影像以及视角和尺度变化大的宽基线影像时,存在匹配正确率低和匹配点对数量少的问题,设计了结合运动平滑约束与核线约束的AKAZE特征匹配提纯算法。(1)为提高影像特征的不变性、显著性和时效性,采用AKAZE算子提取影像特征,经暴力匹配快速构建初始匹配集;(2)基于网格运动统计区分真假匹配,剔除不能满足运动平滑约束的匹配点对;(3)为消除局部相似特征引起的误匹配,采用核线约束提高匹配纯度。实验结果表明:所提算法实现了重复纹理影像、倾斜影像和宽基线影像同名点对的高精度匹配,增加了匹配点对数量,拓展了特征匹配的适用范围。

关键词(KeyWords)： 特征匹配;匹配提纯;运动平滑约束;核线约束;AKAZE算法;随机抽样一致性

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金青年基金项目（41701463）;; 河南省科技攻关项目（172102210020）

作者(Author): 薄单,李宗春,蓝朝桢,訾栓紧

DOI: 10.16251/j.cnki.1009-2307.2021.01.024

参考文献(References)：

• [1] MIKOLAJCZYK K,SCHMID C.Scale & affine invariant interest point detectors[J].International Journal of Computer Vision,2004,60(1):63-86.
• [2] LOWE D G.Distinctive image features from scale-invariant keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
• [3] BAY H,ESS A,TUYTELAARS T,et al.Speeded-up robust features (SURF)[J].Computer Vision & Image Understanding,2008,110(3):346-359.
• [4] RUBLEE E,RABAUD V,KONOLIGE K,et al.ORB:an efficient alternative to SIFT or SURF[C]//International Conference on Computer Vision,Barcelona:ICCV,2012:2564-2571.
• [5] ALCANTARILLA P F,NUEVO J,BARTOLI A.Fast explicit diffusion for accelerated features in nonlinear scale spaces[C]//British Machine Vision Conference.Bristol:BMVC,2013:11,13.
• [6] 安婷,贺一民,张志毅.改进的双向SIFT特征匹配算法[J].计算机工程与科学,2016,38(1):138-143.(AN Ting,HE Yimin,ZHANG ZhiYi.An improved bidirectional SIFT feature matching algorithm[J].Computer Engineering & Science,2016,38(1):138-143.
• [7] 明洋.特殊航空影像自动匹配的关键技术研究[D].武汉大学,2009:19-21.(MING Yang.Research on key technologies of automatic image matching for special aerial image[D].Wuhan University,2009:19-21.)
• [8] 郭莹,牛继强,陈时雨,等.基于图论的影像匹配粗差探测算法[J].测绘科学,2018,43(11):85-91.(GUO Ying,NIU Jiqiang,CHEN Shiyu,et al.An image matching gross error detection algorithm via graph theory[J].Science of Surveying and Mapping,2018,43(11):85-91.)
• [9] 张培耘,华希俊,夏乐春,等.基于RANSAC算法的核线约束立体视觉匹配方法研究[J].组合机床与自动化加工技术,2013(11):20-22.(ZHANG Peiyun,HUA Xijun,XIA Lechun,et al.Stereo matching with epipolar line constraints based on RANSAC algorithm[J].Modular Machine Tool & Automatic Manufacturing Technique,2013(11):20-22.)
• [10] ZHANG W,KOSECKA J.Generalized RANSAC framework for relaxed correspondence problems[C]//International Symposium on 3D Data Processing,Visualization,and Transmission,Chapel Hill:3DPVT’06,2006:854-860.
• [11] 杨化超,张磊,姚国标,等.局部单应约束的高精度图像自动配准方法[J].测绘学报,2012,41(3):401-408.(YANG Huachao,ZHANG Lei,YAO Guobiao,et al.An automated image registration method with accuracy based on local homography constraint[J].Acta Geodaetica et Cartographica Sinica,2012,41(3):401-408.)
• [12] 梁爽.基于SIFT算子的影像匹配方法研究[D].阜新:辽宁工程技术大学,2015:43-45.(LIANG Shuang.Research on image matching method based on SIFT operator[D].Fuxin:Liaoning Technical University,2015:43-45.)
• [13] 张振超.多视角倾斜航空影像匹配技术研究[D].郑州:信息工程大学,2015:17-18.(ZHANG Zhenchao.Research on multi-view oblique aerial image matching[D].Zhengzhou:Information Engineering University,2015:17-18.)
• [14] LIN W Y,WANG F,CHENG M M,et al.CODE:Coherence based decision boundaries for feature correspondence[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2018,40(1):34-47.
• [15] WEINZAEPFEL P,REVAUD J,HARCHAOUI Z,et al.Deepflow:large displacement optical flow with deep matching[C]//IEEE International Conference on Computer Vision.Sydney:IEEE,2013:1385-1392.
• [16] REVAUD,WEINZAEPFEL P,HARCHAOUI,et al.Epicflow:edge-preserving interpolation of correspondences for optical flow[C]//Computer Vision and Pattern Recognition Computer Vision & Pattern Recognition.Boston:CVPR,2015:1164-1172.
• [17] BIAN J W,LIN W Y,MATSUSHITA Y,et al.GMS:grid-based motion statistics for fast,ultra-robust feature correspondence[C]//Computer Vision and Pattern Recognition,Honolulu:CVPR,2017:2828-2837.
• [18] 杨化超.宽基线立体影像点、线特征提取与匹配方法研究[D].徐州:中国矿业大学,2010:2-8.(YANG Huachao.Researching into extracting and matching methods of point and line features for wide baseline stereo images[D].Xuzhou:China University of Mining and Technology,2010:2-8.)
• [19] 杨化超,姚国标,王永波.基于SIFT的宽基线立体影像密集匹配[J].测绘学报,2011,40(5):537-543.(YANG Huachao,YAO Guobiao,WANG Yongbo.Dense matching for wide base-line stereo images based on SIFT[J].Acta Geodaetica et Cartographica Sinica,2011,40(5):537-543.)
• [20] 姚国标,邓喀中,张力,等.基于Harris-Affine的宽基线立体影像LSM匹配方法[J].中南大学学报(自然科学版),2014,45(8):2661-2668.(YAO Guobiao,DENG Kazhong,ZHANG Li,et al.Least square matching method for wide baseline stereo images based on Harris-Affine features[J].Journal of Central South University (Science and Technology),2014,45(8):2661-2668.)
• [21] CHIEN H J,CHUANG C C,CHEN C Y,et al.When to use what feature?SIFT,SURF,ORB,or A-KAZE features for monocular visual odometry[C]//International Conference on Image and Vision Computing New Zealand,Palmerston North:VCNZ,2016:1-6.
• [22] 戴周.基于局部特征和视觉上下文的图像检索系统[D].成都:电子科技大学,2014:30-32.(DAI Zhou.Image retrieval system based on local features and visual context[D].Chendu:School of Computer Science & Engineering,2014:30-32.)
• [23] 刘川熙,赵汝进,刘恩海,等.基于RANSAC的SIFT匹配阈值自适应估计[J].计算机科学,2017,44(S1):157-160.(LIU Chuanxi,ZHAO Rujin,LIU Enhai,et al.Estimate threshold of sift matching adaptively based on RANSAC[J].Computer Science,2017,44(S1):157-160.)
• [24] NEX F,GERKE M,REMONDINO F,et al.ISPRS benchmark for Multi-platform photogrammetry[J].ISPRS Annals of the Photogrammetry,Remote Sensing and Spatial Information Sciences,2015,II-3/W4.